infile = a
elif o == "-o":
outfile = a
promotorUp = 2000
promotorDown = 2000
intervals = csv.reader(open(infile, "r"), delimiter="\t")
writer = csv.writer(open(outfile, "w"), delimiter="\t")
cpgIslands = ExtendedBed(
os.path.expanduser(
"~/mount/publicdata/hg18/cpgislands/cpgislands-0-index.bed"))
genome = Genome()
# load gene data
genedata = Ensembl.EnsemblGenes(assembly="hg18", annotation="ncbi36.1")
headerRow = [
'Ensembl', 'Name', 'chr', 'start', 'stop', 'strand', 'No. Transcripts',
'Avg. Exons per Transcript', "Unique Exons per Gene", "Start positions",
"Start positions / No. Transcripts"
]
#"Promotor G-Count", "Promotor C-Count", "Promotor A-Count", "Promotor T-Count" ,
headerRow.extend([
"Promotor region start",
"Promotor region end",
"Promotor GC Percent",
assembly = a
assert methdatafile != None
# if we have an expression file we need fc and expression columns
if exprfile != None:
assert fccol != None
assert exprcols != None
else:
exprcols = []
assert outputfile != None
genedata = EnsemblGenes(assembly=assembly)
genome = Genome(genomeBuild=assembly)
if assembly == "hg18":
cpgIslands = ExtendedBed(
os.path.expanduser(
"~/mount/publicdata/hg18/cpgislands/cpgislands.bed"))
lINEs = ExtendedBed(
os.path.expanduser("~/mount/publicdata/hg18/repeats/LINEs-0.bed"))
sINEs = ExtendedBed(
os.path.expanduser("~/mount/publicdata/hg18/repeats/SINEs-0.bed"))
elif assembly == "hg19":
cpgIslands = ExtendedBed(
os.path.expanduser(
"~/mount/publicdata/hg19/CpGIslands/cpgislands.bed"))
lINEs = ExtendedBed(
os.path.expanduser(
exprfile = None
ensemblidcol = "ensemblid"
upstreamPromotor = 5000
downstreamPromotor = 1000
for o,a in opts:
if o=="--gene-expression-file":
exprfile = a
assert exprfile != None
print len(matrices)
# WARNING: everything we just read in are pfm (position frequency), we might need position weight matrices
# We have choice of JASPER (downloaded), JASPER (with motility) or TFD or combining them
genedata = EnsemblGenes(assembly="hg18")
genome = Genome(genomeBuild = "hg18")
exprCSV = IndexedCSV(exprfile,keyPos=1)
motifnames = []
for matrix in matrices:
motifnames.append(matrix)
output = csv.writer(open(exprfile+".transcriptionfactors","w"),delimiter='\t')
# header
header = exprCSV.keys[:] # copy keys
header.extend(motifnames)
output.writerow(header)
for testid in exprCSV:
if o == "-o" or o == "--outputFolder":
outputfolder = a
assert infile != None
assert outputfolder != None
def getBlatLocation(line):
result = line.split("\t")
return int(result[0]), result[13], int(result[15]), int(
result[16]), result[8]
def getBlatQStarts(line):
result = line.split("\t")
return [int(y) for y in result[19].split(",")[:-1]]
genome = Genome(genomeBuild=build)
makeDirectory(outputfolder)
with open(outputfolder + "/index.html", "w") as indexFile:
print >> indexFile, """
<html><body>
<head>
<style type="text/css">
td{font-size:small;}
th{font-size:small;}
</style>
</head>
"""
def __init__(self,build):
self.genome = Genome(genomeBuild = build)
self.valuesBehaviour = missingValuesDontCount
self.chromosomeEnds = ChromosomeEnds(build)
else:
regions.append(BedIntervalTree(a))
elif o == "-c":
controlAffyExpressionData = IndexedCSV(a)
#Annotated difference file input
elif o == "-e":
rnaSeqExpressionData = IndexedCSV(a, key="test_id")
elif o == "-a":
assembly = a
UPSTREAM_PROMOTOR_DIST = 2000
DOWNSTREAM_PROMOTOR_DIST = 2000
writer = csv.writer(open(outfile, "w"), delimiter="\t")
genome = Genome(assembly)
###
# load data
genedata = Ensembl.EnsemblGenes(assembly=assembly)
genes = Ensembl.ReverseGeneMapping(genedata)
genespluspromotor = Ensembl.ReverseGeneMapping(
genedata, tssPadding=UPSTREAM_PROMOTOR_DIST)
genepromotors = Ensembl.ReversePromotorMapping(
genedata,
upstreamPadding=UPSTREAM_PROMOTOR_DIST,
affypcol = a
elif o == "--outputfile":
outputfile = a
elif o == "--promotorsize":
upstreamPromotor = int(a)
downstreamPromotor = int(a)
assert methdatafile != None
assert affyfile != None
assert affyfccol != None
assert affyexprcol != None
assert outputfile != None
genedata = EnsemblGenes(assembly="hg18")
genome = Genome(genomeBuild="hg18")
affyannotation = NetAffxAnnotation(genome="hg18", cdfname="HG-U133_Plus_2")
cpgIslands = ExtendedBed(
os.path.expanduser(
"~/mount/publicdata/hg18/cpgislands/cpgislands-0-index.bed"))
affyCSV = IndexedCSV(affyfile)
affyEnsemblLogFCs = collections.defaultdict(list)
affyEnsemblExprs = collections.defaultdict(list)
affyEnsemblPvalues = collections.defaultdict(list)
for affy in affyCSV:
ensembls = affyannotation.getValues(affy, "Ensembl")
if len(ensembls) == 1:
assert infile != None
assert outputfolder != None
def getBlatLocation(line):
result = line.split("\t")
return int(result[0]), result[13], int(result[15]), int(
result[16]), result[8]
def getBlatQStarts(line):
result = line.split("\t")
return [int(y) for y in result[19].split(",")[:-1]]
exonboundaries = False
blockStarts = []
genome = Genome(genomeBuild=build)
makeDirectory(outputfolder)
shutil.copy("arrow-down.gif", outputfolder + "/arrow-down.gif")
shutil.copy("arrow-none.gif", outputfolder + "/arrow-none.gif")
shutil.copy("arrow-up.gif", outputfolder + "/arrow-up.gif")
shutil.copy("sortable.css", outputfolder + "/sortable.css")
shutil.copy("sortable.js", outputfolder + "/sortable.js")
with open(outputfolder + "/index.html", "w") as indexFile:
print >> indexFile, """
<html><body>
<head>
<style type="text/css">
###
def distanceHumanReadable(dist):
return str(dist / 1000) + "kb"
TSS_TTS_Distance = 1000
SURROUNDING_SEQUENCE_Distance = 250 # each side
WINDOW_SIZE = 500
WINDOW_OFFSET = 5
# load data
genome = Genome(genomeBuild="hg18")
chromosomeEnds = ChromosomeEnds("hg18")
genedata = Ensembl.EnsemblGenes(assembly="hg18", annotation="ncbi36.1")
genes = Ensembl.ReverseGeneMapping(genedata)
exons = Ensembl.ReverseExonMapping(genedata)
transcriptionSites = Ensembl.TranscriptionSites(genedata)
cpgIslands = ExtendedBed(
os.path.expanduser(
"~/mount/publicdata/hg18/cpgislands/cpgislands-0-index.bed"))