added mcsm_na scripts to submit batches of 20

mcsm_na/examples.py

@@ -0,0 +1,56 @@
+#!/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/mcsm_na')
+from submit_mcsm_na import *
+from get_results import *
+#%%#####################################################################
+#EXAMPLE RUN for different stages
+#=====================
+# STAGE: submit_mcsm_na.py
+#=====================
+my_host = 'http://biosig.unimelb.edu.au'
+my_prediction_url = f"{my_host}/mcsm_na/run_prediction_list"
+print(my_prediction_url)
+
+my_outdir = homedir + '/git/LSHTM_analysis/mcsm_na'
+
+my_pdb_file = homedir + '/git/Data/streptomycin/input/gid_complex.pdb'
+my_mutation_list = homedir + '/git/LSHTM_analysis/mcsm_na/test_snps_b1.csv'
+my_suffix = 'gid_test_b1'
+
+#----------------------------------------------
+# example 1: 2 snps in a file
+#----------------------------------------------
+submit_mcsm_na(host_url = my_host
+, pdb_file = my_pdb_file
+, mutation_list = my_mutation_list
+, nuc_type = 'RNA'
+, 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/mcsm_na'
+
+#----------------------------------------------
+# example 1: single url in a single file
+#----------------------------------------------
+my_url_file_single = homedir + '/git/LSHTM_analysis/mcsm_na/mcsm_na_temp/mcsm_na_result_url_gid_test_b1.txt'
+print(my_url_file_single)
+my_suffix = 'single'
+
+get_results(url_file  = my_url_file_single
+            , host_url = my_host
+            , output_dir = my_outdir
+            , outfile_suffix = my_suffix)

mcsm_na/get_results.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug 19 14:33:51 2020
+
+@author: tanu
+"""
+#%% load packages
+import os,sys
+import subprocess
+import argparse
+import requests
+import re
+import time
+from bs4 import BeautifulSoup
+import pandas as pd
+from pandas.api.types import is_string_dtype
+from pandas.api.types import is_numeric_dtype
+#%%#####################################################################
+
+def get_results(url_file, host_url, output_dir, outfile_suffix):
+    # initilialise empty df
+    #mcsm_na_results_out_df = pd.DataFrame()
+    with open(url_file, 'r') as f:
+        for count, line in enumerate(f):
+            line = line.strip()
+            print('URL no.', count+1, '\n', line)
+            
+            #============================
+            # Writing results file: csv
+            #============================                   
+            mcsm_na_results_dir = output_dir + '/mcsm_na_results'
+            if not os.path.exists(mcsm_na_results_dir):
+                print('\nCreating dir: mcsm_na_results within:', output_dir )
+                os.makedirs(mcsm_na_results_dir)   
+                          
+        # TODO: add as a cmd option
+            # Download .tar.gz file
+            prediction_number = re.search(r'([0-9]+\.[0-9]+$)', line).group(0)
+            print('CHECK prediction no:', prediction_number)
+            txt_url = f"{host_url}/mcsm_na/static/results/" + prediction_number + '.txt'
+            print('CHECK txt url:', txt_url)
+            
+            out_filename = mcsm_na_results_dir + '/' + outfile_suffix + '_output_' + prediction_number + '.txt'
+            response_txt = requests.get(txt_url, stream = True)
+            if response_txt.status_code == 200:
+                print('\nDownloading .txt:', txt_url
+                      , '\n\nSaving file as:', out_filename)
+                with open(out_filename, 'wb') as f:
+                    f.write(response_txt.raw.read())
+   
+#%%##################################################################### 
+

mcsm_na/mcsm_na_temp/mcsm_na_result_url_gid_test_b1.txt

@@ -0,0 +1 @@
+http://biosig.unimelb.edu.au/mcsm_na/results_prediction/1613147445.16

mcsm_na/run_submit.py

@@ -0,0 +1,40 @@
+#!/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/mcsm_na')
+from submit import *
+
+#%%#####################################################################
+#EXAMPLE RUN for different stages
+#=====================
+# STAGE: submit.py
+#=====================
+my_host = 'http://biosig.unimelb.edu.au'
+my_prediction_url = f"{host}/mcsm_na/run_prediction"
+print(my_prediction_url)
+
+my_outdir = homedir + '/git/LSHTM_analysis/mcsm_na'
+
+my_pdb_file = homedir + '/git/Data/streptomycin/input/gid_complex.pdb'
+my_mutation_list = homedir + '/git/LSHTM_analysis/mcsm_na/input_snp_test_b1.csv'
+my_suffix = 'gid_test1'
+
+#----------------------------------------------
+# example 1: 2 snps in a file
+#----------------------------------------------
+submit_mcsm_na(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) 
+#%%###################################################################
+

mcsm_na/submit_mcsm_na.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Aug 19 14:33:51 2020
+
+@author: tanu
+"""
+#%% load packages
+import os,sys
+import subprocess
+import argparse
+import requests
+import re
+import time
+from bs4 import BeautifulSoup
+import pandas as pd
+from pandas.api.types import is_string_dtype
+from pandas.api.types import is_numeric_dtype
+#%%#####################################################################
+def submit_mcsm_na(host_url
+                        , pdb_file
+                        , mutation_list
+                        , nuc_type
+                        , prediction_url
+                        , output_dir
+                        , outfile_suffix
+                        ):
+    """
+    Makes a POST request for mcsm_na predictions.
+
+    @param host_url: valid host url for submitting the job
+    @type string
+
+    @param pdb_file: valid path to pdb structure
+    @type string
+    
+    @param mutation_list: list of mutations (1 per line) of the format:{chain} {WT}<POS>{Mut} [A X1Z}
+	@type string
+	
+	@param nuc_type: Nucleic acid type
+	@type string
+	        
+	@param prediction_url: mcsm_na url for prediction
+	@type string
+       
+    @param output_dir: output dir
+	@type string
+    
+    @param outfile_suffix: outfile_suffix
+	@type string
+
+    @return writes a .txt file containing url for the snps processed with user provided suffix in filename 
+    @type string
+    """
+    
+    with open(pdb_file, "rb") as pdb_file, open (mutation_list, "rb") as mutation_list:
+        files = {"wild": pdb_file
+                 , "mutation_list": mutation_list}
+        body = {"na_type": nuc_type
+                ,"pred_type": 'list',
+                "pdb_code": ''} # apparently needs it even though blank!
+
+        response = requests.post(prediction_url, files = files, data = body)
+        print(response.status_code)
+        if response.history:
+            print('\nPASS: valid submission. Fetching result url')
+            url_match = re.search('/mcsm_na/results_prediction/.+(?=")', response.text)
+            url = host_url + url_match.group()
+            print('\nURL for snp batch no ', str(outfile_suffix), ':', url)
+            
+            #===============
+            # writing file: result urls
+            #===============
+            mcsm_na_temp_dir = output_dir + '/mcsm_na_temp' # creates a temp dir within output_dir
+            if not os.path.exists(mcsm_na_temp_dir):
+                print('\nCreating mcsm_na_temp in output_dir', output_dir )
+                os.makedirs(mcsm_na_temp_dir)                    
+            
+            out_url_file = mcsm_na_temp_dir + '/mcsm_na_result_url_' + str(outfile_suffix) + '.txt'
+            print('\nWriting output url file:', out_url_file)
+            myfile = open(out_url_file, 'a')    
+            myfile.write(url)
+            myfile.close()
+#%%#####################################################################

mcsm_na/test_snps_b1.csv

@@ -0,0 +1,2 @@
+A P3S
+A I4N