recs.append(rec)
return recs
def justin(recs, ALPHA):
n = len(recs)
sumP = 0
keep = 0
for i in range(n):
sumP += 1 - recs[i].Preg
recs[i].fdr = sumP / float(i + 1)
if (recs[i].fdr > ALPHA): break
else: recs[i].sig = "SIGNIFICANT"
keep = i
return keep
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 3):
exit(ProgramName.get() + " <predictions.txt> <fdr>\n")
(infile, fdr) = sys.argv[1:]
fdr = float(fdr)
preds = loadPredictions(infile)
preds.sort(key=lambda x: 1 - x.Preg)
keep = justin(preds, fdr)
for rec in preds:
rec.print()
def analyze(fields,greaterLess,threshold,threshold2):
array=toFloat(fields)
n=len(array)
count=None
if(greaterLess=="less"): count=countLess(array,threshold)
elif(greaterLess=="greater"): count=countGreater(array,threshold)
else: count=countTwoTailed(array,threshold,threshold2)
P=float(count)/float(n)
return P
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)!=4):
exit(ProgramName.get()+" <thetas.txt> <greater|less|twotailed> <threshold>\n")
(filename,greaterLess,threshold)=sys.argv[1:]
if(greaterLess not in VALID_COMP):
exit("comparison must be one of greater, less, or twotailed")
threshold=float(threshold)
if(threshold<0): exit("threshold cannot be negative")
threshold2=None
if(greaterLess=="twotailed"):
if(threshold==0.0): exit("threshold cannot be 0 for twotailed")
threshold2=float(1.0/threshold)
if(threshold>threshold2): (threshold,threshold2)=(threshold2,threshold)
with open(filename,"rt") as IN:
for line in IN:
fields=line.rstrip().split()
P=analyze(fields,greaterLess,threshold,threshold2)
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:]
files=os.listdir(fastqIn)
writer=SlurmWriter()
for file in files:
if(not rex.find("(.*[_-])R1([_-].*)\.fastq.gz",file)): continue
file1=file
file2=rex[1]+"R2"+rex[2]+".fastq.gz"
cmd=TRIMMOMATIC+" -threads "+str(THREADS)+" -phred33 "+\
fastqIn+"/"+file1+" "+fastqIn+"/"+file2+" "+\
fastqOut+"/"+rex[1]+"_FWD_paired.fq.gz "+\
fastqOut+"/"+rex[1]+"_FWD_unpaired.fq.gz "+\
fastqOut+"/"+rex[1]+"_REV_paired.fq.gz "+\
fastqOut+"/"+rex[1]+"_REV_unpaired.fq.gz "+\
"ILLUMINACLIP:"+adaptersFasta+\
for i in range(n):
print(" (neuron ",nextIndex," (layer ",whichLayer,")",
" (transfer sigmoid) (output)",sep="")
Shuffler.shuffleArray(prevLayer)
inputs=prevLayer[:fanIn]
for j in inputs:
print(" (input (from ",j,") (weight 0))",sep="")
print(" )")
indices.append(nextIndex)
nextIndex+=1
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)!=3):
exit(ProgramName.get()+" <layer-sizes:1000,300,30,1> <fan-ins:10,5,30>\n")
(layerSizes,fanIns)=sys.argv[1:]
layerSizes=[int(x) for x in layerSizes.split(",")]
fanIns=[int(x) for x in fanIns.split(",")]
numLayers=len(layerSizes)
if(len(fanIns)!=numLayers-1): raise Exception("number of fan-ins is wrong")
nextIndex=0
prevLayer=None
print("(network")
for layer in range(numLayers):
if(layer==0):
prevLayer=generateInputLayer(layerSizes[0],nextIndex,layer)
elif(layer<numLayers-1):
prevLayer=generateHiddenLayer(layerSizes[layer],nextIndex,layer,
#!/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) import random import ProgramName import sys from FastaWriter import FastaWriter if (len(sys.argv) != 3): exit(ProgramName.get() + " <length> <id>") L = int(sys.argv[1]) id = sys.argv[2] seq = "" alphabet = ("A", "C", "G", "T") for i in range(L): index = int(random.random() * 4) nuc = alphabet[index] seq += nuc writer = FastaWriter() writer.addToFasta(">" + id, seq, sys.stdout)
#!/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) import random import ProgramName import sys from FastaWriter import FastaWriter if(len(sys.argv)!=3): exit(ProgramName.get()+" <length> <id>") L=int(sys.argv[1]) id=sys.argv[2] seq="" alphabet=("A","C","G","T") for i in range(L): index=int(random.random()*4) nuc=alphabet[index] seq+=nuc writer=FastaWriter() writer.addToFasta(">"+id,seq,sys.stdout)
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
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 2):
exit(ProgramName.get() + " <in.vcf.gz>\n")
(infile, ) = sys.argv[1:]
variants = {}
for line in gzip.open(infile):
line = line.decode("utf-8").rstrip()
if (len(line) > 0 and line[0] == "#"):
print(line)
continue
fields = line.split("\t")
if (len(fields) >= 9):
if (len(fields[0]) < 3 or fields[0][:3] != "chr"):
fields[0] = "chr" + fields[0]
if (fields[2] == "."): fields[2] = fields[0] + "@" + fields[1]
