def makefile_local(name2sample, outdir, paired):
final_files = []
mlist = []
if (paired):
for name, pair in name2sample.items():
input_files = pair
output_files = [
os.path.join(outdir, "%s.%d.fastq" % (name, x)) for x in (1, 2)
]
script = get_script('collapse_paired.py',
seq_package,
arguments={
'--output': os.path.join(outdir, name),
'--log': args.log
},
inp=input_files)
mlist.append(dependence(input_files, output_files, script))
final_files.extend(output_files)
else:
for name, pair in name2sample.items():
input_files = pair
output_files = os.path.join(outdir, "%s.fastq" % name)
script = get_script('collapse_single.py',
seq_package,
arguments={
'--output': os.path.join(outdir, name),
'--log': args.log
},
inp=input_files)
mlist.append(dependence(input_files, output_files, script))
final_files.append(output_files)
mlist.insert(0, get_header(final_files))
mlist.append('clean:\n\techo "nothing to clean."\n')
return "\n\n".join(mlist)
def makefile_local(m_input, control):
#print(m_input)
#print(control)
final_files = []
mlist = []
if (type(m_input) == str):
name = os.path.basename(m_input).split(".")[0]
else:
name = os.path.basename(m_input[0]).split(".")[0]
log_dir = os.path.join('log', name)
os.makedirs(os.path.join(project_path, log_dir), exist_ok=True)
log_file = os.path.join(log_dir, "log.txt")
# Processing bowite2 settings
bs_list = get_bowtie_call(bowtie_settings,
args.bowtie_args,
args.index,
m_input,
name,
threads=args.threads,
reads_format=args.reads_format)
bs_list = ['echo', '\'###bowtie\'', '>', log_file, ';'
] + bs_list + ['2>> >(tee -a %s>&2)' % log_file]
# Map reads with bowtie2
input_files = m_input
output_files = os.path.join('sam', '%s.sam' % name)
script = bs_list
#print(script)
mlist.append(dependence(input_files, output_files, script))
# Convert mappings into coverage
input_files = output_files
output_files = [
os.path.join('coverage', '%s.%s.bed' % (name, x))
for x in ['plus', 'minus']
]
script = get_script('get_sam_stat_paired.py',
mapping_package,
arguments={
'--genome': args.genome,
'--outstat': log_dir,
'--outcoverage': 'coverage',
'--ambiguous': args.ambiguous
},
inp=input_files)
mlist.append(dependence(input_files, output_files, script))
# Assign TPM and annotate the mappings
input_files = output_files
output_files = os.path.join('transcripts', '%s.gff' % name)
covpath = output_files
script = get_script('assign_mappings.py',
mapping_package,
inp=input_files,
out=output_files,
arguments={
'--transcripts': args.annotation,
'--logdir': log_dir
})
mlist.append(dependence(input_files, output_files, script))
#Get header and cleaner for the makefile
mlist.insert(0, get_header(output_files))
mlist.append('clean:\n\techo "nothing to clean."\n')
return "\n\n".join(mlist), name, [output_files]
inp='log',
out=output_files)
mlist.append(dependence(input_files, output_files, script))
#python /home/a_filipchyk/afp/chap/annotate.py regions/regions.gff --maxshift 50 --flen 50 --genes /home/a_filipchyk/genomic_data/coryne/annotation/improved_annotation_2017.gff
###CHANGE
if (False and args.annotation):
input_files = os.path.join('regions', 'regions.gff')
output_files = os.path.join('regions', 'regions.annotated.gff')
final_files.append(output_files)
script = get_script('annotate.py',
chap_package,
arguments={
'--maxshift': region_settings['maxshift'],
'--flen': region_settings['flank'],
'--genes': args.annotation
},
inp=input_files,
out=output_files)
mlist.append(dependence(input_files, output_files, script))
#makefile header
mlist.insert(0, get_header(final_files, phonyfiles=mf_names))
# makefie cleaner
mlist.append('clean:\n%s' %
("\n".join(["\t$(MAKE) -f %s clean" % x for x in mf_multipath])))
with open(os.path.join(project_path, 'Makefile'), 'w') as mf:
mf.write("\n\n".join(mlist))
def makefile_local(m_input, control):
#print(m_input)
#print(control)
todel = []
final_files = []
mlist=[];
if(type(m_input) == str):
name = os.path.basename(m_input).split(".")[0];
else:
name = os.path.basename(m_input[0]).split(".")[0];
log_dir = os.path.join('log', name)
os.makedirs(os.path.join(project_path, log_dir), exist_ok=True);
log_file = os.path.join(log_dir, "log.txt")
