def Indexing(counts, PSIFileDir, output):
""" Indexing is the process of creating strand machine readable binary for SashimiPlot """
gene_feature_db = reimportFeatures(
counts) ### import the exon and gene coordinates
PSIJunctions = importPSIJunctions(
PSIFileDir) ### Retreive all PSI junction pairs
PSIJunctions = importReciprocalJunctions(
PSIFileDir,
PSIJunctions) ### Include other Junctions from ASPIRE/LinRegress
exported = False
for (junction1, junction2) in PSIJunctions:
#if 'ENSMUSG00000066007:E5.1-ENSMUSG00000063245:E3.1' in PSIJunctions[event_pair]:
geneID = string.split(junction1, '__')[0]
if geneID in gene_feature_db:
try:
chr, junction_start, junction_end, strand, selected_event = exportToGff(
junction1, junction2, gene_feature_db[geneID], geneID)
exported = True
except Exception:
pass ### Not handling trans-splicing well
if exported:
### For each exon entry exported for this event, we need a gene entry with the boundary exon positions exported (returned from the above function)
try:
writegene(
chr, junction_start, junction_end, strand, selected_event
) #('chrX', '38600355', '38606652', '+', 'ENSMUSG00000000355__E1.2-E5.1')
except Exception:
pass
### Export coordinate information for the entire gene
for geneID in gene_feature_db:
feature_db = gene_feature_db[geneID]
for event in feature_db:
if 'E1.1-E100.1' in event:
pd = feature_db[event]
chr = pd.Chr()
start, stop = pd.Start(), pd.End()
if start > stop: strand = '-'
else: strand = '+'
try:
chr, junction_start, junction_end, strand, selected_event = exportToGff(
'null', event, gene_feature_db[geneID], geneID)
writegene(
chr, junction_start, junction_end, strand,
selected_event
) #('chrX', '38600355', '38606652', '+', 'ENSMUSG00000000355__E1.2-E5.1')
except Exception:
pass
time.sleep(2)
gff_export_obj.close()
newout = findParentDir(output) + 'sashimi_index/'
try:
ifg.index_gff(output, newout)
except Exception:
print traceback.format_exc()
sys.exit()
print('error in indexing')
def Indexing(counts,inputpsi,output):
gene_feature_db=reimportFeatures(counts)
PSIJunctions=importPSIJunctions(inputpsi)
PSIJunctions=importReciprocalJunctions(inputpsi,PSIJunctions)
for i in range(len(PSIJunctions)):
#if 'ENSMUSG00000066007:E5.1-ENSMUSG00000063245:E3.1' in PSIJunctions[i]:
event_split=string.split(PSIJunctions[i],"__")
gene = event_split[0]
if gene in gene_feature_db:
try: chrom,start_l,end_l,a,ch1=write_index(PSIJunctions[i],gene_feature_db[gene])
except Exception: pass ### Not handling trans-splicing well
for k in range(len(event_split)):
if "ENS" in event_split[k] or '00000' in event_split[k]:
if '-' in event_split[k]:
ji=string.split(event_split[k],'-')
geneID=ji[1]
else:
geneID=event_split[k]
if geneID != event_split[0]:
if geneID in gene_feature_db:
try: chrom,start_l,end_l,a,ch1= write_index(PSIJunctions[i],gene_feature_db[geneID])
except Exception: pass ### Not handling trans-splicing well
try: writegene(chrom,start_l,end_l,a,ch1) #('chrX', '38600355', '38606652', '+', 'ENSMUSG00000000355__E1.2-E5.1')
except Exception: pass
for gene in gene_feature_db:
for event in gene_feature_db[gene]:
if '100.1' in event:
event, position_data = string.split(event,'=')
chr, pos = string.split(position_data,'__')
start,stop = string.split(pos,'-')
if float(stop)>float(start): strand = '+'
else: strand = '-'
geneID = string.split(event,'__')[0] ### just use the gene ID
#chrom,start_l,end_l,a,ch1= write_index(event+' '+string.replace(event,'100','99'),gene_feature_db[geneID])
manualWriteExon(chr,start,stop,strand,geneID)
writegene(chr,start,stop,strand,geneID)
time.sleep(2)
export_in.close()
newout=findParentDir(output)+'sashimi_index/'
try: ifg.index_gff(output,newout)
except Exception:
print traceback.format_exc();sys.exit()
print('error in indexing')
