def combine_alignment_summary(input, output):
"""Combine formatted alignment log files
`input`: Formatted alignment stat log files (*fastqLog.final.txt)
`output`: Combined alignment stat csv file named (DATA_alignment_summary.csv)
"""
print tasks.comment()
#print input
#print output
print colored("Stage 9: Aggrigate alignment summary ....", "green")
print tasks.comment()
result = tasks.combineAlignmentSummary(input, output)
return result
def format_count(input,output):
"""Format count csv file
`input`: csv file
`output`: Formatted *.csv file
"""
print tasks.comment()
print colored("Stage 8: Formatting count file ... ", "green")
print input
print output
print tasks.comment()
result = tasks.formatCount(input,output)
return result
def plot_alignment_summary(input, output):
"""Plot alignment summary
`input`: Alignment summary csv file
`output`: output png file bar plot
"""
print tasks.comment()
print colored("Stage 10: Plot alignment summary ...", "green")
print input
print output
print tasks.comment()
result = tasks.plotAlignmentStat(input, output)
return result
def combine_count_data(input, output):
"""Combine count files
`input`: Formatted *.out.txt count files
`output`: A single summary count csv file nammed 'DATA_COUNT_countcombined.csv' under project dir
"""
print tasks.comment()
print input
print output
print colored("Stage 7: Combining count data ...", "green")
print tasks.comment()
result = tasks.combineCount(input, output)
return result
def format_count(input,output):
"""Format count csv file
`input`: csv file
`output`: Formatted *.csv file
"""
print tasks.comment()
print colored("Stage 8: Formatting count file ... ", "green")
#print input
#print output
print tasks.comment()
result = tasks.formatCount(input,output)
return result
def combine_alignment_summary(input, output):
"""Combine formatted alignment log files
`input`: Formatted alignment stat log files (*fastqLog.final.txt)
`output`: Combined alignment stat csv file named (DATA_alignment_summary.csv)
"""
print tasks.comment()
#print input
#print output
print colored("Stage 9: Aggrigate alignment summary ....", "green")
print tasks.comment()
result = tasks.combineAlignmentSummary(input, output)
return result
def combine_count_data(input, output):
"""Combine count files
`input`: Formatted *.out.txt count files
`output`: A single summary count csv file nammed 'DATA_COUNT_countcombined.csv' under project dir
"""
print tasks.comment()
#print input
#print output
print colored("Stage 7: Combining count data ...", "green")
print tasks.comment()
result = tasks.combineCount(input, output)
return result
def plot_alignment_summary(input, output):
"""Plot alignment summary
`input`: Alignment summary csv file
`output`: output png file bar plot
"""
print tasks.comment()
print colored("Stage 10: Plot alignment summary ...", "green")
print input
print output
print tasks.comment()
result = tasks.plotAlignmentStat(input, output)
return result
def main():
if options.indexed == "yes":
click.echo(
"Indexing the reference genome {}, be patient, it takes longer time"
.format(genomeDir))
pipeline_run(["indexGenome"], verbose=1, multiprocess=cpuNum)
pipeline_run([
"prepare_analysis", "cleanFastq", "bsAlign", "mergeBamSameTissue",
"bamSort", "bamIndex", "createCGmap", "extractCG_Context",
"mergeConCGcall", "icrHotSpot", "convertToBed", "unionBed",
"mergeBed", "countICR"
],
verbose=1,
multiprocess=cpuNum)
# Flowcharts can be printed in a large number of formats including jpg, svg, png and pdf
pipeline_printout_graph("flowchart.pdf",
"pdf", [countICR],
user_colour_scheme={"colour_scheme_index": 6},
pipeline_name="Putative ICR pipeline",
no_key_legend=False)
else:
"""Console script for puticr."""
click.echo(tasks.comment())
t0 = time.time()
click.echo("Starting the process .....")
