(drespo.T < dmax[drespo.index]).sum().rename("nsamples"),
drespo.T[drespo.T < dmax[drespo.index]].median().rename("dependency"),
ml_scores,
],
axis=1,
)
drug_selective["name"] = [i.split(";")[1] for i in drug_selective.index]
drug_selective_set = set(drug_selective.query("skew < -2").index)
# Scatter
grid = GIPlot.gi_regression(
"skew",
"median",
drug_selective,
size="dependency",
size_inverse=True,
size_legend_title="Median IC50",
plot_reg=False,
plot_annot=False,
)
grid.ax_joint.axvline(-1, c=GIPlot.PAL_DTRACE[1], lw=0.3, ls="--")
g_highlight_df = drug_selective.query("skew < -1").sort_values("skew").head(5)
labels = [
grid.ax_joint.text(
row["skew"], row["median"], row["name"], color="k", fontsize=4
)
for _, row in g_highlight_df.iterrows()
]
adjust_text(
labels,
drug_pca_df.corr(),
cmap="Spectral",
annot=True,
center=0,
fmt=".2f",
annot_kws=dict(size=4),
lw=0.05,
figsize=(3, 3),
)
plt.savefig(f"{RPATH}/drug_pca_clustermap.pdf", bbox_inches="tight", dpi=600)
plt.close("all")
#
y_var = "PC1"
g = GIPlot.gi_regression("growth", y_var, drug_pca_df, lowess=True)
g.set_axis_labels("Growth rate", f"{y_var} ({drug_vexp[y_var]*100:.1f}%)")
plt.savefig(f"{RPATH}/drug_pca_regression_growth.pdf", bbox_inches="tight", dpi=600)
plt.close("all")
# Covariates
#
# CRISPR
covs_crispr = LMModels.define_covariates(
institute=crispr_obj.merged_institute,
medium=True,
cancertype=False,
tissuetype=False,
mburden=False,
ploidy=True,
crispr.apply(skew, axis=1).rename("skew"),
crispr.median(1).rename("median"),
(crispr < -0.5).sum(1).rename("nsamples"),
crispr[crispr < -0.5].median(1).rename("dependency").abs(),
ml_scores,
],
axis=1,
)
crispr_selective_set = set(crispr_selective.query("skew < -3").index)
# Scatter
grid = GIPlot.gi_regression(
"skew",
"median",
crispr_selective,
size="dependency",
plot_reg=False,
plot_annot=False,
)
grid.ax_joint.axvline(-3, c=GIPlot.PAL_DTRACE[1], lw=0.3, ls="--")
g_highlight_df = crispr_selective.query("skew < -3").sort_values(
"skew").head(15)
labels = [
grid.ax_joint.text(row["skew"],
row["median"],
i,
color="k",
fontsize=4) for i, row in g_highlight_df.iterrows()
]
adjust_text(