SeqOptPlot.genealogy

SeqOptPlot.genealogy(df_pareto, ax=None, figsize=(8, 5), front_only=True, cmap='viridis')

Mutational-lineage tree of the variants, rooted at the wild-type.

The directed-evolution analogue of a genealogy tree: nodes are variants placed by their number of mutations (depth), each linked to the largest lower-order variant whose mutation set it extends (or to the wild-type), and colored by the first objective. It shows how the designed variants are built up mutation by mutation from the wild-type.

Parameters:

• df_pareto (pd.DataFrame) – Output of SeqOpt.run().

• ax (matplotlib.axes.Axes, optional) – Axes to draw on. A new figure is created when None.

• figsize (tuple, default=(8, 5)) – Figure size when ax is None.

• front_only (bool, default=True) – If True, build the lineage from the first (rank=0) front only.

• cmap (str, default="viridis") – Matplotlib colormap name for the objective coloring.

Returns:

• fig (matplotlib.figure.Figure) – The figure.

• ax (matplotlib.axes.Axes) – The axes the lineage was drawn on.

Examples

import numpy as np, pandas as pd
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
import aaanalysis as aa
aa.options["verbose"] = False
df_feat = aa.load_features(name="DOM_GSEC"); df_seq = aa.load_dataset(name="DOM_GSEC", n=50)
labels = df_seq["label"].to_list(); sf = aa.SequenceFeature()
X = np.asarray(sf.feature_matrix(features=df_feat["feature"], df_parts=sf.get_df_parts(df_seq=df_seq), df_scales=aa.load_scales()), float)
model = RandomForestClassifier(n_estimators=100, random_state=0).fit(X, labels)
wt = df_seq[df_seq["label"] == 0].iloc[[0]].reset_index(drop=True)
objectives = [("substrate", "max", "delta_pred"), ("parsimony", "min", "n_mut")]
seqopt = aa.SeqOpt(mode="importance", model=model, target_class=1, random_state=42)
df_pareto = seqopt.run(df_seq=wt, df_feat=df_feat, objectives=objectives, pop_size=40, n_gen=20, n_mut_max=6, region="tmd")
aa.display_df(df_pareto, n_rows=10, show_shape=True)

DataFrame shape: (5, 8)

	entry	variant	n_mut	sequence_mut	substrate	parsimony	rank	crowding
1	Q14802		0	MQKVTLGLLVFLAGF...PGETPPLITPGSAQS	0.000000	0.000000	0	inf
2	Q14802	C49V+I55R+S58R	3	MQKVTLGLLVFLAGF...PGETPPLITPGSAQS	27.000000	3.000000	0	inf
3	Q14802	C49L+I55R+S58R	3	MQKVTLGLLVFLAGF...PGETPPLITPGSAQS	27.000000	3.000000	0	inf
4	Q14802	S58R	1	MQKVTLGLLVFLAGF...PGETPPLITPGSAQS	14.000000	1.000000	0	0.796296
5	Q14802	C49M+S58R	2	MQKVTLGLLVFLAGF...PGETPPLITPGSAQS	25.000000	2.000000	0	0.574074

aa.plot_settings()
aa.SeqOptPlot().genealogy(df_pareto=df_pareto, front_only=False)
plt.tight_layout(); plt.show()

# cmap colors nodes by the first objective; figsize sets the figure size in inches
aa.plot_settings()
aa.SeqOptPlot().genealogy(df_pareto=df_pareto, cmap="plasma", figsize=(9, 6),
                          front_only=False)
plt.tight_layout(); plt.show()