#click.echo("Starting the pipeline, staring time ...{}".format(datetime.timedelta(seconds=t0)))
#tasks_torun = [prepare_analysis, cleanFastq]
# pipeline_run(["prepare_analysis", "cleanFastq", "bsAlign", "mergeBamSameTissue", "bamSort", "bamIndex", "createCGmap",
# "extractCG_Context", "mergeConCGcall", "icrHotSpot", "convertToBed", "unionBed", "mergeBed", "countICR"], verbose=1, multiprocess=cpuNum)
pipeline_run([
"mergeBamSameTissue", "bamSort", "bamIndex", "createCGmap",
"extractCG_Context", "mergeConCGcall", "icrHotSpot",
"convertToBed", "unionBed", "mergeBed", "countICR"
],
verbose=1,
multiprocess=cpuNum)
#pipeline_run(["icrHotSpot", "convertToBed", "unionBed", "mergeBed", "countICR"], verbose=1, multiprocess=cpuNum)
# Flowcharts can be printed in a large number of formats including jpg, svg, png and pdf
pipeline_printout_graph("flowchart.pdf",
"pdf", [countICR],
user_colour_scheme={"colour_scheme_index": 6},
pipeline_name="Putative ICR pipeline",
no_key_legend=False)
click.echo(".................. {}".format(resultDir))
elapsedTime = int((time.time()) - t0)
elapsedTime = str(datetime.timedelta(seconds=elapsedTime))
click.echo("Time to complete the task .....{}".format(
colored(elapsedTime, "red")))
click.echo(tasks.comment())
def alignment_summary(input, output):
"""Generate Alignment summary
`input`: *fastqLog.final.out files
`output`: Extracted necessary data and create *.txt file for each count log file
"""
outfile = basename(input)
out_suffix = splitext(outfile)[0]
out_file_name = out_suffix + output
out_file_name = join(tempDir, out_file_name)
print tasks.comment()
print colored("Stage 8: Generate Alingmnet summary ....", "green")
#print input
#print output
print tasks.comment()
result = tasks.alignmentSummary(input, out_file_name)
return result
def count_mapped_reads(bamFile, outfile):
"""Coun the mapped sequence to the genome featur5e
`bamFile`: A bam alignment file
`outfile`: Count txt file
"""
import re
p=re.match(r'(.*)_manifest.csv', probFile, re.M|re.I)
gtfF = p.group(1) + ".gtf"
gtfFile = join(resultDir,gtfF)
print tasks.comment()
print colored("Stage 6: Count Mapped file that overlap with genome feature ... ", "green")
print bamFile
print gtfFile
print tasks.comment()
result = tasks.count_mapped(bamFile, outfile, gtfFile)
return result
def alignment_summary(input, output):
"""Generate Alignment summary
`input`: *fastqLog.final.out files
`output`: Extracted necessary data and create *.txt file for each count log file
"""
outfile = basename(input)
out_suffix = splitext(outfile)[0]
out_file_name = out_suffix + output
out_file_name = join(tempDir, out_file_name)
print tasks.comment()
print colored("Stage 8: Generate Alingmnet summary ....", "green")
#print input
#print output
print tasks.comment()
result = tasks.alignmentSummary(input, out_file_name)
return result
def count_mapped_reads(bamFile, outfile):
"""Coun the mapped sequence to the genome featur5e
`bamFile`: A bam alignment file
`outfile`: Count txt file
"""
import re
p=re.match(r'(.*)_manifest.csv', probFile, re.M|re.I)
gtfF = p.group(1) + ".gtf"
gtfFile = join(resultDir,gtfF)
print tasks.comment()
print colored("Stage 6: Count Mapped file that overlap with genome feature ... ", "green")
#print bamFile
#print gtfFile
print tasks.comment()
result = tasks.count_mapped(bamFile, outfile, gtfFile)
return result
def map_to_probes(fastq, output):
"""Map the fastq file to the indexed probe sequences. The fastq must be in the gzipped with the following extension. (*.fastq.gz)
`fastq`: a dir that contains all *.fastq.gz file for the experment
`output`: output .bam files and '*fastqReadPrepGene.out.tab' count files
"""
outfile = basename(output)
outfile = join(tempDir, outfile)
suf = splitext(outfile)[0]
outPrefix = os.path.abspath(suf)
