added count for targets for all genes and ran multiple classification models for all of the genes and target as a start

This commit is contained in:
Tanushree Tunstall 2022-03-04 19:16:04 +00:00
parent 89158bc669
commit 877862acb7
8 changed files with 948 additions and 0 deletions

45
X_categories Normal file
View file

@ -0,0 +1,45 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Mar 4 15:09:37 2022
@author: tanu
"""
X_categ_str = ['ss_class'
, 'wt_prop_water'
, 'mut_prop_water'
, 'wt_prop_polarity'
, 'mut_prop_polarity'
, 'wt_calcprop'
, 'mut_calcprop'
, 'active_aa_pos']
# only valid if we use merged_df2
X_categ_str_lin = X_categ_str + ['lineage_labels']
X_categ_foldx = ['contacts'
'electro_rr'
'electro_mm'
'electro_sm'
'electro_ss'
'disulfide_rr'
'disulfide_mm'
'disulfide_sm'
'disulfide_ss'
'hbonds_rr'
'hbonds_mm'
'hbonds_sm'
'hbonds_ss'
'partcov_rr'
'partcov_mm'
'partcov_sm'
'partcov_ss'
'vdwclashes_rr'
'vdwclashes_mm'
'vdwclashes_sm'
'vdwclashes_ss'
'volumetric_rr'
'volumetric_mm'
'volumetric_sm'
'volumetric_ss']