saving dynamut and mcsm_na jobs submitted and retrieved

dynamut/dynamut_results/dynamut_output_multiple.csv

@@ -1,7 +0,0 @@
-mutationinformation,ddg_dynamut,ddg_encom,ddg_mcsm,ddg_sdm,ddg_duet,dds_encom
-G13V,0.006 kcal/mol (Stabilizing),-0.053 kcal/mol (Destabilizing),-0.261 kcal/mol (Destabilizing),-0.120 kcal/mol (Destabilizing),0.120 kcal/mol (Stabilizing),0.066 kcal.mol-1.K-1 (Increase of molecule flexibility)
-A19T,-0.077 kcal/mol (Destabilizing),0.224 kcal/mol (Destabilizing),-0.631 kcal/mol (Destabilizing),-2.620 kcal/mol (Destabilizing),-0.758 kcal/mol (Destabilizing),-0.280 kcal.mol-1.K-1 (Decrease of molecule flexibility)
-I4N,-0.239 kcal/mol (Destabilizing),-0.720 kcal/mol (Destabilizing),-0.728 kcal/mol (Destabilizing),-0.550 kcal/mol (Destabilizing),-0.461 kcal/mol (Destabilizing),0.900 kcal.mol-1.K-1 (Increase of molecule flexibility)
-P3S,0.727 kcal/mol (Stabilizing),0.334 kcal/mol (Destabilizing),-0.672 kcal/mol (Destabilizing),0.010 kcal/mol (Stabilizing),-0.252 kcal/mol (Destabilizing),-0.418 kcal.mol-1.K-1 (Decrease of molecule flexibility)
-F12S,-0.270 kcal/mol (Destabilizing),0.048 kcal/mol (Destabilizing),-1.028 kcal/mol (Destabilizing),-0.930 kcal/mol (Destabilizing),-0.993 kcal/mol (Destabilizing),-0.060 kcal.mol-1.K-1 (Decrease of molecule flexibility)
-A19V,2.389 kcal/mol (Stabilizing),0.450 kcal/mol (Destabilizing),0.659 kcal/mol (Stabilizing),-0.170 kcal/mol (Destabilizing),1.040 kcal/mol (Stabilizing),-0.562 kcal.mol-1.K-1 (Decrease of molecule flexibility)

dynamut/dynamut_results/dynamut_output_single.csv

@@ -1,3 +0,0 @@
-mutationinformation,ddg_dynamut,ddg_encom,ddg_mcsm,ddg_sdm,ddg_duet,dds_encom
-G13V,0.006 kcal/mol (Stabilizing),-0.053 kcal/mol (Destabilizing),-0.261 kcal/mol (Destabilizing),-0.120 kcal/mol (Destabilizing),0.120 kcal/mol (Stabilizing),0.066 kcal.mol-1.K-1 (Increase of molecule flexibility)
-A19T,-0.077 kcal/mol (Destabilizing),0.224 kcal/mol (Destabilizing),-0.631 kcal/mol (Destabilizing),-2.620 kcal/mol (Destabilizing),-0.758 kcal/mol (Destabilizing),-0.280 kcal.mol-1.K-1 (Decrease of molecule flexibility)

dynamut/dynamut_temp/dynamut_result_url_batch_multiple.txt

@@ -1,3 +0,0 @@
-http://biosig.unimelb.edu.au/dynamut/results_prediction/161296287365
-http://biosig.unimelb.edu.au/dynamut/results_prediction/161296143994
-http://biosig.unimelb.edu.au/dynamut/results_prediction/161296201195

dynamut/dynamut_temp/dynamut_result_url_batch_single.txt

@@ -1 +0,0 @@
-http://biosig.unimelb.edu.au/dynamut/results_prediction/161296287365