print tasks.comment()
print colored("Stage 5: Map sequence fastq file to the indexed genome file ... ", "green")
print fastq
print output
print genomeDir
print outPrefix
print tasks.comment()
result = tasks.map_seq_to_probes(fastq, genomeDir, cpuNum, outPrefix)
return result
def map_to_probes(fastq, output):
"""Map the fastq file to the indexed probe sequences. The fastq must be in the gzipped with the following extension. (*.fastq.gz)
`fastq`: a dir that contains all *.fastq.gz file for the experment
`output`: output .bam files and '*fastqReadPrepGene.out.tab' count files
"""
outfile = basename(output)
outfile = join(tempDir, outfile)
suf = splitext(outfile)[0]
outPrefix = os.path.abspath(suf)
print tasks.comment()
print colored("Stage 5: Map sequence fastq file to the indexed genome file ... ", "green")
#print fastq
#print output
#print genomeDir
#print outPrefix
print tasks.comment()
result = tasks.map_seq_to_probes(fastq, genomeDir, cpuNum, outPrefix)
return result
def main():
t0 = time.time()
print (" Starting time ..... :") + str(t0)
tasks_torun = [prepare_analysis, prepareDB_file, create_gtf_file, indexGenomeFile,
map_to_probes, format_count, combine_count_data, alignment_summary,
combine_alignment_summary,plot_alignment_summary]
pipeline_printout_graph('summary_pipeline_stages_to_run.ps', 'ps', tasks_torun, user_colour_scheme={"colour_scheme_index": 6},
no_key_legend=False, pipeline_name="TempO-seq Analysis", size=(11, 8), dpi = 30,
forcedtorun_tasks = [indexGenomeFile, combine_count_data],draw_vertically=True, ignore_upstream_of_target=False)
pipeline_run(["prepare_analysis", "prepareDB_file",'create_gtf_file', 'indexGenomeFile', 'map_to_probes','count_mapped_reads', 'combine_count_data', 'format_count', 'alignment_summary','combine_alignment_summary'],verbose = 1, multiprocess = cpuNum)
print "....................." + resultDir
tasks.comment()
psfile = options.flowchart
#psfile = "./summary_pipeline_stages_to_run.ps"
convertPs(psfile)
tasks.comment()
elapsedTime = int((time.time()) - t0)
elapsedTime = str(datetime.timedelta(seconds=elapsedTime))
print("Time to complete the task ....." ) + colored (elapsedTime, "red")
def main():
t0 = time.time()
print (" Starting time ..... :") + str(t0)
tasks_torun = [prepare_analysis, prepareDB_file, create_gtf_file, indexGenomeFile,
map_to_probes, format_count, combine_count_data, alignment_summary,
combine_alignment_summary,plot_alignment_summary]
pipeline_printout_graph('summary_pipeline_stages_to_run.ps', 'ps', tasks_torun, user_colour_scheme={"colour_scheme_index": 6},
no_key_legend=False, pipeline_name="TempO-seq Analysis", size=(11, 8), dpi = 30,
forcedtorun_tasks = [indexGenomeFile, combine_count_data],draw_vertically=True, ignore_upstream_of_target=False)
pipeline_run(["prepare_analysis", "prepareDB_file",'create_gtf_file', 'indexGenomeFile', 'map_to_probes','count_mapped_reads', 'combine_count_data', 'format_count', 'alignment_summary','combine_alignment_summary','plot_alignment_summary'],verbose = 1, multiprocess = cpuNum)
print "....................." + resultDir
tasks.comment()
psfile = options.flowchart
#psfile = "./summary_pipeline_stages_to_run.ps"
convertPs(psfile)
tasks.comment()
elapsedTime = int((time.time()) - t0)
elapsedTime = str(datetime.timedelta(seconds=elapsedTime))
print("Time to complete the task ....." ) + colored (elapsedTime, "red")
import sys
import tasks
import users
import log
if len(sys.argv) < 3:
print('error: expected 2 arguments')
print('usage: comment <path-to-task> <comments>')
sys.exit()
sys.argv[0] = 'comment'
taskPath = sys.argv[1]
comments = ' '.join(sys.argv[2:])
print("adding comment: " + comments)
tasks.comment(taskPath, users.current, comments)
log.add(' '.join(sys.argv))
print('comment added.')
