Merge branch 'embb_dev'

mcsm/mcsm.py

@@ -243,7 +243,7 @@ def format_mcsm_output(mcsm_outputcsv):
         mcsm_data = mcsm_data.drop_duplicates(['mutationinformation'])
         print('Dim of data after removing duplicate muts:', mcsm_data.shape
         , '\n===========================================================')
-#%%===================================================================== 
+#%%=====================================================================
     #############
     # Create col: duet_outcome
     #############

mcsm/run_mcsm.py

@@ -79,13 +79,13 @@ gene_match = gene + '_p.'
 # directories
 #============
 if not datadir:
-    datadir = homedir + '/' + 'git/Data'
+    datadir = homedir + '/git/Data/'
     
 if not indir:
-    indir = datadir + '/' + drug + '/input'
+    indir = datadir + drug + 'input/'
     
 if not outdir:
-    outdir = datadir + '/' + drug + '/output'
+    outdir = datadir + drug + 'output/'
 
 #=======
 # input
@@ -95,7 +95,7 @@ if pdb_filename:
 else:
     in_filename_pdb = gene.lower() + '_complex.pdb'
     
-infile_pdb = indir + '/' + in_filename_pdb
+infile_pdb = indir + in_filename_pdb
 
 #in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
 #infile_snps = outdir + '/' + in_filename_snps
@@ -104,8 +104,8 @@ if mutation_filename:
     in_filename_snps = mutation_filename
 else:
     in_filename_snps = gene.lower() + '_mcsm_formatted_snps.csv'
-   
+
-infile_snps = outdir + '/' + in_filename_snps
+infile_snps = outdir + in_filename_snps
 
 #=======
 # output
@@ -113,13 +113,13 @@ infile_snps = outdir + '/' + in_filename_snps
 # mcsm_results globals
 if not result_urls:
     result_urls_filename = gene.lower() + '_result_urls.txt'
-    result_urls =  outdir + '/' + result_urls_filename
+    result_urls =  outdir + result_urls_filename
     if DEBUG:
         print('DEBUG: Result URLs:', result_urls)
 
 if not mcsm_output:
     mcsm_output_filename = gene.lower() + '_mcsm_output.csv'
-    mcsm_output =  outdir + '/' + mcsm_output_filename
+    mcsm_output =  outdir + mcsm_output_filename
     if DEBUG:
         print('DEBUG: mCSM output CSV file:', mcsm_output)
 
@@ -127,7 +127,7 @@ if not mcsm_output:
 #out_filename_format = gene.lower() + '_mcsm_processed.csv'
 if not outfile_format:
     out_filename_format = gene.lower() + '_complex_mcsm_norm.csv'
-    outfile_format =  outdir + '/' + out_filename_format
+    outfile_format =  outdir + out_filename_format
     if DEBUG:
         print('DEBUG: formatted CSV output:', outfile_format)
 #%%=====================================================================

mcsm_na/run_format_results_mcsm_na.py

@@ -52,15 +52,16 @@ if not outdir:
 outdir_na = outdir + 'mcsm_na_results/'
 
 # Input file
-infile_mcsm_na =  outdir_na +  gene + '_output_combined_clean.tsv'
+infile_mcsm_na =  outdir_na +  gene.lower() + '_output_combined_clean.tsv'
 
 # Formatted output file
-outfile_mcsm_na_f = outdir_na + gene + '_complex_mcsm_na_norm.csv'
+outfile_mcsm_na_f = outdir_na + gene.lower() + '_complex_mcsm_na_norm.csv'
 
-#==========================
+#===========================================
 # CALL: format_results_mcsm_na() 
 # Data: gid+streptomycin
-#==========================
+# Data: rpob+rifampicin, date: 18/11/2021
+#===========================================
 print('Formatting results for:', infile_mcsm_na)
 mcsm_na_df_f = format_mcsm_na_output(mcsm_na_output_tsv = infile_mcsm_na)
 

mcsm_na/run_submit_mcsm_na.py

@@ -18,14 +18,14 @@ print(my_prediction_url)
 
 # TODO: add cmd line args
 #gene = 'gid'
-drug = 'streptomycin'
+drug = ''
-datadir = homedir + '/git/Data'
+datadir = homedir + '/git/Data/'
-indir = datadir + '/' + drug + '/input'
+indir = datadir + drug + 'input/'
-outdir = datadir + '/' + drug + '/output'
+outdir = datadir + drug + 'output/'
-outdir_mcsm_na = outdir + 'mcsm_na_results'
+outdir_mcsm_na = outdir + 'mcsm_na_results/'
 
 my_nuc_type = 'RNA'
-my_pdb_file = indir + '/gid_complex.pdb'
+my_pdb_file = indir + gene.lower() + '_complex.pdb'
 
 #=============================================================================
 # batch 26: 25.txt # RAN: 16 Feb:

mcsm_na/split_csv.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+
+# FIXME: This is written for expediency to kickstart running dynamut and mcsm-NA
+
+# Usage: ~/git/LSHTM_analysis/dynamut/split_csv.sh <input file> <output dir> <chunk size in lines>
+# copy your snp file to split into the mcsm_na dir
+
+INFILE=$1
+OUTDIR=$2
+CHUNK=$3
+
+mkdir -p ${OUTDIR}/${CHUNK}
+cd ${OUTDIR}/${CHUNK}
+
+split ../../${INFILE} -l ${CHUNK} -d snp_batch_
+
+# use case
+#~/git/LSHTM_analysis/mcsm_na/split_csv.sh gid_mcsm_formatted_snps.csv snp_batches 50
+#~/git/LSHTM_analysis/mcsm_na/split_csv.sh embb_mcsm_formatted_snps.csv snp_batches 50
+
+
+#~/git/LSHTM_analysis/mcsm_na/split_csv.sh rpob_mcsm_formatted_snps_chain.csv snp_batches 20 # date: 17/11/2021
+
+
+#acccidently replaced file original rpob batches
+
+#~/git/LSHTM_analysis/mcsm_na/split_csv.sh 5uhc_mcsm_formatted_snps_chain.csv snp_batches_5uhc 20 # date: 17/11/2021

scripts/combining_dfs.py

@@ -122,7 +122,9 @@ if gene.lower() == "gid":
     in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SRY.csv' # was incorrectly SAM previously
 if gene.lower() == "embb":
     print("\nReading mCSM file for gene:", gene)
-    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv'
+    #in_filename_mcsm = gene.lower() + '_complex_mcsm_norm1.csv' #798
+    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm2.csv' #844
+
 if gene.lower() in gene_list_normal:
    print("\nReading mCSM file for gene:", gene)
    in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'