def formatAttributeForExport(attribute_db,filename):
import IdentifyAltIsoforms
export_db={}
for (gene,probeset) in attribute_db:
attribute_list = attribute_db[(gene,probeset)]; attribute_list2=[]
for (attribute,direction) in attribute_list: attribute_list2.append(attribute+'|'+direction)
export_db[probeset]=attribute_list2
print 'Exporting:',filename
IdentifyAltIsoforms.exportSimple(export_db,filename,'')
def reAnalyzeRNAProbesetMatches(align_files,species,array_type,pairwise_probeset_combinations):
"""Import matching and non-matching probesets and export the valid comparisons"""
align_files2=[]
for file in align_files:
if array_type in file: align_files2.append(file)
align_files = align_files2
matching={}; not_matching={}
for filename in align_files:
print 'Reading',filename
start_time = time.time()
fn=filepath(filename)
for line in open(fn,'rU').xreadlines():
values = string.replace(line,'\n','')
probeset,call,accession = string.split(values,'\t')
if call == '1':
try: matching[probeset].append(accession)
except KeyError: matching[probeset] = [accession]
else:
try: not_matching[probeset].append(accession)
except KeyError: not_matching[probeset] = [accession]
probeset_matching_pairs={}; matching_in_both=0; match_and_null=0; no_matches=0; no_nulls=0
for (probeset1,probeset2) in pairwise_probeset_combinations:
if probeset1 in matching and probeset2 in matching:
matching[probeset1].sort(); matching[probeset2].sort()
match1 = string.join(matching[probeset1],'|')
match2 = string.join(matching[probeset2],'|')
if match1 != match2:
probeset_matching_pairs[probeset1+'|'+probeset2] = [match1,match2]
matching_in_both+=1
else:
if probeset1 in matching and probeset1 in not_matching:
match = string.join(matching[probeset1],'|')
null_match = string.join(filterNullMatch(not_matching[probeset1],matching[probeset1]),'|')
probeset_matching_pairs[probeset1] = [match,null_match]
match_and_null+=1
elif probeset2 in matching and probeset2 in not_matching:
match = string.join(matching[probeset2],'|')
null_match = string.join(filterNullMatch(not_matching[probeset2],matching[probeset2]),'|')
probeset_matching_pairs[probeset2] = [match,null_match]
match_and_null+=1
elif probeset1 in matching or probeset2 in matching: no_nulls+=1
else:
no_matches+=1
#if no_matches<10: print probeset1,probeset2
print matching_in_both, "probeset pairs with matching isoforms for both recipricol probesets."
print match_and_null, "probeset pairs with a match for one and null for that one."
print no_nulls, "probeset pairs with only one match."
print no_matches, "probeset pairs with no matches."
import IdentifyAltIsoforms
export_file = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_all-transcript-matches.txt'
if analysis_type == 'single':
export_file = 'AltDatabase/'+species+'/'+array_type+'/junction/'+species+'_all-transcript-matches.txt'
IdentifyAltIsoforms.exportSimple(probeset_matching_pairs,export_file,'')
def formatAttributeForExport(attribute_db, filename):
import IdentifyAltIsoforms
export_db = {}
for (gene, probeset) in attribute_db:
attribute_list = attribute_db[(gene, probeset)]
attribute_list2 = []
for (attribute, direction) in attribute_list:
attribute_list2.append(attribute + '|' + direction)
export_db[probeset] = attribute_list2
print 'Exporting:', filename
IdentifyAltIsoforms.exportSimple(export_db, filename, '')
def reAnalyzeRNAProbesetMatches(align_files, species, array_type,
pairwise_probeset_combinations):
"""Import matching and non-matching probesets and export the valid comparisons"""
align_files2 = []
for file in align_files:
if array_type in file: align_files2.append(file)
align_files = align_files2
matching = {}
not_matching = {}
for filename in align_files:
print 'Reading', filename
start_time = time.time()
fn = filepath(filename)
for line in open(fn, 'rU').xreadlines():
values = string.replace(line, '\n', '')
probeset, call, accession = string.split(values, '\t')
if call == '1':
try:
matching[probeset].append(accession)
except KeyError:
matching[probeset] = [accession]
else:
try:
not_matching[probeset].append(accession)
except KeyError:
not_matching[probeset] = [accession]
probeset_matching_pairs = {}
matching_in_both = 0
match_and_null = 0
no_matches = 0
no_nulls = 0
for (probeset1, probeset2) in pairwise_probeset_combinations:
if probeset1 in matching and probeset2 in matching:
matching[probeset1].sort()
matching[probeset2].sort()
match1 = string.join(matching[probeset1], '|')
match2 = string.join(matching[probeset2], '|')
if match1 != match2:
probeset_matching_pairs[probeset1 + '|' +
probeset2] = [match1, match2]
matching_in_both += 1
else:
if probeset1 in matching and probeset1 in not_matching:
match = string.join(matching[probeset1], '|')
null_match = string.join(
filterNullMatch(not_matching[probeset1],
matching[probeset1]), '|')
probeset_matching_pairs[probeset1] = [match, null_match]
match_and_null += 1
elif probeset2 in matching and probeset2 in not_matching:
match = string.join(matching[probeset2], '|')
null_match = string.join(
filterNullMatch(not_matching[probeset2],
matching[probeset2]), '|')
probeset_matching_pairs[probeset2] = [match, null_match]
match_and_null += 1
elif probeset1 in matching or probeset2 in matching:
no_nulls += 1
else:
no_matches += 1
#if no_matches<10: print probeset1,probeset2
print matching_in_both, "probeset pairs with matching isoforms for both recipricol probesets."
print match_and_null, "probeset pairs with a match for one and null for that one."
print no_nulls, "probeset pairs with only one match."
print no_matches, "probeset pairs with no matches."
import IdentifyAltIsoforms
export_file = 'AltDatabase/' + species + '/' + array_type + '/' + species + '_all-transcript-matches.txt'
if analysis_type == 'single':
export_file = 'AltDatabase/' + species + '/' + array_type + '/junction/' + species + '_all-transcript-matches.txt'
IdentifyAltIsoforms.exportSimple(probeset_matching_pairs, export_file, '')
