diff data_manager_amrfinderplus/data_manager/data_manager_amrfinderplus.py @ 0:5ba68abd41f6 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_amrfinderplus/data_manager/data_manager_amrfinderplus.py	Tue May 24 11:46:19 2022 +0000
@@ -0,0 +1,106 @@
+#!/usr/bin/env python
+# Errol Strain, [e-mail]
+# Database downloads for NCBI AMRFinderPlus
+
+import sys
+import os
+import tempfile
+import shutil
+import json
+import re
+import argparse
+from ftplib import FTP
+
+
+def download_from_ncbi(output_directory):
+    NCBI_FTP_SERVER = 'ftp.ncbi.nlm.nih.gov'
+    FILENAME = 'version.txt' 
+    NCBI_DOWNLOAD_PATH = '/pathogen/Antimicrobial_resistance/AMRFinderPlus/database/latest/'
+    
+    email = '[e-mail]'
+
+    cwd = os.getcwd() 
+    os.chdir(output_directory)
+
+    ftp = FTP( NCBI_FTP_SERVER )
+    ftp.login( 'anonymous', email)
+    ftp.cwd(NCBI_DOWNLOAD_PATH)
+    
+    #exclude the allele counts folder
+    files = ftp.nlst()
+    files = filter(lambda x: re.search(r'^((?!allele|(?:invokername=allele)).)*$', x), files)
+
+    for f in files:
+      ftp.retrbinary("RETR " + f, open(f, 'wb').write)
+
+    files = ftp.nlst()
+    files = filter(lambda x: re.search(r'^((?!allele|(?:invokername=allele)).)*$', x), files)
+    pointmuts = filter(lambda x: re.search(r'^((?!tab|(?:invokername=tab)).)*$', x), files)
+    pointmuts = filter(lambda x: re.search(r'AMR_DNA-', x), pointmuts)
+
+
+    # Make blast databases
+    blastcmd = "makeblastdb -in AMRProt -dbtype prot -logfile /dev/null"
+    os.system(blastcmd)
+    blastcmd = "makeblastdb -in AMR_CDS -dbtype nucl -logfile /dev/null"
+    os.system(blastcmd)
+
+    for f in pointmuts:
+      blastcmd = "makeblastdb -in " + f +" -dbtype nucl -logfile /dev/null"
+      os.system(blastcmd)
+
+    # Make HMM indexes
+    hmmcmd="hmmpress -f AMR.LIB > /dev/null 2> /dev/null"
+    os.system(hmmcmd)
+ 
+    # Read in version
+    with open("version.txt") as f:
+      version = f.readline().rstrip()
+
+    ftp.quit()
+    
+    os.chdir(cwd)    
+    
+    return version 
+
+def print_json (version,argspath,argsname,argsout):
+
+    data_table_entry = {
+      'data_tables' : {
+        'amrfinderplus': [
+          {
+            "value":version,
+            "name":argsname,
+            "path":argspath,
+          }
+        ]
+      }
+    }
+
+    with open(argsout, 'w') as fh:
+      json.dump(data_table_entry, fh, indent=2, sort_keys=True)
+        
+def main():
+   
+    parser = argparse.ArgumentParser(description='Download NCBI amrFinderPlus Databases')
+    parser.add_argument('--name', type=str, required=True, nargs=1, help='Database name')
+    parser.add_argument('--out', type=str, required=True, nargs=1, help='output file')
+
+    args = parser.parse_args()
+
+    with open(args.out[0]) as fh:
+        params = json.load(fh)
+
+    output_directory = params['output_data'][0]['extra_files_path']
+    os.mkdir(output_directory)
+    data_manager_dict = {}
+
+    #Fetch the files and build blast databases
+    version=download_from_ncbi(output_directory)    
+
+    tablename = "AMRFinderPlus Database " + version
+
+    #shutil.copytree("amrdb",args.path[0])
+    print_json(version,output_directory,tablename,args.out[0])
+
+if __name__ == "__main__": main()