# Processing bowite2 settings
bs_list = get_bowtie_call(bowtie_settings, args.bowtie_args, args.index, m_input, name, threads=args.threads, reads_format=args.reads_format)
bs_list = ['echo', '\'###bowtie\'', '>', log_file, ';'] + bs_list + ['2>> >(tee -a %s>&2)' % log_file]
# Map reads with bowtie2
input_files = m_input
output_files = os.path.join('sam', '%s.sam' % name)
todel.append(output_files)
script = bs_list
#print(script)
mlist.append(dependence(input_files, output_files, script))
# Convert mappings into coverage
input_files = output_files;
output_files = [os.path.join('coverage', '%s.%s.bed' % (name, x)) for x in ['minus', 'plus']]
arguments = {'--genome': args.genome, '--outstat': log_dir, '--outcoverage': 'coverage', '--ambiguous': args.ambiguous};
if(args.paired):
arguments['--paired'] = True;
script = get_script('get_sam_stat_paired.py', mapping_package, arguments=arguments, inp = input_files)
mlist.append(dependence(input_files, output_files, script));
# Merge coverages coming from different strands
input_files = output_files;
output_files = os.path.join('coverage', '%s.bed' % name)
covpath = output_files
script = get_script('merge_coverages.py', chap_package, inp = input_files, out = output_files)
mlist.append(dependence(input_files, output_files, script));
if(control):
log_dir_control = os.path.join('log', name + "_control")
os.makedirs(os.path.join(project_path, log_dir_control), exist_ok=True);
# Processing of the left chimeric part bowite2 settings
bs_list = get_bowtie_call(bowtie_settings, args.bowtie_args, args.index, control, "%s.control" % name, threads=args.threads)
# Map reads with bowtie2
input_files = control
output_files = os.path.join('sam', '%s.control.sam' % name)
todel.append(output_files)
bs_list = ['echo', '\'###bowtie_control\'', '>>', log_file, ';'] + bs_list + ['2>> >(tee -a %s>&2)' % log_file]
script = bs_list
mlist.append(dependence(input_files, output_files, script))
# Convert mappings into coverage
input_files = output_files;
output_files = [os.path.join('coverage', '%s.control.%s.bed' % (name, x)) for x in ['minus', 'plus']]
arguments = {'--genome': args.genome, '--outstat': log_dir_control, '--outcoverage': 'coverage'};
if(args.paired):
arguments['--paired'] = True;
script = get_script('get_sam_stat_paired.py', mapping_package, arguments=arguments, inp = input_files)
mlist.append(dependence(input_files, output_files, script));
# Merge coverages coming from different strands
input_files = output_files;
output_files = os.path.join('coverage', '%s.control.bed' % name)
script = get_script('merge_coverages.py', chap_package, inp = input_files, out = output_files)
mlist.append(dependence(input_files, output_files, script));
input_files = [covpath, output_files]
output_files = os.path.join('coverage', '%s.adjusted.bed' % name)
covpath = output_files
script = get_script('adjust_coverage_to_control.py', chap_package, inp = input_files[0], arguments={'--control': input_files[1], '--outdir': log_dir }, out = output_files)
mlist.append(dependence(input_files, output_files, script));
# Detect peaks
input_files = output_files
output_files = [os.path.join('peaks', '%s.raw.bed' % name), os.path.join(log_dir, 'convolution.bed'), os.path.join(log_dir, 'convolution.png')]
script = get_script('detect_peaks.py', chap_package, arguments={'--threads': args.threads, '--widthfactor': peak_detection_settings['widthfactor'], '--meanmult': peak_detection_settings['meanmult'], '--convolution': output_files[1] , '--plot': output_files[2]}, inp = input_files, out = output_files[0], log=log_file)
mlist.append(dependence(input_files, output_files, script));
# Filter peaks
input_files = output_files[0]
output_files = [os.path.join('peaks', '%s.filtered.bed' % name), os.path.join("peaks", '%s.assigned.tsv' % name), os.path.join(log_dir, 'filtering.png')]
filtered_path = output_files[0]
script = get_script('filter_peaks.py', chap_package, arguments={'--zscore': peak_filtering_settings['zscore'], '--minmedian': peak_filtering_settings['minmedian'], '-ap': output_files[1] , '--plot': output_files[2], '--coverage': covpath}, inp = input_files, out = output_files[0], log=log_file)
