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)
WARNING: column named 'MEDIA_FACTOR' not found TISSUE FACTOR : included MEDIA FACTOR : NOT included MSI FACTOR : included FEATURE FACTOR : included
To get the drug idenfiers or genomic features, use the following code
an.drugIds[0:5]
['Drug_999_IC50', 'Drug_1039_IC50', 'Drug_1042_IC50', 'Drug_1043_IC50', 'Drug_1046_IC50']
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('Drug_1047_IC50', 'BRAF_mut',
show=True)
/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/pandas/core/index.py:4281: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison return np.sum(name == np.asarray(self.names)) > 1
Note that here this is a PANCAN analysis so all tissues are used. The MSI is also a feature used in the regression.