CPP.simplify

CPP.simplify(df_feat=None, labels=None, strategy='greedy', candidate_search='exact', max_interpret_grade=None, min_cor=0.7, ml_model='svm', ml_metric='balanced_accuracy', ml_th=0.0, ml_cv=5, allow_drop=True, on_unimprovable='keep', redundancy_tie_break='interpretability', label_test=1, label_ref=0, max_std_test=0.2, max_cor=0.5, max_overlap=0.5, check_cat=True, return_details=False)[source]

Simplify a feature set by swapping scales for more interpretable correlated ones.

For each feature (PART-SPLIT-SCALE), an alternative scale from a more interpretable AAontology subcategory (interpretability grade 1-10, 1 = best; per-subcategory grades are in load_scales(name='subcat')) that correlates with the original scale is substituted, keeping PART-SPLIT. The swapped feature’s statistics are recomputed; a swap is accepted only if it passes CPP’s per-feature filtering (max_std_test) and a cross-validation gate (performance not worse than the current set, within ml_th). The swapped set is then redundancy-reduced, yielding a more interpretable and ideally smaller df_feat. The candidate pool (the full rated AAontology scale set) is loaded internally.

Added in version 1.1.0.

Parameters:

df_feat (pd.DataFrame, shape (n_features, n_feature_info)) – Feature DataFrame from run() (the standardized CPP output schema).
labels (array-like, shape (n_samples,)) – Class labels for samples in sequence DataFrame (typically, test=1, reference=0).
strategy ({'greedy', 'consolidate', 'swap_all'}, default='greedy') –
How candidate swaps are chosen and validated (see Notes for full behavior):
- 'greedy': per-feature — each targeted feature is swapped to its best candidate that keeps the cross-validation (CV) score within ml_th.
- 'consolidate': set-level — funnels features into the fewest interpretable subcategories, keeping each batch swap only if the set CV score holds.
- 'swap_all': apply every eligible best-candidate swap with no CV gate (fastest; ml_model / ml_metric / ml_th / ml_cv ignored).
candidate_search ({'exact', 'fast'}, default='exact') – How many candidate scales are evaluated per feature. 'exact' (default) tests every eligible candidate and reproduces the original result exactly. 'fast' is an approximate speed-up that caps the search to the most promising candidates per feature (highest interpretability, then strongest correlation); it can change which features are kept and so is most useful on large scale pools. If none of the searched candidates is accepted, the feature keeps its original scale (it is never dropped for this reason), so 'fast' may leave a feature un-simplified that 'exact' would have swapped. The speed-up is concentrated in strategy='greedy' (one cross-validation per candidate tried); 'consolidate' gains less and 'swap_all' is unaffected (it already stops at the first viable candidate). With return_details=True the df_candidates report is correspondingly shorter under 'fast'.
max_interpret_grade (int, optional) – The maximum (worst) interpretability grade kept (1-10, where grade 1 is the best / most interpretable, so lower is better). Every feature whose scale subcategory is graded worse (higher) than this is targeted for replacement. If None (default), every improvable feature is attempted.
min_cor (float, default=0.7) – Minimum absolute Pearson correlation between a candidate scale and the original scale (between 0 and 1); anti-correlation is allowed via the absolute value.
ml_model (str or sklearn estimator, default='svm') – Model for the cross-validation gate ('greedy' / 'consolidate'). A string preset 'svm' (default; fast), 'rf' (recommended for non-linear feature relationships, but slower), or 'log_reg' (fastest); or any configured scikit-learn classifier instance (e.g. SVC(kernel='poly', C=0.1)), used as-is.
ml_metric (str, default='balanced_accuracy') – Scoring metric for the CV gate (any scikit-learn classification scorer name).
ml_th (float, default=0.0) – CV-gate tolerance: a swap is accepted if its CV score is at least baseline - ml_th (>=0).
ml_cv (int, default=5) – Number of cross-validation folds (>=2, <= smallest class count).
allow_drop (bool, default=True) – Whether simplify may drop features. If False, it only swaps scales and never removes a feature, so the output keeps every input feature 1:1 (the redundancy reduction is skipped and on_unimprovable is forced to 'keep').
on_unimprovable (str, default='keep') – What to do with a targeted feature that cannot be improved: 'keep' (retain the original), 'drop' (remove it), or 'drop_if_perf_allows' (remove only if the CV score does not drop). The last feature is never dropped.
redundancy_tie_break (str, default='interpretability') – When two swapped features are redundant, keep the 'interpretability'-best (then abs_auc) or the 'performance'-best (abs_auc).
label_test (int, default=1) – Class label of the test group in labels.
label_ref (int, default=0) – Class label of the reference group in labels.
max_std_test (float, default=0.2) – Per-feature pre-filter threshold a swapped feature must satisfy (between 0 and 1).
max_cor (float, default=0.5) – Redundancy correlation threshold for the post-swap reduction (between 0 and 1).
max_overlap (float, default=0.5) – Redundancy position-overlap threshold for the post-swap reduction (between 0 and 1).
check_cat (bool, default=True) – Whether the redundancy reduction only compares features within the same scale category.
return_details (bool, default=False) – If True, also return a long-form df_candidates reporting every candidate considered (scale, interpretability, correlation, recomputed std, accepted-flag).

Returns:

df_feat (pd.DataFrame) – The simplified feature DataFrame (CPP output schema), with swapped scales, recomputed statistics, and redundant features removed.
df_candidates (pd.DataFrame) – Returned only if return_details=True: one row per candidate considered.

Notes

The CV-gate model is seeded from the CPP instance’s random_state; set it once via aa.CPP(..., random_state=...) for a reproducible result.
Redundancy reduction protects original features — it never drops a feature the user already had, it only removes a swapped feature when the swap made it redundant with a kept feature (using signed correlation, matching run()).
The strategy controls how swaps are chosen and validated:
- ‘greedy’: per-feature. Each targeted feature is swapped to its best correlated candidate that keeps the cross-validation score within ml_th of the current set; otherwise the next candidate is tried. Each swap is individually justified.
- ‘consolidate’: set-level. Interpretable subcategories are taken best-first, and every targeted feature that can move into the current subcategory is swapped as one batch, which is kept only if the set CV score stays within ml_th. Funnels features into the fewest subcategories.
- ‘swap_all’: apply every eligible best-candidate swap with no cross-validation (fastest); ml_model / ml_metric / ml_th / ml_cv are ignored. A pure interpretability transform to evaluate yourself afterwards.
Features whose scale is not a rated AAontology scale (e.g. run_num pseudo-scales or unclassified scales) carry no interpretability grade and are skipped. If no feature is rated, df_feat is returned unchanged with a RuntimeWarning.
An anti-correlated swap flips the sign of mean_dif (the feature still discriminates); the correlation sign is reported in df_candidates.

See also

run() for the feature DataFrame produced and its schema.
load_scales() for the interpretability-tiered explainable scale sets (top_explain_n).

Examples

CPP().simplify() rewrites a fitted df_feat into a more interpretable, and ideally smaller one. For each feature (PART-SPLIT-SCALE) it swaps the scale for a correlated scale from a better-graded AAontology subcategory (interpretability grade 1-10, where grade 1 is the best, so lower is better), recomputes the feature statistics, and accepts the swap only if it keeps passing CPP filtering and does not reduce a cross-validation score. The swapped set is then redundancy-reduced without dropping any original feature (only a swapped feature that became redundant is removed). We start from a precomputed DOM_GSEC feature set (see [Breimann25]), which already carries feat_importance:

import aaanalysis as aa
aa.options["verbose"] = False
df_feat = aa.load_features(name="DOM_GSEC")
df_seq = aa.load_dataset(name="DOM_GSEC")
labels = df_seq["label"].to_list()
sf = aa.SequenceFeature()
df_parts = sf.get_df_parts(df_seq=df_seq)
# Reproducibility: the CV-gate model is seeded from the CPP instance's random_state
cpp = aa.CPP(df_parts=df_parts, random_state=0)
aa.display_df(df_feat, n_rows=5, show_shape=True)

DataFrame shape: (150, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...3,4)-HUTJ700102	Energy	Entropy	Entropy	Absolute entrop...Hutchens, 1970)	0.229000	0.098224	0.098224	0.106865	0.124608	0.000001	31,32,33,34,35	3.111200	3.109955
5	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000002	32,33	0.000000	0.000000

With only df_feat and labels, simplify runs the default greedy strategy with an SVM cross-validation gate and returns the simplified feature set:

df_simple = cpp.simplify(df_feat=df_feat, labels=labels)
aa.display_df(df_simple, show_shape=True)

DataFrame shape: (94, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
13	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
14	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
15	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
16	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
18	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
19	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
20	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
21	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
22	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
23	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
24	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
25	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
26	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
27	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
28	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
29	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
30	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
31	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
32	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
33	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
34	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
35	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
36	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
37	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
38	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
39	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
40	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
41	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
42	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
43	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
44	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
45	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
46	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
47	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
48	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
49	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
50	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
51	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
52	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
53	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
54	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
55	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
56	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
57	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
58	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
59	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
60	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
61	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
62	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
63	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
64	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
65	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
66	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
67	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
68	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
69	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
70	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
71	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
72	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
73	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
74	TMD_C_JMD_C-Pat...4,8)-KARS160103	Shape	Side chain length	Graph (weighted degree)	Total weighted ...-Knisley, 2016)	0.153000	0.052948	0.052948	0.106553	0.121516	0.002988	0.002988	33,37,40	nan	nan
75	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
76	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
77	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
78	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
79	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
80	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
81	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
82	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
83	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
84	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
85	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
86	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
87	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
88	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
89	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
90	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
91	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
92	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
93	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
94	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

max_interpret_grade caps the worst interpretability grade allowed to remain (1 = best). With max_interpret_grade=2 every feature graded worse than 2 is targeted for replacement; if it is None (default) every improvable feature is attempted:

df_grade = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2)
aa.display_df(df_grade, show_shape=True)