mlist.append(dependence(input_files, output_files, script));
# Normalize coverage
input_files = [output_files[1], covpath]
output_files = os.path.join('coverage', '%s.normalized.bed' % name)
normed_covpath = output_files;
script = get_script('normalize_coverage.py', chap_package, arguments={'--zscore': coverage_settings['zscore'], '--mode': coverage_settings['mode'], '--coverage': input_files[1]}, inp = input_files[0], out = output_files)
mlist.append(dependence(input_files, output_files, script));
# Create UCSC tracks
trackopts = "\'track name=%s description=\"CHAP seq genomic coverage for sample %s\" %s\'" % (name, name, " ".join(["%s=%s" % x for x in coverage_settings['trackopts'].items()]))
input_files = output_files
output_files = os.path.join('ucsc', '%s.bedgraph' % name)
final_files.append(output_files)
script = get_script('coverage2bedgraph.py', mapping_package, arguments={'--multiplier': coverage_settings['multiplier'], '--convert': True, '--trackopts': trackopts}, inp = input_files, out = output_files)
mlist.append(dependence(input_files, output_files, script));
# Annotate peaks
#if(not multi):
input_files = [filtered_path, normed_covpath]
output_files = os.path.join('peaks', '%s.annotated.gff' % name)
local_arguments = {'--coverage': input_files[1], '--outdir': log_dir}
if(args.annotation):
local_arguments['--transcripts'] = args.annotation
script = get_script('annotate.py', chap_package, arguments=local_arguments, inp = input_files[0], out = output_files)
mlist.append(dependence(input_files, output_files, script));
#Create html report
#python ~/afp/chap/log_html.py log/sven3_18h --css ~/afp/afbio/html/table.css > test.html
input_files = [log_dir, output_files]
output_files = os.path.join(log_dir, 'report.html');
final_files.append(output_files)
arguments = {'--css': os.path.join(html_lib, 'table.css')}
if(args.paired):
arguments['--paired'] = True;
script = get_script('log_html.py', chap_package, arguments=arguments, inp = input_files[0], out = output_files)
mlist.append(dependence(input_files, output_files, script));
if(args.annotation):
input_files = os.path.join('peaks', '%s.annotated.gff' % name)
output_files = os.path.join(log_dir, 'peaks.html'), os.path.join(log_dir, 'peaks.tsv');
final_files.extend(output_files)
script = get_script('html_annotated_peaks.py', chap_package, arguments={'--css': os.path.join(html_lib, 'table.css'), '--js': os.path.join(html_lib, 'table.js'), '--ucsc': args.ucsc, '--name': name, '--outdir': log_dir, '--genome': args.genome}, inp = input_files)
mlist.append(dependence(input_files, output_files, script));
#Get header and cleaner for the makefile
mlist.insert(0, get_header(final_files))
todel = "\n\t".join( ['rm %s' % x for x in todel] )
mlist.append('clean:\n\t%s\n' % todel);
return "\n\n".join(mlist), name, [normed_covpath] + [filtered_path]
def makefile_local(m_input):
todel = []
final_files = []
mlist = []
if (type(m_input) == str):
name = os.path.basename(m_input).split(".")[0]
else:
name = os.path.basename(m_input[0]).split(".")[0]
log_dir = os.path.join('log', name)
os.makedirs(os.path.join(project_path, log_dir), exist_ok=True)
log_file = os.path.join(log_dir, "log.txt")
# Processing bowite2 settings
bs_list = get_bowtie_call(bowtie_settings,
args.bowtie_args,
args.index,
m_input,
name,
threads=args.threads,
reads_format=args.reads_format)
bs_list = ['echo', '\'###bowtie\'', '>', log_file, ';'
] + bs_list + ['2>> >(tee -a %s>&2)' % log_file]
# Map reads with bowtie2
input_files = m_input
output_files = os.path.join('sam', '%s.sam' % name)
todel.append(output_files)
script = bs_list
#print(script)
mlist.append(dependence(input_files, output_files, script))
# Demultiplex mapping hits into single and chimeric reads
input_files = output_files # SAM FILE
output_files = os.path.join('chimeras', '%s.bed' % name)
script = get_script('demultiplex_chimera.py',
arguments={
'--maxgap':
chimera_settings['maxgap'],
'--s_distance':
chimera_settings['s_distance'],
'--ch_distance':
chimera_settings['ch_distance'],
'--splice_distance':
chimera_settings['splice_distance'],
'--maxoverlap':
chimera_settings['maxoverlap']
