def Sashimiplottting(bamdir, countsin, inputpsi, genelis):
inputpsi = unique.filepath(inputpsi)
text_file = open(inputpsi, 'rU')
lines = text_file.readlines()
text_file.close()
samp = sample(inputpsi)
gene_label, gene_sym = genelist(inputpsi)
header = True
junction_max = []
countsin = unique.filepath(countsin)
for line in open(countsin, 'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data, '\t')
if header:
samples = t[1:]
header = False
exon_sum_array = [0] * len(samples)
count_sum_array = [0] * len(samples)
else:
values = map(float, t[1:])
count_sum_array = [
sum(value) for value in zip(*[count_sum_array, values])
]
for i in range(len(samp)):
sample_read[samp[i]] = count_sum_array[i]
#print samp[i],sample_read[samp[i]]
genelis = unique.filepath(genelis)
sashmi_plot_list(bamdir, genelis, gene_label, lines, samp, gene_sym)
def retreiveAllKnownSpliceSites():
### Uses a priori strand information when none present
import export, unique
chromosomes_found={}
parent_dir = export.findParentDir(bam_file)
species = None
for file in os.listdir(parent_dir):
if 'AltAnalyze_report' in file and '.log' in file:
log_file = unique.filepath(parent_dir+'/'+file)
log_contents = open(log_file, "rU")
species_tag = ' species: '
for line in log_contents:
line = line.rstrip()
if species_tag in line:
species = string.split(line,species_tag)[1]
if species == None:
species = IndicatedSpecies
splicesite_db={}
refExonCoordinateFile = unique.filepath('AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt')
firstLine=True
for line in open(refExonCoordinateFile,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t'); #'gene', 'exon-id', 'chromosome', 'strand', 'exon-region-start(s)', 'exon-region-stop(s)', 'constitutive_call', 'ens_exon_ids', 'splice_events', 'splice_junctions'
geneID, exon, chr, strand, start, stop = t[:6]
#start = int(start); stop = int(stop)
#geneID = string.split(exon,':')[0]
splicesite_db[chr,start]=strand
splicesite_db[chr,stop]=strand
if len(chr)<5 or ('GL0' not in chr and 'GL' not in chr and 'JH' not in chr and 'MG' not in chr):
chromosomes_found[string.replace(chr,'chr','')] = []
return splicesite_db,chromosomes_found
def Sashimiplottting(bamdir,countsin,PSIFilename,eventsToVisualizeFilename,events=None):
PSIFilename = unique.filepath(PSIFilename)
header=True
junction_max=[]
countsin = unique.filepath(countsin)
count_sum_array=[]
count=0
for line in open(countsin,'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data,'\t')
if header:
samples = []
for s in t[1:]:
if '.bed' not in s: s+='.bed'
samples.append(s)
header=False
count_sum_array=[0]*len(samples)
else:
values = map(float,t[1:])
count_sum_array = [sum(value) for value in zip(*[count_sum_array,values])]
count+=1
if count >30000 and 'salomonis' in bamdir: break
index=0
for sample in samples:
count_sum_array_db[sample] = count_sum_array[index]
index+=1
if events==None:
#print 'Preparing Sashimi-Input:',eventsToVisualizeFilename
eventsToVisualizeFilename = unique.filepath(eventsToVisualizeFilename)
gene_to_symbol=sashmi_plot_list(bamdir,eventsToVisualizeFilename,PSIFilename,events=events)
return gene_to_symbol
def retreiveAllKnownSpliceSites():
### Uses a priori strand information when none present
import export, unique
chromosomes_found={}
parent_dir = export.findParentDir(bam_file)
for file in os.listdir(parent_dir):
if 'AltAnalyze_report' in file and '.log' in file:
log_file = unique.filepath(parent_dir+'/'+file)
log_contents = open(log_file, "rU")
species_tag = ' species: '
for line in log_contents:
line = line.rstrip()
if species_tag in line:
species = string.split(line,species_tag)[1]
splicesite_db={}
refExonCoordinateFile = unique.filepath('AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt')
firstLine=True
for line in open(refExonCoordinateFile,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t'); #'gene', 'exon-id', 'chromosome', 'strand', 'exon-region-start(s)', 'exon-region-stop(s)', 'constitutive_call', 'ens_exon_ids', 'splice_events', 'splice_junctions'
geneID, exon, chr, strand, start, stop = t[:6]
#start = int(start); stop = int(stop)
#geneID = string.split(exon,':')[0]
splicesite_db[chr,start]=strand
splicesite_db[chr,stop]=strand
if len(chr)<5 or ('GL0' not in chr and 'GL' not in chr and 'JH' not in chr and 'MG' not in chr):
chromosomes_found[string.replace(chr,'chr','')] = []
return splicesite_db,chromosomes_found
def Sashimiplottting(bamdir,countsin,inputpsi,genelis):
inputpsi = unique.filepath(inputpsi)
text_file = open(inputpsi,'rU')
lines = text_file.readlines()
text_file.close()
samp=sample(inputpsi)
gene_label,gene_sym=genelist(inputpsi)
header=True
junction_max=[]
countsin = unique.filepath(countsin)
for line in open(countsin,'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data,'\t')
if header:
samples = t[1:]
header=False
exon_sum_array=[0]*len(samples)
count_sum_array=[0]*len(samples)
else:
values = map(float,t[1:])
count_sum_array = [sum(value) for value in zip(*[count_sum_array,values])]
for i in range(len(samp)):
sample_read[samp[i]]=count_sum_array[i]
#print samp[i],sample_read[samp[i]]
genelis = unique.filepath(genelis)
sashmi_plot_list(bamdir,genelis,gene_label,lines,samp,gene_sym)
def retreiveAllKnownSpliceSites(returnExonRetention=False,DesignatedSpecies=None,path=None):
### Uses a priori strand information when none present
import export, unique
chromosomes_found={}
try: parent_dir = export.findParentDir(bam_file)
except Exception: parent_dir = export.findParentDir(path)
species = None
for file in os.listdir(parent_dir):
if 'AltAnalyze_report' in file and '.log' in file:
log_file = unique.filepath(parent_dir+'/'+file)
log_contents = open(log_file, "rU")
species_tag = ' species: '
for line in log_contents:
line = line.rstrip()
if species_tag in line:
species = string.split(line,species_tag)[1]
if species == None:
try: species = IndicatedSpecies
except Exception: species = DesignatedSpecies
splicesite_db={}
gene_coord_db={}
try:
if ExonReference==None:
exon_dir = 'AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt'
length = verifyFileLength(exon_dir)
except Exception:
#print traceback.format_exc();sys.exit()
length = 0
if length==0:
exon_dir = ExonReference
refExonCoordinateFile = unique.filepath(exon_dir)
firstLine=True
for line in open(refExonCoordinateFile,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t'); #'gene', 'exon-id', 'chromosome', 'strand', 'exon-region-start(s)', 'exon-region-stop(s)', 'constitutive_call', 'ens_exon_ids', 'splice_events', 'splice_junctions'
geneID, exon, chr, strand, start, stop = t[:6]
spliceEvent = t[-2]
#start = int(start); stop = int(stop)
#geneID = string.split(exon,':')[0]
try:
gene_coord_db[geneID,chr].append(int(start))
gene_coord_db[geneID,chr].append(int(stop))
except Exception:
gene_coord_db[geneID,chr] = [int(start)]
gene_coord_db[geneID,chr].append(int(stop))
if returnExonRetention:
if 'exclusion' in spliceEvent or 'exclusion' in spliceEvent:
splicesite_db[geneID+':'+exon]=[]
else:
splicesite_db[chr,start]=strand
splicesite_db[chr,stop]=strand
if len(chr)<5 or ('GL0' not in chr and 'GL' not in chr and 'JH' not in chr and 'MG' not in chr):
chromosomes_found[string.replace(chr,'chr','')] = []
for i in gene_coord_db:
gene_coord_db[i].sort()
gene_coord_db[i] = [gene_coord_db[i][0],gene_coord_db[i][-1]]
return splicesite_db,chromosomes_found,gene_coord_db
def Sashimiplottting(bamdir,countsin,PSIFilename,eventsToVisualizeFilename,events=None):
PSIFilename = unique.filepath(PSIFilename)
header=True
junction_max=[]
countsin = unique.filepath(countsin)
count_sum_array=[]
count=0
for line in open(countsin,'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data,'\t')
if header:
samples = []
for s in t[1:]:
if '.bed' not in s: s+='.bed'
samples.append(s)
header=False
count_sum_array=[0]*len(samples)
else:
values = map(float,t[1:])
count_sum_array = [sum(value) for value in zip(*[count_sum_array,values])]
count+=1
if count >30000 and 'salomonis' in bamdir: break
index=0
for sample in samples:
count_sum_array_db[sample] = count_sum_array[index]
index+=1
if events==None:
#print 'Preparing Sashimi-Input:',eventsToVisualizeFilename
eventsToVisualizeFilename = unique.filepath(eventsToVisualizeFilename)
gene_to_symbol=sashmi_plot_list(bamdir,eventsToVisualizeFilename,PSIFilename,events=events)
return gene_to_symbol
def verifyFile(filename):
status = False
try:
fn=unique.filepath(filename)
for line in open(fn,'rU').xreadlines(): status = True;break
except Exception: status = False
return status
def importIsoformAnnotations(species,platform,psievents,annotType=None,junctionPairFeatures={},dataType='reciprocal'):
count=0
if annotType == 'domain':
if dataType == 'reciprocal':
fn = 'AltDatabase/'+species+'/'+platform+'/'+'probeset-domain-annotations-exoncomp.txt'
else:
fn = 'AltDatabase/'+species+'/'+platform+'/junction/'+'probeset-domain-annotations-exoncomp.txt'
else:
if dataType == 'reciprocal':
fn = 'AltDatabase/'+species+'/'+platform+'/'+'probeset-protein-annotations-exoncomp.txt'
else:
fn = 'AltDatabase/'+species+'/'+platform+'/junction/'+'probeset-protein-annotations-exoncomp.txt'
fn = unique.filepath(fn)
for line in open(fn,'rU'):
line = line.rstrip('\n')
values = string.split(line,'\t')
junctions = string.split(values[0],'|')
features = formatFeatures(values[1:])
antiFeatures = inverseFeatureDirections(features)
if tuple(junctions) in psievents:
try: junctionPairFeatures[tuple(junctions)].append(string.join(features,', '))
except Exception: junctionPairFeatures[tuple(junctions)] = [string.join(features,', ')]
if dataType == 'reciprocal':
junctions.reverse()
if tuple(junctions) in psievents:
try: junctionPairFeatures[tuple(junctions)].append(string.join(antiFeatures,', '))
except Exception: junctionPairFeatures[tuple(junctions)] = [string.join(antiFeatures,', ')]
count+=1
print count, 'protein predictions added'
return junctionPairFeatures
def importDatabaseEventAnnotations(species,platform):
terminal_exons={}
header=True
count=0
fn = 'AltDatabase/'+species+'/'+platform+'/'+species+'_Ensembl_exons.txt'
fn = unique.filepath(fn)
for line in open(fn,'rU'):
line = line.rstrip('\n')
values = string.split(line,'\t')
if header:
eI = values.index('splice_events')
header=False
continue
exon = values[0]
event = values[eI]
if 'alt-N-term' in event or 'altPromoter' in event:
if 'cassette' not in event:
terminal_exons[exon] = 'altPromoter'
count+=1
elif 'alt-C-term' in event:
if 'cassette' not in event:
terminal_exons[exon] = 'alt-C-term'
count+=1
"""
elif 'bleedingExon' in event or 'altFinish' in event:
terminal_exons[exon] = 'bleedingExon'
count+=1"""
print count, 'terminal exon annotations stored'
return terminal_exons
def indexdic(fname):
fname = unique.filepath(fname)
head=0
for line in open(fname,'rU').xreadlines():
#for k in range(len(a['AltAnalyze_ID'])):
if head ==0:
head=1
continue
else:
a=string.split(line,'\t')
#p=a['AltAnalyze_ID'][k]
p=a[0]
j=string.split(p,':')
#print j[0]
for i in range(len(j)):
if "ENS" in j[i]:
if '-' in j[i]:
ji=string.split(j[i],'-')
jj=ji[1]
else:
jj=j[i]
#print jj,'first check'
if jj in index_read:
index_read[jj].append(p)
else:
index_read[jj]=[p,]
return index_read
def importExpressionValues(filename):
""" Imports tab-delimited expression values"""
header = True
sample_expression_db = {}
fn = unique.filepath(filename)
for line in open(fn, "rU").xreadlines():
data = UI.cleanUpLine(line)
if header:
sample_names = string.split(data, "\t")
header = False
else:
exp_values = string.split(data, "\t")
gene = exp_values[0]
index = 1
for value in exp_values[1:]:
sample_name = sample_names[index]
if sample_name in sample_expression_db:
gene_expression_db = sample_expression_db[sample_name]
gene_expression_db[gene] = value
else:
gene_expression_db = {}
gene_expression_db[gene] = value
sample_expression_db[sample_name] = gene_expression_db
index += 1
return sample_expression_db
def extractFeatures(species,countinp):
import export
ExonsPresent=False
if 'counts.' in countinp:
feature_file = string.replace(countinp,'counts.','features.')