DataFrame shape: (96, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
13	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
14	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
15	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
16	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
18	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
19	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
20	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
21	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
22	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
23	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
24	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
25	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
26	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
27	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
28	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
29	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
30	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
31	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
32	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
33	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
34	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
35	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
36	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
37	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
38	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
39	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
40	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
41	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
42	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
43	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
44	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
45	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
46	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
47	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
48	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
49	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
50	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
51	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
52	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
53	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
54	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
55	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
56	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
57	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
58	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
59	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
60	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
61	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
62	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
63	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
64	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
65	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
66	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
67	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
68	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
69	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
70	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
71	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
72	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
73	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
74	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
75	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
76	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
77	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
78	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
79	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
80	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
81	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
82	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
83	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
84	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
85	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
86	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
87	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
88	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
89	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
90	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
91	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
92	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
93	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
94	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
95	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
96	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

The strategy controls how swaps are chosen and validated. greedy swaps feature by feature behind the CV gate; consolidate batches features by subcategory toward the fewest subcategories; swap_all applies every eligible swap with no cross-validation (fastest):

import pandas as pd
rows = []
for strategy in ["greedy", "consolidate", "swap_all"]:
    out = cpp.simplify(df_feat=df_feat, labels=labels, strategy=strategy)
    rows.append([strategy, len(out), out["subcategory"].nunique()])
df_strategies = pd.DataFrame(rows, columns=["strategy", "n_features", "n_subcategories"])
aa.display_df(df_strategies)

	strategy	n_features	n_subcategories
1	greedy	94	25
2	consolidate	92	25
3	swap_all	94	25

The candidate_search mode trades exactness for speed. exact (default) tests every eligible candidate per feature and reproduces the result exactly; fast is an opt-in heuristic that caps the search to the most promising candidates (best interpretability, then strongest correlation), which speeds up large scale pools — it mainly accelerates greedy (swap_all already stops at the first viable candidate). The kept-feature set stays close to exact:

df_exact = cpp.simplify(df_feat=df_feat, labels=labels, candidate_search="exact")
df_fast = cpp.simplify(df_feat=df_feat, labels=labels, candidate_search="fast")
kept_exact, kept_fast = set(df_exact["feature"]), set(df_fast["feature"])
jaccard = len(kept_exact & kept_fast) / len(kept_exact | kept_fast)
df_cs = pd.DataFrame([["exact", len(df_exact)], ["fast", len(df_fast)]],
                     columns=["candidate_search", "n_features"])
print(f"kept-feature Jaccard (fast vs exact): {jaccard:.2f}")
aa.display_df(df_cs)

kept-feature Jaccard (fast vs exact): 1.00

	candidate_search	n_features
1	exact	94
2	fast	94

The cross-validation gate (greedy / consolidate) decides whether a swap is kept. ml_model selects the classifier — a preset 'svm' (default; fast), 'rf' (recommended for non-linear relationships, slower), or 'log_reg' (fastest), or a custom scikit-learn estimator instance. ml_metric is the scoring metric, ml_cv the number of folds, and ml_th the tolerated CV-score drop (a swap is kept if its score is at least baseline - ml_th):

df_rf = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                     ml_model="rf", ml_metric="accuracy", ml_cv=3, ml_th=0.05)
aa.display_df(df_rf, show_shape=True)

DataFrame shape: (96, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
13	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
14	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
15	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
16	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
18	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
19	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
20	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
21	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
22	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
23	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
24	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
25	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
26	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
27	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
28	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
29	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
30	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
31	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
32	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
33	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
34	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
35	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
36	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
37	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
38	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
39	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
40	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
41	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
42	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
43	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
44	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
45	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
46	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
47	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
48	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
49	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
50	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
51	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
52	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
53	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
54	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
55	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
56	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
57	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
58	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
59	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
60	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
61	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
62	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
63	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
64	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
65	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
66	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
67	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
68	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
69	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
70	TMD_C_JMD_C-Seg...,11)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.280000	0.112063	0.112063	0.084763	0.131666	0.000000	0.000000	28,29	nan	nan
71	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
72	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
73	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
74	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
75	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
76	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
77	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
78	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
79	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
80	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
81	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
82	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
83	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
84	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
85	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
86	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
87	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
88	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
89	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
90	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
91	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
92	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
93	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
94	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
95	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
96	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

A custom estimator instance can be passed directly as ml_model (used as-is):

from sklearn.svm import SVC
df_custom = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                         ml_model=SVC(kernel="linear"))
aa.display_df(df_custom, show_shape=True)

DataFrame shape: (109, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	TMD_C_JMD_C-Seg...6,9)-RICJ880113	Conformation	α-helix (C-cap)	α-helix (C-terminal, inside)	Relative prefer...chardson, 1988)	0.198000	0.138293	0.138293	0.172194	0.198814	0.000000	0.000017	32,33	0.832400	1.383718
13	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
14	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
15	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
16	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
17	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
18	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
19	JMD_N_TMD_N-Pat...,10)-AURR980116	Conformation	α-helix (C-cap)	α-helix (C-terminal, C-cap)	Normalized posi...ora-Rose, 1998)	0.184000	0.112728	-0.112728	0.166431	0.183800	0.000001	0.000061	11,15	0.857600	1.339550
20	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
21	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
22	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
23	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
24	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
25	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
26	TMD-Pattern(N,4,7)-AURR980116	Conformation	α-helix (C-cap)	α-helix (C-terminal, C-cap)	Normalized posi...ora-Rose, 1998)	0.181000	0.118349	-0.118349	0.169282	0.185522	0.000002	0.000078	14,17	1.226400	1.510986
27	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
28	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
29	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
30	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
31	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
32	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
33	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
34	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
35	TMD_C_JMD_C-Seg...4,5)-TANS770106	Conformation	β-turn (TM helix)	β-turn in double bend	Normalized freq...Scheraga, 1977)	0.175000	0.078020	0.078020	0.113536	0.125285	0.000005	0.000129	33,34,35,36	0.000000	0.000000
36	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
37	JMD_N_TMD_N-Per...4,3)-QIAN880138	Conformation	Coil (C-term)	Coil (C-terminal)	Weights for coi...ejnowski, 1988)	0.174000	0.067216	0.067216	0.105047	0.116197	0.000005	0.000133	1,4,8,11,15,18	0.000000	0.000000
38	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
39	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
40	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
41	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
42	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
43	JMD_N_TMD_N-Pat...,11)-QIAN880127	Conformation	Coil (N-term)	Coil (N-terminal)	Weights for coi...ejnowski, 1988)	0.168000	0.071770	-0.071770	0.116934	0.123667	0.000011	0.000216	4,7,11	0.616400	1.124195
44	TMD_C_JMD_C-Seg...2,2)-RICJ880113	Conformation	α-helix (C-cap)	α-helix (C-terminal, inside)	Relative prefer...chardson, 1988)	0.168000	0.067627	0.067627	0.098469	0.110321	0.000011	0.000215	31,32,33,34,35,36,37,38,39,40	1.105200	1.425601
45	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
46	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
47	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
48	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
49	TMD-Pattern(C,5...,12)-HUTJ700102	Energy	Entropy	Entropy	Absolute entrop...Hutchens, 1970)	0.165000	0.063134	-0.063134	0.104624	0.113955	0.000015	0.000258	19,22,26	0.000000	0.000000
50	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
51	TMD_C_JMD_C-Pat...,12)-CHOP780212	Conformation	β-sheet (C-term)	β-turn (1st residue)	Frequency of th...-Fasman, 1978b)	0.164000	0.076207	-0.076207	0.125506	0.147002	0.000016	0.000267	24,28,32	1.095600	1.575630
52	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
53	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
54	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
55	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
56	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
57	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
58	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
59	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
60	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
61	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
62	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
63	JMD_N_TMD_N-Pat...,13)-RICJ880107	Conformation	π-helix	α-helix	Relative prefer...chardson, 1988)	0.155000	0.066867	-0.066867	0.105803	0.129430	0.000047	0.000496	3,6,9,13	0.335200	0.649905
64	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
65	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
66	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
67	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
68	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
69	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
70	TMD-Pattern(N,2...,11)-RACS820101	Conformation	β-sheet (N-term)	α-helix with fl...α structure (i)	Average relativ...Scheraga, 1982)	0.153000	0.062678	-0.062678	0.109868	0.123054	0.000061	0.000570	12,15,18,21	0.333600	0.598524
71	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
72	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
73	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
74	JMD_N_TMD_N-Pat...,11)-RACS820101	Conformation	β-sheet (N-term)	α-helix with fl...α structure (i)	Average relativ...Scheraga, 1982)	0.149000	0.063073	-0.063073	0.107731	0.126806	0.000091	0.000716	10,13,16,19	0.000000	0.000000
75	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
76	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
77	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
78	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
79	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
80	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
81	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
82	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
83	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
84	JMD_N_TMD_N-Seg...3,6)-VASM830102	Energy	Non-bonded energy	Free energy (Extended)	Relative popula...z et al., 1983)	0.141000	0.067593	0.067593	0.146572	0.140332	0.000225	0.001173	7,8,9,10	0.484800	0.832789
85	TMD_C_JMD_C-Pat...,14)-FUKS010111	Composition	AA composition	Proteins of mesophiles (EXT)	Entire chain co...ishikawa, 2001)	0.003000	0.015230	-0.015230	0.140051	0.227922	0.959141	0.959141	30,34	nan	nan
86	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
87	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
88	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
89	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
90	TMD_C_JMD_C-Pat...,10)-QIAN880138	Conformation	Coil (C-term)	Coil (C-terminal)	Weights for coi...ejnowski, 1988)	0.137000	0.065719	-0.065719	0.114425	0.146722	0.000312	0.001404	31,35,39	0.360800	0.882718
91	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
92	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
93	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
94	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
95	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
96	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
97	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
98	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
99	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
100	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
101	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
102	JMD_N_TMD_N-Pat...,11)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.130000	0.087733	-0.087733	0.180612	0.187328	0.000674	0.002190	10,13,17	0.420000	0.643453
103	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
104	JMD_N_TMD_N-Pat...,11)-VASM830102	Energy	Non-bonded energy	Free energy (Extended)	Relative popula...z et al., 1983)	0.129000	0.077724	0.077724	0.148907	0.164954	0.000708	0.002247	4,8,11	0.160400	0.302939
105	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
106	JMD_N_TMD_N-Seg...3,9)-KOEP990102	Conformation	β-sheet (N-term)	Extended (designed β-sheet)	Beta-sheet prop...l-Levitt, 1999)	0.128000	0.086726	0.086726	0.184173	0.184291	0.000769	0.002364	5,6	0.565600	0.778424
107	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
108	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
109	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

