def loadGFF_transcript(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
begin=int(fields[3])-1
end=int(fields[4])
rex=Rex()
if(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
transcriptBeginEnd[transcriptId]=[begin,end]
strand=fields[6]
transcriptExtraFields=""
for i in range(8,len(fields)):
transcriptExtraFields+=fields[i]+" "
transcript=transcripts.get(transcriptId,None)
if(transcript is None):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder;
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
transcript.setBegin(begin)
transcript.setEnd(end)
geneId=None
if(rex.find("genegrp=(\S+)",line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*\"?([^\s\;"]+)\"?',line)):
geneId=rex[1]
if(not geneId): raise Exception("can't parse GTF: "+line)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(not gene): genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
gene.addTranscript(transcript)
transcript.extraFields=transcriptExtraFields
def parseRecord(self, fields):
if (len(fields) > 9):
raise Exception("too many fields in GFF3 record" +
"\t".join(fields))
(substrate, source, type, begin, end, score, strand, frame,
extra) = fields
extra = extra.rstrip()
extraFields = extra.split(";")
extraHash = {}
rex = Rex()
for field in extraFields:
if (not rex.find("(.+)=(.+)", field)):
raise Exception("Can't parse GFF3 field: " + field)
key = rex[1]
value = rex[2]
extraHash[key] = value
rec = {
"substrate": substrate,
"source": source,
"type": type,
"begin": int(begin) - 1,
"end": int(end),
"score": score,
"strand": strand,
"frame": frame,
"extra": extraHash
}
return rec
def loadGFF_UTR(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
exonBegin=int(fields[3])-1
exonEnd=int(fields[4])
exonScore=fields[5]
strand=fields[6]
frame=fields[7]
transcriptId=None
rex=Rex()
if(rex.find('transgrp[:=]\s*(\S+)',line)): transcriptId=rex[1]
elif(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
elif(rex.find('Parent=([^;,\s]+)',line)): transcriptId=rex[1]
geneId=None
if(rex.find('genegrp=(\S+)',line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*"?([^\s\;"]+)"?',line)): geneId=rex[1]
if(transcriptId is None): transcriptId=geneId
if(geneId is None): geneId=transcriptId
if(transcriptId is None):
raise Exception(line+" : no transcript ID found")
if(rex.find("(\S+);$",transcriptId)): transcriptId=rex[1]
if(rex.find("(\S+);$",geneId)): geneId=rex[1]
extra=""
for i in range(8,len(fields)): extra+=fields[i]+" "
if(exonBegin>exonEnd): (exonBegin,exonEnd)=(exonEnd,exonBegin)
transcript=transcripts.get(transcriptId,None)
if(not transcript):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
if(transcriptBeginEnd.get(transcriptId,None) is not None):
(begin,end)=transcriptBeginEnd[transcriptId]
transcript.setBegin(begin)
transcript.setEnd(end)
else:
transcript.setBegin(exonBegin)
transcript.setEnd(exonEnd)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(gene is None):
genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
exon=Exon(exonBegin,exonEnd,transcript)
exon.extraFields=extra
if(transcript.rawExons is not None):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.rawExons.append(exon)
elif(not transcript.exonOverlapsExon(exon)):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.UTR.append(exon) # OK -- we sort later
gene.addTranscript(transcript)
def loadGFF_UTR(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
exonBegin=int(fields[3])-1
exonEnd=int(fields[4])
exonScore=fields[5]
strand=fields[6]
frame=fields[7]
transcriptId=None
rex=Rex()
if(rex.find('transgrp[:=]\s*(\S+)',line)): transcriptId=rex[1]
elif(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
elif(rex.find('Parent=([^;,\s]+)',line)): transcriptId=rex[1]
geneId=None
if(rex.find('genegrp=(\S+)',line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*"?([^\s\;"]+)"?',line)): geneId=rex[1]
if(transcriptId is None): transcriptId=geneId