fe = export.ExportFile(feature_file)
firstLine = True
for line in open(countinp,'rU').xreadlines():
if firstLine: firstLine=False
else:
feature_info = string.split(line,'\t')[0]
fe.write(feature_info+'\n')
if ExonsPresent == False:
exon = string.split(feature_info,'=')[0]
if '-' not in exon:
ExonsPresent = True
### Add exon-info if necessary
if ExonsPresent == False:
exons_file = unique.filepath('AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt')
firstLine = True
for line in open(exons_file,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t')
gene = t[0]
exon = t[1]
chr = t[2]
strand = t[3]
start = t[4]
end = t[5]
fe.write(gene+':'+exon+'='+chr+':'+start+'-'+end+'\n')
fe.close()
return feature_file
def importPSIJunctions(fname):
fname = unique.filepath(fname)
header=True
for line in open(fname,'rU').xreadlines():
line = line.rstrip(os.linesep)
if header: header = False
else:
t=string.split(line,'\t')
try:
### Re-order these to have the exclusion be listed first
j1a,j1b = string.split(t[2],'-')
j2a,j2b = string.split(t[3],'-')
j1a = string.split(j1a,':')[1]
j2a = string.split(j2a,':')[1]
j1a = int(float(string.split(j1a,'.')[0][1:]))
j1b = int(float(string.split(j1b,'.')[0][1:]))
j2a = int(float(string.split(j2a,'.')[0][1:]))
j2b = int(float(string.split(j2b,'.')[0][1:]))
#print [j1a,j2a,j1b,j2b], t[2], t[3]
if j1a>j2a or j1b<j2b:
val = t[2]+' '+t[3]
else:
val=t[3]+' '+t[2]
except Exception:
#print traceback.format_exc();sys.exit()
val=t[2]+' '+t[3]
if '-' not in t[2]:
val = t[3]+' '+t[2]
val = string.replace(val,":","__")
lis.append(val)
#print t[0]
return lis
def importAgilentExpressionValues(filename,array,channel_to_extract):
""" Imports Agilent Feature Extraction files for one or more channels """
print '.',
red_expr_db={}
green_expr_db={}
parse=False
fn=unique.filepath(filename)
for line in open(fn,'rU').xreadlines():
data = UI.cleanUpLine(line)
if parse==False:
if 'ProbeName' in data:
headers = string.split(data,'\t')
pn = headers.index('ProbeName')
try: gc = headers.index('gProcessedSignal')
except Exception: pass
try: rc = headers.index('rProcessedSignal')
except Exception: pass
parse = True
else:
t = string.split(data,'\t')
probe_name = t[pn]
try: green_channel = math.log(float(t[gc])+1,2) #min is 0
except Exception: pass
try: red_channel = math.log(float(t[rc])+1,2) #min is 0
except Exception: pass
if 'red' in channel_to_extract:
red_expr_db[probe_name] = red_channel
if 'green' in channel_to_extract:
green_expr_db[probe_name] = green_channel
if 'red' in channel_to_extract:
red_channel_db[array] = red_expr_db
if 'green' in channel_to_extract:
green_channel_db[array] = green_expr_db
def genelist(fname):
fname = unique.filepath(fname)
header=True
for line in open(fname,'rU').xreadlines():
line = line.rstrip(os.linesep)
if header: header = False
else:
t=string.split(line,'\t')
try:
### Re-order these to have the exclusion be listed first
j1a,j1b = string.split(t[2],'-')
j2a,j2b = string.split(t[3],'-')
j1a = string.split(j1a,':')[1]
j2a = string.split(j2a,':')[1]
j1a = int(float(string.split(j1a,'.')[0][1:]))
j1b = int(float(string.split(j1b,'.')[0][1:]))
j2a = int(float(string.split(j2a,'.')[0][1:]))
j2b = int(float(string.split(j2b,'.')[0][1:]))
#print [j1a,j2a,j1b,j2b], t[2], t[3]
if j1a>j2a or j1b<j2b:
val = t[2]+' '+t[3]
else:
val=t[3]+' '+t[2]
except Exception:
#print traceback.format_exc();sys.exit()
val=t[2]+' '+t[3]
if '-' not in t[2]:
val = t[3]+' '+t[2]
val = string.replace(val,":","__")
lis.append(val)
#print t[0]
return lis
def importPSIJunctions(fname):
All_PSI_Reciprocol_Junctions=[]
fname = unique.filepath(fname)
header=True
for line in open(fname,'rU').xreadlines():
line = line.rstrip(os.linesep)
if header: header = False
else:
t=string.split(line,'\t')
junction1 = t[2]
junction2 = t[3]
try:
### Re-order these to have the exclusion be listed first
j1a,j1b = string.split(t[2],'-')
j2a,j2b = string.split(t[3],'-')
j1a = string.split(j1a,':')[1]
j2a = string.split(j2a,':')[1]
j1a = int(float(string.split(j1a,'.')[0][1:]))
j1b = int(float(string.split(j1b,'.')[0][1:]))
j2a = int(float(string.split(j2a,'.')[0][1:]))
j2b = int(float(string.split(j2b,'.')[0][1:]))
#print [j1a,j2a,j1b,j2b], t[2], t[3]
event1 = string.replace(junction2,":","__") ### first listed junction
event2 = string.replace(junction2,":","__") ### second listed junction
if j1a>j2a or j1b<j2b:
event_pair = event1,event2
else:
event_pair=event2,event1
except Exception:
#print traceback.format_exc();sys.exit()
event_pair=event1,event2
if '-' not in event1:
event_pair = event2,event1
All_PSI_Reciprocol_Junctions.append(event_pair)
return All_PSI_Reciprocol_Junctions
def importCircularRNAEvents(folder, circ_p):
dataset_events = {}
files = unique.read_directory(folder)
for file in files:
if 'circRNA.' in file and '.txt' in file:
events = []
dataset = file[:-4]
fn = unique.filepath(folder + '/' + file)
firstRow = True
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data, '\t')
if firstRow:
index = 0
""" Standard Fields from MultiPath-PSI """
for i in t:
if 'PValue' == i:
pv = index
if 'logFC' == i:
lf = index
index += 1
firstRow = False
else:
id = t[0]
pval = float(t[pv])
logFC = float(t[lf])
ci = circInformation(id, pval, logFC)
if pval < circ_p:
events.append(ci)
dataset_events[dataset] = events
return dataset_events
def reimportFeatures(featureFile):
""" Import the exon and gene coordinates """
gene_event_db = {}
featureFile = unique.filepath(featureFile)
head = 0
for line in open(featureFile, 'rU').xreadlines():
#for k in range(len(strand['AltAnalyze_ID'])):
if head == 0: head = 1
else:
line = line.rstrip('\n')
event = string.split(
line, '\t'
)[0] #example event: ENSMUSG00000025915:E17.2-E17.5=chr1:9885753-9886047
event = string.replace(event, ':', '__')
event_split = string.split(event, '__')
for i in range(len(event_split)):
if "ENS" in event_split[i] or '00000' in event_split[i]:
if '-' in event_split[i]:
ji = string.split(event_split[i], '-')
gene = ji[1]
else:
gene = event_split[i]
featureID, position = string.split(
event, '='
) ### store the feature (exon or junction) position and ID separately
pd = PositionData(position)
if gene in gene_event_db:
feature_db = gene_event_db[gene]
feature_db[featureID] = pd
else:
feature_db = {featureID: pd}
gene_event_db[gene] = feature_db
return gene_event_db
def importExpressionValues(filename):
""" Imports tab-delimited expression values"""
header = True
sample_expression_db={}
fn=unique.filepath(filename)
for line in open(fn,'rU').xreadlines():
data = UI.cleanUpLine(line)
if header:
sample_names = string.split(data,'\t')
header = False
else:
exp_values = string.split(data,'\t')
gene = exp_values[0]
index=1
for value in exp_values[1:]:
sample_name = sample_names[index]
if sample_name in sample_expression_db:
gene_expression_db = sample_expression_db[sample_name]
gene_expression_db[gene] = value
else:
gene_expression_db={}
gene_expression_db[gene] = value
sample_expression_db[sample_name] = gene_expression_db
index+=1
return sample_expression_db
def reimportFeatures(featureFile):
""" Import the exon and gene coordinates """
gene_event_db={}
featureFile = unique.filepath(featureFile)
head=0
for line in open(featureFile,'rU').xreadlines():
#for k in range(len(strand['AltAnalyze_ID'])):
if head ==0: head=1
else:
line = line.rstrip('\n')
event=string.split(line,'\t')[0] #example event: ENSMUSG00000025915:E17.2-E17.5=chr1:9885753-9886047
event = string.replace(event,':','__')
event_split=string.split(event,'__')
for i in range(len(event_split)):
if "ENS" in event_split[i] or '00000' in event_split[i]:
if '-' in event_split[i]:
ji=string.split(event_split[i],'-')
gene=ji[1]
else:
gene=event_split[i]
featureID,position = string.split(event,'=') ### store the feature (exon or junction) position and ID separately
pd = PositionData(position)
if gene in gene_event_db:
feature_db = gene_event_db[gene]
feature_db[featureID] = pd
else:
feature_db = {featureID:pd}
gene_event_db[gene]=feature_db
return gene_event_db
def genelist(fname):
fname = unique.filepath(fname)
for line in open(fname,'rU').xreadlines():
line = line.rstrip(os.linesep)
t=string.split(line,'\t')
val=t[2]+' '+t[3]
lis.append(val)
#print t[0]
return lis
def verifyFileLength(filename):
count = 0
try:
fn=unique.filepath(filename)
for line in open(fn,'rU').xreadlines():
count+=1
if count>9: break
except Exception: null=[]
return count
def extractFeatures(species,countsFileDir):
import export
ExonsPresent=False
lastgene = None
lastend = None
genes_detected={}
count=0
first_last_exons = {} ### Make strand fake junction comprised of the first and last exon
if 'counts.' in countsFileDir:
### The feature_file contains only ExonID or Gene IDs and associated coordinates
feature_file = string.replace(countsFileDir,'counts.','features.')
fe = export.ExportFile(feature_file)
firstLine = True
for line in open(countsFileDir,'rU').xreadlines():
if firstLine: firstLine=False
else:
feature_info = string.split(line,'\t')[0]
fe.write(feature_info+'\n')
junction_annotation = string.split(feature_info,'=')[0]
if '-' in junction_annotation:
geneid = string.split(junction_annotation,':')[0]
genes_detected[geneid]=[]
if ExonsPresent == False:
exon = string.split(feature_info,'=')[0]
if '-' not in exon:
ExonsPresent = True
### Add exon-info if necessary
exons_file = unique.filepath('AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt')
firstLine = True
for line in open(exons_file,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t')
gene,exon,chr,strand,start,end = t[:6]
if gene!=lastgene:
if len(genes_detected)==0 or gene in genes_detected: ### restrict to detected genes
first_last_exons[gene,strand] = [(chr,start)]
if len(genes_detected)==0 or lastgene in genes_detected: ### restrict to detected genes
try: first_last_exons[lastgene,laststrand].append(lastend)
except Exception:
pass ### occurs for the first gene
if ExonsPresent == False:
fe.write(gene+':'+exon+'='+chr+':'+start+'-'+end+'\n')
lastgene = gene; lastend = end; laststrand = strand
if len(genes_detected)==0 or lastgene in genes_detected:
first_last_exons[lastgene,laststrand].append(lastend)
### Add strand fake junction for the whole gene
for (gene,strand) in first_last_exons:
(chr,start),end = first_last_exons[gene,strand]
if strand == '-':
start,end = end,start # Need to encode strand in this annotation, do this by strand orienting the positions
fe.write(gene+':E1.1-E100.1'+'='+chr+':'+start+'-'+end+'\n')
fe.close()
return feature_file ### return the location of the exon and gene coordinates file
def filepath(filename):
try:
import unique ### local to AltAnalyze
fn = unique.filepath(filename)
except Exception:
### Should work fine when run as a script with this (AltAnalyze code is specific for packaging with AltAnalyze)
dir=os.path.dirname(dirfile.__file__)
try: dir_list = os.listdir(filename); fn = filename ### test to see if the path can be found (then it is the full path)
except Exception: fn=os.path.join(dir,filename)
return fn
def filepath(filename):
try:
import unique ### local to AltAnalyze
fn = unique.filepath(filename)
except Exception:
### Should work fine when run as a script with this (AltAnalyze code is specific for packaging with AltAnalyze)
dir=os.path.dirname(dirfile.__file__)
try: dir_list = os.listdir(filename); fn = filename ### test to see if the path can be found (then it is the full path)
except Exception: fn=os.path.join(dir,filename)
return fn
def extractFeatures(species,countinp):
import export
ExonsPresent=False
lastgene = None
lastend = None
genes_detected={}
count=0
first_last_exons = {} ### Make a fake junction comprised of the first and last exon
if 'counts.' in countinp:
feature_file = string.replace(countinp,'counts.','features.')
