def annotateJunctionIDsAsExon(species,array_type):
import ExonSeqModule
probeset_annotations_file = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_junction_probesets-filtered.txt'
if array_type == 'RNASeq':
probeset_annotations_file = string.replace(probeset_annotations_file,'junction_probesets-filtered','exons')
junction_exon_db = ExonSeqModule.importSplicingAnnotationDatabase(probeset_annotations_file,array_type)
probeset_annotations_file = 'AltDatabase/'+species+'/exon/'+species+'_Ensembl_probesets.txt'
exon_db = ExonSeqModule.importSplicingAnnotationDatabase(probeset_annotations_file,array_type)
### Extract unique exon regions from Exon Array annotations
multiple_exon_regions={}; unique_exon_regions={}
for probeset in exon_db:
y = exon_db[probeset]
geneid = y.GeneID()
if '|' in y.ExonRegionID():
exonids = string.split(y.ExonRegionID(),'|')
for exonid in exonids: multiple_exon_regions[geneid,exonid] = y
else:
unique_exon_regions[geneid,y.ExonRegionID()] = y
### Add missing exons to unique
for uid in multiple_exon_regions:
if uid not in unique_exon_regions: unique_exon_regions[uid]=multiple_exon_regions[uid]
"""
for i in unique_exon_regions:
if 'ENSMUSG00000066842' in i:
print i
stop
"""
### Extract unique exon regions from Junction Array annotation
junction_to_exonids={}
for probeset in junction_exon_db:
if 'ENSMUSG00000066842' in probeset: print probeset
y = junction_exon_db[probeset]
geneid = y.GeneID()
if '|' in y.ExonRegionID():
exonids = string.split(y.ExonRegionID(),'|')
if probeset == 'ENSMUSG00000066842|E60.1': print [[exonids]]
for exonid in exonids:
if (geneid,exonid) in unique_exon_regions:
y = unique_exon_regions[geneid,exonid]
if probeset == 'ENSMUSG00000066842:E60.1': print [y.Probeset()]
junction_to_exonids[probeset] = y.Probeset()
else:
if (geneid,string.replace(y.ExonRegionID(),'.','-')) in unique_exon_regions:
#if ':' in probeset: print [probeset,y.ExonRegionID()];kill
y = unique_exon_regions[geneid,string.replace(y.ExonRegionID(),'.','-')]
junction_to_exonids[probeset] = y.Probeset()
output_file = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_'+array_type+'-exon_probesets.txt'
fn=filepath(output_file); data = open(fn,'w')
data.write(array_type+'_probeset\texon_probeset\n')
for probeset in junction_to_exonids:
exon_probeset = junction_to_exonids[probeset]
data.write(probeset+'\t'+exon_probeset+'\n')
data.close()
def getParametersAndExecute(probeset_seq_file,array_type,species,data_type):
if data_type == 'critical-exons':
if array_type == 'RNASeq': probeset_annotations_file = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_exons.txt'
else: probeset_annotations_file = 'AltDatabase/'+species+'/'+array_type+'/'+species+'_Ensembl_'+array_type+'_probesets.txt'
###Import probe-level associations
exon_db = ExonSeqModule.importSplicingAnnotationDatabase(probeset_annotations_file,array_type)
start_time = time.time()
probeset_seq_db = importProbesetSeqeunces(probeset_seq_file,exon_db,species) ###Do this locally with a function that works on tab-delimited as opposed to fasta sequences (exon array)
end_time = time.time(); time_diff = int(end_time-start_time)
elif data_type == 'junctions':
start_time = time.time(); biotype = 'gene' ### Indicates whether to store information at the level of genes or probesets
probeset_seq_db = importSplicingAnnotationDatabaseAndSequence(species,array_type,biotype)
end_time = time.time(); time_diff = int(end_time-start_time)
print "Analyses finished in %d seconds" % time_diff
return probeset_seq_db
def getParametersAndExecute(probeset_seq_file, array_type, species, data_type):
if data_type == 'critical-exons':
if array_type == 'RNASeq':
probeset_annotations_file = 'AltDatabase/' + species + '/' + array_type + '/' + species + '_Ensembl_exons.txt'
else:
probeset_annotations_file = 'AltDatabase/' + species + '/' + array_type + '/' + species + '_Ensembl_' + array_type + '_probesets.txt'
###Import probe-level associations
exon_db = ExonSeqModule.importSplicingAnnotationDatabase(
probeset_annotations_file, array_type)
start_time = time.time()
probeset_seq_db = importProbesetSeqeunces(
probeset_seq_file, exon_db, species
) ###Do this locally with a function that works on tab-delimited as opposed to fasta sequences (exon array)
end_time = time.time()
time_diff = int(end_time - start_time)
elif data_type == 'junctions':
start_time = time.time()
biotype = 'gene' ### Indicates whether to store information at the level of genes or probesets
probeset_seq_db = importSplicingAnnotationDatabaseAndSequence(
species, array_type, biotype)
end_time = time.time()
time_diff = int(end_time - start_time)
print "Analyses finished in %d seconds" % time_diff
return probeset_seq_db