def Indexing(counts,inputpsi,output):
head=0
index_read=indexdic(counts)
#print len(index_read)
#for k in range(len(a['AltAnalyze_ID'])):
gene_label=genelist(inputpsi)
for i in range(len(gene_label)):
#if 'ENSMUSG00000066007:E5.1-ENSMUSG00000063245:E3.1' in gene_label[i]:
try:
if head==0:
head=1
continue
p=string.split(gene_label[i],":")
#print gene_label[i]
if p[0] in index_read:
chrom,start_l,end_l,a,ch1=write_index(gene_label[i],index_read[p[0]])
for k in range(len(p)):
#print p[k]
if "ENS" in p[k]:
if '-' in p[k]:
ji=string.split(p[k],'-')
jj=ji[1]
else:
jj=p[k]
if jj != p[0]:
if jj in index_read:
chrom,start_l,end_l,a,ch1= write_index(gene_label[i],index_read[jj])
writegene(chrom,start_l,end_l,a,ch1)
except Exception:
continue
time.sleep(2)
export_in.close()
newout=findParentDir(output)+'trial_index/'
try:
ifg.index_gff(output,newout)
except Exception:
print('error in indexing')
def Indexing(counts, inputpsi, output):
head = 0
index_read = indexdic(counts)
#print len(index_read)
#for k in range(len(a['AltAnalyze_ID'])):
gene_label = genelist(inputpsi)
for i in range(len(gene_label)):
#if 'ENSMUSG00000066007:E5.1-ENSMUSG00000063245:E3.1' in gene_label[i]:
try:
if head == 0:
head = 1
continue
p = string.split(gene_label[i], ":")
#print gene_label[i]
if p[0] in index_read:
chrom, start_l, end_l, a, ch1 = write_index(
gene_label[i], index_read[p[0]])
for k in range(len(p)):
#print p[k]
if "ENS" in p[k]:
if '-' in p[k]:
ji = string.split(p[k], '-')
jj = ji[1]
else:
jj = p[k]
if jj != p[0]:
if jj in index_read:
chrom, start_l, end_l, a, ch1 = write_index(
gene_label[i], index_read[jj])
writegene(chrom, start_l, end_l, a, ch1)
except Exception:
continue
time.sleep(2)
export_in.close()
newout = findParentDir(output) + 'trial_index/'
try:
ifg.index_gff(output, newout)
except Exception:
print('error in indexing')
def Indexing(counts,PSIFileDir,output):
""" Indexing is the process of creating strand machine readable binary for SashimiPlot """
gene_feature_db=reimportFeatures(counts) ### import the exon and gene coordinates
PSIJunctions=importPSIJunctions(PSIFileDir) ### Retreive all PSI junction pairs
PSIJunctions=importReciprocalJunctions(PSIFileDir,PSIJunctions) ### Include other Junctions from ASPIRE/LinRegress
exported = False
for (junction1,junction2) in PSIJunctions:
#if 'ENSMUSG00000066007:E5.1-ENSMUSG00000063245:E3.1' in PSIJunctions[event_pair]:
geneID = string.split(junction1,'__')[0]
if geneID in gene_feature_db:
try:
chr,junction_start,junction_end,strand,selected_event=exportToGff(junction1,junction2,gene_feature_db[geneID],geneID)
exported=True
except Exception: pass ### Not handling trans-splicing well
if exported:
### For each exon entry exported for this event, we need a gene entry with the boundary exon positions exported (returned from the above function)
try: writegene(chr,junction_start,junction_end,strand,selected_event) #('chrX', '38600355', '38606652', '+', 'ENSMUSG00000000355__E1.2-E5.1')
except Exception: pass
### Export coordinate information for the entire gene
for geneID in gene_feature_db:
feature_db = gene_feature_db[geneID]
for event in feature_db:
if 'E1.1-E100.1' in event:
pd = feature_db[event]
chr = pd.Chr()
start,stop = pd.Start(), pd.End()
if start>stop: strand = '-'
else: strand = '+'
try:
chr,junction_start,junction_end,strand,selected_event=exportToGff('null',event,gene_feature_db[geneID],geneID)
writegene(chr,junction_start,junction_end,strand,selected_event) #('chrX', '38600355', '38606652', '+', 'ENSMUSG00000000355__E1.2-E5.1')
except Exception:
pass
time.sleep(2)
gff_export_obj.close()
newout=findParentDir(output)+'sashimi_index/'
try: ifg.index_gff(output,newout)
except Exception:
print traceback.format_exc();sys.exit()
print('error in indexing')