Similarly to notebook 1 (introduction) and 3 (one drug analysis), we use the ANOVA class but call another function called anova_one_drug_one_feature
%pylab inline
matplotlib.rcParams['figure.figsize'] = (10,6)
Populating the interactive namespace from numpy and matplotlib
from gdsctools import ANOVA, ic50_test
an = ANOVA(ic50_test)
To get the drug idenfiers or genomic features, use the following code
an.drugIds[0:5]
[999, 1039, 1042, 1043, 1046]
an.feature_names[0:6]
['ABCB1_mut', 'ABL2_mut', 'ACACA_mut', 'ACVR1B_mut', 'ACVR2A_mut', 'AFF4_mut']
note: the first 3 feature names are not real features and should be ignored for now.
results = an.anova_one_drug_one_feature(1047, 'BRAF_mut',
show=True)
Note that here this is a PANCAN analysis so all tissues are used. The MSI is also a feature used in the regression.