added split_csv.sh

dynamut/split_csv.sh

@@ -0,0 +1,18 @@
+#!/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 dynamut 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/dynamut/split_csv.sh gid_mcsm_formatted_snps.csv snp_batches 50

dynamut/submit.py

@@ -16,17 +16,34 @@ from bs4 import BeautifulSoup
 import pandas as pd
 from pandas.api.types import is_string_dtype
 from pandas.api.types import is_numeric_dtype
+#%% homedir
+homedir = os.path.expanduser('~')
+print('My homedir is:', homedir)
+
 #%%
 host = 'http://biosig.unimelb.edu.au'
 prediction_url = f"{host}/dynamut/prediction_list"
 print(prediction_url)
 
-#%%
+#%% example params
-#def format_data(data_file):
+gene_name = 'gid'
+drug = 'streptomycin'
+datadir = homedir + '/git/Data'
+indir = datadir + '/' + drug + '/input'
+#outdir = datadir + '/' + drug + '/output'
+outdir = homedir + '/git/LSHTM_analysis/dynamut' # for example
+
+dynamut_temp_dir = outdir + '/dynamut_temp'
+
+if not os.path.exists(dynamut_temp_dir):
+    print('Creating dynamut_temp in outdir', outdir )
+    os.makedirs(dynamut_temp_dir)
+    
+batch_no = 1
+out_url_file = dynamut_temp_dir + '/dynamut_result_url_batch_' + str(batch_no) + '.txt'
+
    
 #%% request calculation (no def)
-output_dir = "/home/tanu/git/LSHTM_analysis/dynamut"
-gene_name = 'gid'
 with open("/home/tanu/git/Data/streptomycin/input/gid_complex.pdb", "rb") as pdb_file, open ("/home/tanu/git/LSHTM_analysis/dynamut/snp_test2.csv") as mutation_list:
         files = {"wild": pdb_file
                  , "mutation_list": mutation_list}
@@ -43,21 +60,11 @@ with open("/home/tanu/git/Data/streptomycin/input/gid_complex.pdb", "rb") as pdb
             #===============
             # writing file: result urls
             #===============
-            out_url_file = output_dir + '/' + gene_name.lower() + '_snp_batch' + '_result_url.txt'
+            out_url_file = dynamut_temp_dir + '/dynamut_result_url_batch_' + str(batch_no) + '.txt'
-            print(out_url_file)
+            print('Writing output url file:', out_url_file)
             myfile = open(out_url_file, 'a')    
-            myfile.write(url + '\n')
+            myfile.write(url)
             myfile.close()
-        else:
-            print('ERROR: invalid mutation! Wild-type residue doesn\'t match pdb file.'
-                 , '\nSkipping to the next mutation in file...')
-             #===============
-             # writing file: invalid mutations
-             #===============
-            out_error_file = output_dir + '/' + gene_name.lower() + '_errors.txt'
-            failed_muts = open(out_error_file, 'a')    
-            failed_muts.write(mutation_list + '\n')
-            failed_muts.close()
 
 #%%
 def request_calculation(pdb_file, mutation_list
@@ -66,7 +73,8 @@ def request_calculation(pdb_file, mutation_list
                         , prediction_url
                         , output_dir
                         , gene_name
-                        , url_file):
+                        , batch_no
+                        , out_url_file):
     """
     Makes a POST request for a ligand affinity prediction.