Candidate eligibility and per-feature filtering. min_cor is the minimum absolute correlation a candidate scale must have with the original scale (anti-correlation allowed), and max_std_test is the CPP per-feature pre-filter threshold the recomputed swapped feature must satisfy:

df_strict = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                         min_cor=0.8, max_std_test=0.2)
aa.display_df(df_strict, show_shape=True)

DataFrame shape: (120, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...3,4)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.289000	0.193943	0.193943	0.159718	0.184043	0.000000	0.000000	31,32,33,34,35	nan	nan
11	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
12	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
13	TMD_C_JMD_C-Seg...3,4)-PRAM820102	Shape	Shape and Surface	Slope in Regression	Slope in Regres...nnuswamy, 1982)	0.199000	0.073023	-0.073023	0.087336	0.107750	0.000000	0.000017	31,32,33,34,35	0.616000	0.847660
14	TMD_C_JMD_C-Seg...6,9)-RICJ880113	Conformation	α-helix (C-cap)	α-helix (C-terminal, inside)	Relative prefer...chardson, 1988)	0.198000	0.138293	0.138293	0.172194	0.198814	0.000000	0.000017	32,33	0.832400	1.383718
15	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
16	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
18	TMD_C_JMD_C-Seg...6,9)-TANS770106	Conformation	β-turn (TM helix)	β-turn in double bend	Normalized freq...Scheraga, 1977)	0.189000	0.093759	0.093759	0.136715	0.137320	0.000001	0.000039	32,33	0.000000	0.000000
19	TMD_C_JMD_C-Pat...4,8)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.283000	0.239889	0.239889	0.181777	0.235674	0.000000	0.000000	33,37	nan	nan
20	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
21	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
22	JMD_N_TMD_N-Pat...,10)-AURR980116	Conformation	α-helix (C-cap)	α-helix (C-terminal, C-cap)	Normalized posi...ora-Rose, 1998)	0.184000	0.112728	-0.112728	0.166431	0.183800	0.000001	0.000061	11,15	0.857600	1.339550
23	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
24	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
25	TMD_C_JMD_C-Seg...4,5)-RICJ880113	Conformation	α-helix (C-cap)	α-helix (C-terminal, inside)	Relative prefer...chardson, 1988)	0.182000	0.121315	0.121315	0.147184	0.184212	0.000002	0.000070	33,34,35,36	0.865200	1.553379
26	TMD-Pattern(C,3...,15)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.182000	0.098529	-0.098529	0.141641	0.162412	0.000002	0.000072	16,20,24,28	0.221200	0.519240
27	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
28	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
29	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
30	TMD-Pattern(N,4,7)-AURR980116	Conformation	α-helix (C-cap)	α-helix (C-terminal, C-cap)	Normalized posi...ora-Rose, 1998)	0.181000	0.118349	-0.118349	0.169282	0.185522	0.000002	0.000078	14,17	1.226400	1.510986
31	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
32	TMD_C_JMD_C-Pat...,12)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.180000	0.096784	-0.096784	0.151260	0.170153	0.000002	0.000084	25,29,32	0.356800	0.617224
33	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
34	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
35	JMD_N_TMD_N-Per...4,3)-QIAN880138	Conformation	Coil (C-term)	Coil (C-terminal)	Weights for coi...ejnowski, 1988)	0.179000	0.069852	0.069852	0.103576	0.116589	0.000003	0.000093	3,6,10,13,17,20	0.385200	0.555965
36	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
37	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
38	TMD_C_JMD_C-Pat...,12)-FAUJ880108	Energy	Electron-ion interaction pot.	Electrical Effect	Localized Elect...e et al., 1988)	0.176000	0.064253	-0.064253	0.092619	0.113588	0.000004	0.000113	21,24,28,32	0.826400	1.303426
39	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
40	TMD_C_JMD_C-Seg...4,5)-TANS770106	Conformation	β-turn (TM helix)	β-turn in double bend	Normalized freq...Scheraga, 1977)	0.175000	0.078020	0.078020	0.113536	0.125285	0.000005	0.000129	33,34,35,36	0.000000	0.000000
41	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
42	JMD_N_TMD_N-Per...4,3)-QIAN880138	Conformation	Coil (C-term)	Coil (C-terminal)	Weights for coi...ejnowski, 1988)	0.174000	0.067216	0.067216	0.105047	0.116197	0.000005	0.000133	1,4,8,11,15,18	0.000000	0.000000
43	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
44	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
45	TMD_C_JMD_C-Seg...2,3)-PRAM820102	Shape	Shape and Surface	Slope in Regression	Slope in Regres...nnuswamy, 1982)	0.172000	0.056268	-0.056268	0.074692	0.093571	0.000006	0.000151	27,28,29,30,31,32,33	0.303600	0.618242
46	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
47	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
48	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
49	TMD_C_JMD_C-Seg...2,2)-RICJ880113	Conformation	α-helix (C-cap)	α-helix (C-terminal, inside)	Relative prefer...chardson, 1988)	0.168000	0.067627	0.067627	0.098469	0.110321	0.000011	0.000215	31,32,33,34,35,36,37,38,39,40	1.105200	1.425601
50	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
51	TMD-Pattern(C,5...,12)-PRAM820102	Shape	Shape and Surface	Slope in Regression	Slope in Regres...nnuswamy, 1982)	0.167000	0.077343	0.077343	0.135340	0.134263	0.000012	0.000228	19,22,26	1.301600	1.697263
52	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
53	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
54	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
55	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
56	TMD-PeriodicPat...3,1)-COHE430101	ASA/Volume	Partial specific volume	Partial specific volume	Partial specifi...n-Edsall, 1943)	0.164000	0.058745	0.058745	0.092103	0.106413	0.000017	0.000276	12,15,18,21,24,27,30	1.141600	1.375595
57	TMD-Pattern(C,4,7)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.163000	0.128817	-0.128817	0.184672	0.227780	0.000020	0.000293	24,27	0.872800	1.063156
58	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
59	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
60	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
61	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
62	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
63	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
64	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
65	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
66	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
67	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
68	JMD_N_TMD_N-Pat...,13)-RICJ880107	Conformation	π-helix	α-helix	Relative prefer...chardson, 1988)	0.155000	0.066867	-0.066867	0.105803	0.129430	0.000047	0.000496	3,6,9,13	0.335200	0.649905
69	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
70	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
71	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
72	TMD-Pattern(C,5...,12)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.154000	0.062226	0.062226	0.144085	0.119863	0.000057	0.000548	19,22,26	0.715200	1.186306
73	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
74	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
75	TMD-Pattern(N,2...,11)-RACS820101	Conformation	β-sheet (N-term)	α-helix with fl...α structure (i)	Average relativ...Scheraga, 1982)	0.153000	0.062678	-0.062678	0.109868	0.123054	0.000061	0.000570	12,15,18,21	0.333600	0.598524
76	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
77	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
78	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
79	TMD_C_JMD_C-Pat...,13)-CHOP780212	Conformation	β-sheet (C-term)	β-turn (1st residue)	Frequency of th...-Fasman, 1978b)	0.149000	0.069627	-0.069627	0.113251	0.143949	0.000093	0.000725	26,29,33	0.842800	1.314094
80	JMD_N_TMD_N-Pat...,11)-RACS820101	Conformation	β-sheet (N-term)	α-helix with fl...α structure (i)	Average relativ...Scheraga, 1982)	0.149000	0.063073	-0.063073	0.107731	0.126806	0.000091	0.000716	10,13,16,19	0.000000	0.000000
81	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
82	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
83	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
84	TMD_C_JMD_C-Seg...2,5)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.147000	0.079575	-0.079575	0.145620	0.160200	0.000115	0.000811	25,26,27,28	0.322000	0.559943
85	TMD-Pattern(C,4...,11)-RICJ880107	Conformation	π-helix	α-helix	Relative prefer...chardson, 1988)	0.146000	0.068957	0.068957	0.131400	0.140413	0.000131	0.000868	20,23,27	0.697200	1.056350
86	TMD_C_JMD_C-Seg...,11)-COHE430101	ASA/Volume	Partial specific volume	Partial specific volume	Partial specifi...n-Edsall, 1943)	0.145000	0.124999	0.124999	0.180151	0.242281	0.000145	0.000912	28,29	1.740800	2.317117
87	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
88	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
89	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
90	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
91	JMD_N_TMD_N-Seg...3,6)-VASM830102	Energy	Non-bonded energy	Free energy (Extended)	Relative popula...z et al., 1983)	0.141000	0.067593	0.067593	0.146572	0.140332	0.000225	0.001173	7,8,9,10	0.484800	0.832789
92	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
93	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
94	TMD_C_JMD_C-Pat...,12)-QIAN880114	Conformation	β-sheet (N-term)	β-sheet (N-terminal)	Weights for bet...ejnowski, 1988)	0.138000	0.070821	-0.070821	0.121293	0.151868	0.000310	0.001400	24,28,32	0.718800	1.295090
95	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
96	TMD_C_JMD_C-Pat...,15)-KOEH090102	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.186000	0.073577	0.073577	0.103456	0.126131	0.000305	0.000305	26,30,33	nan	nan
97	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
98	TMD_C_JMD_C-Pat...,10)-QIAN880138	Conformation	Coil (C-term)	Coil (C-terminal)	Weights for coi...ejnowski, 1988)	0.137000	0.065719	-0.065719	0.114425	0.146722	0.000312	0.001404	31,35,39	0.360800	0.882718
99	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
100	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
101	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
102	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
103	TMD_C_JMD_C-Seg...6,9)-PALJ810113	Conformation	α-helix (left-handed)	β-turn (α class)	Normalized freq...u et al., 1981)	0.135000	0.072992	-0.072992	0.138972	0.165851	0.000412	0.001667	32,33	0.292400	0.546994
104	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
105	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
106	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
107	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
108	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
109	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
110	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
111	TMD_C_JMD_C-Pat...,10)-TANS770106	Conformation	β-turn (TM helix)	β-turn in double bend	Normalized freq...Scheraga, 1977)	0.131000	0.056621	0.056621	0.144377	0.128425	0.000597	0.002043	31,34,38	0.726800	0.885807
112	JMD_N_TMD_N-Pat...,11)-ANDN920101	Structure-Activity	Backbone-dynamics (-CH)	α-CH chemical s...kbone-dynamics)	alpha-CH chemic...n et al., 1992)	0.130000	0.087733	-0.087733	0.180612	0.187328	0.000674	0.002190	10,13,17	0.420000	0.643453
113	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
114	JMD_N_TMD_N-Seg...2,4)-QIAN880114	Conformation	β-sheet (N-term)	β-sheet (N-terminal)	Weights for bet...ejnowski, 1988)	0.130000	0.058210	0.058210	0.127516	0.112411	0.000633	0.002111	6,7,8,9,10	0.140800	0.376807
115	JMD_N_TMD_N-Pat...,11)-VASM830102	Energy	Non-bonded energy	Free energy (Extended)	Relative popula...z et al., 1983)	0.129000	0.077724	0.077724	0.148907	0.164954	0.000708	0.002247	4,8,11	0.160400	0.302939
116	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
117	JMD_N_TMD_N-Seg...3,9)-KOEP990102	Conformation	β-sheet (N-term)	Extended (designed β-sheet)	Beta-sheet prop...l-Levitt, 1999)	0.128000	0.086726	0.086726	0.184173	0.184291	0.000769	0.002364	5,6	0.565600	0.778424
118	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
119	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
120	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