fe = export.ExportFile(feature_file)
firstLine = True
for line in open(countinp,'rU').xreadlines():
if firstLine: firstLine=False
else:
feature_info = string.split(line,'\t')[0]
fe.write(feature_info+'\n')
junction_annotation = string.split(feature_info,'=')[0]
if '-' in junction_annotation:
geneid = string.split(junction_annotation,':')[0]
genes_detected[geneid]=[]
if ExonsPresent == False:
exon = string.split(feature_info,'=')[0]
if '-' not in exon:
ExonsPresent = True
### Add exon-info if necessary
exons_file = unique.filepath('AltDatabase/ensembl/'+species+'/'+species+'_Ensembl_exon.txt')
firstLine = True
for line in open(exons_file,'rU').xreadlines():
if firstLine: firstLine=False
else:
line = line.rstrip('\n')
t = string.split(line,'\t')
gene,exon,chr,strand,start,end = t[:6]
if gene!=lastgene:
if len(genes_detected)==0 or gene in genes_detected: ### restrict to detected genes
first_last_exons[gene] = [(chr,start)]
if len(genes_detected)==0 or lastgene in genes_detected: ### restrict to detected genes
try: first_last_exons[lastgene].append(lastend)
except Exception:
pass ### occurs for the first gene
if ExonsPresent == False:
fe.write(gene+':'+exon+'='+chr+':'+start+'-'+end+'\n')
lastgene = gene; lastend = end
if len(genes_detected)==0 or lastgene in genes_detected:
first_last_exons[lastgene].append(lastend)
### Add a fake junction for the whole gene
for gene in first_last_exons:
(chr,start),end = first_last_exons[gene]
fe.write(gene+':E1.1-E100.1'+'='+chr+':'+start+'-'+end+'\n')
fe.close()
return feature_file
def importExonCoordinates(species):
""" Import exon block, intron block and gene coordinates """
firstRow = True
exon_coordinate_path = 'AltDatabase/ensembl/' + species + '/' + species + '_Ensembl_exon.txt'
fn = unique.filepath(exon_coordinate_path)
gene_coordinates = {}
gene_to_exons = {}
exon_block_coordinates = {}
gene_chr_strand = {}
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data, '\t')
if firstRow:
firstRow = False
else:
gene, exonid, chr, strand, exon_region_starts, exon_region_ends, constitutive_call, ens_exon_ids, splice_events, splice_junctions = t
exon_region_starts = map(int, string.split(exon_region_starts,
'|'))
exon_region_ends = map(int, string.split(exon_region_ends, '|'))
exon_block = gene + ':' + string.split(exonid, '.')[0]
gene_chr_strand[gene] = chr, strand
if gene in gene_to_exons:
gene_to_exons[gene].append(exon_block)
else:
gene_to_exons[gene] = [exon_block]
if gene in gene_coordinates:
gene_coordinates[gene] += exon_region_starts + exon_region_ends
else:
gene_coordinates[gene] = exon_region_starts + exon_region_ends
if exon_block in exon_block_coordinates:
exon_block_coordinates[
exon_block] += exon_region_starts + exon_region_ends
else:
exon_block_coordinates[
exon_block] = exon_region_starts + exon_region_ends
for gene in gene_coordinates:
gene_coordinates[gene].sort()
start = gene_coordinates[gene][0]
end = gene_coordinates[gene][-1]
chr, strand = gene_chr_strand[gene]
gene_coordinates[gene] = chr, strand, start, end
for exon in exon_block_coordinates:
exon_block_coordinates[exon].sort()
start = exon_block_coordinates[exon][0]
end = exon_block_coordinates[exon][-1]
chr, strand = gene_chr_strand[string.split(exon, ':')[0]]
exon_block_coordinates[exon] = chr, strand, start, end
print len(gene_coordinates), 'genes'
print len(exon_block_coordinates), 'exons/introns'
return gene_coordinates, exon_block_coordinates, gene_to_exons
def update_plot_settings(bamdir, group_psi_values, sample_headers):
### This functions writes out the sample orders, colors and sequence coverage for each BAM files for SashimiPlot
bams = []
sample_colors = []
sample_coverage = []
colors = [
"red",
"blue",
"green",
"grey",
"orange",
"purple",
"yellow",
"peach",
"pink",
"violet",
"magenta",
"navy",
]
colors = colors * 300
color_index = 0
for group in group_psi_values:
for index in group_psi_values[group]:
g = sample_headers[index].replace(".bed", ".bam")
bams.append('"' + g + '"')
sample_colors.append('"' + colors[color_index] + '"')
sample_coverage.append(str(int(sampleReadDepth[index])))
color_index += 1 ### reset for the new group
bams = string.join(bams, ",")
sample_colors = string.join(sample_colors, ",")
sample_coverage = string.join(sample_coverage, ",")
export_pl = open(unique.filepath("Config/sashimi_plot_settings.txt"), "w")
export_pl.write("[data]\n")
export_pl.write("bam_prefix = " + bamdir + "\n")
export_pl.write("bam_files =[" + bams + "]\n")
export_pl.write("\n")
export_pl.write("[plotting]")
export_pl.write("\n")
export_pl.write("fig_width = 7 \nfig_height = 7 \nintron_scale = 30 \nexon_scale = 4 \nlogged = False\n")
export_pl.write("font_size = 6 \nbar_posteriors = False \nnyticks = 4 \nnxticks = 4 \n")
export_pl.write("show_ylabel = False \nshow_xlabel = True \nshow_posteriors = False \nnumber_junctions = True \n")
export_pl.write("resolution = .5 \nposterior_bins = 40 \ngene_posterior_ratio = 5 \n")
export_pl.write("colors =[" + sample_colors + "]\n")
export_pl.write("coverages =[" + sample_coverage + "]\n")
export_pl.write('bar_color = "b" \nbf_thresholds = [0, 1, 2, 5, 10, 20]')
export_pl.close()
def searchDirectory(directory, var, secondary=None):
directory = unique.filepath(directory)
files = unique.read_directory(directory)
for file in files:
if var in file:
if secondary == None:
return directory + '/' + file
break
elif secondary in file:
return directory + '/' + file
break
### if all else fails
return directory + '/' + file
def sample(fname):
fname = unique.filepath(fname)
head=0
samplelis=[]
for line in open(fname,'rU').xreadlines():
line = cleanUpLine(line)
if head ==0:
t=string.split(line,'\t')
#print t
for p in range(11,len(t)):
samplelis.append(t[p])
head=1
else:
break;
return samplelis
def searchDirectory(directory,var,secondary=None):
directory = unique.filepath(directory)
files = unique.read_directory(directory)
for file in files:
if var in file:
if secondary== None:
return directory+'/'+file
break
elif secondary in file:
return directory+'/'+file
break
### if all else fails
return directory+'/'+file
def sample(fname):
fname = unique.filepath(fname)
head = 0
samplelis = []
for line in open(fname, 'rU').xreadlines():
line = cleanUpLine(line)
if head == 0:
t = string.split(line, '\t')
#print t
for p in range(11, len(t)):
samplelis.append(t[p])
head = 1
else:
break
return samplelis
def update_plot_settings(bamdir, group_psi_values, sample_headers):
### This functions writes out the sample orders, colors and sequence coverage for each BAM files for SashimiPlot
bams = []
sample_colors = []
sample_coverage = []
colors = [
'red', 'blue', 'green', 'grey', 'orange', 'purple', 'yellow', 'peach',
'pink', 'violet', 'magenta', 'navy'
]
colors = colors * 300
color_index = 0
for group in group_psi_values:
for index in group_psi_values[group]:
g = sample_headers[index].replace('.bed', '.bam')
bams.append('"' + g + '"')
sample_colors.append('"' + colors[color_index] + '"')
sample_coverage.append(str(int(sampleReadDepth[index])))
color_index += 1 ### reset for the new group
bams = string.join(bams, ',')
sample_colors = string.join(sample_colors, ',')
sample_coverage = string.join(sample_coverage, ',')
export_pl = open(unique.filepath('Config/sashimi_plot_settings.txt'), 'w')
export_pl.write('[data]\n')
export_pl.write('bam_prefix = ' + bamdir + '\n')
export_pl.write('bam_files =[' + bams + ']\n')
export_pl.write('\n')
export_pl.write('[plotting]')
export_pl.write('\n')
export_pl.write(
'fig_width = 7 \nfig_height = 7 \nintron_scale = 30 \nexon_scale = 4 \nlogged = False\n'
)
export_pl.write(
'font_size = 6 \nbar_posteriors = False \nnyticks = 4 \nnxticks = 4 \n'
)
export_pl.write(
'show_ylabel = False \nshow_xlabel = True \nshow_posteriors = False \nnumber_junctions = True \n'
)
export_pl.write(
'resolution = .5 \nposterior_bins = 40 \ngene_posterior_ratio = 5 \n')
export_pl.write('colors =[' + sample_colors + ']\n')
export_pl.write('coverages =[' + sample_coverage + ']\n')
export_pl.write('bar_color = "b" \nbf_thresholds = [0, 1, 2, 5, 10, 20]')
export_pl.close()
def genelist(fname):
fname = unique.filepath(fname)
lis = []
for line in open(fname, 'rU').xreadlines():
line = cleanUpLine(line)
t = string.split(line, '\t')
gene = string.split(t[2], ':')
val = t[2] + ' ' + t[3]
lis.append(val)
if gene[0] in gene_sym:
continue
else:
gene_sym[gene[0]] = t[0]
#print t[0]
return lis, gene_sym
def remoteSashimiPlot(species, fl, bamdir, genelis):
global inputpsi
global outputdir
try:
countinp = fl.CountsFile()
root_dir = fl.RootDir()
except Exception:
root_dir = fl
search_dir = root_dir + '/ExpressionInput'
files = unique.read_directory(search_dir)
for file in files:
if 'counts.' in file and 'steady-state.txt' not in file:
countinp = search_dir + '/' + file
inputpsi = root_dir + '/AltResults/AlternativeOutput/' + species + '_RNASeq_top_alt_junctions-PSI.txt'
#outputdir=findParentDir(inputpsi)+"sashimiplots"
outputdir = root_dir + '/ExonPlots'
outputdir = root_dir + '/SashimiPlots'
try:
os.mkdir(unique.filepath(outputdir))
except Exception:
pass
#print bamdir
#print countinp
#print inputpsi
#print genelis
Sashimiplottting(bamdir, countinp, inputpsi, genelis)
gene_label, gene_sym = genelist(inputpsi)
for filename in os.listdir(outputdir):
if '.pdf' in filename:
newname = string.split(filename, ':')
if newname[0] in gene_sym:
new_filename = str(filename)
if ':' in filename:
new_filename = string.split(filename, ':')[1]
elif '\\' in filename:
new_filename = string.split(filename, '\\')[1]
elif '/' in filename:
new_filename = string.split(filename, '/')[1]
nnname = gene_sym[newname[0]] + '-SashimiPlot_' + new_filename
os.rename(os.path.join(outputdir, filename),
os.path.join(outputdir, nnname))
else:
continue
def genelist(fname):
fname = unique.filepath(fname)
