UP
v1.1 dev-preview · stable on PyPI: 1.0.3
Ecosystem Map
Python packages only · the interpretable protein-feature & workflow layer between bioinformatics I/O and ML / XAI / causal / design
UPSTREAM COMPLEMENTS · data in
1 · Biological data, I/O & fetch
Biopython
Biotite
bs
bioservices
gget
UniProt
scikit-bio
FASTA / PDB I/O · UniProt · NCBI · PDB · gget / bioservices
2 · Protein representations
fair-esm
transformers
be
bio-embeddings
AlphaFold DB
PDB
Bio.PDB
T5
ProtT5
embeddings · structure · PTM / site → pseudo-scales
4 · CORE LAYER — interpretable protein-feature layer
v1.1
sequence → physicochemical scales → interpretable features → explainable ML
CPP · Part × Split × Scale · CPP.run_num (numeric) · AAontology
SequenceFeature · AAclust · NumericalFeature · dPULearn · AAWindowSampler
TreeModel · ShapModel · CPPPlot · AAlogoPlot · AAMut · SeqMut · SeqOpt
where on the sequence × how to read it × which physicochemical property
vs
3 · Feature engineering
input + benchmark
iF
iFeature
p3
propy3
PB
PyBioMed
AAanalysis
single-residue · contrastive · explained
10 · Omics inputs
optional
MS · proteomics
pt
pyteomics
pyopenms
AlphaPept
single-cell · spatial
scverse
ad
AnnData
DOWNSTREAM COMPLEMENTS · consume the interpretable feature matrix, explanations & objectives
5 · ML / DL models
scikit-learn
XGBoost
LightGBM
PyTorch
compatible · trained on matrix X
6 · Optimization
Optuna
pm
pymoo
DE
DEAP
BoTorch / Ax
candidate · ΔCPP objectives
7 · Protein design
PR
PyRosetta
PM
ProteinMPNN
RF
RFdiffusion
ESM-IF
candidate · score / steer ΔCPP
9 · XAI evaluation
Quantus
OX
OpenXAI
faithfulness · robustness ·
localization · complexity
candidate · benchmark explanations
8 · Explainability (XAI) · method taxonomy
implemented in AAanalysis
candidate to adopt from other packages
METHOD CATEGORY
AIM
METHOD EXAMPLES
STATUS
Feature attribution
local & global importance
SHAP
· PFI · PDP · ICE · ALE · LIME · LRP · IntGrad · Grad-CAM
ShapModel
Example-based
representative & counterfactual
Di
MMD-CRITIC · Wachter · DiCE · CEM
to adopt
Rule-extraction
logical IF-THEN rules
Ab
ANCHOR · RULE-FIT · LORE · TREPAN
to adopt
Neural methods
explain DL internals
LRP · IntGrad · Grad-CAM · TCAV · GNNExplainer · XGNN
Captum
Non-post-hoc / complementary trust layers
Surrogate models
distill black-box
train white-box on black-box predictions
to adopt
Uncertainty estimation
prediction confidence
M
conformal prediction · MAPIE
MAPIE
Causal modelling
cause → effect
DoWhy · EconML (PyWhy)
DoWhy / EconML
Already in AAanalysis: ShapModel (SHAP) & TreeModel importance — the rest are candidates to adopt; CPP makes them biologically readable.
CROSS-CUTTING · Model validation (protein-specific protocols)
homology-aware splits · same/different-protein splits · shuffled-label controls · feature stability · per-protein AP · PU-label sanity checks | tracking: MLflow
Relationship to AAanalysis
Upstream complement (data in)
Downstream complement (models · XAI · causal · design)
Direct comparison / benchmark
Optional side branch
Core message: AAanalysis is the interpretable middle band — it complements the stack around it, and competes only with
classical descriptor libraries, on interpretability and task-awareness rather than breadth.
Maturity
implemented
candidate / future
optional bridge
⬇ Download ▾
PNG (high-res)
PDF
HTML