Unimprovable features. When a targeted feature has no accepted swap, on_unimprovable decides its fate: 'keep' (retain the original, default), 'drop' (remove it), or 'drop_if_perf_allows' (remove only if the CV score does not drop). The last feature is never dropped:

df_drop = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                       on_unimprovable="drop")
aa.display_df(df_drop, show_shape=True)

DataFrame shape: (78, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
3	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
4	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
6	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
7	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
8	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
9	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
10	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
11	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
12	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
13	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
14	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
15	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
16	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
17	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
18	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
19	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
20	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
21	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
22	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
23	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
24	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
25	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
26	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
27	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
28	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
29	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
30	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
31	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
32	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
33	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
34	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
35	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
36	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
37	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
38	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
39	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
40	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
41	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
42	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
43	TMD-Pattern(N,1...4,7)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.218000	0.114519	-0.114519	0.151936	0.147686	0.000024	0.000024	11,14,17	nan	nan
44	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
45	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
46	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
47	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
48	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
49	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
50	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
51	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
52	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
53	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
54	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
55	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
56	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
57	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
58	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
59	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
60	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
61	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
62	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
63	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
64	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
65	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
66	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
67	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
68	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
69	TMD_C_JMD_C-Seg...6,9)-PALJ810105	Conformation	β-turn	β-turn	Normalized freq...u et al., 1981)	0.087000	0.050175	-0.050175	0.089871	0.163195	0.091373	0.091373	32,33	nan	nan
70	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
71	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
72	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
73	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
74	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
75	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
76	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
77	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
78	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

Redundancy reduction removes only swapped features that became redundant — original features are always protected. redundancy_tie_break chooses the keeper of a redundant pair ('interpretability' or 'performance'); max_cor and max_overlap are the scale-correlation and position-overlap thresholds; and check_cat restricts comparisons to the same scale category:

df_red = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                      redundancy_tie_break="performance", max_cor=0.5, max_overlap=0.5,
                      check_cat=True)
aa.display_df(df_red, show_shape=True)

DataFrame shape: (96, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
13	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
14	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
15	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
16	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
18	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
19	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
20	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
21	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
22	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
23	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
24	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
25	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
26	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
27	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
28	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
29	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
30	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
31	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
32	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
33	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
34	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
35	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
36	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
37	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
38	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
39	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
40	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
41	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
42	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
43	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
44	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
45	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
46	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
47	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
48	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
49	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
50	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
51	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
52	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
53	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
54	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
55	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
56	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
57	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
58	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
59	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
60	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
61	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
62	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
63	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
64	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
65	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
66	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
67	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
68	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
69	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
70	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
71	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
72	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
73	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
74	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
75	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
76	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
77	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
78	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
79	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
80	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
81	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
82	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
83	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
84	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
85	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
86	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
87	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
88	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
89	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
90	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
91	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
92	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
93	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
94	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
95	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
96	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

label_test / label_ref name the test and reference classes in labels (default 1 / 0); set them to match a different encoding:

df_lab = cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=2,
                      label_test=1, label_ref=0)
aa.display_df(df_lab, show_shape=True)

DataFrame shape: (96, 15)