},
inp=input_files,
out=output_files,
package=chimera_package)
mlist.append(dependence(input_files, output_files, script))
#Annotate chimeras with their types
input_files = output_files
output_files = os.path.join('chimeras', '%s.annotated.gff' % name)
script = get_script('annotate_novel.py',
arguments={
'--reverse': True,
'--reference': args.genome
},
inp=input_files,
out=output_files,
package=chimera_package)
mlist.append(dependence(input_files, output_files, script))
#Annotate chimeras with their types
input_files = output_files
output_files = os.path.join('chimeras', '%s.sorted.gff' % name)
script = get_script('sort.py',
arguments={},
inp=input_files,
out=output_files,
package=bin_package)
mlist.append(dependence(input_files, output_files, script))
#Merge sam hits into chimeras in doublebed format
input_files = output_files
output_files = os.path.join('interactions', '%s.gff' % name)
script = get_script('collapse2interaction.py',
arguments={
'--name':
name,
'--dictionary':
os.path.join('interactions', '%s.dict.tsv' % name)
},
inp=input_files,
out=output_files,
package=chimera_package)
mlist.append(dependence(input_files, output_files, script))
final_files.append(output_files)
#Get header and cleaner for the makefile
mlist.insert(0, get_header(final_files))
todel = "\n\t".join(['rm %s' % x for x in todel])
mlist.append('clean:\n\t%s\n' % todel)
return "\n\n".join(mlist), name, final_files
def makefile_local(m_input, control):
#print(m_input)
#print(control)
todel = []
final_files = []
mlist=[];
if(type(m_input) == str):
name = os.path.basename(m_input).split(".")[0];
else:
name = os.path.basename(m_input[0]).split(".")[0];
log_dir = os.path.join('log', name)
os.makedirs(os.path.join(project_path, log_dir), exist_ok=True);
log_file = os.path.join(log_dir, "log.txt")
# Processing bowite2 settings
bs_list = get_bowtie_call(bowtie_settings, args.bowtie_args, args.index, m_input, name, threads=args.threads, reads_format=args.reads_format)
bs_list = ['echo', '\'###bowtie\'', '>', log_file, ';'] + bs_list + ['2>> >(tee -a %s>&2)' % log_file]
# Map reads with bowtie2
input_files = m_input
output_files = os.path.join('sam', '%s.sam' % name)
todel.append(output_files)
script = bs_list
#print(script)
mlist.append(dependence(input_files, output_files, script))
# Convert mappings into coverage
input_files = output_files;
output_files = [os.path.join('coverage', '%s.%s.bed' % (name, x)) for x in ['plus', 'minus']]
arguments = {'--genome': args.genome, '--outstat': log_dir, '--outcoverage': 'coverage', '--ambiguous': args.ambiguous}
if(args.collapsed):
arguments['--collapsed'] = 'True'
script = get_script('get_sam_stat_paired.py', mapping_package, arguments=arguments, inp = input_files)
mlist.append(dependence(input_files, output_files, script));
# UCSC coverage
for of, strand in zip(output_files, ['plus', 'minus']):
trackopts = "\'track name=%s_%s description=\"CHAP seq genomic coverage for sample %s\" %s\'" % (name, strand, name, " ".join(["%s=%s" % x for x in coverage_settings['trackopts'].items()]))
input_files = of
output_files = os.path.join('ucsc', '%s_%s.bedgraph' % (name, strand))
final_files.append(output_files)
script = get_script('coverage2bedgraph.py', mapping_package, arguments={'--multiplier': coverage_settings['multiplier'], '--convert': True, '--trackopts': trackopts}, inp = input_files, out = output_files)
mlist.append(dependence(input_files, output_files, script));
# Assign TPM and annotate the mappings
input_files = [os.path.join('coverage', '%s.%s.bed' % (name, x)) for x in ['plus', 'minus']]
output_files = os.path.join('transcripts', '%s.gff' % name)
covpath = output_files
script = get_script('assign_mappings.py', mapping_package, inp = input_files, out = output_files, arguments={'--transcripts': args.annotation, '--logdir': log_dir} )
mlist.append(dependence(input_files, output_files, script));
final_files.append(output_files)
#Get header and cleaner for the makefile
mlist.insert(0, get_header(final_files))
todel = "\n\t".join( ['rm %s' % x for x in todel] )
mlist.append('clean:\n\t%s\n' % todel);
return "\n\n".join(mlist), name, final_files