line = ""
for field in fields[:len(fields) - 1]:
reduction=0
increase=0
for i in range(n):
if(thetas[i]<maxLeft): reduction+=1
if(thetas[i]>minRight): increase+=1
leftP=float(reduction)/float(n)
rightP=float(increase)/float(n)
Preg=leftP if leftP>rightP else rightP
print(ID,median,CI_left,CI_right,Preg,sep="\t")
#=========================================================================
# main()
#=========================================================================
(options,args)=getopt.getopt(sys.argv[1:],"s:t:")
if(len(args)!=6):
exit(ProgramName.get()+" [-s stanfile] [-t thetafile] <model> <min-effect> <input.txt> <output.txt> <#MCMC-samples> <firstVariant-lastVariant>\n -s = save raw STAN file\n -t = save theta samples\n variant range is zero-based and inclusive\n min-effect (lambda) must be >= 1\n")
(model,minEffect,inFile,outfile,numSamples,numVariants)=args
stanFile=None
thetaFile=None
for pair in options:
(key,value)=pair
if(key=="-s"): stanFile=value
if(key=="-t"): thetaFile=value
if(not rex.find("(\d+)-(\d+)",numVariants)):
exit(numVariants+": specify range of variants: first-last")
firstIndex=int(rex[1])
lastIndex=int(rex[2])
minEffect=float(minEffect)
if(minEffect<1): raise Exception("Min-effect must be >= 1")
THETA=None
if(thetaFile is not None): THETA=open(thetaFile,"wt")
#!/usr/bin/env python
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)
import ProgramName
import sys
import os
from Interval import Interval
from ConfigFile import ConfigFile
from SummaryStats import SummaryStats
import random
# Process command line
name=ProgramName.get();
if(len(sys.argv)!=3):
print(name," <parm1> <parm2>")
exit()
parm1=sys.argv[1]
parm2=sys.argv[2]
print(parm1, parm2)
print ("Hello, world\n")
for i in range(1,10):
print (i,end="")
print("\n")
i1=Interval(1,10)
i2=Interval(1.5,7.3)
sub=i1.minus(i2)
def toFloat(fields):
array = []
for field in fields:
array.append(float(field))
return array
def analyze(fields, lower, upper):
array = toFloat(fields)
npArray = np.array(array)
a = np.percentile(npArray, lower * 100)
b = np.percentile(npArray, upper * 100)
return (a, b)
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 3):
exit(ProgramName.get() + " <thetas.txt> <alpha>\n")
(filename, alpha) = sys.argv[1:]
alpha = float(alpha)
lower = alpha / 2.0
upper = 1.0 - lower
with open(filename, "rt") as IN:
for line in IN:
fields = line.rstrip().split()
(a, b) = analyze(fields, lower, upper)
print(a, b, sep="\t")
c = bases[i]
if (c in ACGT):
if (index >= len(qual)):
exit(bases + "\n" + qual + "\n" + str(index) + "\t" + c)
q = qual[index]
#print(c,q,ord(q),sep="\t")
if (QUALITY[ord(q)] >= MIN_QUAL): counts[c] = counts.get(c, 0) + 1
index += 1
return counts
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 4):
exit(ProgramName.get() + " <sorted.vcf.gz> <pileup.txt> <min-quality>\n")
(vcf, pileup, MIN_QUAL) = sys.argv[1:]
MIN_QUAL = int(MIN_QUAL)
# Process the VCF file to get the ref and alt alleles
variants = {}
for line in gzip.open(vcf):
line = line.decode("utf-8")
if (len(line) > 0 and line[0] == "#"): continue
fields = line.rstrip().split()
if (len(fields) < 9): continue
(chr, pos, id, ref, alt, x, Pass, flags, GT) = fields[:9]
altFields = alt.split(",")
alt = altFields[0] # Keeping only the first alternate allele
#if(id=="."): continue
if (id == "."): id = chr + "@" + pos
#!/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) import os import sys import ProgramName # Process command line name=ProgramName.get(); if(len(sys.argv)!=2): sys.exit(name+" <classname>") className=sys.argv[1] # Write file filename=className+".py" if(os.path.exists(filename)): sys.exit(filename+" exists"); fh=open(filename,"w") header="\n".join(["#=========================================================================", "# 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,",
ID = IDs[i]
phenotypeRec = phenotypes.get(ID, None)
if (phenotypeRec is None): continue
phenotype = phenotypeRec[phenotypeID]
point = [phenotype]
point.extend(phenotypeRec[5:])
points.append(point)
#print(points)
#exit()
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 2):
exit(ProgramName.get() + " <phenotype:1-5>\n")
(phenotypeID, ) = sys.argv[1:]
phenotypeID = int(phenotypeID) - 1
if (phenotypeID < 0): exit("phenotype must be 1-5")
phenotypes = loadPhenotypes(PHENOTYPES)
effects = loadEffects(EFFECTS)
IDs = None
