def tophatBam_BigWig(project_root):
"""
input: project root. real input is the accepted_hits.bam
structure: the project root/tophat/sampleName/accepted_bam
:param project_root:
:return: bigwig file for making track
"""
# create track/, track_bin/ , create file UCSC_trackTxt.txt
track_dir = os.path.join(project_root, "track")
if not os.path.exists(track_dir):
os.mkdir(track_dir)
track_bin = os.path.join(project_root, "track_bin")
if not os.path.exists(track_bin):
os.mkdir(track_bin)
# find accepted_hits.bam files
bams = os.path.join(project_root, "tophat/*", "accepted_hits.bam")
for bam in glob.glob(bams):
sample_name = bam.split("/")[
-2] # get sample name, one level up from .bam
cmds = cmds_bamToBigWig(sample_name, track_dir, bam)
binname = sample_name + "_track"
# cmd.generate_pbs(cmds=cmds, binName=binname, binPath=track_bin)
cmd.generate_submit_pbs(cmds=cmds, binName=binname, binPath=track_bin)
pass
def main():
projectDir = sys.argv[
1] + "tophat" # /archive2/tmhyxb9/FBL/fastq/rmUMI/MAPPING_EXON/tophat_exon/
samples = os.listdir(projectDir)
gtfBeds = ["CDS", "5UTR", "3UTR", "exon", "intron", "whole"]
for sample in samples:
inputDir = os.path.join(projectDir, sample, "sortedBed")
for gtf in gtfBeds:
cmds = map_gtf_bed(inputDir, gtf, sample)
binPath = os.path.join(projectDir, sample, "bins")
binName = sample + "_" + gtf
# cmd.generate_pbs(cmds, binName, binPath)
cmd.generate_submit_pbs(cmds, binName, binPath)
pass
def main():
inputfiles = [
"/archive2/tmhyxb9/FBL/fastq/Ctr2_sh/control2.fq",
"/archive2/tmhyxb9/FBL/fastq/FBL_sh/FBL.fq",
"/archive2/tmhyxb9/FBL/fastq/FBL2_sh/FBL2.fq",
"/archive2/tmhyxb9/FBL/fastq/EZH2_sh1/EZHsh1_1.fq",
"/archive2/tmhyxb9/FBL/fastq/EZH22_sh1/EZHsh1_2.fq",
"/archive2/tmhyxb9/FBL/fastq/EZH2_sh2/EZHsh2_1.fq",
"/archive2/tmhyxb9/FBL/fastq/EZH22_sh2/EZHsh2_2.fq"
]
for file in inputfiles:
outputDir = "/archive2/tmhyxb9/FBL/fastq/rmUMI/fastq/"
binname = "rmUMI_" + os.path.basename(file).split(".")[0]
cmds = generate_cmds(file, outputDir)
binpath = "/archive2/tmhyxb9/FBL/fastq/rmUMI/bin"
cmd.generate_submit_pbs(cmds=cmds, binName=binname, binPath=binpath)
pass
def main():
projectDir = sys.argv[
1] + "tophat" #/archive2/tmhyxb9/FBL/fastq/rmUMI/MAPPING_EXON/tophat_exon/
samples = os.listdir(projectDir)
for sample in samples:
inputDir = os.path.join(projectDir, sample)
outputDir = os.path.join(inputDir, "sortedBed")
if not os.path.exists(outputDir):
os.mkdir(outputDir)
cmds = generate_cmds(inputDir=inputDir, outputDir=outputDir)
binPath = os.path.join(inputDir, "bins")
if not os.path.exists(binPath):
os.mkdir(binPath)
binName = os.path.join(binPath, sample + "_bam2bed")
# cmd.generate_pbs(cmds, binName, binPath)
cmd.generate_submit_pbs(cmds, binName, binPath)
pass
import pandas as pd
import os, os.path, sys
sys.path.insert(0, "/archive2/tmhyxb9/ToolBox")
import cmd
samples = ["Control", "FBL", "EZH2sh1", "EZH2sh2"]
for sample in samples:
geneGTF = "/archive2/tmhyxb9/ref_data/hg19/hg19.ucscgenes.knowngene.gtf"
outputFile = "/archive2/tmhyxb9/FBL/RNA_seq/tophat_pair/HTseq_RNAseq/HTseq_RNAseq_results" + sample + "_RNAC_raw_count.txt"
cmd0 = "cd /archive2/tmhyxb9/FBL/RNA_seq/tophat_pair/tophat/" + sample
cmd1 = "module load samtools/1.9"
cmd2 = "samtools sort accepted_hits.bam > accepted_hits.sorted.bam"
cmd3 = "samtools index accepted_hits.sorted.bam"
cmd4 = "module load python/2.7.11"
cmd5 = "htseq-count -f bam accepted_hits.sorted.bam -s no -m intersection-nonempty " + geneGTF + " > " + outputFile
cmds = [cmd0, cmd1, cmd2, cmd3, cmd4, cmd5]
binPath = "/archive2/tmhyxb9/FBL/RNA_seq/tophat_pair/HTseq_RNAseq/bin"
cmd.generate_submit_pbs(cmds = cmds , binName = sample, binPath = binPath)