lis=[]
for line in open(fname,'rU').xreadlines():
line = cleanUpLine(line)
t=string.split(line,'\t')
gene=string.split(t[2],':')
val=t[2]+' '+t[3]
lis.append(val)
if gene[0] in gene_sym:
continue
else:
gene_sym[gene[0]]=t[0]
#print t[0]
return lis,gene_sym
def remoteSashimiPlot(species,fl,bamdir,genelis):
global inputpsi
global outputdir
try:
countinp = fl.CountsFile()
root_dir = fl.RootDir()
except Exception:
root_dir = fl
search_dir = root_dir+'/ExpressionInput'
files = unique.read_directory(search_dir)
for file in files:
if 'counts.' in file and 'steady-state.txt' not in file:
countinp = search_dir+'/'+file
inputpsi = root_dir+'/AltResults/AlternativeOutput/'+species+'_RNASeq_top_alt_junctions-PSI.txt'
#outputdir=findParentDir(inputpsi)+"sashimiplots"
outputdir = root_dir+'/ExonPlots'
outputdir = root_dir+'/SashimiPlots'
try: os.mkdir(unique.filepath(outputdir))
except Exception: pass
#print bamdir
#print countinp
#print inputpsi
#print genelis
Sashimiplottting(bamdir,countinp,inputpsi,genelis)
gene_label,gene_sym=genelist(inputpsi)
for filename in os.listdir(outputdir):
if '.pdf' in filename:
newname=string.split(filename,'__')
if newname[0] in gene_sym:
new_filename = str(filename)
if '__' in filename:
new_filename = string.split(filename,'__')[1]
elif '\\' in filename:
new_filename = string.split(filename,'\\')[1]
elif '/' in filename:
new_filename = string.split(filename,'/')[1]
nnname=gene_sym[newname[0]]+'-SashimiPlot_'+new_filename
os.rename(os.path.join(outputdir, filename), os.path.join(outputdir,nnname))
else:
continue
def importAgilentExpressionValues(filename, array, channel_to_extract):
""" Imports Agilent Feature Extraction files for one or more channels """
print '.',
red_expr_db = {}
green_expr_db = {}
parse = False
fn = unique.filepath(filename)
for line in open(fn, 'rU').xreadlines():
data = UI.cleanUpLine(line)
if parse == False:
if 'ProbeName' in data:
headers = string.split(data, '\t')
pn = headers.index('ProbeName')
try:
gc = headers.index('gProcessedSignal')
except Exception:
pass
try:
rc = headers.index('rProcessedSignal')
except Exception:
pass
parse = True
else:
t = string.split(data, '\t')
probe_name = t[pn]
try:
green_channel = math.log(float(t[gc]) + 1, 2) #min is 0
except Exception:
pass
try:
red_channel = math.log(float(t[rc]) + 1, 2) #min is 0
except Exception:
pass
if 'red' in channel_to_extract:
red_expr_db[probe_name] = red_channel
if 'green' in channel_to_extract:
green_expr_db[probe_name] = green_channel
if 'red' in channel_to_extract:
red_channel_db[array] = red_expr_db
if 'green' in channel_to_extract:
green_channel_db[array] = green_expr_db
def importSplicingEvents(folder):
dataset_events = {}
files = unique.read_directory(folder)
for file in files:
if 'PSI.' in file and '.txt' in file:
events = []
dataset = file[:-4]
fn = unique.filepath(folder + '/' + file)
firstRow = True
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data, '\t')
if firstRow:
index = 0
""" Standard Fields from MultiPath-PSI """
for i in t:
if 'Event-Direction' == i:
ed = index
if 'ClusterID' == i:
ci = index
if 'AltExons' == i:
ae = index
if 'EventAnnotation' == i:
ea = index
if 'Coordinates' == i:
co = index
index += 1
firstRow = False
else:
id = t[0]
event_direction = t[ed]
clusterID = t[ci]
altExons = t[ae]
coordinates = t[co]
ei = EventInformation(id, event_direction, clusterID,
altExons, coordinates)
events.append(ei)
dataset_events[dataset] = events
return dataset_events
def download(url,dir,file_type):
global suppress_printouts
try: suppress_printouts = Suppress_Printouts
except Exception: suppress_printouts = 'no'
try: dp = download_protocol(url,dir,file_type); output_filepath, status = dp.getStatus(); fp = output_filepath
except Exception:
try:
dir = unique.filepath(dir) ### Can result in the wrong filepath exported for AltDatabase RNA-Seq zip files (don't include by default)
dp = download_protocol(url,dir,file_type); output_filepath, status = dp.getStatus(); fp = output_filepath
except Exception:
output_filepath='failed'; status = "Internet connection not established. Re-establish and try again."
fp = filepath(dir+url.split('/')[-1]) ### Remove this empty object if saved
if 'Internet' not in status:
if '.zip' in fp or '.gz' in fp or '.tar' in fp:
#print "\nRemoving zip file:",fp
try: os.remove(fp); status = 'removed'
except Exception: null=[] ### Not sure why this error occurs since the file is not open
#print "\nRemoving zip file:",string.replace(fp,'.gz','')
if '.tar' in fp:
try: os.remove(string.replace(fp,'.gz',''))
except Exception: null=[]
return output_filepath, status
def eCLIPimport(folder):
eCLIP_dataset_peaks = {}
files = unique.read_directory(folder)
for file in files:
if '.bed' in file:
peaks = []
dataset = file[:-4]
fn = unique.filepath(folder + '/' + file)
for line in open(fn, 'rU').xreadlines():
data = cleanUpLine(line)
t = string.split(data, '\t')
chr = t[0]
start = int(t[1])
end = int(t[2])
strand = t[5]
annotation = t[6]
gene = string.split(t[8], '.')[0]
symbol = t[-2]
pi = PeakInformation(chr, start, end, strand, annotation, gene,
symbol)
peaks.append(pi)
eCLIP_dataset_peaks[dataset] = peaks
return eCLIP_dataset_peaks
def importPSIJunctions(fname):
All_PSI_Reciprocol_Junctions = []
fname = unique.filepath(fname)
header = True
for line in open(fname, 'rU').xreadlines():
line = line.rstrip(os.linesep)
if header: header = False
else:
t = string.split(line, '\t')
junction1 = t[2]
junction2 = t[3]
try:
### Re-order these to have the exclusion be listed first
j1a, j1b = string.split(t[2], '-')
j2a, j2b = string.split(t[3], '-')
j1a = string.split(j1a, ':')[1]
j2a = string.split(j2a, ':')[1]
j1a = int(float(string.split(j1a, '.')[0][1:]))
j1b = int(float(string.split(j1b, '.')[0][1:]))
j2a = int(float(string.split(j2a, '.')[0][1:]))
j2b = int(float(string.split(j2b, '.')[0][1:]))
#print [j1a,j2a,j1b,j2b], t[2], t[3]
event1 = string.replace(junction2, ":",
"__") ### first listed junction
event2 = string.replace(junction2, ":",
"__") ### second listed junction
if j1a > j2a or j1b < j2b:
event_pair = event1, event2
else:
event_pair = event2, event1
except Exception:
#print traceback.format_exc();sys.exit()
event_pair = event1, event2
if '-' not in event1:
event_pair = event2, event1
All_PSI_Reciprocol_Junctions.append(event_pair)
return All_PSI_Reciprocol_Junctions
def update_plot_settings(bamdir,group_psi_values,sample_headers):
### This functions writes out the sample orders, colors and sequence coverage for each BAM files for SashimiPlot
bams=[]
sample_colors=[]
sample_coverage=[]
colors = ['red','blue','green','grey','orange','purple','yellow','peach','pink','violet','magenta','navy']
colors = colors*300
color_index=0
for group in group_psi_values:
for index in group_psi_values[group]:
g=sample_headers[index].replace('.bed','.bam')
bams.append('"'+g+'"')
sample_colors.append('"'+colors[color_index]+'"')
sample_coverage.append(str(int(sampleReadDepth[index])))
color_index+=1 ### reset for the new group
bams = string.join(bams,',')
sample_colors = string.join(sample_colors,',')
sample_coverage = string.join(sample_coverage,',')
export_pl=open(unique.filepath('Config/sashimi_plot_settings.txt'),'w')
export_pl.write('[data]\n')
export_pl.write('bam_prefix = '+bamdir+'\n')
export_pl.write('bam_files =['+bams+']\n')
export_pl.write('\n')
export_pl.write('[plotting]')
export_pl.write('\n')
export_pl.write('fig_width = 7 \nfig_height = 7 \nintron_scale = 30 \nexon_scale = 4 \nlogged = False\n')
export_pl.write('font_size = 6 \nbar_posteriors = False \nnyticks = 4 \nnxticks = 4 \n')
export_pl.write('show_ylabel = False \nshow_xlabel = True \nshow_posteriors = False \nnumber_junctions = True \n')
export_pl.write('resolution = .5 \nposterior_bins = 40 \ngene_posterior_ratio = 5 \n')
export_pl.write('colors =['+sample_colors+']\n')
export_pl.write('coverages =['+sample_coverage+']\n')
export_pl.write('bar_color = "b" \nbf_thresholds = [0, 1, 2, 5, 10, 20]')
export_pl.close()
def reimportFeatures(featureFile):
gene_event_db={}
featureFile = unique.filepath(featureFile)
head=0
for line in open(featureFile,'rU').xreadlines():
#for k in range(len(a['AltAnalyze_ID'])):
if head ==0: head=1
else:
line = line.rstrip('\n')
event=string.split(line,'\t')[0] #example event: ENSMUSG00000025915:E17.2-E17.5=chr1:9885753-9886047
event = string.replace(event,':','__')
event_split=string.split(event,'__')
for i in range(len(event_split)):
if "ENS" in event_split[i] or '00000' in event_split[i]:
if '-' in event_split[i]:
ji=string.split(event_split[i],'-')
gene=ji[1]
else:
gene=event_split[i]
if gene in gene_event_db:
gene_event_db[gene].append(event)
else:
gene_event_db[gene]=[event]
return gene_event_db
max_len: define the upper limitation for the length of command string. A
command string will be passed to R by a temporary file if it is longer
than this value.
use_numpy: Used as a boolean value. A False value will disable numpy even
if it has been imported.
use_dict: named list will be returned a dict if use_dict is True, otherwise
it will be a list of tuples (name, value).
host: The computer name (or IP) on which the R interpreter is
installed. The value "localhost" means that the R locates on the
the localhost computer. On POSIX systems (including Cygwin
environment on Windows), it is possible to use R on a remote
computer if the command "ssh" works. To do that, the user need set
this value, and perhaps the parameter "user".
user: The user name on the remote computer. This value need to be set
only if the user name is different on the remote computer. In
interactive environment, the password can be input by the user if
prompted. If running in a program, the user need to be able to
login without typing password!
ssh: The program to login to remote computer.