points = []
initialized = False
predictorNum = 1
for chrom in CHROMS:
vcf = VCF + "/" + chrom + "/" + chrom + ".vcf.gz"
#print("processing",vcf,flush=True)
IN = gzip.open(vcf, "rt")
for line in IN:
#!/usr/bin/env python #========================================================================= # Copyright (C)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 ProgramName #========================================================================= # main() #========================================================================= if (len(sys.argv) != 2): exit(ProgramName.get() + " <>\n") () = sys.argv[1:]
#!/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. # Author: 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 ProgramName from EssexParser import EssexParser #========================================================================= # main() #========================================================================= if (len(sys.argv) != 2): exit(ProgramName.get() + " <in.essex>\n") (infile, ) = sys.argv[1:] parser = EssexParser(infile) while (True): tree = parser.nextElem() if (tree is None): break tree.print(sys.stdout)
def parseBases(bases):
bases = removeIndels(bases)
bases = bases.upper()
counts = {}
for c in bases:
if (c in ACGT): counts[c] = counts.get(c, 0) + 1
return counts
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 3):
exit(ProgramName.get() + " <sorted.vcf.gz> <pileup.txt>\n")
(vcf, pileup) = sys.argv[1:]
# Process the VCF file to get the ref and alt alleles
variants = {}
for line in gzip.open(vcf):
line = line.decode("utf-8")
if (len(line) > 0 and line[0] == "#"): continue
fields = line.rstrip().split()
if (len(fields) < 9): continue
(chr, pos, id, ref, alt, x, Pass, flags, GT) = fields[:9]
altFields = alt.split(",")
alt = altFields[0] # Keeping only the first alternate allele
if (id == "."): continue
if (variants.get(chr, None) is None): variants[chr] = []
variants[chr].append(Variant(int(pos), id, ref, alt))
for line in IN:
fields = line.rstrip().split()
if (len(fields) != 12): continue
(chrom, pos, variant, P, Padj, effect, DNAref, DNAalt, RNAref,
RNAalt, ref, alt) = fields
rnaFreq = float(RNAalt) / float(RNAref + RNAalt)
dnaFreq = float(DNAalt) / float(DNAref + DNAalt)
hash[variant] = (rnaFreq, dnaFreq)
return hash
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 3):
exit(ProgramName.get() + " <bowtie.txt> <hisat.txt>\n")
(bowtieFile, hisatFile) = sys.argv[1:]
bowtie = load(bowtieFile)
hisat = load(hisatFile)
keys = bowtie.keys()
rnaGreater = 0
rnaLess = 0
rnaSame = 0
dnaGreater = 0
dnaLess = 0
dnaSame = 0
agree = 0
disagree = 0
for variant in keys:
if (hisat.get(variant, None) == None): continue
bestDiff=None
bestI=None
for i in range(n):
x=legal[i]
diff=abs(value-x)
if(best is None or diff<bestDiff):
best=x
bestDiff=diff
bestI=i
return (best,bestI)
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)!=5):
exit("\n"+ProgramName.get()+" <FDR> <effect> <maf> <depth>\n\
FDR is one of 0.1, 0.05, 0.1\n\
effect is ratio of transcriptional reates for alt versus ref allele\n\
")
(fdr,theta,maf,depth)=sys.argv[1:]
fdr=float(fdr)
theta=float(theta)
maf=float(maf)
depth=int(depth)
# Check that parms are legal
if(fdr!=0.1 and fdr!=0.05 and fdr!=0.01):
exit("FDR must be one of 0.1, 0.05, 0.01")
if(theta<0): exit("effect must be > 0")
if(maf<=0 or maf>=1): exit("maf must be between 0 and 1")
if(depth<=0): exit("depth must be > 0")
#=========================================================================
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 StanParser import StanParser
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)<3):
exit(ProgramName.get()+" <infile.txt> <var1> <var2> ...\n")
infile=sys.argv[1]
variables=sys.argv[2:]
parser=StanParser(infile)
#(median,mean,SD,min,max)=parser.getSummary(variable)
#print("# posterior median=",median,sep="")
samplesByVar=[]
n=0
for var in variables:
samples=parser.getVariable(var)
samplesByVar.append(samples)
n=len(samples)
for i in range(n):
line=[]
for sample in samplesByVar: line.append(str(sample[i]))
