tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

added

Browse source
This commit is contained in:
Tanushree Tunstall 2022-09-01 12:54:41 +01:00
parent 82e2da4f3b
commit f94eadf1d4
3 changed files with 40 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

4
scripts/count_vars_ML.R
View file

@ -1,11 +1,11 @@
# count numbers for ML # count numbers for ML
#source("~/git/LSHTM_analysis/config/alr.R") source("~/git/LSHTM_analysis/config/alr.R")
#source("~/git/LSHTM_analysis/config/embb.R") #source("~/git/LSHTM_analysis/config/embb.R")
#source("~/git/LSHTM_analysis/config/gid.R") #source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/katg.R") #source("~/git/LSHTM_analysis/config/katg.R")
#source("~/git/LSHTM_analysis/config/pnca.R") #source("~/git/LSHTM_analysis/config/pnca.R")
source("~/git/LSHTM_analysis/config/rpob.R") #source("~/git/LSHTM_analysis/config/rpob.R")
############################# #############################
# GET the actual merged dfs # GET the actual merged dfs

35
scripts/ml/ml_functions/GetMLData_v2.py → scripts/ml/ml_functions/GetMLData_v1.py
View file

@ -450,15 +450,15 @@ def getmldata(gene, drug
if gene.lower() in geneL_na: if gene.lower() in geneL_na:
gene_affinity_colnames = ['mcsm_na_affinity'] gene_affinity_colnames = ['mcsm_na_affinity', 'nca_distance']
#X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols #X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity'] cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity']
cols_to_mask_ppi2 = [] cols_to_mask_ppi2 = []
cols_to_mask_na = ['mcsm_na_affinity'] cols_to_mask_na = ['mcsm_na_affinity']
# both
if gene.lower() in geneL_na_ppi2: if gene.lower() in geneL_na_ppi2:
gene_affinity_colnames = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] gene_affinity_colnames = ['mcsm_na_affinity','nca_distance', 'mcsm_ppi2_affinity', 'interface_dist']
#X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols #X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
#cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity'] #cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity'] cols_to_mask = ['ligand_affinity_change']#, 'mcsm_na_affinity']
@ -481,27 +481,40 @@ def getmldata(gene, drug
# mask the mcsm ligand affinity AND mcsm_na affinity columns where ligand distance > 10 # mask the mcsm ligand affinity AND mcsm_na affinity columns where ligand distance > 10
my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0 my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0
#mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask]
mask_check_cols = ['mutationinformation', 'ligand_distance'] + cols_to_mask
#--------------------------- #---------------------------
# mask the mcsm_ppi2_affinity column where interface_dist > 10 # mask the mcsm_ppi2_affinity column where interface_dist > 10
#--------------------------- #---------------------------
if len(cols_to_mask_ppi2) > 0: if len(cols_to_mask_ppi2) > 0:
my_df_ml.loc[(my_df_ml['interface_dist'] > 10), cols_to_mask_ppi2] = 0 my_df_ml.loc[(my_df_ml['interface_dist'] > 10), cols_to_mask_ppi2] = 0
add_cols_mask = ['interface_dist'] + cols_to_mask_ppi2 add_cols_mask = ['interface_dist'] + cols_to_mask_ppi2
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask] #mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
else: mask_check_cols = mask_check_cols + add_cols_mask
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask ]
#--------------------------- #---------------------------
# mask the na_affinity column where nca_distance > 10 # mask the na_affinity column where nca_distance > 10
#--------------------------- #---------------------------
if len(cols_to_mask_na) > 0: if len(cols_to_mask_na) > 0:
my_df_ml.loc[(my_df_ml['nca_distance'] > 10), cols_to_mask_na] = 0 my_df_ml.loc[(my_df_ml['nca_distance'] > 10), cols_to_mask_na] = 0
add_cols_mask = ['nca_distance'] + cols_to_mask_na add_cols_mask = ['nca_distance'] + cols_to_mask_na
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask] #mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
else: mask_check_cols = mask_check_cols + add_cols_mask
mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask ]
# if gene.lower() in geneL_na_ppi2:
# #---------------------------
# # RPOB: mask ppi2 + na + lig cols
# #---------------------------
# mask_check = my_df_ml[['mutationinformation',
# 'ligand_distance', 'ligand_affinity_change',
# 'nca_distance','mcsm_na_affinity',
# 'mcsm_ppi2_affinity','interface_dist']]
# GET mask data
mask_check = my_df_ml[mask_check_cols]
# sanity check: check script SANITY_CHECK_mask.py # sanity check: check script SANITY_CHECK_mask.py
if write_maskfile: if write_maskfile:
# write mask file for sanity check # write mask file for sanity check

14
scripts/ml/ml_functions/TEST_GetMLData.py Normal file
View file

@ -0,0 +1,14 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Sep 1 12:22:27 2022
@author: tanu
"""
getmldata(gene = "katG"
, drug = "isoniazid"
, data_combined_model = False
, use_or = False
, omit_all_genomic_features = False
, write_maskfile = True
, write_outfile = False)