'''
if isinstance(Robj, basestring):
Robj = R(RCMD=Robj, max_len=max_len, use_numpy=use_numpy, use_dict=use_dict, host=host, user=user, ssh=ssh)
rlt = Robj.run(CMDS=CMDS)
if len(rlt) == 1: rlt = rlt[0]
return rlt
if __name__ == '__main__':
import unique
path = unique.filepath("AltDatabase/R/Contents/MacOS/R")
r = R(RCMD='R',use_numpy=True)
def remoteGene(gene,Species,root_dir,comparison_file):
global Transcript_Annotations_File
global ExonRegion_File
global Selected_Gene
global Prt_Trans_File
global Prt_Regions_File
global Prt_Boundaries_File
global SplicingIndex_File
global UniPrt_Regions_File
global microRNA_File
global domainAnnotation_db
global platform
global species
Selected_Gene = str(gene)
species = Species
comparison_name = string.split(export.findFilename(comparison_file),'.')[0]
ExonRegion_File = unique.filepath("AltDatabase/ensembl/"+species+"/"+species+"_Ensembl_exon.txt")
Transcript_Annotations_File = unique.filepath("AltDatabase/ensembl/"+species+"/"+species+"_Ensembl_transcript-annotations.txt")
Prt_Trans_File = searchDirectory("AltDatabase/ensembl/"+species+"/",'Ensembl_Protein')
Prt_Regions_File = searchDirectory("AltDatabase/ensembl/"+species+"/",'ProteinFeatures')
Prt_Boundaries_File = searchDirectory("AltDatabase/ensembl/"+species+"/",'ProteinCoordinates')
UniPrt_Regions_File = searchDirectory("AltDatabase/uniprot/"+species+"/",'FeatureCoordinate')
SplicingIndex_File = searchDirectory(root_dir+'/AltResults/ProcessedSpliceData/','splicing-index',secondary=comparison_name)
platform = getPlatform(SplicingIndex_File)
microRNA_File = searchDirectory("AltDatabase/"+species+"/"+platform,'microRNAs_multiple')
#print(SplicingIndex_File)
total_val = ProteinCentricIsoformView(Selected_Gene)
junctions = total_val[0]
p_boundaries = total_val[1]
p_domains = total_val[2]
transcript_db = total_val[3]
exon_db = total_val[4]
splice_db = total_val[5]
microRNA_db = total_val[6]
domainAnnotation_db = total_val[7]
#for i in exon_db:
# print("THE", i, exon_db[i], "\n")
#for i in microRNA_db:
# m_test = microRNA_db[i]
# print(len(m_test))
# for q in m_test:
# print("microRNA", q.ExonBlock(), q.Description(), q.BP(), "\n")
#for i in exon_db["ENST00000349238"]:
# print(i[2].EnsemblRegion())
domain_color_list = []
for i in p_domains:
ploy = p_domains[i]
for a in ploy:
domain_color_list.append(a[1])
domain_color_list = list(set(domain_color_list))
domain_color_key = {}
c_color1 = [0.8, 0.6, 0.1]
c_color2 = [0.1, 0.6, 0.8]
c_color3 = [0.6, 0.1, 0.8]
c_color4 = [0.95, 0.6, 0.3]
c_color5 = [0.3, 0.6, 0.95]
c_color6 = [0.6, 0.3, 0.95]
FLAG = 1
for item in domain_color_list:
if(FLAG == 1):
domain_color_key[item] = c_color1
FLAG = FLAG + 1
continue
if(FLAG == 2):
domain_color_key[item] = c_color2
FLAG = FLAG + 1
continue
if(FLAG == 3):
domain_color_key[item] = c_color3
FLAG = FLAG + 1
continue
if(FLAG == 4):
domain_color_key[item] = c_color4
FLAG = FLAG + 1
continue
if(FLAG == 5):
domain_color_key[item] = c_color5
FLAG = FLAG + 1
continue
if(FLAG == 6):
domain_color_key[item] = c_color6
FLAG = 1
continue
#for i in domain_color_key:
#print(i, domain_color_key[i], "\n")
Y = 100
Transcript_to_Y = {}
for transcript in transcript_db:
Transcript_to_Y[transcript] = Y
Y = Y + 300
import traceback
def onpick(event):
#ind = event.ind
print(event.artist.get_label())
#for i in domainAnnotation_db: print(i,len(domainAnnotation_db));break
fig = pylab.figure()
ylim = Y + 200
currentAxis = pylab.gca()
#ax = pylab.axes()
ax = fig.add_subplot(111)
X_Pos_List = []
CoordsBank = []
for transcript in transcript_db:
try:
Junc_List = junctions[transcript]
y_pos = Transcript_to_Y[transcript]
Gene_List = exon_db[transcript]
color_flag = 1
for entry in Gene_List:
G_start = entry[0][0]
G_end = entry[0][1]
Exon_Object = entry[2]
try:
LabelClass = splice_db[Exon_Object.EnsemblRegion()]
ExonName = Exon_Object.EnsemblExon()
RegCall = LabelClass.RegCall()
SplicingIndex = LabelClass.SplicingIndex()
PVal = LabelClass.PVal()
Midas = LabelClass.Midas()
Label = "\n" + "Exon: " + str(ExonName) + "\n" + "RegCall: " + str(RegCall) + "\n" + "Splicing Index: " + str(SplicingIndex) + "\n" + "P-Value: " + str(PVal) + "\n" + "Midas Value: " + str(Midas) + "\n"
Label = string.replace(Label,"\n"," ")
if(RegCall == "UC"):
color_choice = "Grey"
else:
S_Int = float(SplicingIndex)
if(S_Int > 0):
#color_choice = (0.7, 0.7, 0.99)
color_choice = 'blue'
if(S_Int < 0):
#color_choice = (0.8, 0.4, 0.4)
color_choice = 'red'
except:
#print(traceback.format_exc());sys.exit()
Label = ""
color_choice = "Grey"
#print("Start", G_start, "end", G_end, "Region", entry[2].EnsemblRegion())
if((color_flag % 2) == 0):
currentAxis.add_patch(Rectangle((G_start, y_pos), (G_end - G_start), 50, color = color_choice, label = (entry[2].EnsemblRegion() + Label), picker = True))
y_end = y_pos + 50
try: CoordsBank.append((G_start, G_end, y_pos, y_end, 'Exon: '+entry[2].EnsemblRegion()+' '+ 'SI: '+str(SplicingIndex)[:4]+' Pval: '+str(Midas)[:4]))
except Exception:
CoordsBank.append((G_start, G_end, y_pos, y_end, 'Exon: '+entry[2].EnsemblRegion()))
#print(entry[2].EnsemblRegion(),y_pos,y_end)
if((color_flag % 2) != 0):
currentAxis.add_patch(Rectangle((G_start, y_pos), (G_end - G_start), 50, color = color_choice, label = (entry[2].EnsemblRegion() + Label), picker = True))
y_end = y_pos + 50
try: CoordsBank.append((G_start, G_end, y_pos, y_end, 'Exon: '+entry[2].EnsemblRegion()+' '+ 'SI: '+str(SplicingIndex)[:4]+' p-value: '+str(Midas)[:4]))
except Exception:
CoordsBank.append((G_start, G_end, y_pos, y_end, 'Exon: '+entry[2].EnsemblRegion()))
#print(entry[2].EnsemblRegion(),y_pos,y_end)
color_flag = color_flag + 1
if(entry[2].EnsemblRegion() in microRNA_db):
microRNA_object = microRNA_db[entry[2].EnsemblRegion()]
mr_label = "MICRORNA MATCHES" + "\n"
for class_object in microRNA_object:
mr_exonname = class_object.ExonBlock()
mr_desc = class_object.Description() + " " + class_object.Algorithms()
#print(mr_desc)
mr_label = mr_label + mr_desc + "\n"
currentAxis.add_patch(Rectangle((G_start, (y_pos - 75)), (G_end - G_start), 40, color = "Green", label = (mr_label), picker = True))
y_start = y_pos - 75
y_end = y_pos - 35
CoordsBank.append((G_start, G_end, y_start, y_end, mr_desc))
for entry in Junc_List:
junctionID = entry[-1]
try:
LabelClass = splice_db[entry[2]]
RegCall = LabelClass.RegCall()
SplicingIndex = LabelClass.SplicingIndex()
PVal = LabelClass.PVal()
Midas = LabelClass.Midas()
Label = "\n" + "RegCall: " + str(RegCall) + "\n" + "Splicing Index: " + str(SplicingIndex) + "\n" + "P-Value: " + str(PVal) + "\n" + "Midas Value: " + str(Midas) + "\n"
if(float(SplicingIndex) > 0):
color_junc = "blue"
if(float(SplicingIndex) < 0):
color_junc = "red"
if(RegCall == "UC"):
color_junc = "grey"
except:
Label = ""
color_junc = "grey"
currentAxis.add_patch(Rectangle((entry[0], y_pos), (entry[1] - entry[0]), 50, color = "White", label = (str(entry[2]) + Label), picker = True))
ax.arrow(entry[0], (y_pos+50), 8, 40, label = (str(entry[2]) + Label), color = color_junc, picker = True)
ax.arrow((entry[0] + 8), (y_pos+90), 11, -40, label = (str(entry[2]) + Label), color = color_junc, picker = True)
y_start = y_pos
y_end = y_pos + 30
#print(junctionID,y_start,y_end)
CoordsBank.append((G_start, G_end, y_start, y_end, junctionID))
try:
P_Bound_List = p_boundaries[transcript]
E_Start = P_Bound_List[-2]
E_End = P_Bound_List[-1]
P_Start = P_Bound_List[1]
P_End = P_Bound_List[2]
#print("Boundaries: ", P_Start, P_End)
X_Pos_List.append(int(E_End))
#currentAxis.add_patch(Rectangle((E_Start, y_pos), E_End, 50, color = "Blue"))
try:
currentAxis.add_patch(Rectangle((P_Start, (y_pos + 120)), (P_End - P_Start), 10))
except:
pass
p_label_list = ["DEF"]
#CoordsBank.append((P_Start, P_End, y_pos, P_End - P_Start, transcript)) ### Added by NS - needs work
try: P_Domain_List = p_domains[transcript]
except Exception: P_Domain_List=[]
for entry in P_Domain_List:
#print("Domain", entry)
color_domain_choice = domain_color_key[entry[1]]
domain_annotation = domainAnnotation_db[entry[1]]
#domain_annotation = string.replace(domain_annotation,'REGION-','')
p_label = (str(entry[0]) + " " + str(domain_annotation))
#print(entry[0], entry[2], entry[3], P_Start, P_End, domain_annotation, )
Repeat_Flag = 0
for i in p_label_list:
if(p_label == i):
Repeat_Flag = 1
if(Repeat_Flag == 1):
continue
p_label_list.append(p_label)
currentAxis.add_patch(Rectangle((entry[2], y_pos + 100), (entry[3] - entry[2]), 50, color = color_domain_choice, label= p_label, picker = True))
y_start = y_pos + 100
y_end = y_pos + 150
CoordsBank.append((entry[2], entry[3], y_start, y_end, p_label))
except Exception:
pass
#print(traceback.format_exc())
except:
#print(traceback.format_exc())
pass
pylab.ylim([0.0, ylim])
try:
max_x = max(X_Pos_List)
except:
max_x = 5000
try:
pylab.xlim([0.0, max_x])
except:
pylab.xlim([0.0, 3000])
fig.canvas.mpl_connect('pick_event', onpick)
def format_coord(x, y):
for m in CoordsBank:
if(x >= m[0] and x <= m[1] and y >= m[2] and y <= m[3]):
string_display = m[4]
return string_display
string_display = " "
return string_display
ax.format_coord = format_coord
#datacursor(hover=True, formatter='{label}'.format, bbox=dict(fc='yellow', alpha=1), arrowprops=None)
pylab.show()
def remoteSashimiPlot(Species, fl, bamdir, eventsToVisualizeFilename, events=None, show=False):
global PSIFilename
global outputdir
global root_dir
global steady_state_exp_file
global species
species = Species
try:
countinp = fl.CountsFile()
root_dir = fl.RootDir()
except Exception:
root_dir = fl
search_dir = root_dir + "/ExpressionInput"
files = unique.read_directory(search_dir)
for file in files:
if "counts." in file and "steady-state.txt" not in file:
countinp = search_dir + "/" + file
PSIFilename = root_dir + "/AltResults/AlternativeOutput/" + species + "_RNASeq_top_alt_junctions-PSI.txt"
import ExpressionBuilder
dir_list = unique.read_directory(root_dir + "/ExpressionInput")
for file in dir_list:
if "exp." in file and "steady-state" not in file:
exp_file = root_dir + "/ExpressionInput/" + file
elif "exp." in file and "steady-state" in file:
steady_state_exp_file = root_dir + "/ExpressionInput/" + file
global sample_group_db
sample_group_db = ExpressionBuilder.simplerGroupImport(exp_file)
# outputdir=findParentDir(PSIFilename)+"sashimiplots"
outputdir = root_dir + "/ExonPlots"
outputdir = root_dir + "/SashimiPlots"
try:
os.mkdir(unique.filepath(outputdir))
except Exception:
pass
if show:
s = open(outputdir + "/show.txt", "w")
s.write("TRUE")
s.close()
else:
s = open(outputdir + "/show.txt", "w")
s.write("FALSE")
s.close()
geneSymbol_db = Sashimiplottting(bamdir, countinp, PSIFilename, eventsToVisualizeFilename, events=events)
for filename in os.listdir(outputdir):
if ".pdf" in filename or ".png" in filename:
fn = string.replace(filename, ".pdf", "")
fn = string.replace(fn, ".png", "")
newname = string.split(fn, "__")
if newname[0] in geneSymbol_db:
new_filename = str(filename)
if "__" in filename:
new_filename = string.split(filename, "__")[1]
elif "\\" in filename:
new_filename = string.split(filename, "\\")[1]
elif "/" in filename:
new_filename = string.split(filename, "/")[1]
nnname = geneSymbol_db[newname[0]][0] + "-SashimiPlot_" + new_filename
try:
os.rename(os.path.join(outputdir, filename), os.path.join(outputdir, nnname))
except Exception:
if "already exists" in traceback.format_exc():
### File already exists, delete the new one
try:
os.remove(os.path.join(outputdir, nnname))
except Exception:
pass
### Now right the new one
try:
os.rename(os.path.join(outputdir, filename), os.path.join(outputdir, nnname))
except Exception:
pass
pass
else:
continue
print ""
def remoteGene(gene):
global Transcript_Annotations_File
global ExonRegion_File
global Selected_Gene
global Prt_Trans_File
global Prt_Regions_File
global Prt_Boundaries_File
global Etc_File
import unique
Selected_Gene = gene
ExonRegion_File = unique.filepath("ExonViewFiles/Hs_Ensembl_exon.txt")
Transcript_Annotations_File = unique.filepath("ExonViewFiles/Hs_Ensembl_transcript-annotations.txt")
Prt_Trans_File = unique.filepath("ExonViewFiles/Hs_Ensembl_Protein__65_37.txt")
Prt_Regions_File = unique.filepath("ExonViewFiles/Hs_ProteinFeatures_build_65_37.txt")
Prt_Boundaries_File = unique.filepath("ExonViewFiles/Hs_ProteinCoordinates_build_65_37.tab")
Etc_File = unique.filepath("ExonViewFiles/Hs_RNASeq_K562_SRSF2_P95mut_vs_K562_SRSF2_WT.ExpCutoff-5.0_average-splicing-index-ProcessedSpliceData.txt")
#"ENSG00000005801"
#"ENSG00000110514"
total_val = ProteinCentricIsoformView(Selected_Gene)
junctions = total_val[0]
p_boundaries = total_val[1]
p_domains = total_val[2]
transcript_db = total_val[3]
exon_db = total_val[4]
splice_db = total_val[5]
#for i in exon_db["ENST00000349238"]:
# print(i[2].EnsemblRegion())
domain_color_list = []
for i in p_domains:
ploy = p_domains[i]
for a in ploy:
domain_color_list.append(a[1])
domain_color_list = list(set(domain_color_list))
domain_color_key = {}
c_color1 = [0.8, 0.6, 0.1]
c_color2 = [0.1, 0.6, 0.8]
c_color3 = [0.6, 0.1, 0.8]
c_color4 = [0.95, 0.6, 0.3]
c_color5 = [0.3, 0.6, 0.95]
c_color6 = [0.6, 0.3, 0.95]
FLAG = 1
for item in domain_color_list:
if(FLAG == 1):
domain_color_key[item] = c_color1
FLAG = FLAG + 1
continue
if(FLAG == 2):
domain_color_key[item] = c_color2
FLAG = FLAG + 1
continue
if(FLAG == 3):
domain_color_key[item] = c_color3
FLAG = FLAG + 1
continue
if(FLAG == 4):
domain_color_key[item] = c_color4
FLAG = FLAG + 1
continue
if(FLAG == 5):
domain_color_key[item] = c_color5
FLAG = FLAG + 1
continue
if(FLAG == 6):
domain_color_key[item] = c_color6
FLAG = 1
continue
for i in domain_color_key:
print(i, domain_color_key[i], "\n")
Y = 50
Transcript_to_Y = {}
for transcript in transcript_db:
Transcript_to_Y[transcript] = Y
Y = Y + 200
import traceback
ylim = Y + 200
currentAxis = plt.gca()
ax = plt.axes()
X_Pos_List = []
for transcript in transcript_db:
try:
Junc_List = junctions[transcript]
y_pos = Transcript_to_Y[transcript]
Gene_List = exon_db[transcript]
color_flag = 1
for entry in Gene_List:
G_start = entry[0][0]
G_end = entry[0][1]
Exon_Object = entry[2]
try:
LabelClass = splice_db[Exon_Object.EnsemblRegion()]
ExonName = Exon_Object.EnsemblExon()
RegCall = LabelClass.RegCall()
SplicingIndex = LabelClass.SplicingIndex()
PVal = LabelClass.PVal()
Midas = LabelClass.Midas()
Label = "\n" + "Exon: " + str(ExonName) + "\n" + "RegCall: " + str(RegCall) + "\n" + "Splicing Index: " + str(SplicingIndex) + "\n" + "P-Value: " + str(PVal) + "\n" + "Midas Value: " + str(Midas)
if(RegCall == "UC"):
color_choice = "Grey"
else:
S_Int = float(SplicingIndex)
if(S_Int > 0):
color_choice = (0.7, 0.7, 0.99)
if(S_Int < 0):
color_choice = (0.8, 0.4, 0.4)
except:
#print(traceback.format_exc());sys.exit()
Label = ""
color_choice = "Grey"
#print("Start", G_start, "end", G_end, "Region", entry[2].EnsemblRegion())
if((color_flag % 2) == 0):
currentAxis.add_patch(Rectangle((G_start, y_pos), (G_end - G_start), 50, color = color_choice, label = (entry[2].EnsemblRegion() + Label)))
if((color_flag % 2) != 0):
currentAxis.add_patch(Rectangle((G_start, y_pos), (G_end - G_start), 50, color = color_choice, label = (entry[2].EnsemblRegion() + Label)))
color_flag = color_flag + 1
for entry in Junc_List:
try:
LabelClass = splice_db[entry[2]]
RegCall = LabelClass.RegCall()
SplicingIndex = LabelClass.SplicingIndex()
PVal = LabelClass.PVal()
Midas = LabelClass.Midas()
Label = "\n" + "RegCall: " + str(RegCall) + "\n" + "Splicing Index: " + str(SplicingIndex) + "\n" + "P-Value: " + str(PVal) + "\n" + "Midas Value: " + str(Midas)
if(float(SplicingIndex) > 0):
color_junc = "blue"
if(float(SplicingIndex) < 0):
color_junc = "red"
if(RegCall == "UC"):
color_junc = "grey"
except:
Label = ""
color_junc = "grey"
currentAxis.add_patch(Rectangle((entry[0], y_pos), (entry[1] - entry[0]), 50, color = "White", label = (str(entry[2]) + Label)))
ax.arrow(entry[0], (y_pos+50), 8, 40, label = (str(entry[2]) + Label), color = color_junc)
ax.arrow((entry[0] + 8), (y_pos+90), 11, -40, label = (str(entry[2]) + Label), color = color_junc)
P_Bound_List = p_boundaries[transcript]
P_Domain_List = p_domains[transcript]
E_Start = P_Bound_List[-2]
E_End = P_Bound_List[-1]
P_Start = P_Bound_List[1]
P_End = P_Bound_List[2]
#print("Boundaries: ", P_Start, P_End)
X_Pos_List.append(int(E_End))
#currentAxis.add_patch(Rectangle((E_Start, y_pos), E_End, 50, color = "Blue"))
try:
currentAxis.add_patch(Rectangle((P_Start, (y_pos + 120)), (P_End - P_Start), 10, label = ("Protein: " + str(P_Bound_List[0]))))
except:
pass
for entry in P_Domain_List:
#print("Domain", entry)
color_domain_choice = domain_color_key[entry[1]]
currentAxis.add_patch(Rectangle((entry[2], y_pos + 100), (entry[3] - entry[2]), 50, color = color_domain_choice, label= ("Protein: " + str(entry[0]) + "\n" + "Domain: " + str(entry[1]))))
except:
continue
plt.ylim([0.0, ylim])
try:
max_x = max(X_Pos_List)
except:
max_x = 5000
try:
plt.xlim([0.0, max_x])
except:
plt.xlim([0.0, 3000])
datacursor(hover=True, formatter='{label}'.format, bbox=dict(fc='yellow', alpha=1), arrowprops=None)
plt.show()
def sashmi_plot_list(bamdir,fname,gene_label,lines,samp,gene_sym):
splicing_events=[]
type = None
firstLine = True
for line in open(fname,'rU').xreadlines():
line = cleanUpLine(line)
t = string.split(line,'\t')
if firstLine:
if 'junctionID-1' in t:
j1i = t.index('junctionID-1')
j2i = t.index('junctionID-2')
type='ASPIRE'
if 'ANOVA' in t:
type='PSI'
elif 'independent confirmation' in t:
type='confirmed'
elif 'ANOVA' in fname:
type = 'ANOVA'
firstLine=False
if ' ' in t[0] and ':' in t[0]:
splicing_events.append(t[0])
elif type=='ASPIRE':
splicing_events.append(t[j1i] +' '+ t[j2i])
elif type=='ANOVA':
try:
a,b = string.split(t[0],'|')
a = string.split(a,':')
a = string.join(a[1:],':')
splicing_events.append(a +' '+ b)
except Exception: pass
elif type=='PSI':
try:
j1,j2 = string.split(t[0],'|')
a,b,c = string.split(j1,':')
j1 = b+':'+c
splicing_events.append(j1 +' '+ j2)
except Exception:
#print traceback.format_exc();sys.exit()
pass
elif type=='confirmed':
try:
event_pair1 = string.split(t[1],'|')[0]
a,b,c,d = string.split(event_pair1,'-')
splicing_events.append(a+'-'+b +' '+ c+'-'+d)
except Exception: pass
if len(splicing_events)==0:
forceNoCompatibleEventsInFile
print 'Exporting plots',
for li in splicing_events:
if ":U" in li or "-U" in li:
continue
else:
li=cleanUpLine(li)
#print li
#dem[0]=['ENSG00000132424:I10.1 ENSG00000132424:E10.1-E11.1','ENSG00000146147:E10.3-E11.1 ENSG00000146147:E9.3-E15.1']
de=string.split(li,'\t')
dem[0]=de
#print dem[0]
for key in dem:
for i in range(len(dem[key])):
list1=[]
list2=[]
try:
k=gene_label.index(dem[key][i])
flag=1
lt=cleanUpLine(lines[k])
t=string.split(lt,'\t')
#print t
t=t[11:]
#print t
#list3=[]
#ind=[]
for x in range(len(t)):
#print x,t[x]
if(t[x]!=''):
if float(t[x]) < 0.8:
list1.append(x)
#print x
#print 'list1:'+str(x)
else:
list2.append(x)
#print x
# print str(x)
else:
continue
if len(list1)>5:
list1=list1[1:5]
if len(list2)>5:
list2=list2[1:5]
#print len(list1),len(list2)
except Exception:
for ij in range(len(samp)):
list1.append(ij)
update_plot_settings(bamdir,list1,list2,samp)
a=string.split(dem[key][i]," ")
if '-' in a[1]:
ch1=a[1]
f=string.split(a[0],':')
else:
ch1=a[0]
f=string.split(a[1],':')
event=findParentDir(inputpsi)
event=event+"trial_index/"
setting =unique.filepath("Config/sashimi_plot_settings.txt")
try: ch1=string.replace(ch1,':','__')
except Exception: pass
name=ch1
#outputdir=findParentDir(inputpsi)+"sashimiplots"
try: os.makedirs(outputdir)
except Exception: pass
#print '********',[ch1],[event],outputdir
try:
ssp.plot_event(ch1,event,setting,outputdir)
except Exception:
#print '^^^^^^^^^^^^',[ch1],[event],outputdir;sys.exit()
#print traceback.format_exc()
#print "error2"
#sys.exit()
continue
#outputdir=findParentDir(inputpsi)+"sashimiplots"
for filename in os.listdir(outputdir):
newname=string.split(filename,'/')
#print newname[0]
if newname[0] in gene_sym:
new_path = gene_sym[newname[0]]+'-'+filename
#new_path = string.replace()
os.rename(filename,new_path)
else:
continue
def filepath(filename):
fn = unique.filepath(filename)
return fn
def formatAndSubmitSplicingEventsToSashimiPlot(
filename, bamdir, splicing_events, sample_group_db, groups, expandedSearch
):
### Begin exporting parameters and events for SashimiPlot visualization
firstLine = True
setting = unique.filepath("Config/sashimi_plot_settings.txt")
psi_parent_dir = findParentDir(filename)
if "PSI" not in filename:
index_dir = string.split(psi_parent_dir, "ExpressionInput")[0] + "AltResults/AlternativeOutput/sashimi_index/"
else:
index_dir = psi_parent_dir + "sashimi_index/"
spliced_junctions = [] ### Alternatively, compare to just one of the junctions
for splicing_event in splicing_events:
try:
j1, j2 = string.split(splicing_event, " ")
spliced_junctions.append(j1)
spliced_junctions.append(j2)
except Exception:
spliced_junctions.append(splicing_event) ### single gene ID or junction
if "PSI" not in filename:
splicing_events_db = {}
for event in splicing_events:
event = string.replace(event, ":", "__")
if " " in event:
event = string.split(event, " ")[-1]
gene = string.split(event, "__")[0]
try:
splicing_events_db[gene].append(event)
except Exception:
splicing_events_db[gene] = [event]
splicing_events = splicing_events_db
import collections
analyzed_junctions = []
processed_events = []
for line in open(filename, "rU").xreadlines():
line = cleanUpLine(line)
t = string.split(line, "\t")
if firstLine:
if "PSI" in filename:
sampleIndexBegin = 11
sample_headers = t[sampleIndexBegin:]
else:
sampleIndexBegin = 1
sample_headers = t[sampleIndexBegin:]
if ".bed" not in sample_headers[0]: ### Add .bed if removed manually
sample_headers = map(lambda s: s + ".bed", sample_headers)
index = 0
sample_group_index = {}
for s in sample_headers:
group = sample_group_db[s]
sample_group_index[index] = group
try:
sampleReadDepth[index] = count_sum_array_db[s]
except Exception:
sampleReadDepth[index] = count_sum_array_db[s]
index += 1
firstLine = False
else:
if "PSI" in filename:
splicing_event = val = t[2] + " " + t[3]
j1 = t[2]
j2 = t[3]
if t[2] in analyzed_junctions and t[3] in analyzed_junctions:
continue
else:
splicing_event = t[0] ### The gene ID
j1 = t[0]
j2 = t[0]
if ":U" in splicing_event or "-U" in splicing_event:
continue
else:
### First check to see if the full splicing event matches the entry
### If not (and not a PSI regulation hits list), look for an individual junction match
if splicing_event in splicing_events or (
expandedSearch and (j1 in spliced_junctions or j2 in spliced_junctions)
):
if splicing_event in processed_events:
continue
if j2 in processed_events:
continue
if j1 in processed_events:
continue
processed_events.append(splicing_event)
processed_events.append(j1)
processed_events.append(j2)
# print processed_events, splicing_event
if "PSI" in filename:
geneID = string.split(t[2], ":")[0]
symbol = t[0]
analyzed_junctions.append(t[2])
analyzed_junctions.append(t[3])
else: ### For exp.dataset-steady-state.txt files
geneID = splicing_event
events = splicing_events[geneID]
index = 0
import collections
initial_group_psi_values = {}
try:
group_psi_values = collections.OrderedDict()
except Exception:
try:
import ordereddict
group_psi_values = ordereddict.OrderedDict()
except Exception:
group_psi_values = {}
for i in t[sampleIndexBegin:]: ### Value PSI range in the input file
try:
group = sample_group_index[index]
except Exception:
group = None
try:
try:
initial_group_psi_values[group].append([float(i), index])
except Exception:
initial_group_psi_values[group] = [[float(i), index]]
except Exception:
# print traceback.format_exc();sys.exit()
pass ### Ignore the NULL values
index += 1
### limit the number of events reported and sort based on the PSI values in each group
if "None" in groups and len(groups) == 1:
initial_group_psi_values["None"].sort()
group_size = len(initial_group_psi_values["None"]) / 2
filtered_group_index1 = map(lambda x: x[1], initial_group_psi_values["None"][:group_size])
filtered_group_index2 = map(lambda x: x[1], initial_group_psi_values["None"][group_size:])
group_psi_values["low"] = filtered_group_index1
group_psi_values["high"] = filtered_group_index2
else:
gn = 0
for group in groups:
gn += 1
# if gn>4: break
if group in initial_group_psi_values:
initial_group_psi_values[group].sort()
if len(groups) > 7:
filtered_group_indexes = map(lambda x: x[1], initial_group_psi_values[group][:1])
elif len(groups) > 5:
filtered_group_indexes = map(lambda x: x[1], initial_group_psi_values[group][:2])
elif len(groups) > 3:
filtered_group_indexes = map(lambda x: x[1], initial_group_psi_values[group][:4])
else:
filtered_group_indexes = map(lambda x: x[1], initial_group_psi_values[group][:5])
group_psi_values[group] = filtered_group_indexes
try:
update_plot_settings(bamdir, group_psi_values, sample_headers)
except Exception:
print "Cannot update the settings file. Likely permissions issue."
try:
reordered = reorderEvents([t[2] + " " + t[3]])
reordered = string.split(reordered[0], " ")
except Exception:
reordered = [t[2] + " " + t[3]]
reordered = string.split(reordered[0], " ")
# print reordered
if "PSI" in filename:
try:
formatted_splice_event = string.replace(reordered[1], ":", "__")
except Exception:
pass
### Submit the query
try:
ssp.plot_event(formatted_splice_event, index_dir, setting, outputdir)
success = True
except Exception:
success = False
# print traceback.format_exc()
else:
for event in events:
try:
ssp.plot_event(event, index_dir, setting, outputdir)
# print 'success' #formatted_splice_event='ENSMUSG00000000355__E4.1-E5.1'
except Exception: ### If it fails, output the gene-level plot
try:
ssp.plot_event(geneID, index_dir, setting, outputdir)
success = True
except Exception:
success = False
# print traceback.format_exc()
"""
### Second attempt
if 'PSI' in filename and success==False: ### Only relevant when parsing the junction pairs but not genes
try: formatted_splice_event=string.replace(reordered[0],':','__')
except Exception: pass
try: ssp.plot_event(formatted_splice_event,index_dir,setting,outputdir); # print 'success'
except Exception: pass
"""
return processed_events
def ProteinCentricIsoformView(Selected_Gene):
Transcript_List = []
Transcript_db = {}
Exon_db = {}
for line in open(Transcript_Annotations_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
if(line[0] == Selected_Gene):
transcriptID = line[-1]
exonID = line[5]
start = line[3]
stop = line[4]
strand = line[2]
chr = line[1]
if 'chr' not in chr:
chr = 'chr'+chr
exon_data = EnsemblRegionClass(start,stop,exonID,None,strand)
exon_data.setChr(chr)
Transcript_List.append((transcriptID, exonID))
try:
Transcript_db[transcriptID].append(exon_data)
except Exception:
Transcript_db[transcriptID]=[exon_data]
try:
Exon_db[exonID].append(transcriptID)
except Exception:
Exon_db[exonID]=[transcriptID]
Transcript_Protein_db = {}
Protein_Transcript_db = {}
Protein_List = []
count = 0
for line in open(Prt_Trans_File, "rU").xreadlines():
if(count == 0):
count = 1
continue
line = line.rstrip()
line = line.split("\t")
if(len(line) != 3):
continue
geneID = line[0]
transcriptID = line[1]
proteinID = line[2]
if Selected_Gene == geneID:
Transcript_Protein_db[transcriptID] = proteinID
Protein_Transcript_db[proteinID] = transcriptID
Protein_List.append(proteinID)
#MicroRNA File
microRNA_db = {}
for line in open(microRNA_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
try:
gene_and_exon_id = line[0].split(":")
current_gene_id = gene_and_exon_id[0]
current_exon_id = gene_and_exon_id[1]
except Exception:
continue
#print([current_gene_id,current_exon_id,Selected_Gene]);break
current_description = line[1]
current_base_pairs = line[2]
algorithms = line[3]
if(current_gene_id == Selected_Gene):
m = MicroRNAClass(current_exon_id, current_description, current_base_pairs, algorithms)
try:
if(len(microRNA_db[current_exon_id]) > 6):
continue
microRNA_db[current_exon_id].append(m)
#print("ADDED!")
except:
microRNA_db[current_exon_id] = [m]
Transcript_ExonRegion_db={}
geneExonRegion_db={}
exon_coord_db={}
exonRegion_db={}
AllBlocks = [("E", []), ("I", [])]
# Store the exon region positions and later link them to the Ensembl exons
for line in open(ExonRegion_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
geneID = line[0]
exon_region = line[1]
chr = line[2]
exonID = line[1]
strand = line[3]
start = line[4]
stop = line[5]
er = EnsemblRegionClass(start,stop,exonID,exon_region,strand)
if(geneID == Selected_Gene):
Block_Num = exon_region[1:]
I_E_id = exon_region[0]
if(I_E_id == "E"):
AllBlocks[0][1].append(Block_Num)
if(I_E_id == "I"):
AllBlocks[1][1].append(Block_Num)
continue
exon_added = False
#Exon_List = line[7].split("|")
exon_coord_db[chr,int(start),'start'] = exon_region
exon_coord_db[chr,int(stop),'stop'] = exon_region
exonRegion_db[Selected_Gene,exon_region] = er
#print chr,start,'start'
probeset_to_ExonID={}
if platform != 'RNASeq':
for line in open(unique.filepath('AltDatabase/'+species+'/'+string.lower(platform)+'/'+species+'_Ensembl_probesets.txt'), "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
gene = line[2]
if gene == Selected_Gene:
probeset = line[0]
exon_region = line[12]
if '.' not in exon_region:
exon_region = string.replace(exon_region,'-','.')
probeset_to_ExonID[probeset] = exon_region
ETC_List = []
for line in open(SplicingIndex_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
if ':' in line[0]:
GeneLine = line[0].split(":")
FeatureID = GeneLine[1]
else:
FeatureID = line[0]
Gene = line[1]
regcall = line[2]
spl_index = line[3]
pval = line[4]
midas = line[5]
S_I_data = SplicingIndexClass(regcall, spl_index, pval, midas)
if(Gene == Selected_Gene):
if platform != 'RNASeq':
if FeatureID in probeset_to_ExonID:
FeatureID = probeset_to_ExonID[FeatureID]
#print(FeatureID)
ETC_List.append((FeatureID, S_I_data))
else:
try:
FeatureID = FeatureID.split("_")
FeatureID = FeatureID[0]
ETC_List.append((FeatureID, S_I_data))
except:
pass
ETC_dict = {}
# Link the exon regions to the Ensembl exons
for transcriptID in Transcript_db:
for exon_data in Transcript_db[transcriptID]:
start = exon_data.Start()
stop = exon_data.Stop()
chr = exon_data.Chr()
strand = exon_data.Strand()
try:
start_exon_region = exon_coord_db[chr,start,'start']
stop_exon_region = exon_coord_db[chr,stop,'stop']
proceed = True
except Exception: ### Not clear why this error occurs. Erroring region was found to be an intron region start position (I7.2 ENSMUSG00000020385)
proceed = False
if proceed:
if '-' in strand:
stop_exon_region,start_exon_region = start_exon_region,stop_exon_region
regions = [start_exon_region]
block,start_region = start_exon_region.split('.')
start_region = int(float(start_region))
block,stop_region = stop_exon_region.split('.')
stop_region = int(float(stop_region))
region = start_region+1
while region<stop_region:
er = block+'.'+str(region)
regions.append(er)
region+=1
if stop_region != start_region:
regions.append(stop_exon_region)
for region in regions:
er = exonRegion_db[Selected_Gene,region]
try:
Transcript_ExonRegion_db[transcriptID].append(er)
except:
Transcript_ExonRegion_db[transcriptID] = [er]
exon_virtualToRealPos= c.OrderedDict()
junction_transcript_db = {}
for transcriptID in Transcript_ExonRegion_db:
#print('transcripts:',transcriptID)
position=0
Buffer=15
for exon_object in Transcript_ExonRegion_db[transcriptID]:
if position!=0:
if last_exon != exon_object.ExonBlock():
#print last_exon_region+'-'+exon_object.EnsemblRegion(),position,Buffer
junctionID = last_exon_region+'-'+exon_object.EnsemblRegion()
try: junction_transcript_db[transcriptID].append((position,position+Buffer, junctionID)) ### virtual junction positions
except: junction_transcript_db[transcriptID] = [(position,position+Buffer, junctionID)]
position+=Buffer
virtualStart = position
virtualStop = virtualStart + exon_object.Length()
position = virtualStop
try:
exon_virtualToRealPos[transcriptID].append(([virtualStart,virtualStop],[exon_object.Start(), exon_object.Stop()],exon_object))
except Exception:
exon_virtualToRealPos[transcriptID]=[([virtualStart,virtualStop],[exon_object.Start(), exon_object.Stop()],exon_object)]
#print transcriptID,exon_object.ExonBlock(),exon_object.EnsemblExon(),exon_object.EnsemblRegion(),exon_object.Start(),exon_object.Stop(),virtualStart,virtualStop,"\n"
last_exon = exon_object.ExonBlock()
last_exon_region = exon_object.EnsemblRegion()
for i in ETC_List:
Region = i[0]
S_I = i[1]
Region = Region.split("-")
if(len(Region) > 1):
#Delete underscores from values.
