Mercurial > repos > jjohnson > find_in_reference

comparison find_in_reference.py @ 2:c4fd2ea4f988

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Add the option to test the reversed sequence and the DNA reverse complement of the sequence (ignored if the sequence cannot be interpreted as DNA)
author Jim Johnson <jj@umn.edu>
date Thu, 13 Nov 2014 14:09:50 -0600
parents e83e0ce8fb68
children 2429b413d90a
comparison
equal deleted inserted replaced
1:e83e0ce8fb68 2:c4fd2ea4f988
40 parser.add_option( '-f', '--filtered', dest='filtered', help='The output file for input lines not in the output') 40 parser.add_option( '-f', '--filtered', dest='filtered', help='The output file for input lines not in the output')
41 parser.add_option('-c','--input_column', dest='input_column', default=None, help='The column for the value in the input file. (first column = 1, default to last column)') 41 parser.add_option('-c','--input_column', dest='input_column', default=None, help='The column for the value in the input file. (first column = 1, default to last column)')
42 parser.add_option('-C','--reference_column', dest='reference_column', default=None, help='The column for the value in the reference file. (first column = 1, default to last column)') 42 parser.add_option('-C','--reference_column', dest='reference_column', default=None, help='The column for the value in the reference file. (first column = 1, default to last column)')
43 parser.add_option( '-I', '--case_insensitive', dest='ignore_case', action="store_true", default=False, help='case insensitive' ) 43 parser.add_option( '-I', '--case_insensitive', dest='ignore_case', action="store_true", default=False, help='case insensitive' )
44 parser.add_option( '-R', '--reverse_find', dest='reverse_find', action="store_true", default=False, help='find the reference string in the input string' ) 44 parser.add_option( '-R', '--reverse_find', dest='reverse_find', action="store_true", default=False, help='find the reference string in the input string' )
45 parser.add_option( '-B', '--test_reverse', dest='test_reverse', action="store_true", default=False, help='Also search for reversed input string in reference' )
46 parser.add_option( '-D', '--test_dna_reverse_complement', dest='test_reverse_comp', action="store_true", default=False, help='Also search for the DNA reverse complement of input string' )
45 parser.add_option( '-k', '--keep', dest='keep', action="store_true", default=False, help='' ) 47 parser.add_option( '-k', '--keep', dest='keep', action="store_true", default=False, help='' )
46 parser.add_option( '-a', '--annotation_columns', dest='annotation_columns', default=None, help='If string is found, add these columns from reference' ) 48 parser.add_option( '-a', '--annotation_columns', dest='annotation_columns', default=None, help='If string is found, add these columns from reference' )
47 parser.add_option( '-s', '--annotation_separator', dest='annotation_separator', default=';', help='separator character between annotations from different lines' ) 49 parser.add_option( '-s', '--annotation_separator', dest='annotation_separator', default=';', help='separator character between annotations from different lines' )
48 parser.add_option( '-S', '--annotation_col_sep', dest='annotation_col_sep', default=',', help='separator character between annotation column from the same line' ) 50 parser.add_option( '-S', '--annotation_col_sep', dest='annotation_col_sep', default=',', help='separator character between annotation column from the same line' )
49 parser.add_option( '-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stdout' ) 51 parser.add_option( '-d', '--debug', dest='debug', action='store_true', default=False, help='Turn on wrapper debugging to stdout' )
50 (options, args) = parser.parse_args() 52 (options, args) = parser.parse_args()
53
54 revcompl = lambda x: ''.join([{'A':'T','C':'G','G':'C','T':'A','a':'t','c':'g','g':'c','t':'a','N':'N','n':'n'}[B] for B in x][::-1])
55 def test_rcomplement(seq, target):
56 if options.test_reverse_comp:
57 try:
58 comp = revcompl(seq)
59 return comp in target
60 except:
61 pass
62 return False
63
64 def test_reverse(seq,target):
65 return options.test_reverse and seq and seq[::-1] in target
66
51 # Input files 67 # Input files
52 if options.input != None: 68 if options.input != None:
53 try: 69 try:
54 inputPath = os.path.abspath(options.input) 70 inputPath = os.path.abspath(options.input)
55 inputFile = open(inputPath, 'r') 71 inputFile = open(inputPath, 'r')
114 target_string = target_string.upper() 130 target_string = target_string.upper()
115 search = search_string if not options.reverse_find else target_string 131 search = search_string if not options.reverse_find else target_string
116 target = target_string if not options.reverse_find else search_string 132 target = target_string if not options.reverse_find else search_string
117 if options.debug: 133 if options.debug:
118 print >> sys.stderr, "in: %s %s %s" % (search,search in target,target) 134 print >> sys.stderr, "in: %s %s %s" % (search,search in target,target)
119 if search in target: 135 if search in target or test_reverse(search,target) or test_rcomplement(search,target):
120 found = True 136 found = True
121 if annotate: 137 if annotate:
122 annotation = options.annotation_col_sep.join([fields[i] for i in annotation_columns]) 138 annotation = options.annotation_col_sep.join([fields[i] for i in annotation_columns])
123 annotations.append(annotation) 139 annotations.append(annotation)
124 else: 140 else: