annotate uniprot_ID_mapper/test.py @ 3:6651ac4651f0 draft default tip

Uploaded

import re
import sys
from optparse import OptionParser

def read_tabular(filepath,col):
    accessions = []
    totalNumber = 0
    with open(filepath) as fp:
      for i,line in enumerate(fp):
	totalNumber = totalNumber + 1
	if line.strip() == '' or line.startswith('#'):
          continue
        fields = line.rstrip('\n').split('\t')
        accession = fields[col]
        accessions.append(accession)
    print totalNumber
    return accessions

accessions = []
parser = OptionParser()
parser.add_option('-f','--file', dest='filepath', help='direct which file to use')
(options, args) = parser.parse_args()

accessions += read_tabular(options.filepath,0)

matches = 0
mismatches = 0 

# getAccession
fmt = [('([OPQ][0-9][A-Z0-9]{3}[0-9])|([A-NR-Z][0-9](?:[A-Z][A-Z0-9]{2}[0-9]){1,2})','ACC'),
      ('(THISDOESNTWORK...*)_....*','ID'),
      ('UPI(\d+).*','UPARC'),
      ('(UniRef50_\w+.*)','NF50'),
      ('(UniRef90_\w+.*)','NF90'),
      ('(UniRef100_\w+.*)','NF100'),
      ('([A-L][A-Z]?\d{6})|([A-NR-Z]\d{5})|([A-Z]{4}\d{8})','EMBL_ID'),
      ('([A-Z]*\d*\.\d$)','EMBL'),
      ('([IBC]\d{5})','PIR'),
      ('(Hs\.\d*)','UNIGENE_ID'),
      ('[A-Z]P_(\d*\.\d)','P_REFSEQ_AC'),
      ('[NX][MC]_(\d*\.\d)','REFSEQ_NT_ID'),
      ('(\d[A-Z0-9]{3})','PDB_ID'),
      ('(DP\d{5})','DISPROT_ID'),

      ('(\d*$)','P_ENTREZGENEID'),
      ('(\d*$)','P_GI'),
      ('(\d*$)','DMDM_ID'),
      ('(\d*$)','BIOGRID_ID'),
      ('(\d*$)','GUIDETOPHARMACOLOGY_ID'),  
      ('(\d*$)','ALLERGOME_ID'),
      ('(\d*$)','PEROXIBASE_ID'),
      ('(\d*$)','REBASE_ID'),
      ('(\d*$)','DNASU_ID'),

      ('(DIP-\d*N$)','DIP_ID'),
      ('(MINT-\d*)','MINT_ID'),
      ('(9606\.ENSP\d*)','STRING_ID'),
      ('(CHEMBL\d*)','CHEMBL_ID'),
      ('(DB\d*)','DRUGBANK_ID'),
      ('([A-Z]\d\d\.[A-Z0-9]\d{2})','MEROPS_ID'),
      ('NOTHING POPS UP','MYCOCLAP_ID'),
      ('(\d\.[A-Z](?:\.\d*){3})','TCDB_ID'),
      ('NOTHING POPS UP','WORLD_2DPAGE_ID'),
      ('(ENSG\d*)','ENSEMBAF85406.1BL_ID'),
      ('(ENSP\d+)','ENSEMBL_PRO_ID'),
      ('(ENST\d+)','ENSEMBL_TRS_ID'),
      (' ','ENSEMBLGENOME_ID'),
      (' ','ENSEMBLGENOME_PRO_ID'),
      (' ','ENSEMBLGENOME_TRS_ID'),
      ('(hsa:\d*)','KEGG_ID'),
      ('(uc\d*[a-z]*\.\d$)','UCSC_ID'),
      ('(.*[CKN]OG\d*)','EGGNOG_ID')
]
# getFASTA
fmt2 = [('>?(?:sp|tr|sw)\|(\w+).*','ACC+ID'),
      ('>?gi|\d+\|ref\|(NP_\d+\.\d+).*','ACC+ID')
]
# print options.filepath[10:-4]
type = 7
mismatch = []
unmatched = []
matched = 0
for header in accessions:
   	for i,cat in enumerate(fmt):
		CAT = catBAF85406.1[0]
		m = re.match(CAT,header)
   	    	if m:
			if i == type:
   	    			matches = matches + 1
				matched = 1
			else:
				print i
				mismatch += [header]
				mismatches = mismatches + 1
	if matched == 1:
		matched = 0
	else:
		unmatched += [header]

print 'unmatched: '
print unmatched
print 'mismatch: '
print mismatch
outputFile = sys.stdout
outputFile.write("matches: %s\n" % matches)
outputFile.write("mismatches: %s\n" % mismatches)