R_Start = Region[0]
R_End = Region[1]
R_Start = R_Start.split("_")
R_End = R_End.split("_")
R_Start = R_Start[0]
R_End = R_End[0]
R_Final = R_Start + "-" + R_End
R_Type = R_Final[0]
#print(R_Final)
ETC_dict[R_Final] = S_I
else:
Region = Region[0]
Region = Region.split("_")
Region = Region[0]
Region_type = Region[0]
ETC_dict[Region] = S_I
#if(Region_type == "E"):
# for entry in AllBlocks[0][1]:
# if(Region[1:] == entry):
# ETC_dict[("E" + entry)] = S_I
#if(Region_type == "I"):
# for entry in AllBlocks[1][1]:
# if(Region[1:] == entry):
# ETC_dict[("I" + entry)] = S_I
#for a in ETC_dict:
# print(ETC_dict[a].RegCall(), a)
#for i in junction_transcript_db:
# print i, junction_transcript_db[i], "\n"
Protein_Pos_Db = {}
last_protein=None
stored_stop=None
for line in open(Prt_Boundaries_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
proteinID = line[0]
if(proteinID in Protein_List):
Stop = int(line[-1])
Start = int(line[-2])
if(proteinID != last_protein):
if stored_stop !=None:
#print proteinID,stored_start,stored_stop
Protein_Pos_Db[last_protein] = [[stored_start,stored_stop,None]]
stored_start = int(Start)
if(proteinID == last_protein):
stored_stop = int(Stop)
last_protein = str(proteinID)
Protein_Pos_Db[last_protein] = [(stored_start,stored_stop,None)]
Protein_virtualPos = RealToVirtual(Protein_Pos_Db, exon_virtualToRealPos, Protein_Transcript_db,Transcript_ExonRegion_db)
Domain_Pos_Db={}
domainAnnotation_db={}
#"""
for line in open(Prt_Regions_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
proteinID = line[0]
if proteinID in Protein_Pos_Db:
domain_start = int(float(line[3]))
domain_stop = int(float(line[4]))
domainID = line[-2]
domainName = line[-1]
try:
Domain_Pos_Db[proteinID].append((domain_start,domain_stop,domainID))
except:
Domain_Pos_Db[proteinID] = [(domain_start,domain_stop,domainID)]
domainAnnotation_db[domainID] = domainName
#"""
for line in open(UniPrt_Regions_File, "rU").xreadlines():
line = line.rstrip()
line = line.split("\t")
proteinID = line[0]
if proteinID in Protein_Pos_Db:
domain_start = int(float(line[3]))
domain_stop = int(float(line[4]))
domainID = line[-1]
domainName = line[-1]
try:
Domain_Pos_Db[proteinID].append((domain_start,domain_stop,domainID))
except:
Domain_Pos_Db[proteinID] = [(domain_start,domain_stop,domainID)]
domainAnnotation_db[domainID] = domainName
#print('--',domainName,domain_start,domain_stop)
# Do the same for domain coordinates
Domain_virtualPos = RealToVirtual(Domain_Pos_Db, exon_virtualToRealPos, Protein_Transcript_db,Transcript_ExonRegion_db)
return_val = ((junction_transcript_db, Protein_virtualPos, Domain_virtualPos, Transcript_db, exon_virtualToRealPos, ETC_dict, microRNA_db, domainAnnotation_db))
return return_val
def performGroupNormalization(filename,export_dir,platform):
expressionDataFormat,increment,convertNonLogToLog = ExpressionBuilder.checkExpressionFileFormat(filename)
groups_dir = string.replace(export_dir,'exp.','batch.')
fn=unique.filepath(filename); row_number=0; exp_db={}; relative_headers_exported = False
group_db = importGroups(groups_dir)
export_data = export.ExportFile(export_dir)
for line in open(fn,'rU').xreadlines():
data = ExpressionBuilder.cleanUpLine(line)
t = string.split(data,'\t')
if data[0]=='#' and row_number==0: row_number = 0
elif row_number==0:
sample_list = t[1:]
new_sample_list = []
for group in group_db:
group_samples = group_db[group]
try:
sample_index_list = map(lambda x: sample_list.index(x), group_samples)
group_db[group] = sample_index_list
new_sample_list+=group_samples
except Exception:
missing=[]
for x in sample_list:
if x not in t[1:]: missing.append(x)
print 'missing:',missing
print t
print sample_list
print filename, groups_dir
print 'Unknown Error!!! Skipping cluster input file build (check column and row formats for conflicts)'; forceExit
title = string.join([t[0]]+new_sample_list,'\t')+'\n' ### output the new sample order (group file order)
export_data.write(title)
row_number=1
else:
gene = t[0]
if expressionDataFormat == 'non-log' and (convertNonLogToLog or platform == 'RNASeq'):
### Convert to log2 RPKM values - or counts
try: all_values = map(lambda x: math.log(float(x)+increment,2), t[1:])
except Exception:
all_values = ExpressionBuilder.logTransformWithNAs(t[1:],increment)
else:
try: all_values = map(float,t[1:])
except Exception:
all_values = ExpressionBuilder.logTransformWithNAs(t[1:],increment)
row_number+=1 ### Keep track of the first gene as to write out column headers for the relative outputs
gene_log_folds = []
for group in group_db:
sample_index_list = group_db[group]
### Calculate log-fold values relative to the mean of all sample expression values
try: values = map(lambda x: all_values[x], sample_index_list) ### simple and fast way to reorganize the samples
except Exception:
print len(values), sample_index_list;kill
try: avg = statistics.avg(values)
except Exception:
values2=[]
for v in values:
try: values2.append(float(v))
except Exception: pass
values = values2
try: avg = statistics.avg(values)
except Exception:
if len(values)>0: avg = values[0]
else: avg = 0
try: log_folds = map(lambda x: (x-avg), values)
except Exception:
log_folds=[]
for x in values:
try: log_folds.append(x-avg)
except Exception: log_folds.append('')
gene_log_folds+=log_folds
gene_log_folds = map(lambda x: str(x),gene_log_folds)
export_data.write(string.join([gene]+gene_log_folds,'\t')+'\n')
export_data.close()
def remoteSashimiPlot(Species,
fl,
bamdir,
eventsToVisualizeFilename,
events=None,
show=False):
global PSIFilename
global outputdir
global root_dir
global steady_state_exp_file
global species
species = Species
try:
countinp = fl.CountsFile()
root_dir = fl.RootDir()
except Exception:
root_dir = fl
search_dir = root_dir + '/ExpressionInput'
files = unique.read_directory(search_dir)
for file in files:
if 'counts.' in file and 'steady-state.txt' not in file:
countinp = search_dir + '/' + file
PSIFilename = root_dir + '/AltResults/AlternativeOutput/' + species + '_RNASeq_top_alt_junctions-PSI.txt'
import ExpressionBuilder
dir_list = unique.read_directory(root_dir + '/ExpressionInput')
for file in dir_list:
if 'exp.' in file and 'steady-state' not in file:
exp_file = root_dir + '/ExpressionInput/' + file
elif 'exp.' in file and 'steady-state' in file:
steady_state_exp_file = root_dir + '/ExpressionInput/' + file
global sample_group_db
sample_group_db = ExpressionBuilder.simplerGroupImport(exp_file)
#outputdir=findParentDir(PSIFilename)+"sashimiplots"
outputdir = root_dir + '/ExonPlots'
outputdir = root_dir + '/SashimiPlots'
try:
os.mkdir(unique.filepath(outputdir))
except Exception:
pass
if show:
s = open(outputdir + '/show.txt', 'w')
s.write('TRUE')
s.close()
else:
s = open(outputdir + '/show.txt', 'w')
s.write('FALSE')
s.close()
geneSymbol_db = Sashimiplottting(bamdir,
countinp,
PSIFilename,
eventsToVisualizeFilename,
events=events)
for filename in os.listdir(outputdir):
if '.pdf' in filename or '.png' in filename:
fn = string.replace(filename, '.pdf', '')
fn = string.replace(fn, '.png', '')
newname = string.split(fn, '__')
if newname[0] in geneSymbol_db:
new_filename = str(filename)
if '__' in filename:
new_filename = string.split(filename, '__')[1]
elif '\\' in filename:
new_filename = string.split(filename, '\\')[1]
elif '/' in filename:
new_filename = string.split(filename, '/')[1]
nnname = geneSymbol_db[
newname[0]][0] + '-SashimiPlot_' + new_filename
try:
os.rename(os.path.join(outputdir, filename),
os.path.join(outputdir, nnname))
except Exception:
if 'already exists' in traceback.format_exc():
### File already exists, delete the new one
try:
os.remove(os.path.join(outputdir, nnname))
except Exception:
pass
### Now right the new one
try:
os.rename(os.path.join(outputdir, filename),
os.path.join(outputdir, nnname))
except Exception:
pass
pass
else:
continue
print ''
"iconfile": "Viewer.icns"}
}
setup(name=_appName,
app=[_script],
version=_appVersion,
description=_appDescription,
author=_authorName,
author_email=_authorEmail,
url=_authorURL,
options=options,
#data_files=data_files,
setup_requires=["py2app"]
)
import unique, shutil
root_path = unique.filepath('')
software_path = root_path+'/dist/AltAnalyzeViewer.app/Contents/Frameworks/Tcl.framework'
shutil.rmtree(software_path)
software_path = root_path+'/dist/AltAnalyzeViewer.app/Contents/Frameworks/Tk.framework'
shutil.rmtree(software_path)
software_path = root_path+'/dist/AltAnalyzeViewer.app/Contents/Resources/mpl-data/sample_data'
shutil.rmtree(software_path)
software_path = root_path+'/dist/AltAnalyzeViewer.app/Contents/Resources/lib/python2.7/matplotlib/tests'
shutil.rmtree(software_path)
if sys.platform.startswith("win"):
### example command: python setup.py py2exe
from distutils.core import setup
import py2exe
import suds
import numpy
def filepath(filename):
fn = unique.filepath(filename)
return fn
def update_plot_settings(bamdir,list1,list2,samp):
export_pl=open(unique.filepath('Config/sashimi_plot_settings.txt'),'w')
export_pl.write('[data]')
export_pl.write('\n')
export_pl.write('bam_prefix = '+bamdir+'\n')
export_pl.write('bam_files =[')
for i in range(len(list1)):
g=samp[list1[i]].replace('.bed','.bam')
#print i
if i==len(list1)-1 and len(list2)==0:
export_pl.write('"'+g+'"]')
else:
export_pl.write('"'+g+'",')
for j in range(len(list2)):
#print j
g=samp[list2[j]].replace('.bed','.bam')
export_pl.write('"'+g+'"')
if j==len(list2)-1:
export_pl.write(']')
else:
export_pl.write(',')
export_pl.write('\n')
export_pl.write('[plotting]')
export_pl.write('\n')
export_pl.write('fig_width = 7 \nfig_height = 7 \nintron_scale = 30 \nexon_scale = 4 \nlogged = False\n')
export_pl.write('font_size = 6 \nbar_posteriors = False \nnyticks = 4 \nnxticks = 4 \n')
export_pl.write('show_ylabel = False \nshow_xlabel = True \nshow_posteriors = False \nnumber_junctions = True \n')
export_pl.write('resolution = .5 \nposterior_bins = 40 \ngene_posterior_ratio = 5 \n')
export_pl.write('colors =[')
for i in range(len(list1)):
export_pl.write('"'+'red'+'"')
if i==len(list1)-1 and len(list2)==0:
export_pl.write(']')
else:
export_pl.write(',')
for j in range(len(list2)):
export_pl.write('"'+'blue'+'"')
if j==len(list2)-1:
export_pl.write(']')
else:
export_pl.write(',')
export_pl.write('\n')
export_pl.write('coverages =[')
for i in range(len(list1)):
e=sample_read[samp[list1[i]]]
export_pl.write(str(int(e)))
if i==len(list1)-1 and len(list2)==0:
export_pl.write(']')
else:
export_pl.write(',')
for j in range(len(list2)):
e=sample_read[samp[list2[j]]]
export_pl.write(str(int(e)))
if j==len(list2)-1:
export_pl.write(']')
else:
export_pl.write(',')
export_pl.write('\n')
export_pl.write('bar_color = "b" \nbf_thresholds = [0, 1, 2, 5, 10, 20]')
export_pl.close()