def main():
''' main method for the commandline interface of the circ_combination module '''
print('Program call:')
print(' '.join(sys.argv))
_, o = get_command_line_options()
create_output_dirs(o)
t_start = wutils.get_current_time()
print(t_start[1] + 'Start Combination of circRNA predictions')
algo_circ_combination.combine_circular_rna(o.inCircs1, o.inCircs2,
o.outIntersection, o.outUnion,
o.outIntersectedUnion,
o.minReads)
t_end = wutils.get_current_time()
print(t_end[1] + 'Finished. Check out the results in ' +
o.outIntersection + ', ' + o.outIntersection + ' and ' +
o.outIntersectedUnion)
wutils.print_resources(t_end[0] - t_start[0], child_processes=False)
if (o.returnFilePath is not None):
returnVars = [('circIntersection', o.outIntersection),
('circUnion', o.outUnion),
('circIntersectedUnion', o.outIntersectedUnion)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method for running phantompeakqualtools as watchdog module '''
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# check options and prepare output location
_, o = get_command_line_options()
paths = create_outfiles(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for running phantompeakqualtools!\n')
# run the external program
call_phantom_peak_script(o.inBam, paths[0], paths[1], paths[2], o.sppPath,
o.rscriptPath, o.tmpdir, o.threads)
# log
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] +
'Module finished successfully!\n-> check out the results:\n' +
'\n'.join(paths))
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
def main():
''' main method for running the bwa aln wrapper as watchdog module '''
# check options and prepare output locations
_, o = get_command_line_options()
create_outfiles(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for running bwa sampe !\n')
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# run the main program
run_bwa_sampe(o.bwaIndex, o.inReads1, o.inReads2, o.inSai1, o.inSai2,
o.outSam, o.bwaPath, o.indexInRam)
# log
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] + 'Module finished successfully!\n-> check out \'' +
o.outSam + '\' for the output of bwa aln')
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
# write return file for watchdog
if (o.returnFilePath is not None):
returnVars = [('bwaPairedSamFile', o.outSam)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method for converting bam -> bigwig using the watchdog module '''
# check options and prepare output location
_, o = get_command_line_options()
create_outfiles(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for converting bam to bigwig format !\n')
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# run the main program
run_bam_coverage(o.inBam, o.outBw, o.binSize, o.numberOfProcessors,
o.bamCoveragePath)
# log
end_timepoint = wutils.get_current_time()
print(
end_timepoint[1] +
'Module finished successfully!\n-> the bigwig file is located at \'' +
o.outBw + '\'')
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
# write return file for watchdog
if (o.returnFilePath is not None):
returnVars = [('bigWigFile', o.outBw)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method for converting bam to bedgraph and tdf '''
# print command
print('Program call:')
print(' '.join(sys.argv)+'\n')
# check options and prepare output location
p,o = get_command_line_options()
create_tdf = check_option_interactions(p,o)
bedgraph_out, tdf_out = create_outfiles(o)
# log
start_timepoint=wutils.get_current_time()
print(start_timepoint[1]+'Welcome to the genomeCoverage Module!\n')
# perform conversion bam -> bedgraph -> tdf
bam_to_bedgraph(o.bam, bedgraph_out, bedtools_exec=o.bedtoolsPath)
if create_tdf:
bedgraph_to_tdf(bedgraph_out, o.genome, tdf_out, igvtools_exec=o.igvtoolsPath)
# log
end_timepoint=wutils.get_current_time()
print(end_timepoint[1]+'Module finished successfully!')
if create_tdf:
print('-> the tdf file is located at \''+tdf_out+'\'')
else:
print('-> the bedgraph file is located at \''+bedgraph_out+'\'')
wutils.print_resources(end_timepoint[0]-start_timepoint[0], child_processes=True)
def main():
''' main method for running the module'''
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# check options and prepare output locations
_, o = get_command_line_options()
re_unmapped, re_imppairs, qual_cut, hit_cut, single_end = process_option_interactions(
o)
check_input_file(o)
create_outfiles(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for fitlering the output of bwa sampe !\n')
algo_filter_bwa_sampe.remove_reads(o.inSamBam, o.outSamBam, re_unmapped,
re_imppairs, qual_cut, hit_cut,
single_end)
# log
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] + 'Module finished successfully!\n-> check out \'' +
o.outSamBam + '\' with the filtered read pairs')
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=False)
# write return file for watchdog
if (o.returnFilePath is not None):
returnVars = [('filteredPairs', o.outSamBam)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method running the command line interface '''
print('Program call:')
print(' '.join(sys.argv))
# parse command line
p, o = get_command_line_options()
check_inputfiles(p, o)
get_and_create_outfiles(o)
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] + 'Starting CIRI2 wrapper...')