	feature	category	subcategory	scale_name	scale_description	abs_auc	abs_mean_dif	mean_dif	std_test	std_ref	p_val_mann_whitney	p_val_fdr_bh	positions	feat_importance	feat_importance_std
1	TMD_C_JMD_C-Seg...3,4)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.244000	0.103666	0.103666	0.106692	0.110506	0.000000	0.000000	31,32,33,34,35	0.970400	1.438918
2	TMD_C_JMD_C-Seg...3,4)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.243000	0.085064	0.085064	0.098774	0.096946	0.000000	0.000000	31,32,33,34,35	0.000000	0.000000
3	TMD_C_JMD_C-Seg...6,9)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.233000	0.137044	0.137044	0.161683	0.176964	0.000000	0.000001	32,33	1.554800	2.109848
4	TMD_C_JMD_C-Seg...6,9)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.223000	0.095071	0.095071	0.114758	0.132829	0.000000	0.000002	32,33	0.000000	0.000000
5	TMD_C_JMD_C-Seg...2,3)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.222000	0.058671	0.058671	0.064895	0.069547	0.000000	0.000001	27,28,29,30,31,32,33	0.000000	0.000000
6	TMD_C_JMD_C-Seg...3,4)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.215000	0.124317	0.124317	0.166309	0.153364	0.000000	0.000004	31,32,33,34,35	1.080400	1.296094
7	TMD_C_JMD_C-Seg...,10)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.212000	0.141305	-0.141305	0.168603	0.217235	0.000000	0.000005	33,34	1.747200	2.150664
8	TMD_C_JMD_C-Seg...6,9)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.125350	0.125350	0.160819	0.174121	0.000000	0.000005	32,33	1.788800	2.700803
9	TMD_C_JMD_C-Seg...2,3)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.211000	0.077355	0.077355	0.102965	0.107453	0.000000	0.000005	27,28,29,30,31,32,33	3.048800	3.623912
10	TMD_C_JMD_C-Seg...6,9)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.205000	0.125868	-0.125868	0.172165	0.188333	0.000000	0.000009	32,33	0.000000	0.000000
11	TMD_C_JMD_C-Seg...4,5)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.204000	0.105513	0.105513	0.132849	0.145219	0.000000	0.000009	33,34,35,36	1.992000	2.929460
12	JMD_N_TMD_N-Seg...1,2)-KARP850101	Structure-Activity	Flexibility	Flexibility (0 ...igid neighbors)	Flexibility par...s-Schulz, 1985)	0.196000	0.062671	0.062671	0.083456	0.090427	0.000000	0.000023	1,2,3,4,5,6,7,8,9,10	1.574400	1.835403
13	TMD_C_JMD_C-Seg...4,5)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.193000	0.076770	0.076770	0.092804	0.114150	0.000000	0.000027	33,34,35,36	0.000000	0.000000
14	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.189000	0.125674	0.125674	0.183876	0.218813	0.000001	0.000039	28,29	4.729200	4.776785
15	TMD_C_JMD_C-Seg...6,9)-KOEH090103	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.323000	0.248255	0.248255	0.196374	0.181558	0.000000	0.000000	32,33	nan	nan
16	TMD_C_JMD_C-Seg...4,5)-CHOC760103	ASA/Volume	Buried	Buried	Proportion of r...(Chothia, 1976)	0.185000	0.105474	-0.105474	0.157535	0.163039	0.000001	0.000059	33,34,35,36	0.000000	0.000000
17	TMD_C_JMD_C-Seg...6,9)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.185000	0.101798	0.101798	0.145676	0.155096	0.000001	0.000054	32,33	0.000000	0.000000
18	TMD_C_JMD_C-Pat...,15)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.184000	0.062096	0.062096	0.078809	0.091271	0.000000	0.000017	26,30,33	0.147200	0.345306
19	JMD_N_TMD_N-Seg...2,4)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.183000	0.063902	-0.063902	0.090842	0.101427	0.000002	0.000068	6,7,8,9,10	0.823200	1.404583
20	TMD-Pattern(C,3...,15)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.198000	0.109532	0.109532	0.133076	0.159918	0.000122	0.000122	16,20,24,28	nan	nan
21	TMD-Pattern(C,3...,15)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.182000	0.096246	0.096246	0.160859	0.159538	0.000002	0.000070	16,20,24,28	0.508400	0.738667
22	JMD_N_TMD_N-Seg...2,4)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.182000	0.066394	-0.066394	0.097857	0.103426	0.000002	0.000070	6,7,8,9,10	0.000000	0.000000
23	TMD_C_JMD_C-Seg...2,3)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.182000	0.063819	0.063819	0.101691	0.105987	0.000002	0.000071	27,28,29,30,31,32,33	0.000000	0.000000
24	TMD_C_JMD_C-Seg...,11)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.181000	0.057287	-0.057287	0.072234	0.106512	0.000002	0.000076	28,29	1.919600	2.094497
25	TMD_C_JMD_C-Pat...,12)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.220000	0.147418	0.147418	0.172594	0.195572	0.000020	0.000020	25,29,32	nan	nan
26	TMD-PeriodicPat...3,4)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.180000	0.069277	-0.069277	0.094949	0.119524	0.000002	0.000082	13,16,20,23,27	1.818000	2.308293
27	JMD_N_TMD_N-Pat...,15)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.179000	0.115042	-0.115042	0.151938	0.189623	0.000002	0.000068	6,9,12,15	0.648400	1.061142
28	TMD-Pattern(C,4,7)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.176000	0.120892	0.120892	0.198986	0.216030	0.000004	0.000113	24,27	0.714800	1.118149
29	TMD_C_JMD_C-Pat...4,8)-KANM800103	Conformation	α-helix	α-helix	Average relativ...sa-Tsong, 1980)	0.176000	0.087846	0.087846	0.140464	0.157561	0.000004	0.000113	24,28	2.704000	4.076269
30	TMD_C_JMD_C-Pat...,12)-BULH740102	ASA/Volume	Partial specific volume	Partial specific volume	Apparent partia...l-Breese, 1974)	0.262000	0.153437	0.153437	0.130978	0.164028	0.000000	0.000000	21,24,28,32	nan	nan
31	TMD-Pattern(C,4,7)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.176000	0.056675	-0.056675	0.099355	0.114698	0.000004	0.000113	24,27	0.372000	0.882270
32	TMD_C_JMD_C-Seg...2,3)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.175000	0.055597	-0.055597	0.089100	0.105827	0.000005	0.000126	27,28,29,30,31,32,33	0.664000	1.089536
33	TMD_C_JMD_C-Pat...,11)-QIAN880122	Conformation	β-strand	β-sheet	Weights for bet...ejnowski, 1988)	0.173000	0.056328	0.056328	0.067428	0.094795	0.000006	0.000147	25,28,31	0.483200	0.913371
34	JMD_N_TMD_N-Per...3,2)-CHAM830104	Shape	Side chain length	n atoms in side chain (2+1)	The number of a...-Charton, 1983)	0.172000	0.087470	-0.087470	0.135114	0.144731	0.000005	0.000137	2,5,8,11,14,17,20	0.444000	0.721620
35	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
36	TMD_C_JMD_C-Seg...2,3)-LINS030101	ASA/Volume	Volume	Accessible surface area (ASA)	Total accessibl...s et al., 2003)	0.239000	0.099677	0.099677	0.098523	0.119762	0.000004	0.000004	27,28,29,30,31,32,33	nan	nan
37	TMD_C_JMD_C-Seg...2,3)-KOEH090106	Polarity	Hydrophilicity	Polarity (hydrophilicity)	Hydrophobicity ...r et al. (2009)	0.224000	0.088025	0.088025	0.095746	0.124611	0.000014	0.000014	27,28,29,30,31,32,33	nan	nan
38	TMD_C_JMD_C-Seg...4,5)-OOBM770101	Polarity	Hydrophilicity	Non-bonded energy per atom	Average non-bon...take-Ooi, 1977)	0.277000	0.217063	0.217063	0.180330	0.208994	0.000000	0.000000	33,34,35,36	nan	nan
39	TMD_C_JMD_C-Pat...,14)-KLEP840101	Energy	Charge	Charge	Net charge (Kle...n et al., 1984)	0.168000	0.086323	0.086323	0.121405	0.138577	0.000000	0.000030	30,34	0.140400	0.391229
40	TMD_C_JMD_C-Seg...4,5)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.167000	0.080568	0.080568	0.128898	0.128726	0.000011	0.000218	33,34,35,36	1.299200	2.159535
41	TMD_C_JMD_C-Seg...4,5)-AURR980110	Conformation	α-helix	α-helix (middle)	Normalized posi...ora-Rose, 1998)	0.166000	0.081797	0.081797	0.121170	0.149555	0.000013	0.000239	33,34,35,36	1.295200	2.225137
42	TMD-Pattern(C,4,7)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.121210	-0.121210	0.143560	0.207767	0.000015	0.000254	24,27	1.302000	1.466618
43	TMD_C_JMD_C-Pat...5,8)-VELV850101	Energy	Electron-ion interaction pot.	Electron-ion in...ction potential	Electron-ion in...c et al., 1985)	0.165000	0.119568	-0.119568	0.143560	0.205817	0.000014	0.000253	25,28	0.000000	0.000000
44	TMD_C_JMD_C-Seg...5,7)-TANS770108	Conformation	β/α-bridge	β/α-bridge	Normalized freq...Scheraga, 1977)	0.164000	0.079708	0.079708	0.135324	0.137910	0.000016	0.000271	32,33,34	0.462400	0.706967
45	TMD-PeriodicPat...3,1)-OOBM850101	Structure-Activity	Stability	Stability (extended-coil)	Optimized beta-...e et al., 1985)	0.197000	0.046799	0.046799	0.052251	0.070467	0.000133	0.000133	12,15,18,21,24,27,30	nan	nan
46	TMD-Pattern(C,4,7)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.300000	0.236619	0.236619	0.165353	0.219458	0.000000	0.000000	24,27	nan	nan
47	TMD_C_JMD_C-Pat...,11)-EISD860101	Polarity	Hydrophobicity	Solvation free energy	Solvation free ...cLachlan, 1986)	0.162000	0.083936	-0.083936	0.143338	0.147948	0.000021	0.000304	30,33,37	0.330400	0.377566
48	TMD_C_JMD_C-Pat...5,8)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.162000	0.070292	-0.070292	0.096915	0.128362	0.000020	0.000302	21,25,28	1.528400	2.418922
49	TMD-Pattern(C,4...,11)-QIAN880130	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.161000	0.068424	-0.068424	0.096915	0.126975	0.000024	0.000332	20,24,27	0.000000	0.000000
50	JMD_N_TMD_N-Seg...2,4)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.161000	0.058976	-0.058976	0.096823	0.114647	0.000025	0.000335	6,7,8,9,10	0.000000	0.000000