if(geneId is None): geneId=transcriptId
if(transcriptId is None):
raise Exception(line+" : no transcript ID found")
if(rex.find("(\S+);$",transcriptId)): transcriptId=rex[1]
if(rex.find("(\S+);$",geneId)): geneId=rex[1]
extra=""
for i in range(8,len(fields)): extra+=fields[i]+" "
if(exonBegin>exonEnd): (exonBegin,exonEnd)=(exonEnd,exonBegin)
transcript=transcripts.get(transcriptId,None)
if(not transcript):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
if(transcriptBeginEnd.find(transcriptId,None) is not None):
(begin,end)=transcriptBeginEnd[transcriptId]
transcript.setBegin(begin)
transcript.setEnd(end)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(gene is None):
genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
exon=Exon(exonBegin,exonEnd,transcript)
exon.extraFields=extra
if(transcript.rawExons is not None):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.rawExons.append(exon)
elif(not transcript.exonOverlapsExon(exon)):
exon.frame=frame
exon.score=exonScore
exon.type=fields[2]
transcript.UTR.append(exon) # OK -- we sort later
gene.addTranscript(transcript)
def parseRecord(self,fields):
if(len(fields)>9):
raise Exception("too many fields in GFF3 record"+"\t".join(fields))
(substrate,source,type,begin,end,score,strand,frame,extra)=fields
extra=extra.rstrip()
extraFields=extra.split(";")
extraHash={}
rex=Rex()
for field in extraFields:
if(not rex.find("(.+)=(.+)",field)):
raise Exception("Can't parse GFF3 field: "+field)
key=rex[1]; value=rex[2]
extraHash[key]=value
rec={"substrate":substrate,
"source":source,
"type":type,
"begin":begin,
"end":end,
"score":score,
"strand":strand,
"frame":frame,
"extra":extraHash}
return rec
def crear_aldea(nombre, num_rex, num_spinosaurus, num_triceraptors):
a = Aldea(nombre)
for i in range(num_rex):
a.add_dinosaurio(
Rex("r" + str(i), 1000, random.randrange(-200, 200), a))
for i in range(num_spinosaurus):
a.add_dinosaurio(
Spinosaurus("s" + str(i), 1000, random.randrange(-200, 200),
a))
for i in range(num_triceraptors):
a.add_dinosaurio(
Triceraptors("t" + str(i), 1000, random.randrange(-200, 200),
a))
return a
def loadGFF_transcript(self,fields,line,transcriptBeginEnd,GFF,
transcripts,readOrder,genes):
begin=int(fields[3])-1
end=int(fields[4])
rex=Rex()
if(rex.find('transcript_id[:=]?\s*"?([^\s";]+)"?',line)):
transcriptId=rex[1]
transcriptBeginEnd[transcriptId]=[begin,end]
strand=fields[6]
score=fields[5]
transcriptExtraFields=""
for i in range(8,len(fields)):
transcriptExtraFields+=fields[i]+" "
transcript=transcripts.get(transcriptId,None)
if(transcript is None):
transcripts[transcriptId]=transcript= \
Transcript(transcriptId,strand)
transcript.setStopCodons(self.stopCodons)
transcript.readOrder=readOrder;
readOrder+=1
transcript.substrate=fields[0]
transcript.source=fields[1]
transcript.setBegin(begin)
transcript.setEnd(end)
if(transcript.score is None and
score!="."): transcript.score=float(score)
geneId=None
if(rex.find("genegrp=(\S+)",line)): geneId=rex[1]
elif(rex.find('gene_id[:=]?\s*\"?([^\s\;"]+)\"?',line)):
geneId=rex[1]
if(not geneId): raise Exception("can't parse GTF: "+line)
transcript.geneId=geneId
gene=genes.get(geneId,None)
if(not gene): genes[geneId]=gene=Gene(); gene.setId(geneId)
transcript.setGene(gene)
gene.addTranscript(transcript)
transcript.extraFields=transcriptExtraFields
#!/usr/bin/env python #========================================================================= # This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import os from Rex import Rex rex=Rex() COMBINED="/home/bmajoros/1000G/assembly/combined" OUTDIR="/home/bmajoros/1000G/assembly/cryptic" MIN_COUNT=3 EXPRESSED="/home/bmajoros/1000G/assembly/expressed.txt" def loadExpressed(filename): hash={} with open(filename,"rt") as fh: for line in fh: fields=line.split() (gene,transcript,fpkm,SS)=fields if(rex.find("ALT\d+_(\S+)",transcript)): ### transcript=rex[1] ### hash[transcript]=True return hash
