From f94eadf1d4f9d728aea2136b81e831e5a7d06442 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Thu, 1 Sep 2022 12:54:41 +0100
Subject: [PATCH] added

---
 scripts/count_vars_ML.R                       |  4 +--
 .../{GetMLData_v2.py => GetMLData_v1.py}      | 35 +++++++++++++------
 scripts/ml/ml_functions/TEST_GetMLData.py     | 14 ++++++++
 3 files changed, 40 insertions(+), 13 deletions(-)
 rename scripts/ml/ml_functions/{GetMLData_v2.py => GetMLData_v1.py} (95%)
 create mode 100644 scripts/ml/ml_functions/TEST_GetMLData.py

diff --git a/scripts/count_vars_ML.R b/scripts/count_vars_ML.R
index 059cbc6..464fd6d 100644
--- a/scripts/count_vars_ML.R
+++ b/scripts/count_vars_ML.R
@@ -1,11 +1,11 @@
 # 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/gid.R")
 #source("~/git/LSHTM_analysis/config/katg.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
diff --git a/scripts/ml/ml_functions/GetMLData_v2.py b/scripts/ml/ml_functions/GetMLData_v1.py
similarity index 95%
rename from scripts/ml/ml_functions/GetMLData_v2.py
rename to scripts/ml/ml_functions/GetMLData_v1.py
index 180d586..d5eab71 100755
--- a/scripts/ml/ml_functions/GetMLData_v2.py
+++ b/scripts/ml/ml_functions/GetMLData_v1.py
@@ -450,15 +450,15 @@ def getmldata(gene, drug
 
     
     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
         cols_to_mask =       ['ligand_affinity_change']#, 'mcsm_na_affinity']
         cols_to_mask_ppi2 =  []
         cols_to_mask_na =    ['mcsm_na_affinity']
 
-    
+    # both
     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
         #cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_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
     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
     #---------------------------
     if len(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
-        mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
-    else:
-        mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask ]
-    
+        #mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
+        mask_check_cols = mask_check_cols + add_cols_mask
+
     #---------------------------
     # mask the na_affinity column where nca_distance > 10
     #---------------------------
     if len(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
-        mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
-    else:
-        mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask ]
-        
+        #mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask + add_cols_mask]
+        mask_check_cols = mask_check_cols + add_cols_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
     if write_maskfile:
         # write mask file for sanity check
diff --git a/scripts/ml/ml_functions/TEST_GetMLData.py b/scripts/ml/ml_functions/TEST_GetMLData.py
new file mode 100644
index 0000000..8bf23c5
--- /dev/null
+++ b/scripts/ml/ml_functions/TEST_GetMLData.py
@@ -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)
\ No newline at end of file