CAVA ported to python3

.gitignore

@@ -13,3 +13,6 @@
 /*/*/__pycache__
 /*/*/*/__pycache__
 doc/sphinx/_build
+/test/tmp.*
+/test/hg38.fa
+/test/hg38.fa.fai

README → README.md

@@ -1,3 +1,15 @@
+<!-- vim-markdown-toc GFM -->
+
+* [CAVA v1.2.3 README](#cava-v123-readme)
+    * [1 INTRODUCTION](#1-introduction)
+    * [2 PUBLICATION](#2-publication)
+    * [3 DEPENDENCIES](#3-dependencies)
+    * [4 INSTALLATION ON LINUX OR MAC](#4-installation-on-linux-or-mac)
+    * [5 RUNNING CAVA](#5-running-cava)
+    * [6 DOCUMENTATION](#6-documentation)
+    * [7 LICENCE](#7-licence)
+
+<!-- vim-markdown-toc -->
 
 CAVA v1.2.3 README
 ==================
@@ -22,7 +34,7 @@ Márton Münz, Elise Ruark, Anthony Renwick, Emma Ramsay, Matthew Clarke, Shazia
 --------------
 
 To install and run CAVA v1.2.3 you will need the following dependencies installed:
-- Python 2.7.9 or later (Python2 series)
+- Python 3
 - GCC and GNU make
 - virtualenv
 

bin/CAVA.py

@@ -1,11 +1,11 @@
-#!env/bin/python
+#!env/bin/python3
 
 from optparse import OptionParser
 from cava_ import main
 from cava_ import helper
 
 # Version
-version = 'v1.2.3'
+version = 'v2.0.0'
 
 # Read default configuration file name from the default_config_path file
 default_config_file = helper.defaultConfigPath()

bin/EnsemblDB.py

@@ -1,10 +1,10 @@
-#!env/bin/python
+#!env/bin/python3
 
 from optparse import OptionParser
 from ensembldb import main
 
 # Version
-version = '1.2.3'
+version = '2.0.0'
 
 # Command line argument parsing
 descr = 'CAVA ensembl_db v' + version

bin/dbSNPDB.py

@@ -1,4 +1,4 @@
-#!env/bin/python
+#!env/bin/python3
 
 import os
 import sys
@@ -54,7 +54,7 @@ def processData(options, datafile, IDs):
 
     sys.stdout.write('\rProcessing SNPs on all chrs ... OK')
     sys.stdout.flush()
-    print ''
+    print('')
     datafile.close()
     outfile.close()
     return counter
@@ -83,16 +83,16 @@ def printMetaData(datafile):
         line = line.strip()
         if line.startswith('#'):
             if line.startswith('##dbSNP_BUILD_ID='):
-                print 'Input file build: '+line[17:]
+                print('Input file build: '+line[17:])
                 ret = int(line[17:])
-            if line.startswith('##reference='): print 'Reference: '+line[12:]+'\n'
+            if line.startswith('##reference='): print('Reference: '+line[12:]+'\n')
         else:
             return ret
 
 #######################################################################################################################
 
 # Version
-version = '1.2.3'
+version = '2.0.0'
 
 descr =  'CAVA dbsnp_db v' + version
 epilog = '\nExample usage: CAVA-{}/dbsnp_db -d 00-All.vcf.gz -s 138 -o out\n\n'.format(version)
@@ -106,39 +106,39 @@ def printMetaData(datafile):
 
 # Check options
 if options.release is None:
-    print '\nError: no dbSNP release specified'
-    print 'Please use option -s to specify dbSNP release version\n'
+    print('\nError: no dbSNP release specified')
+    print('Please use option -s to specify dbSNP release version\n')
     quit()
 if options.data is None:
-    print '\nError: no 00-All.vcf.gz data file specified'
-    print 'Please use option -d to specify path to data file\n'
+    print('\nError: no 00-All.vcf.gz data file specified')
+    print('Please use option -d to specify path to data file\n')
     quit()
 if not os.path.isfile(options.data):
-    print '\nError: 00-All.vcf.gz file (' + options.data + ') cannot be found.\n'
+    print('\nError: 00-All.vcf.gz file (' + options.data + ') cannot be found.\n')
     quit()
 
 # Print out version information
-print "\n---------------------------------------------------------------------------------------"
-print 'CAVA ' + version + ' dbSNP database preparation tool (dbsnp_db) is now running.'
-print 'Started: ', datetime.datetime.now(), '\n'
+print("\n---------------------------------------------------------------------------------------")
+print('CAVA ' + version + ' dbSNP database preparation tool (dbsnp_db) is now running.')
+print('Started: ', datetime.datetime.now(), '\n')
 
 # Open data fie for reading
-datafile = gzip.open(options.data, 'r')
+datafile = gzip.open(options.data, 'rt')
 
 # Print out meta data
 build = printMetaData(datafile)
 datafile.seek(0)
 if int(options.release) > build:
-    print 'Error: requested release must be <=' + str(build) + '\n'
+    print('Error: requested release must be <=' + str(build) + '\n')
     quit()
 
 # Print out info
-print 'Requested dbSNP release: ' + str(options.release)
+print('Requested dbSNP release: ' + str(options.release))
 IDs = []
 if options.input is not None:
     IDs = readIDs(options.input)
-    print '\nInput file contains ' + str(len(IDs)) + ' dbSNP IDs to be included in the database'
-print ''
+    print('\nInput file contains ' + str(len(IDs)) + ' dbSNP IDs to be included in the database')
+print('')
 
 # Create compressed output file
 N = processData(options, datafile, IDs)
@@ -150,13 +150,13 @@ def printMetaData(datafile):
 os.remove(options.output)
 
 # Print out summary information
-print '\nA total of ' + str(N) + ' SNPs have been retrieved\n'
-print '---------------------'
-print 'Output files created:'
-print '---------------------'
-print options.output + '.gz (SNP database)'
-print options.output + '.gz.tbi (index file)'
-print ''
-print 'CAVA dbsnp_db successfully finished: ', datetime.datetime.now()
-print "---------------------------------------------------------------------------------------\n"
+print('\nA total of ' + str(N) + ' SNPs have been retrieved\n')
+print('---------------------')
+print('Output files created:')
+print('---------------------')
+print(options.output + '.gz (SNP database)')
+print(options.output + '.gz.tbi (index file)')
+print('')
+print('CAVA dbsnp_db successfully finished: ', datetime.datetime.now())
+print("---------------------------------------------------------------------------------------\n")
 

cava_/conseq.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python
+#!/usr/bin/env python3
 
 
 # CLASS annotation
@@ -219,4 +219,4 @@ def checkUTR(transcript, variant):
         y = variant.pos + len(variant.ref) - 1
     if transcript.isPositionOutsideCDS_5prime(x) or transcript.isPositionOutsideCDS_5prime(y): return 'UTR5'
     if transcript.isPositionOutsideCDS_3prime(x) or transcript.isPositionOutsideCDS_3prime(y): return 'UTR3'
-    return ''
+    return ''