# run BWA
if (o.inSAM is None):
# get index for BWA
if (o.bwaIndex is None):
index_prefix = o.outPrefix + 'bwaIndex'
runner.buildIndex(o.reference, index_prefix, o.bwaPath)
else:
index_prefix = o.bwaIndex
# call bwa mem
bwa_sam_file = o.outPrefix + 'bwa.sam'
runner.runBWA(o.inReads1, o.inReads2, index_prefix, bwa_sam_file,
o.bwaThreads, o.bwaPath, o.bwaSeedSize,
o.bwaScoreThreshold)
else:
bwa_sam_file = o.inSAM
# run CIRI
ciri_raw_output = o.outPrefix + 'rawPred.txt'
runner.runCIRI2(bwa_sam_file, ciri_raw_output, o.reference,
o.ciriAnnotation, o.ciriThreads, o.ciriPath,
o.ciriStringency, o.ciriKeepTmpFiles)
# create the final output
if (o.outCirc is None):
final_output_file = o.outPrefix + 'ciriCirc.txt'
else:
final_output_file = o.outCirc
runner.writeOutput(ciri_raw_output, final_output_file)
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] + 'CIRI2 finished, check out \'' +
final_output_file + '\' for the results')
# output resources consumed by the script
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
# write watchdog return variables
if (o.returnFilePath is not None):
wutils.write_watchdog_return_file(o.returnFilePath,
[('ciriCircs', final_output_file)])
def main():
''' main method for running the watchdog module for calculation of readout in recount data '''
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# check options and prepare output location
_, o = get_command_line_options()
remove_tmp_sample, remove_tmp_proj, parallel_down = resolve_booleans(o)
check_gene_tsv(o)
proj_list = get_project_list(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for calculating readout from recount !\n')
# iterate over all projects
for projID in proj_list:
proj_timepoint = wutils.get_current_time()
print(proj_timepoint[1] + 'Processing project ' + projID)
# create output and tmp folder for the current project
res_folder, tmp_folder = create_outfolders(o, projID)
# run the R code if possible
try:
run_Rscript_recount(projID, o.geneTSV, res_folder, tmp_folder,
o.threads, remove_tmp_sample, parallel_down,
o.localRecountFolder, o.Rscript)
except subprocess.CalledProcessError:
sys.stderr.write('An error occurred in the R script \n')
raise
# clean up temporary data
finally:
remove_tmp_data(remove_tmp_sample, remove_tmp_proj, res_folder,
tmp_folder)
# log
end_timepoint = wutils.get_current_time()
print(
end_timepoint[1] +
'Module finished successfully!\n-> the readout data is located at \'' +
o.outfolder + '\'')
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
def main():
''' main method for calling removeLinearReads from commandline '''
print('Program call:')
print(' '.join(sys.argv))
_,o = get_command_line_options()
wutils.make_parent_dirs(o.circOut)
t_start = wutils.get_current_time()
print(t_start[1]+'Start Removal of Linearly Mappable Reads')
algo.remove_linearly_mappable_reads(o.circRNAPrediction, o.mapping, o.circOut, o.minReads, o.paired)
t_end = wutils.get_current_time()
print(t_end[1]+'Finished. Check out the results in '+o.circOut)
wutils.print_resources(t_end[0]-t_start[0], child_processes=False)
if(o.returnFilePath is not None):
returnVars = [('filteredCircs', o.circOut)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method for converting bam -> bed using the watchdog module '''
# check options and prepare output location
_, o = get_command_line_options()
create_outfiles(o)
# log
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] +
'Welcome to the module for converting bam to bed format !\n')
# print command
print('Program call:')
print(' '.join(sys.argv) + '\n')
# run the main program
split_spliced = True
if o.nosplit:
split_spliced = False
run_bedtools_bamtobed(bam_file=o.inBam,
bed_file=o.outBed,
bedtools_path=o.bedtoolsPath,
split=split_spliced)
# log
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] +
'Module finished successfully!\n-> the bed file is located at \'' +
o.outBed + '\'')
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
# write return file for watchdog
if (o.returnFilePath is not None):
returnVars = [('bedFile', o.outBed)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main function calling the rrna filter '''
# print command
print('Program call:')
print(' '.join(sys.argv)+'\n')
# check options and prepare output locations
p,o = get_command_line_options()
check_input_files(p,o)
create_outfiles(o)