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public
# License (GPL) version 3, as described at www.opensource.org.
#=========================================================================
from __future__ import (absolute_import, division, print_function,
unicode_literals, generators, nested_scopes,
with_statement)
from builtins import (bytes, dict, int, list, object, range, str, ascii, chr,
hex, input, next, oct, open, pow, round, super, filter,
map, zip)
# The above imports should allow this program to run in both Python 2 and
# Python 3. You might need to update your version of module "future".
import sys
import ProgramName
import gzip
from Rex import Rex
rex = Rex()
from scipy import stats
from statsmodels.stats.multitest import multipletests
def getCounts(filename, variants, MIN_COUNT):
counts = {}
with open(filename, "rt") as IN:
for line in IN:
fields = line.rstrip().split()
if (len(fields) != 7): continue
(id, chr, pos, ref, alt, refCount, altCount) = fields
refCount = int(refCount)
altCount = int(altCount)
if (refCount + altCount < MIN_COUNT): continue
counts[id] = [refCount, altCount]
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2017 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys import os import ProgramName from SlurmWriter import SlurmWriter from Rex import Rex rex=Rex() ROOT="/home/bmajoros/PopSTARR/graham" MEM=50000 NICE=500 jobName="TRIM" maxParallel=1000 THREADS=31 TRIMMOMATIC="java -jar /data/reddylab/software/Trimmomatic-0.33/Trimmomatic-0.33/trimmomatic-0.33.jar PE" #========================================================================= # main() #========================================================================= if(len(sys.argv)!=5): exit(ProgramName.get()+" <adapters.fasta> <fastq-in> <fastq-out> <full-path-to-slurms>\n") (adaptersFasta,fastqIn,fastqOut,slurmDir)=sys.argv[1:]
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys from Transcript import Transcript from Interval import Interval from GffTranscriptReader import GffTranscriptReader from Rex import Rex rex=Rex() if(len(sys.argv)!=8): exit(sys.argv[0]+ " <indiv> <hap> <in.broken-sites> <junctions.bed> <in.gff> <in.readcounts> <all-broken-sites.txt>") (indiv,hap,infile,junctionsFile,gffFile,readCountsFile,masterFile)=sys.argv[1:] #============================= main() ================================= # Read the readcounts file totalMappedReads=None readCounts={} with open(readCountsFile,"rt") as IN: while(True): line=IN.readline() if(line==""): break
#!/usr/bin/env python #========================================================================= # This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys from Rex import Rex rex=Rex() if(len(sys.argv)!=2): exit(sys.argv[0]+" <p-values.txt>") infile=sys.argv[1] values=[] with open(infile,"rt") as fh: for line in fh: if(rex.find("(\S+\d\S+)",line)): values.append(float(rex[1])) values.sort() L=len(values) qValues=(0.1,0.05,0.01,0.005,0.001) for q in qValues: bestP=None
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2018 William H. Majoros ([email protected]) #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys import os import math import ProgramName from Rex import Rex rex=Rex() import TempFilename import getopt WARMUP=1000 ALPHA=0.05 STDERR=TempFilename.generate(".stderr") INPUT_FILE=TempFilename.generate(".staninputs") INIT_FILE=TempFilename.generate(".staninit") OUTPUT_TEMP=TempFilename.generate(".stanoutputs") def printFields(fields,hFile): numFields=len(fields) for i in range(7,numFields): print(i-6,"=",fields[i],sep="",end="",file=hFile) if(i<numFields-1): print("\t",end="",file=hFile)
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys from FastaReader import FastaReader from FastaWriter import FastaWriter from GffTranscriptReader import GffTranscriptReader from Rex import Rex rex=Rex() # Process command line if(len(sys.argv)!=4): exit(sys.argv[0]+" <in.fasta> <in.gff> <out.fasta>") (fastaFile,gffFile,outFile)=sys.argv[1:] # Read GFF reader=GffTranscriptReader() hash=reader.hashBySubstrate(gffFile) # Open output file OUT=open(outFile,"wt") writer=FastaWriter() # Process each substrate in the FASTA file reader=FastaReader(fastaFile)
#=========================================================================
from __future__ import (absolute_import, division, print_function,
unicode_literals, generators, nested_scopes,
with_statement)
from builtins import (bytes, dict, int, list, object, range, str, ascii, chr,
hex, input, next, oct, open, pow, round, super, filter,
map, zip)
