# takes in a csv file of intervals and tells us some stuff about them
for o, a in opts:
if o == "-i":
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([
# 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(
"~/mount/publicdata/hg19/Repeats/UCSC_HG19_LINEs.bed"),
defaultkeys=["chrom", "chromStart", "chromEnd", "name", "strand"])
sINEs = ExtendedBed(
os.path.expanduser(
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)
# UCSC table browser - Expression & Regulation - CpG Islands
# Download all columns with exception of "bin"
cpgIslands = ExtendedBed(
os.path.expanduser("/mnt/50tb/publicdata/" + assembly +
"/CpGIslands/cpgislands.bed"))
# UCSC table browser - Mapping and Sequencing - Chromosome Bands
# Download all columns with exception of "gieStain"
gBanding = ExtendedBed(os.path.expanduser("/mnt/50tb/publicdata/" + assembly +
"/G-Banding/cytogenetic.map.bed"),
defaultkeys=["chrm", "start", "stop", "band"],
forcekeys=True)
chromosomeEnds = ChromosomeEnds(assembly)
###
###
###
from bed.treatment import ExtendedBed
from sam.SamFormat import SAMFile
import os
import sys
lads = ExtendedBed(
os.path.expanduser("~/mount/privatedata/non-Adams/donahue.greg/LADs.bed"))
alignments = SAMFile(os.path.expanduser(sys.argv[1]))
numbInLAD = 0
numbNotInLAD = 0
currentSeq = None
def previousKey(key, isin, isnotin):
print key, isin, isnotin, isin / float(isin + isnotin)
for samEntry in alignments:
if samEntry.chrm == "*":
continue
if currentSeq != None and samEntry.key != currentSeq:
# print the stats on the previous key
previousKey(currentSeq, numbInLAD, numbNotInLAD)
numbInLAD = 0
numbNotInLAD = 0
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:
affyFC = float(affyCSV[affy][affyfccol])
affylogFC = math.log(affyFC) if affyFC > 0.0 else math.log(
abs(affyFC)) * -1.0
affyEnsemblLogFCs[ensembls[0]].append(affylogFC)
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)
def isUpstream(distance, strand):
if strand == "+":
return 'Y' if distance >= 0 else 'N'
elif strand == "-":
return 'Y' if distance <= 0 else 'N'
else:
# wtf went wrong here
exit(-1)
# 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"))
affyannotation = NetAffxAnnotation()
paddedGenes = Ensembl.ReverseGeneMapping(genedata, tssPadding=TSS_TTS_Distance)
# store full mapping here for the end
geneToMethProbeMapping = collections.defaultdict(list)
geneToAffyProbeMapping = collections.defaultdict(list)
def isUpstream(distance, strand):
assert strand in ['+', '-']
if strand == "+":
return distance >= 0