51	JMD_N_TMD_N-Pat...,11)-PRAM820103	Shape	Shape and Surface	Correlation coe...t in regression	Correlation coe...nnuswamy, 1982)	0.161000	0.057828	0.057828	0.088362	0.106085	0.000024	0.000328	1,5,8,11	1.304400	1.657101
52	TMD_C_JMD_C-Seg...5,7)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.160000	0.059281	-0.059281	0.100693	0.120806	0.000027	0.000359	32,33,34	0.757200	1.471249
53	TMD_C_JMD_C-Pat...4,8)-FINA910104	Conformation	α-helix (C-cap)	α-helix termination	Helix terminati...n et al., 1991)	0.159000	0.103808	0.103808	0.140977	0.179008	0.000014	0.000248	33,37	0.233200	0.593921
54	JMD_N_TMD_N-Seg...,13)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.157000	0.127895	-0.127895	0.151304	0.258491	0.000035	0.000420	5,6	0.833200	1.360696
55	TMD_C_JMD_C-Pat...4,8)-JANJ780101	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	Average accessi...n et al., 1978)	0.155000	0.110281	0.110281	0.178578	0.202098	0.000046	0.000486	33,37,40	0.272400	0.623809
56	JMD_N_TMD_N-Pat...,12)-AURR980113	Conformation	α-helix	α-helix	Normalized posi...ora-Rose, 1998)	0.208000	0.105550	-0.105550	0.151448	0.143693	0.000055	0.000055	9,12,15	nan	nan
57	JMD_N_TMD_N-Pat...,15)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.155000	0.059593	-0.059593	0.104862	0.110749	0.000050	0.000508	6,9,12,15	0.482000	0.672000
58	JMD_N_TMD_N-Pat...,11)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.154000	0.092099	-0.092099	0.142836	0.171547	0.000052	0.000520	4,7,11	1.065200	1.916900
59	TMD_C_JMD_C-Seg...,10)-CHAM820102	Polarity	Hydrophobicity (interface)	Free energy (interface)	Free energy of ...-Charton, 1982)	0.154000	0.082300	-0.082300	0.136264	0.177551	0.000050	0.000508	33,34	0.366800	0.691767
60	TMD-Pattern(C,5...,12)-FAUJ880107	Structure-Activity	Stability	α-CH chemical s...kbone-dynamics)	N.m.r. chemical...e et al., 1988)	0.123000	0.065435	-0.065435	0.173044	0.140726	0.017378	0.017378	19,22,26	nan	nan
61	TMD_C_JMD_C-Pat...,11)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.153000	0.085041	-0.085041	0.135864	0.161279	0.000059	0.000561	30,33,37	0.473600	0.930690
62	TMD_C_JMD_C-Pat...,15)-WILM950103	Polarity	Hydrophobicity (interface)	Hydrophobicity (interface)	Hydrophobicity ...e et al., 1995)	0.153000	0.069595	-0.069595	0.107314	0.134698	0.000060	0.000566	26,29,33	0.770800	1.299178
63	TMD_C_JMD_C-Pat...,15)-LINS030106	ASA/Volume	Accessible surface area (ASA)	Hydrophilic ASA...olded proteins)	Hydrophilic med...s et al., 2003)	0.151000	0.071208	0.071208	0.136279	0.155749	0.000078	0.000657	26,30,33	0.326400	0.451202
64	TMD-Pattern(C,3...,14)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.150000	0.056439	-0.056439	0.094520	0.108682	0.000084	0.000685	17,20,24,28	0.684400	0.941892
65	TMD_C_JMD_C-Pat...,10)-LEVM760105	Shape	Side chain length	Side chain length	Radius of gyrat... (Levitt, 1976)	0.149000	0.073526	0.073526	0.133612	0.157088	0.000090	0.000714	31,34,38	2.050800	2.338278
66	JMD_N_TMD_N-Seg...2,6)-ARGP820101	Polarity	Hydrophobicity	Hydrophobicity	Hydrophobicity ...s et al., 1982)	0.148000	0.076361	-0.076361	0.140513	0.148387	0.000108	0.000790	4,5,6	0.537200	1.041739
67	JMD_N_TMD_N-Pat...,15)-BROC820101	Polarity	Hydrophobicity	Hydrophobicity ...on coefficient)	Retention Coeff...e et al., 1982)	0.148000	0.067069	-0.067069	0.120409	0.137261	0.000103	0.000768	6,9,12,15	0.106400	0.249766
68	TMD_C_JMD_C-Pat...4,8)-CORJ870108	Polarity	Hydrophilicity	TOTLS index	TOTLS index (Co...e et al., 1987)	0.251000	0.170889	-0.170889	0.167914	0.219014	0.000001	0.000001	24,28	nan	nan
69	TMD_C_JMD_C-Seg...2,5)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.260000	0.141016	0.141016	0.107804	0.160336	0.000000	0.000000	25,26,27,28	nan	nan
70	TMD_C_JMD_C-Seg...,11)-LIFS790102	Conformation	β-strand	β-strand	Conformational ...n-Sander, 1979)	0.333000	0.246278	0.246278	0.183876	0.212529	0.000000	0.000000	28,29	nan	nan
71	JMD_N_TMD_N-Pat...,11)-BIGC670101	ASA/Volume	Volume	Volume	Residue volume (Bigelow, 1967)	0.143000	0.067181	-0.067181	0.141579	0.135502	0.000184	0.001045	5,8,11	0.382000	0.675082
72	JMD_N_TMD_N-Pat...,11)-CIDH920102	Polarity	Hydrophobicity	Hydrophobicity	Normalized hydr...d et al., 1992)	0.142000	0.070908	-0.070908	0.135389	0.144272	0.000190	0.001062	5,8,11	0.384400	0.570074
73	JMD_N_TMD_N-Pat...,14)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.142000	0.058743	-0.058743	0.117342	0.120311	0.000187	0.001056	6,10,14	0.197200	0.344958
74	TMD-Pattern(N,4,7)-QIAN880113	Conformation	π-helix	α-helix (C-terminal)	Weights for alp...ejnowski, 1988)	0.141000	0.070553	-0.070553	0.164819	0.154840	0.000217	0.001151	14,17	0.634800	0.816456
75	JMD_N_TMD_N-Seg...3,6)-PALJ810111	Conformation	β-sheet	β-sheet	Normalized freq...u et al., 1981)	0.108000	0.053468	-0.053468	0.129405	0.141614	0.035900	0.035900	7,8,9,10	nan	nan
76	TMD_C_JMD_C-Pat...4,8)-MITS020101	Polarity	Amphiphilicity	Amphiphilicity	Amphiphilicity ...u et al., 2002)	0.140000	0.066859	0.066859	0.130397	0.147129	0.000229	0.001185	33,37,40	0.334800	0.632640
77	JMD_N_TMD_N-Seg...2,7)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.139000	0.070195	-0.070195	0.113589	0.146944	0.000259	0.001276	3,4,5	0.498800	0.924962
78	JMD_N_TMD_N-Seg...2,6)-RACS770103	ASA/Volume	Accessible surface area (ASA)	Side chain orientation	Side chain orie...Scheraga, 1977)	0.138000	0.069674	0.069674	0.151437	0.143090	0.000308	0.001398	4,5,6	0.214400	0.501327
79	TMD_C_JMD_C-Seg...4,8)-MIYS850101	Polarity	Hydrophobicity	Effective partition energy	Effective parti...Jernigan, 1985)	0.215000	0.123198	0.123198	0.127012	0.166940	0.000030	0.000030	28,29,30	nan	nan
80	JMD_N_TMD_N-Seg...7,8)-KARS160114	Shape	Side chain length	Eccentricity (average)	Average weighte...-Knisley, 2016)	0.137000	0.056352	-0.056352	0.122287	0.122893	0.000322	0.001432	16,17	1.170800	1.925978
81	TMD_C_JMD_C-Seg...,14)-ROSM880103	Structure-Activity	Backbone-dynamics (-CH)	Loss of hydropa...helix formation	Loss of Side ch...(Roseman, 1988)	0.136000	0.080537	-0.080537	0.194254	0.165343	0.000150	0.000932	26,27	0.638000	0.796859
82	TMD_C_JMD_C-Seg...,10)-BAEK050101	Conformation	β-strand	Linker index (n...AA long region)	Linker index (B...e et al., 2005)	0.136000	0.072267	-0.072267	0.142246	0.173638	0.000352	0.001527	33,34	1.013200	1.315181
83	TMD_C_JMD_C-Pat...5,8)-LINS030107	ASA/Volume	Accessible surface area (ASA)	ASA (folded protein)	% total accessi...s et al., 2003)	0.136000	0.064864	-0.064864	0.078387	0.131618	0.000367	0.001565	25,28	0.842000	0.904274
84	JMD_N_TMD_N-Pat...6,9)-ZHOH040101	Structure-Activity	Stability	Stability	The stability s...hou-Zhou, 2004)	0.135000	0.062723	-0.062723	0.120282	0.141044	0.000396	0.001638	3,6,9	0.696800	1.062095
85	TMD-Pattern(N,1...4,7)-RADA880106	ASA/Volume	Volume	Accessible surface area (ASA)	Accessible surf...olfenden, 1988)	0.135000	0.058024	-0.058024	0.115415	0.124556	0.000385	0.001610	11,14,17	0.244400	0.503183
86	JMD_N_TMD_N-Seg...,10)-CRAJ730102	Conformation	β-sheet	β-sheet	Normalized freq...d et al., 1973)	0.134000	0.096792	-0.096792	0.182935	0.210285	0.000461	0.001775	5,6	0.485600	0.792949
87	JMD_N_TMD_N-Pat...,14)-QIAN880134	Conformation	Coil	Coil	Weights for coi...ejnowski, 1988)	0.133000	0.071020	0.071020	0.161372	0.138873	0.000491	0.001836	6,10,14	0.000000	0.000000
88	JMD_N_TMD_N-Seg...7,9)-BURA740102	Conformation	β-strand	Extended	Normalized freq...s et al., 1974)	0.132000	0.056043	0.056043	0.119813	0.123454	0.000562	0.001981	14,15	0.231600	0.356019
89	TMD-Segment(3,8)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.132000	0.055783	-0.055783	0.129933	0.133383	0.000558	0.001977	16,17	0.502400	0.761626
90	TMD-Pattern(N,1...,10)-QIAN880124	Conformation	β-sheet (C-term)	β-sheet (C-terminal)	Weights for bet...ejnowski, 1988)	0.131000	0.069857	0.069857	0.157078	0.159138	0.000580	0.002008	11,14,17,20	0.502800	0.811308
91	JMD_N_TMD_N-Pat...,11)-FUKS010109	Composition	AA composition	Proteins of thermophiles (INT)	Entire chain co...ishikawa, 2001)	0.178000	0.109835	0.109835	0.133383	0.179887	0.000587	0.000587	10,13,17	nan	nan
92	JMD_N_TMD_N-Pat...,14)-BIOV880101	ASA/Volume	Buried	Buriability	Information val...u et al., 1988)	0.130000	0.067433	-0.067433	0.133237	0.146065	0.000642	0.002130	7,11,14	0.306800	0.574245
93	TMD_C_JMD_C-Pat...3,7)-MAXF760105	Conformation	α-helix (left-handed)	α-helix (left-handed)	Normalized freq...Scheraga, 1976)	0.129000	0.071374	0.071374	0.180851	0.152571	0.000727	0.002285	23,27	0.000000	0.000000
94	TMD_C_JMD_C-Pat...,11)-TANS770102	Conformation	α-helix (C-term, out)	α-helix (C-terminal, outside)	Normalized freq...Scheraga, 1977)	0.128000	0.062708	-0.062708	0.113629	0.123346	0.000767	0.002362	25,28,31	0.407200	0.686822
95	JMD_N_TMD_N-Seg...2,3)-CHAM830105	Shape	Side chain length	n atoms in side chain (3+1)	The number of a...-Charton, 1983)	0.128000	0.057140	-0.057140	0.128493	0.130946	0.000672	0.002187	7,8,9,10,11,12,13	0.121600	0.273037
96	JMD_N_TMD_N-Seg...3,9)-ISOY800102	Conformation	β-strand	Extended	Normalized rela...i et al., 1980)	0.126000	0.079975	-0.079975	0.169167	0.182954	0.000926	0.002636	5,6	1.002000	1.075427

