def __init__(self, build, annotation, exons, minExons, numbExons, tsses,
chunks, ud, ui, dd, di):
assert not (exons and tsses)
#Stores all parameters
self.exons = exons
self.minExons = minExons
self.numbExons = numbExons
self.tsses = tsses
self.geneNumbChunks = 20 if (chunks == None) else chunks
self.upstreamDistance = 5000 if (ud == None) else ud
self.upstreamInterval = 1000 if (ui == None) else ui
self.downstreamDistance = 5000 if (dd == None) else dd
self.downstreamInterval = 1000 if (di == None) else di
# Gets dictionaries of genes, exons transcripts etc from Ensembl class
#assert build == "hg18", "Non hg-18 not supported for Ensembl regions at the moment"
#Gets the lengths of chromosomes
# we keep this as a non instance variable as well so that the subclass below can access it
genedata = Ensembl.EnsemblGenes(assembly=build, annotation=annotation)
self.genedata = genedata
self.chromosomeEnds = ChromosomeEnds(build)
# Gets an object of the genelist class
class EnsemblNameAndIDFormatter(list):
def __init__(self, genesToUseLocation):
geneList = GeneList(genesToUseLocation)
self.seengenes = set()
for gene in geneList:
if gene in self.seengenes:
# seen this gene id before (generally shouldnt be the case as using GeneList which guarantees this
# for the source list at least
pass
elif gene in genedata:
# we've not seen the gene but it's in the ensembl ids list
self.append(gene)
self.seengenes.add(gene)
else:
# it's not in the ensembl ids list, it could be a gene name
found = False
for geneid in genedata.getGeneIDs(gene):
if geneid not in self.seengenes:
self.append(geneid)
self.seengenes.add(geneid)
found = True
if not found:
print "No GeneID for:" + gene
print genesToUseLocation + ":" + str(len(self))
self.regionIterator = EnsemblNameAndIDFormatter
try:
opts, args = getopt.getopt(sys.argv[1:], "g:", [])
except getopt.GetoptError, err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
sys.exit(2)
UPSTREAM_PROMOTOR_DIST = 5000
genelists = []
for o, a in opts:
if o == "-g":
genelists.append(GeneList(a))
assert len(genelists) > 0
genedata = Ensembl.EnsemblGenes(assembly="hg18", annotation="ncbi36.1")
for genelist in genelists:
print genelist.getFullName()
for gene in genedata:
# does the gene match the pattern
for pattern in genelist:
if re.match(pattern, genedata[gene].name):
start, stop = genedata[gene].getGeneWithPromotor(
upstreamPadding=UPSTREAM_PROMOTOR_DIST)
print genedata[gene].id, genedata[gene].name, genedata[
gene].chr, start, stop
break
print str(err) # will print something like "option -a not recognized"
sys.exit(2)
assembly = "hg19"
ensemblids = []
fastaFile = None
for o, a in opts:
if o == "--ensemblids":
ensemblids = GeneList(a)
elif o == "--fasta":
fastaFile = FastAFile(a)
if len(ensemblids) > 0:
genedata = Ensembl.EnsemblGenes(assembly=assembly)
print "ensemblid", "chr", "start", "stop", "transcripts", "stemloops", "polyas"
for ensemblid in ensemblids:
stemloops = 0
polyas = 0
for transcriptid in genedata[ensemblid]:
# http://genome-euro.ucsc.edu/cgi-bin/hgc?db=hg19&g=htcGeneMrna&i=ENST00000314332&o=ensGene&table=ensGene
chrm = genedata[ensemblid][transcriptid].chr
start = str(genedata[ensemblid][transcriptid].start)
stop = str(genedata[ensemblid][transcriptid].end)
vstepWidth = 200 #default
numbSlices = 20 # default
for o, a in opts:
# need a vstep width
if o == "-s":
vstepWidth = int(a)
# need a vstep file
elif o == "-v":
vstepFile = a
# need a list of genes -> coords
elif o == "-e":
genesFileName = a # eg : "genes-and-exons-human-NCBI36.csv"
print "Loading gene mapping"
genesmapping = Ensembl.GenesMapping(genesFileName)
# need an output folder
elif o == "-o":
outputFolder = a
# need a number of slices
elif o == "-p":
numbSlices = a
elif o == "-f":
friendlyGenesNames = Ensembl.FriendlyGeneNames(a)
elif o == "-w":
webroot = a
# need lists of genes
geneListLocations = args
# create output folder
print str(err) # will print something like "option -a not recognized"
print "Usage: main.py [Space seperated list of gene id sets]"
sys.exit(2)
for o, a in opts:
if (o == "-G") or (o == "--gtf"):
gtfFile = a
elif (o == "-D") or (o == "--gene-expression-difference"):
differences = a
elif (o == "-o") or (o == "--output"):
outputFile = a
else:
print "Unknown parameter: " + o + " " + a
sys.exit(2)
genedata = Ensembl.EnsemblGenes(assembly="hg19",
annotation="EnsemblGenes73")
gtfReader = csv.reader(open(gtfFile, "r"), delimiter="\t")
cuffGeneIdsToEnsemblGeneIds = collections.defaultdict(set)
missing = set()
for row in gtfReader:
detailsColumn = row[8]
details = dict(
item.replace("\"", "").split(" ")
for item in detailsColumn.split("; "))
if "nearest_ref" not in details:
continue
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,
downstreamPadding=DOWNSTREAM_PROMOTOR_DIST)
exons = Ensembl.ReverseExonMapping(genedata)
transcriptionSites = Ensembl.TranscriptionSites(genedata)
opts, args = getopt.getopt(sys.argv[1:], "", [])
except getopt.GetoptError, err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
sys.exit(2)
UPSTREAM_PROMOTOR_DIST = 5000
DOWNSTREAM_PROMOTOR_DIST = 1000
# probably want to change this to be exons rather than genes
###
# load data
genedata = Ensembl.EnsemblGenes(assembly="hg18", annotation="ncbi36.1")
bp = 0
for gene in genedata:
bp += genedata[gene].end - genedata[gene].start
print bp
#genedata = Ensembl.GenesMapping(os.path.expanduser("~/mount/publicdata/hg18/ncbi36.1/genes-and-exons-human-NCBI36.1.csv"))
genes = Ensembl.ReverseGeneMapping(genedata)
genespluspromotor = Ensembl.ReverseGeneMapping(
genedata, tssPadding=UPSTREAM_PROMOTOR_DIST)
genepromotors = Ensembl.ReversePromotorMapping(
reader = csv.reader(open(infile), delimiter="\t")
writer = csv.writer(open(outfile, "w"), delimiter="\t")
###
TSS_TTS_Distance = 5000
TTS_TTS_Distance_Human = str(TSS_TTS_Distance / 1000) + "kb"
Small_TSS_TTS_Distance = 1000
Small_TTS_TTS_Distance_Human = str(Small_TSS_TTS_Distance / 1000) + "kb"
# load data
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"))
affyannotation = NetAffxAnnotation()
paddedGenes = Ensembl.ReverseGeneMapping(genedata, tssPadding=TSS_TTS_Distance)