# log
start_timepoint=wutils.get_current_time()
print(start_timepoint[1]+'Welcome to the rRNA filter module!\n')
# run the main program
rrna_filter_algo.runFilter.run(in1=o.in1, in2=o.in2, rrnaIndex=o.rrnaIndex, workdir=o.workdir, out1=o.out1, out2=o.out2, sam=o.sam,
seedSize=o.seedSize, threads = o.threads, maxEditDistance=o.maxEditDistance, maxMismatches=o.maxMismatches, maxIndels=o.maxIndels,
pairFiltering=o.pairFiltering, bwapath=o.bwaPath, keeptmp=o.keepTmp)
# log
end_timepoint=wutils.get_current_time()
res_files = o.out1
if(o.out2 is not None):
res_files+= ', '+o.out2
print(end_timepoint[1]+'Module finished successfully!\n-> check out \''+res_files+'\' for the non-rRNA reads')
wutils.print_resources(end_timepoint[0]-start_timepoint[0], child_processes=True)
# write return file for watchdog
if(o.returnFilePath is not None):
returnVars = [('rrnaSAMFile', o.sam), ('filteredFQ1', o.out1)]
if(o.out2 is None):
returnVars.append(('filteredFQ2', 'not_defined_for_single_end'))
else:
returnVars.append(('filteredFQ2', o.out2))
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
def main():
''' main method for the commandline interface of the circrna_finder module '''
print('Program call:')
print(' '.join(sys.argv))
# handle command line options
p, o = get_command_line_options()
check_inputfiles(p, o)
get_and_create_outfiles(o)
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] + 'Starting circRNA_finder wrapper')
# call STAR
if (o.inSTAR is None):
# build STAR index
if (o.starIndex is None):
index_location = o.outPrefix + 'star_index'
os.mkdir(index_location)
run_circrna_finder.build_STAR_index(o.reference,
index_location,
star_path=o.starPath,
star_thread_nr=o.starThreads)
else:
index_location = o.starIndex
# map reads with STAR
star_file_prefix = o.outPrefix
run_circrna_finder.map_with_STAR(o.inReads1,
o.inReads2,
index_location,
star_file_prefix,
star_path=o.starPath,
star_thread_nr=o.starThreads)
else:
star_file_prefix = o.inSTAR
# call circRNA_finder
run_circrna_finder.run_circRNA_finder(star_file_prefix,
o.outPrefix,
circRNA_finder_path=o.cfPath)
# create final output file
if (o.outCirc is None):
final_file = o.outPrefix + 'cfCirc.txt'
else:
final_file = o.outCirc
run_circrna_finder.annotate_and_wirte_output(o.outPrefix, star_file_prefix,
final_file, o.strandedLibrary)
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] + 'circRNA_finder finished, check out \'' +
final_file + '\' for the results')
# output resources
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=True)
# write watchdog return variables
if (o.returnFilePath is not None):
wutils.write_watchdog_return_file(o.returnFilePath,
[('cfCircs', final_file)])
# start of execution
start_timepoint = wutils.get_current_time()
print(start_timepoint[1] + 'Starting trimmedFastqPairFilter module...')
print('Input:')
print(inpaths)
print('Output:')
print(outpaths)
algo_trimmedFastqPairFilter.filterFastqs(inpaths[0], inpaths[1],
outpaths[0], outpaths[1],
outpaths[2])
# end of execution
end_timepoint = wutils.get_current_time()
print(end_timepoint[1] +
'trimmedFastqPairFilter module finished, check out \'' +
','.join(outpaths) + '\' for the results')
# output resources consumed by the script
wutils.print_resources(end_timepoint[0] - start_timepoint[0],
child_processes=False)
# write return variables
if (o.returnFilePath is not None):
returnVars = [('pairedReads1', outpaths[0]),
('pairedReads2', outpaths[1]),
('singletonReads', outpaths[2])]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)
cmdl_options = parser.parse_args()
return parser, cmdl_options
def create_output_dirs(cmdl_options):
''' create parent directories of concatenated output file '''
wutils.make_parent_dirs(cmdl_options.outFile)
if __name__ == '__main__':
print('Program call:')
print(' '.join(sys.argv))
p, o = get_command_line_options()
create_output_dirs(o)
t_start = wutils.get_current_time()
print(t_start[1] + 'Welcome! Concatenation of files in progress...')
algo_concatenate.concatenate_files(o.inFile, o.outFile)
t_end = wutils.get_current_time()
print(t_end[1] + 'Finished. Check out the results in ' + o.outFile)
wutils.print_resources(t_end[0] - t_start[0], child_processes=False)
if (o.returnFilePath is not None):
returnVars = [('concatenatedFile', o.outFile)]
wutils.write_watchdog_return_file(o.returnFilePath, returnVars)