dynamut/examples.py

@@ -1,71 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Fri Feb 12 12:15:26 2021
-
-@author: tanu
-"""
-import os
-homedir = os.path.expanduser('~')
-os.chdir (homedir + '/git/LSHTM_analysis/dynamut')
-from submit_dynamut import *
-from get_results_dynamut import *
-#%%#####################################################################
-#EXAMPLE RUN for different stages
-#=====================
-# STAGE: submit.py
-#=====================
-my_host = 'http://biosig.unimelb.edu.au'
-my_prediction_url = f"{my_host}/dynamut/prediction_list"
-print(my_prediction_url)
-
-my_outdir = homedir + '/git/LSHTM_analysis/dynamut'
-my_chain = 'A'
-my_email = 'tanushree.tunstall@lshtm.ac.uk'
-
-my_pdb_file = homedir + '/git/Data/streptomycin/input/gid_complex.pdb'
-my_mutation_list = homedir + '/git/LSHTM_analysis/dynamut/snp_test1.csv'
-my_suffix = 'gid_test1'
-
-#----------------------------------------------
-# example 1: 2 snps in a file
-#----------------------------------------------
-submit_dynamut(host_url = my_host
-, pdb_file = my_pdb_file
-, mutation_list = my_mutation_list
-, chain = my_chain
-, email_address = my_email
-, prediction_url = my_prediction_url
-, output_dir = my_outdir
-, outfile_suffix = my_suffix) 
-#%%###################################################################
-#=====================
-# STAGE: get_results.py
-#=====================
-my_host = 'http://biosig.unimelb.edu.au'
-my_outdir = homedir + '/git/LSHTM_analysis/dynamut'
-
-#----------------------------------------------
-# example 1: multiple urls in a single file
-#----------------------------------------------
-my_url_file_multiple = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_multiple.txt'
-print(my_url_file_multiple)
-my_suffix = 'multiple'
-
-get_results(url_file  = my_url_file_multiple
-            , host_url = my_host
-            , output_dir = my_outdir
-            , outfile_suffix = my_suffix)
-
-#----------------------------------------------
-# example 2: single url in a file
-#----------------------------------------------
-my_url_file_single = homedir + '/git/LSHTM_analysis/dynamut/dynamut_temp/dynamut_result_url_batch_single.txt'
-print(my_url_file_single)
-my_suffix = 'single'
-
-get_results(my_url_file_single
-            , host_url = my_host
-            , output_dir = my_outdir
-            , outfile_suffix = my_suffix)
-#%%###################################################################

dynamut/get_results_dynamut.py

@@ -67,7 +67,7 @@ def get_results(url_file, host_url, output_dir, outfile_suffix):
     #============================
     # Writing results file: csv
     #============================                   
-    dynamut_results_dir = output_dir + '/dynamut_results'
+    dynamut_results_dir = output_dir + 'dynamut_results/'
     if not os.path.exists(dynamut_results_dir):
         print('\nCreating dir: dynamut_results within:', output_dir )
         os.makedirs(dynamut_results_dir)   
@@ -79,7 +79,7 @@ def get_results(url_file, host_url, output_dir, outfile_suffix):
     #dynamut_results_out_df.to_csv('/tmp/test_dynamut.csv', index = False)
     
     # build out filename
-    out_filename = dynamut_results_dir + '/dynamut_output_' + outfile_suffix + '.csv'
+    out_filename = dynamut_results_dir + 'dynamut_output_' + outfile_suffix + '.csv'
     dynamut_results_out_df.to_csv(out_filename, index = False)
        
 # TODO: add as a cmd option

dynamut/run_get_results_dynamut.py

@@ -19,23 +19,20 @@ my_host = 'http://biosig.unimelb.edu.au'
 # TODO: add cmd line args
 #gene = 'gid'
 drug = 'streptomycin'
-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_dynamut_temp = datadir + drug + '/output/dynamut_results/dynamut_temp/'
 #==============================================================================
-# batch 8: 07.txt, # RETRIEVED 23 Feb 08:54
+# batch 8: 08.txt, # RETRIEVED 23 Feb 08:54
 #my_url_file =  outdir + '/dynamut_temp/dynamut_result_url_gid_b8.txt'
-#my_suffix = 'gid_b8'
+#my_suffix = 'gid_b7'
 
-# batch 9: 08.txt, # RETRIEVED 23 Feb 08:55
+#b09 and b10 failed!
-my_url_file =  outdir + '/dynamut_temp/dynamut_result_url_gid_b9.txt'
-my_suffix = 'gid_b9'
-
-# batch 10: 09.txt, # RETRIEVED
-#my_url_file =  outdir + '/dynamut_temp/dynamut_result_url_gid_b10.txt'
-#my_suffix = 'gid_b10'
 
+# batch 9: 09.txt,
+my_url_file =  outdir_dynamut_temp + 'dynamut_result_url_gid_b10_ab.txt'
+my_suffix = 'gid_b10_ab'
 #==============================================================================
 
