added test2/ for testing updated foldx script

foldx/test2/test2_output/gid_foldx.csv

@@ -0,0 +1,3 @@
+mutationinformation,ddg,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
+S2C,0.30861700000000003,-2.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,-1.0,-1.0,0.0,0.0
+S2F,-0.6481899999999999,-8.0,-4.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,2.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,1.0,0.0,0.0,0.0,-1.0,-1.0,0.0,0.0

foldx/test2/test2_output/pnca_foldx.csv

@@ -0,0 +1,3 @@
+mutationinformation,ddg,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
+L4S,5.7629,22.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,6.0,0.0,0.0,4.0
+L159R,1.66524,-56.0,-26.0,0.0,-2.0,-24.0,0.0,0.0,0.0,0.0,-2.0,0.0,-2.0,0.0,0.0,0.0,0.0,0.0,-1.0,0.0,0.0,-1.0,-4.0,0.0,-4.0,0.0

foldx/test2/testing_foldx_cmds

@@ -0,0 +1,27 @@
+./runFoldx_test2.py -g pncA --datadir /home/tanu/git/LSHTM_analysis/foldx/test2 -i /home/tanu/git/LSHTM_analysis/foldx/test2 -o /home/tanu/git/LSHTM_analysis/foldx/test2/test2_output -p /home/tanu/git/LSHTM_analysis/foldx/test2/test2_process -pdb 3pl1.pdb -m pnca_muts_sample.csv -c1 A
+
+============
+# Example 1: pnca
+# Delete processing output, copy rotabase.txt and individual_list_3pl1.txt in place, run a test
+============
+# 
+clear; rm -rf test2_process/*; cp individual_list_3pl1.txt test2_process/ ; cp rotabase.txt test2_process/; ./runFoldx_test2.py -g pncA --datadir /home/tanu/git/LSHTM_analysis/foldx/test2 -i /home/tanu/git/LSHTM_analysis/foldx/test2 -o /home/tanu/git/LSHTM_analysis/foldx/test2/test2_output -p ./test2_process -pdb 3pl1.pdb -m /tmp/pnca_muts_sample.csv -c1 A
+
+============
+# Example 2: gidb
+============
+clear
+rm Unrecognized_molecules.txt
+rm -rf test2_process/*
+cp rotabase.txt test2_process/
+
+./runFoldx.py \
+-g gid \
+--datadir /home/tanu/git/LSHTM_analysis/foldx/test2 \
+-i /home/tanu/git/LSHTM_analysis/foldx/test2 \
+-o /home/tanu/git/LSHTM_analysis/foldx/test2/test2_output \
+-p ./test2_process \
+-pdb gid_test2.pdb \
+-m gid_test_snps.csv \
+-c1 A
+

scripts/DOCS

@@ -0,0 +1,13 @@
+dir structure
+
+~/git/Data
+    aa_codes.csv
+    
+~/git/Data/<drug>/input
+~/git/Data/<drug>/output
+
+data_extraction.py
+must have the dirs else creates it
+in the curr dir needs
+reference_dict.py
+tidy_split.py

scripts/temp_results.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Nov 12 15:20:32 2020
+
+@author: tanu
+"""
+print('============================================'
+      , '\nQuick summary output for', drug, 'and' , gene.lower()
+      , '\n============================================'
+      , '\nTotal samples:', total_samples
+      , '\nNo. of Sus and Res', drug, 'samples:\n', meta_data[drug].value_counts()
+	  , '\n'
+      , '\nPercentage of Sus and Res', drug, 'samples:\n', meta_data[drug].value_counts(normalize = True)*100
+	  , '\n'
+      , '\nTotal no.of unique dr muts:', mut_grouped[dr_muts_col]
+      , '\nTotal no.of unique other muts:', mut_grouped[other_muts_col]     
+      , '\nTotal no.of unique missense muts:', gene_LF1['mutationinformation'].nunique()
+      , '\nTotal no.of unique positions associated with missense muts:',gene_LF1['position'].nunique()
+      , '\nTotal no. of samples with missense muts:', len(gene_LF1)
+      , '\nTotal no. of unique samples with missense muts:', gene_LF1['id'].nunique()  
+      , '\n'
+      , '\nTotal no.of samples with common_ids:',  nu_common_ids['id']
+      , '\nTotal no.of samples with ambiguous muts:', len(inspect)
+      #, '\nTotal no.of unique ambiguous muts:', len(common_muts)
+      , '\nTotal no.of unique ambiguous muts:', inspect['mutation'].nunique()
+      , '\n============================================================='
+      , '\n\n\n')
+
+print('\n----------------------------------'
+      , '\nWriting subsetted gwas data:', gene
+      , '\n----------------------------------'
+      , '\nFile', check_file
+      , '\nDim:', meta_data.shape)