return_details=True additionally returns a long-form table of every candidate scale considered for each feature, with its interpretability grade, correlation with the original scale, recomputed std_test, and whether it was accepted:

df_simple2, df_candidates = cpp.simplify(df_feat=df_feat, labels=labels,
                                         max_interpret_grade=2, return_details=True)
aa.display_df(df_candidates, show_shape=True)

DataFrame shape: (78, 9)

	feature	candidate_scale	interpretability_orig	interpretability_cand	cor	std_test	accepted	cv_score	reason
1	TMD_C_JMD_C-Seg...6,9)-TANS770106	RADA880101	8.000000	1.000000	-0.742074	0.208957	False	nan	max_std_test
2	TMD_C_JMD_C-Seg...6,9)-TANS770106	KOEH090103	8.000000	1.000000	0.737712	0.196374	True	0.907051	accepted
3	TMD-Pattern(C,3...,15)-ANDN920101	FUKS010109	8.000000	1.000000	-0.728856	0.133076	True	0.907051	accepted
4	TMD_C_JMD_C-Pat...,12)-ANDN920101	FUKS010109	8.000000	1.000000	-0.728856	0.172594	True	0.907051	accepted
5	TMD_C_JMD_C-Seg...4,5)-TANS770106	RADA880101	8.000000	1.000000	-0.742074	0.162400	True	0.907051	accepted
6	TMD-Pattern(C,5...,15)-OOBM770105	KARS160117	8.000000	1.000000	-0.959796	0.082837	True	0.907051	accepted
7	TMD-Pattern(C,4,7)-ANDN920101	FUKS010109	8.000000	1.000000	-0.728856	0.165353	True	0.907051	accepted
8	TMD_C_JMD_C-Seg...3,4)-MONM990101	KOEH090102	8.000000	1.000000	0.922232	0.134902	True	0.907051	accepted
9	TMD_C_JMD_C-Pat...3,7)-OOBM770105	KARS160117	8.000000	1.000000	-0.959796	0.117714	True	0.907051	accepted
10	TMD_C_JMD_C-Seg...2,5)-ANDN920101	FUKS010109	8.000000	1.000000	-0.728856	0.107804	True	0.907051	accepted
11	JMD_N_TMD_N-Seg...3,6)-VASM830102	PALJ810111	8.000000	1.000000	-0.754824	0.129405	True	0.907051	accepted
12	TMD_C_JMD_C-Pat...,15)-MONM990101	KOEH090102	8.000000	1.000000	0.922232	0.103456	True	0.907051	accepted
13	TMD_C_JMD_C-Pat...,10)-TANS770106	RADA880101	8.000000	1.000000	-0.742074	0.178993	True	0.907051	accepted
14	JMD_N_TMD_N-Pat...,11)-ANDN920101	FUKS010109	8.000000	1.000000	-0.728856	0.133383	True	0.907051	accepted
15	JMD_N_TMD_N-Pat...,11)-VASM830102	PALJ810111	8.000000	1.000000	-0.754824	0.125346	True	0.907051	accepted
16	TMD_C_JMD_C-Seg...3,4)-PRAM820102	LINS030101	7.000000	1.000000	-0.756652	0.121842	True	0.907051	accepted
17	TMD_C_JMD_C-Pat...,12)-FAUJ880108	BULH740102	7.000000	4.000000	-0.740983	0.130978	True	0.907051	accepted
18	TMD_C_JMD_C-Seg...2,3)-PRAM820102	LINS030101	7.000000	1.000000	-0.756652	0.098523	True	0.907051	accepted
19	TMD-Pattern(C,5...,12)-PRAM820102	LINS030101	7.000000	1.000000	-0.756652	0.110439	True	0.907051	accepted
20	JMD_N_TMD_N-Seg...,15)-FAUJ880101	RACS820111	7.000000	1.000000	0.796898	0.194309	True	0.907051	accepted
21	JMD_N_TMD_N-Seg...3,8)-FAUJ880101	RACS820111	7.000000	1.000000	0.796898	0.163724	True	0.907051	accepted
22	JMD_N_TMD_N-Seg...2,4)-MEIH800101	MIYS850101	7.000000	1.000000	-0.956832	0.096040	True	0.907051	accepted
23	JMD_N_TMD_N-Seg...2,6)-MEIH800101	MIYS850101	7.000000	1.000000	-0.956832	0.117602	True	0.907051	accepted
24	TMD_C_JMD_C-Pat...4,8)-MEIH800101	MIYS850101	7.000000	1.000000	-0.956832	0.153526	True	0.907051	accepted
25	TMD_C_JMD_C-Seg...4,8)-MEIH800101	MIYS850101	7.000000	1.000000	-0.956832	0.127012	True	0.907051	accepted
26	JMD_N_TMD_N-Per...4,3)-QIAN880138	QIAN880112	6.000000	5.000000	-0.774206	0.089768	True	0.907051	accepted
27	JMD_N_TMD_N-Per...4,3)-QIAN880138	QIAN880112	6.000000	5.000000	-0.774206	0.090360	True	0.907051	accepted
28	JMD_N_TMD_N-Pat...,11)-QIAN880127	OOBM850105	6.000000	1.000000	-0.812942	0.118719	True	0.907051	accepted
29	TMD_C_JMD_C-Pat...,10)-QIAN880138	QIAN880112	6.000000	5.000000	-0.774206	0.101748	True	0.907051	accepted
30	TMD_C_JMD_C-Seg...2,3)-CHOP780212	PALJ810106	5.000000	1.000000	0.800921	0.109387	True	0.907051	accepted
31	TMD_C_JMD_C-Pat...,12)-FINA770101	AURR980113	5.000000	1.000000	0.848669	0.103029	True	0.907051	accepted
32	TMD_C_JMD_C-Pat...,12)-CHOP780212	PALJ810106	5.000000	1.000000	0.800921	0.156745	True	0.907051	accepted
33	TMD-Pattern(N,1...4,7)-FINA770101	AURR980113	5.000000	1.000000	0.848669	0.151936	True	0.907051	accepted
34	JMD_N_TMD_N-Pat...,12)-FINA770101	AURR980113	5.000000	1.000000	0.848669	0.151448	True	0.907051	accepted
35	TMD-Pattern(C,5...,12)-MAXF760105	FAUJ880107	5.000000	1.000000	-0.771112	0.173044	True	0.907051	accepted
36	TMD-Pattern(N,2...,11)-RACS820101	CIDH920104	5.000000	1.000000	-0.716346	0.128234	True	0.907051	accepted
37	TMD_C_JMD_C-Pat...,13)-CHOP780212	PALJ810106	5.000000	1.000000	0.800921	0.158145	True	0.907051	accepted
38	JMD_N_TMD_N-Pat...,11)-RACS820101	CIDH920104	5.000000	1.000000	-0.716346	0.126433	True	0.907051	accepted
39	TMD-Pattern(C,4...,11)-FINA770101	AURR980113	5.000000	1.000000	0.848669	0.127339	True	0.907051	accepted
40	TMD_C_JMD_C-Pat...,12)-QIAN880114	CIDH920103	5.000000	1.000000	-0.763299	0.124914	True	0.907051	accepted
41	TMD_C_JMD_C-Seg...6,9)-PALJ810113	PALJ810105	5.000000	1.000000	0.732768	0.089871	True	0.907051	accepted
42	JMD_N_TMD_N-Seg...2,4)-QIAN880114	CIDH920103	5.000000	1.000000	-0.763299	0.095751	True	0.907051	accepted
43	TMD_C_JMD_C-Pat...3,7)-MAXF760105	FAUJ880107	5.000000	1.000000	-0.771112	0.211477	False	nan	max_std_test
44	JMD_N_TMD_N-Seg...3,9)-KOEP990102	GRAR740102	5.000000	1.000000	0.773220	0.156564	True	0.907051	accepted
45	TMD_C_JMD_C-Seg...3,4)-HUTJ700102	LINS030101	4.000000	1.000000	0.869506	0.121842	True	0.907051	accepted
46	TMD_C_JMD_C-Seg...3,4)-JANJ790102	KOEH090106	4.000000	1.000000	-1.000000	0.159718	True	0.907051	accepted
47	TMD_C_JMD_C-Seg...6,9)-DESM900102	OOBM770101	4.000000	1.000000	-0.949505	0.202111	False	nan	max_std_test
48	TMD_C_JMD_C-Seg...6,9)-DESM900102	LINS030107	4.000000	1.000000	-0.948654	0.193808	True	0.907051	accepted
49	TMD_C_JMD_C-Seg...6,9)-RICJ880113	WILM950101	4.000000	1.000000	-0.708204	0.109849	True	0.907051	accepted
50	TMD_C_JMD_C-Pat...5,8)-RADA880104	EISD840101	4.000000	1.000000	0.908505	0.052593	True	0.907051	accepted
51	TMD-Pattern(C,4,7)-RADA880104	EISD840101	4.000000	1.000000	0.908505	0.052593	True	0.907051	accepted
52	TMD_C_JMD_C-Pat...4,8)-JANJ790102	KOEH090106	4.000000	1.000000	-1.000000	0.181777	True	0.907051	accepted
53	JMD_N_TMD_N-Pat...,10)-AURR980116	QIAN880110	4.000000	1.000000	0.753792	0.153325	True	0.907051	accepted
54	TMD_C_JMD_C-Seg...4,5)-RICJ880113	WILM950101	4.000000	1.000000	-0.708204	0.102916	True	0.907051	accepted
55	TMD-Pattern(N,4,7)-AURR980116	QIAN880110	4.000000	1.000000	0.753792	0.167930	True	0.914744	accepted
56	TMD_C_JMD_C-Seg...4,5)-YUTK870103	EISD860102	4.000000	3.000000	-0.838651	0.180052	True	0.914744	accepted
57	TMD_C_JMD_C-Pat...,15)-YUTK870101	GUYH850105	4.000000	1.000000	-0.840600	0.126437	True	0.914744	accepted
58	TMD_C_JMD_C-Seg...2,3)-HUTJ700102	LINS030101	4.000000	1.000000	0.869506	0.098523	True	0.914744	accepted
59	TMD_C_JMD_C-Seg...2,3)-JANJ790102	KOEH090106	4.000000	1.000000	-1.000000	0.095746	True	0.914744	accepted
60	TMD_C_JMD_C-Seg...4,5)-DESM900102	OOBM770101	4.000000	1.000000	-0.949505	0.180330	True	0.914744	accepted
61	TMD_C_JMD_C-Seg...2,2)-RICJ880113	WILM950101	4.000000	1.000000	-0.708204	0.067646	True	0.914744	accepted
62	TMD-Pattern(C,5...,12)-HUTJ700102	LINS030101	4.000000	1.000000	0.869506	0.110439	True	0.914744	accepted
63	TMD-PeriodicPat...3,1)-COHE430101	OOBM850101	4.000000	1.000000	0.759615	0.052251	True	0.914744	accepted
64	JMD_N_TMD_N-Pat...,13)-RICJ880107	ROSG850101	4.000000	1.000000	0.796390	0.101561	True	0.914744	accepted
65	TMD_C_JMD_C-Pat...4,8)-CORJ870107	CORJ870108	4.000000	1.000000	-0.996278	0.167914	True	0.914744	accepted
66	TMD-Pattern(C,4...,11)-RICJ880107	ROSG850101	4.000000	1.000000	0.796390	0.124610	False	0.907051	cv_drop
67	TMD-Pattern(C,4...,11)-RICJ880107	CHOP780203	4.000000	1.000000	-0.792356	0.138664	True	0.922436	accepted
68	TMD_C_JMD_C-Seg...,11)-COHE430101	OOBM850101	4.000000	1.000000	0.759615	0.084763	False	0.914744	cv_drop
69	TMD_C_JMD_C-Seg...,11)-COHE430101	PALJ810106	4.000000	1.000000	-0.717945	0.167896	False	0.914744	cv_drop
70	TMD_C_JMD_C-Seg...,11)-COHE430101	LIFS790102	4.000000	1.000000	0.713730	0.183876	True	0.922436	accepted
71	JMD_N_TMD_N-Seg...,10)-RICJ880111	BHAR880101	4.000000	1.000000	-0.812868	0.178100	True	0.922436	accepted
72	TMD_C_JMD_C-Pat...,14)-HUTJ700102	LINS030101	4.000000	1.000000	0.869506	0.165586	True	0.922436	accepted
73	JMD_N_TMD_N-Pat...,11)-HUTJ700102	LINS030101	4.000000	1.000000	0.869506	0.137245	True	0.922436	accepted
74	TMD_C_JMD_C-Seg...2,3)-YUTK870103	EISD860102	4.000000	3.000000	-0.838651	0.108394	True	0.922436	accepted
75	JMD_N_TMD_N-Pat...,12)-RICJ880111	BHAR880101	4.000000	1.000000	-0.812868	0.164544	True	0.922436	accepted
76	TMD_C_JMD_C-Seg...4,5)-FAUJ880109	GUYH850105	3.000000	1.000000	0.926858	0.157550	True	0.922436	accepted
77	TMD_C_JMD_C-Seg...4,6)-FAUJ880109	GUYH850105	3.000000	1.000000	0.926858	0.162605	True	0.922436	accepted
78	TMD_C_JMD_C-Seg...2,2)-FAUJ880109	GUYH850105	3.000000	1.000000	0.926858	0.086797	True	0.922436	accepted