# 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 ProgramName from BetaBinomial import BetaBinomial #========================================================================= # main() #========================================================================= if (len(sys.argv) != 5): exit(ProgramName.get() + " <alpha> <beta> <n> <k>\n") (alpha, beta, n, k) = sys.argv[1:] alpha = int(alpha) beta = int(beta) n = int(n) k = int(k) bb = BetaBinomial() P = bb.P(alpha, beta, n, k) print(P)
#!/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. # Author: 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 ProgramName #========================================================================= # main() #========================================================================= if (len(sys.argv) != 2): exit(ProgramName.get() + " <infile.txt>\n") (infile, ) = sys.argv[1:] lines = [] with open(infile, "rt") as IN: for line in IN: lines.append(line) for i in range(len(lines) - 1, -1, -1): print(lines[i], end="")
#!/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) from Fastb import Fastb import ProgramName import sys if (len(sys.argv) != 2): sys.exit(ProgramName.get() + " in.fastb") filename = sys.argv[1] fastb = Fastb(filename) numTracks = fastb.numTracks() for i in range(numTracks): track = fastb.getIthTrack(i) L = track.getLength() id = track.getID() print(id + "\t" + str(L))
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
writer.addToFasta(defline, seq, OUT)
OUT.close()
interval.begin=interval.intCenter()
interval.end=interval.begin+1
interval.type="peak"
interval.dir=direction
array.append(interval)
def loadPeaks(bedDir,timepoint,expression):
addPeaks(bedDir,timepoint,"up",expression)
addPeaks(bedDir,timepoint,"down",expression)
addPeaks(bedDir,timepoint,"nonresp",expression)
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)!=3):
exit(ProgramName.get()+" <bed-dir> <t8> \n")
(bedDir,timepoint)=sys.argv[1:]
print("loading TSSs...",file=sys.stderr,flush=True)
tssHash=loadTSS()
print("loading expression data...",file=sys.stderr,flush=True)
expression=loadExpression(timepoint,tssHash)
print("loading peaks...",file=sys.stderr,flush=True)
#upPeaks=BedReader.readAll(bedDir+"/"+timepoint+"_up.bed")
#downPeaks=BedReader.readAll(bedDir+"/"+timepoint+"_down.bed")
#samePeaks=BedReader.readAll(bedDir+"/"+timepoint+"_nonresp.bed")
loadPeaks(bedDir,timepoint,expression)
print("loading Hi-C data...",file=sys.stderr,flush=True)
#!/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) from Fastb import Fastb import ProgramName import sys if(len(sys.argv)!=2): sys.exit(ProgramName.get()+" in.fastb") filename=sys.argv[1] fastb=Fastb(filename) numTracks=fastb.numTracks() for i in range(numTracks): track=fastb.getIthTrack(i) L=track.getLength() id=track.getID() print(id+"\t"+str(L))
# Python 3. You might need to update your version of module "future".
import sys
import ProgramName
import gzip
from Pipe import Pipe
import TempFilename
HEADERFILE = TempFilename.generate(".header")
SORTEDFILE = TempFilename.generate(".sorted")
#=========================================================================
# main()
#=========================================================================
if (len(sys.argv) != 4):
exit(
ProgramName.get() +
" in.mtx.gz column out.mtx.gz\n where column = 1-based field index\n"
)
(infile, index, outfile) = sys.argv[1:]
OUT = open(HEADERFILE, "wt")
numHeader = 1
with gzip.open(infile, "rt") as IN:
for line in IN:
if (len(line) == 0): raise Exception("unexpected empty line")
if (line[0] == "%"):
numHeader += 1
print(line, file=OUT, end="")
else:
print(line, file=OUT, end="")
break
newThisObjects=[]; newOtherObjects=[]
for obj in thisObjects:
if(obj.type=="gene"): newOtherObjects.append(obj)
else: newThisObjects.append(obj)
for obj in otherObjects:
if(obj.type=="gene"): newThisObjects.append(obj)
else: newOtherObjects.append(obj)
thisRec.objects=newThisObjects
otherRec.objects=newOtherObjects
#=========================================================================
# main()
#=========================================================================
if(len(sys.argv)!=4):
exit(ProgramName.get()+" <bed-dir> <t8> <randomize:0|1>\n")
(bedDir,timepoint,WANT_RANDOM)=sys.argv[1:]
WANT_RANDOM=int(WANT_RANDOM)
print("loading TSSs...",file=sys.stderr,flush=True)
tssHash=loadTSS()
print("loading expression data...",file=sys.stderr,flush=True)
expression=loadExpression(timepoint,tssHash)
print("loading peaks...",file=sys.stderr,flush=True)
loadPeaks(bedDir,timepoint,expression)
print("loading Hi-C data...",file=sys.stderr,flush=True)
loadHiC(expression)