 #==========================

dynamut/run_submit_dynamut.py

@@ -19,27 +19,30 @@ print(my_prediction_url)
 # TODO: add cmd line args
 #gene = 'gid'
 drug = 'streptomycin'
-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_dynamut = outdir + 'dynamut_results/'
 
 my_chain = 'A'
 my_email = 'tanushree.tunstall@lshtm.ac.uk'
 
-my_pdb_file = indir + '/gid_complex.pdb'
+my_pdb_file = indir + 'gid_complex.pdb'
 
 #==============================================================================
-# batch 8: 07.txt, # RAN: 22 Feb 09:26
+# batch 7: 07.txt, # RAN: 22 Feb 09:26
 #my_mutation_list = outdir + '/snp_batches/50/snp_batch_07.txt'
+#my_suffix = 'gid_b7'
+
+# batch 8: 08.txt, # RAN: 22 Feb 09:26
+#my_mutation_list = outdir + '/snp_batches/50/snp_batch_08.txt'
 #my_suffix = 'gid_b8'
 
-# batch 9: 08.txt, # RAN: 22 Feb 09:26
+# batch 9 and 10 failed!
-#my_mutation_list = outdir + '/snp_batches/50/snp_batch_08.txt'
+# bissecting: b10, split into 5 (1st failed, 2nd worked, but then comb rest)
-#my_suffix = 'gid_b9'
 
-# batch 10: 09.txt, # RAN:22 Feb 09:26
+my_mutation_list = outdir + 'snp_batches/50/b9_b10_bissect/b10_21.txt'
-my_mutation_list = outdir + '/snp_batches/50/snp_batch_09.txt'
+my_suffix = 'gid_b10_21'
-my_suffix = 'gid_b10'
 #==============================================================================
 
 #==========================
@@ -52,6 +55,6 @@ submit_dynamut(host_url = my_host
                , chain = my_chain
                , email_address = my_email
                , prediction_url = my_prediction_url
-               , output_dir = outdir
+               , output_dir = outdir_dynamut
                , outfile_suffix = my_suffix) 
 #%%#####################################################################               

dynamut/snp_test1.csv

@@ -1,2 +0,0 @@
-F12S
-A19V

dynamut/snp_test2.csv

@@ -1,2 +0,0 @@
-G13V
-A19T

dynamut/split_csv.sh

@@ -16,3 +16,4 @@ split ../../${INFILE} -l ${CHUNK} -d snp_batch_
 
 # use case
 #~/git/LSHTM_analysis/dynamut/split_csv.sh gid_mcsm_formatted_snps.csv snp_batches 50
+#~/git/LSHTM_analysis/dynamut/split_csv.sh embb_mcsm_formatted_snps.csv snp_batches 50

dynamut/submit_dynamut.py

@@ -74,12 +74,12 @@ def submit_dynamut(host_url
             #===============
             # writing file: result urls
             #===============
-            dynamut_temp_dir = output_dir + '/dynamut_temp' # creates a temp dir within output_dir
+            dynamut_temp_dir = output_dir + 'dynamut_temp/' # creates a temp dir within output_dir
             if not os.path.exists(dynamut_temp_dir):
                 print('\nCreating dynamut_temp in output_dir', output_dir )
                 os.makedirs(dynamut_temp_dir)                    
             
-            out_url_file = dynamut_temp_dir + '/dynamut_result_url_' + str(outfile_suffix) + '.txt'
+            out_url_file = dynamut_temp_dir + 'dynamut_result_url_' + str(outfile_suffix) + '.txt'
             print('\nWriting output url file:', out_url_file)
             myfile = open(out_url_file, 'a')    
             myfile.write(url)

mcsm_na/run_submit_mcsm_na.py

@@ -22,6 +22,7 @@ drug = 'streptomycin'
 datadir = homedir + '/git/Data'
 indir = datadir + '/' + drug + '/input'
 outdir = datadir + '/' + drug + '/output'
+outdir_mcsm_na = outdir + 'mcsm_na_results'
 
 my_nuc_type = 'RNA'
 my_pdb_file = indir + '/gid_complex.pdb'
@@ -43,6 +44,6 @@ submit_mcsm_na(host_url = my_host
                , mutation_list = my_mutation_list
                , nuc_type = my_nuc_type
                , prediction_url = my_prediction_url
-               , output_dir = outdir
+               , output_dir = outdir_mcsm_na
                , outfile_suffix = my_suffix) 
 #%%#####################################################################