CPPPlot().feature_map — the signature CPP visualization — makes the simplification visible: it lays the per-feature mean differences out along the sequence, groups the rows by subcategory, and shows feature importance as the bar track. With 150 features the map is unreadable, so we show the top 40 features by importance on a tall canvas. The original feature set already carries feat_importance:

import matplotlib.pyplot as plt
cpp_plot = aa.CPPPlot()
aa.plot_settings(weight_bold=False)
df_feat_top = df_feat.sort_values("feat_importance", ascending=False).head(40)
cpp_plot.feature_map(df_feat=df_feat_top, figsize=(8, 14))
plt.show()

../_images/cpp_simplify_1_output_25_0.png

And the simplified set (swapped features carry no importance, so we re-attach it with TreeModel) — it speaks in fewer, more interpretable subcategories, with the original (most interpretable) features protected:

df_scales_all = aa.load_scales()
X = sf.feature_matrix(features=list(df_simple["feature"]), df_parts=df_parts,
                      df_scales=df_scales_all)
df_simple_imp = aa.TreeModel().fit(X, labels=labels).add_feat_importance(df_feat=df_simple, drop=True, sort=True)
df_simple_top = df_simple_imp.head(40)
cpp_plot.feature_map(df_feat=df_simple_top, figsize=(8, 14))
plt.show()

/Users/stephanbreimann/Programming/1Packages/aaanalysis-simplify-fast/aaanalysis/feature_engineering/_backend/cpp_run.py:143: UserWarning: CPP is using the Python kernel fallback — the compiled Cython extension is not available in this install. Output is bit-exact with the Cython path but ~2x slower. Reinstall via pip install --force-reinstall aaanalysis to fetch a prebuilt wheel.
  warnings.warn(

../_images/cpp_simplify_2_output_27_1.png

Finally, an overview of how the subcategory vocabulary shifts as max_interpret_grade is tightened from 10 (keep everything) down to 1 (only the best, grade-1 tier). Each grade level is one colored series (aa.plot_get_clist(n_colors=10)); as the grade tightens, features in worse-graded subcategories are replaced and migrate into the most interpretable ones:

import matplotlib.pyplot as plt
import pandas as pd

levels = list(range(1, 11))
colors = aa.plot_get_clist(n_colors=10)
counts = {g: cpp.simplify(df_feat=df_feat, labels=labels, max_interpret_grade=g)
          ["subcategory"].value_counts() for g in levels}
df_levels = pd.DataFrame(counts).fillna(0).astype(int)
print(df_levels)

top_subcats = df_levels[10].sort_values(ascending=False).head(8).index
df_plot = df_levels.loc[top_subcats]

aa.plot_settings(weight_bold=False)
ax = df_plot.plot(kind="barh", figsize=(7, 6), color=colors, width=0.85, legend=False)
ax.invert_yaxis()
ax.set_xlabel("number of features")
ax.set_ylabel("subcategory")
ax.legend(title="max_interpret_grade", labels=[str(g) for g in levels],
          loc="upper center", bbox_to_anchor=(0.5, -0.12), ncol=5, frameon=False)
plt.tight_layout()
plt.show()

                               1   2   3   4   5   6   7   8   9   10
subcategory
AA composition                  5   5   5   5   5   5   5   0   0   0
Accessible surface area (ASA)   6   6   6   6   6   6   6   6   6   6
Amphiphilicity                  0   3   3   3   3   3   3   3   3   3
Amphiphilicity (α-helix)        0   0   0   3   3   3   3   3   3   3
Backbone-dynamics (-CH)         2   2   2   2   2   2   2   7   7   7
Buried                          5   5   5   5   5   5   5   5   5   5
Charge                          3   3   3   3   3   3   3   3   3   3
Coil                            5   5   5   5   5   5   5   5   5   5
Coil (C-term)                   0   0   0   0   0   3   3   3   3   3
Coil (N-term)                   0   0   0   0   0   1   1   1   1   1
Electron-ion interaction pot.   3   3   3   3   3   3   4   4   4   4
Entropy                         0   0   0   5   5   5   5   5   5   5
Flexibility                     1   1   1   1   1   1   1   1   1   1
Free energy (unfolding)         0   0   0   8   8   8   8   8   8   8
Hydrophilicity                  4   4   4   2   1   1   1   0   0   0
Hydrophobicity                  7   7   7   6   6   6   6   6   6   6
Hydrophobicity (interface)      4   4   4   4   4   4   4   4   4   4
Isoelectric point               0   0   3   3   3   3   3   3   3   3
Non-bonded energy               0   0   0   0   0   0   0   4   4   4
Partial specific volume         1   1   1   2   2   2   2   2   2   2
Reduced distance                0   0   0   0   0   0   4   4   4   4
Shape and Surface               1   1   1   1   1   1   4   4   4   4
Side chain length               8   7   7   7   7   7   7   7   7   7
Stability                       6   6   6   5   4   4   4   4   4   4
Stability (helix-coil)          0   0   0   0   4   4   4   4   4   4
Steric parameter                0   0   0   0   0   0   2   2   2   2
Volume                          7   7   7   6   6   6   5   5   5   5
α-helix                         5   5   5   4   4   4   4   4   4   4
α-helix (C-cap)                 3   3   3   8   8   8   8   8   8   8
α-helix (C-term, out)           3   3   3   3   3   3   3   3   3   3
α-helix (left-handed)           1   1   1   1   3   3   3   3   3   3
β-sheet                         2   2   2   2   2   2   2   1   1   1
β-sheet (C-term)                1   1   1   1   4   4   4   4   4   4
β-sheet (N-term)                0   0   0   0   5   5   5   5   5   5
β-strand                        9   9   9   8   8   8   8   8   8   8
β-turn (TM helix)               0   0   0   0   0   0   0   5   5   5
β/α-bridge                      1   1   1   1   1   1   1   1   1   1
π-helix                         1   1   1   5   5   5   5   5   5   5

../_images/cpp_simplify_3_output_29_1.png