# The above imports should allow this program to run in both Python 2 and
# Python 3. You might need to update your version of module "future".
import sys
import ProgramName
from FastaReader import FastaReader
from FastaWriter import FastaWriter
from Rex import Rex
rex = Rex()
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 3):
exit(ProgramName.get() + " <in.fasta> <out.fasta>\n")
(infile, outfile) = sys.argv[1:]
OUT = open(outfile, "wt")
writer = FastaWriter()
reader = FastaReader(infile)
while (True):
(defline, seq) = reader.nextSequence()
if (not defline): break
if (not rex.find(">chr", defline)): continue
#!/usr/bin/env python #========================================================================= # This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". from Rex import Rex rex=Rex() MIN_READS=3 ASSEMBLY="/home/bmajoros/1000G/assembly" READS=ASSEMBLY+"/reads.txt-rev3" EXPRESSED=ASSEMBLY+"/expressed.txt" expressed={} with open(EXPRESSED,"rt") as fh: for line in fh: fields=line.split() if(len(fields)!=4): continue (gene,trans,meanFPKM,SS)=fields expressed[trans]=True hasAlts={} supportedAlts={} with open(READS,"rt") as fh:
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys from Transcript import Transcript from Interval import Interval from GffTranscriptReader import GffTranscriptReader from Rex import Rex rex=Rex() if(len(sys.argv)!=5): exit(sys.argv[0]+ " <in.broken-sites> <junctions.bed> <in.gff> <in.readcounts>") (infile,junctionsFile,gffFile,readCountsFile)=sys.argv[1:] #============================= main() ================================= # Read the readcounts file totalMappedReads=None readCounts={} with open(readCountsFile,"rt") as IN: while(True): line=IN.readline() if(line==""): break
#========================================================================= # This is OPEN SOURCE SOFTWARE governed by the Gnu General Public # License (GPL) version 3, as described at www.opensource.org. # Copyright (C)2016 William H. Majoros ([email protected]). #========================================================================= from __future__ import (absolute_import, division, print_function, unicode_literals, generators, nested_scopes, with_statement) from builtins import (bytes, dict, int, list, object, range, str, ascii, chr, hex, input, next, oct, open, pow, round, super, filter, map, zip) # The above imports should allow this program to run in both Python 2 and # Python 3. You might need to update your version of module "future". import sys import os import glob from Rex import Rex rex=Rex() if(len(sys.argv)!=2): exit(sys.argv[0]+" <dir>") directory=sys.argv[1] files=glob.glob(directory+"/*.fastb") for file in files: with open("tmp.fastb","wt") as OUT: with open(file,"rt") as IN: for line in IN: if(rex.find(">\S+",line)): OUT.write(">dna\n") else: OUT.write(line) os.system("mv tmp.fastb "+file)
#!/usr/bin/env python
#=========================================================================
# This is OPEN SOURCE SOFTWARE governed by the Gnu General Public
# License (GPL) version 3, as described at www.opensource.org.
#=========================================================================
from __future__ import (absolute_import, division, print_function,
unicode_literals, generators, nested_scopes,
with_statement)
from builtins import (bytes, dict, int, list, object, range, str, ascii, chr,
hex, input, next, oct, open, pow, round, super, filter,
map, zip)
# The above imports should allow this program to run in both Python 2 and
# Python 3. You might need to update your version of module "future".
import sys
from Rex import Rex
rex = Rex()
#=========================================================================
# main()
#=========================================================================
counts = {}
for line in sys.stdin:
fields = line.rstrip().split()
id = fields[0]
alleles = counts.get(id, None)
if (alleles is None): alleles = counts[id] = {}
for field in fields[1:]:
if (not rex.find("(\S+)=(\d+)", field)):
raise Exception("can't parse field: " + field)
allele = rex[1]
count = int(rex[2])
with_statement)
from builtins import (bytes, dict, int, list, object, range, str, ascii, chr,
hex, input, next, oct, open, pow, round, super, filter,
map, zip)
# The above imports should allow this program to run in both Python 2 and
# Python 3. You might need to update your version of module "future".
import sys
import ProgramName
import gzip
import math
import numpy as np
from sklearn import linear_model
import statsmodels.api as sm
from scipy import stats
from Rex import Rex
rex = Rex()
MAX_P_ADJ = 1.0
MAX_P = 0.05
NUM_COVARIATES = 11
SKIP_NA = True
BASE = "/home/bmajoros/PopSTARR/sarah"
#EFFECTS=BASE+"/test-lucif-aug28-chr10.txt"
EFFECTS = BASE + "/test-sarah-beta-2sided.txt"
VCF = BASE + "/vcf"
PHENOTYPES = BASE + "/phenotypes.txt"
CHROMS = ("chr10", "chr11", "chr21", "chr5", "chr8")
CENTERS = ("A", "E", "F", "K", "N", "P", "Q")
CENTER_CODES = {}
nextCode = 0
