def get_repeat_gff(outfile):
"""This task downloads UCSC repetetive RNA types.
"""
ModuleTrna.getRepeatDataFromUCSC(
dbhandle=connectToUCSC(),
repclasses=P.as_list(PARAMS["ucsc_rnatypes"]),
outfile=outfile,
remove_contigs_regex=PARAMS["ucsc_remove_contigs"],
job_memory="3G")
def merge_features(infiles, outfile):
"""This function will merge all of the outputs from featurecounts and
create a single tsv file for all samples"""
features = ModuleTrna.merge_feature_data(infiles)
features.to_csv(outfile, sep="\t", header=True, index=True)
def process_reads(infile, outfile):
"""
Runs trimmomatic quality related trimming
"""
if PARAMS["trimmomatic_run"]:
trimmomatic_options = PARAMS["trimmomatic_options"]
trimmomatic_options = "ILLUMINACLIP:%s:%s:%s:%s" % (
PARAMS["trimmomatic_adapter"], PARAMS["trimmomatic_mismatches"],
PARAMS["trimmomatic_p_thresh"],
PARAMS["trimmomatic_c_thresh"]) + "\t" + trimmomatic_options
phred = PARAMS["trimmomatic_phred"]
ModuleTrna.process_trimmomatic(infile, outfile, phred,
trimmomatic_options)
else:
statement = "cp %(infile)s %(outfile)s"
P.run(statement)
def merge_idx_stats(infiles, outfile):
final_df = ModuleTrna.merge_counts_data(infiles)
final_df.to_csv(outfile, sep="\t", compression="gzip")
def connectToUCSC():
return ModuleTrna.connectToUCSC(host=PARAMS["ucsc_host"],
user=PARAMS["ucsc_user"],
database=PARAMS["ucsc_database"])
def build_bam_stats(infiles, outfile):
'''count number of reads mapped, duplicates, etc.
Excludes regions overlapping repetitive RNA sequences
Parameters
----------
infiles : list
infiles[0] : str
Input filename in :term:`bam` format
infiles[1] : str
Input filename with number of reads per sample
outfile : str
Output filename with read stats
annotations_interface_rna_gtf : str
:term:`PARMS`. :term:`gtf` format file with repetitive rna
'''
job_memory = "32G"
# Only one sample
if len(infiles) == 3:
bamfile, readsfile, rna_file = infiles
# If there are multiple samples, programme specifies which .nreads file to use, by matching name to bam file
else:
bamfile = infiles[0]
rna_file = infiles[-1]
# Split file name up into directory and file name(/), then further split up by file name and file type and take file name (.)
bam_name = bamfile.split('/')[1].split('.')[0]
for i in range(1, len(infiles) - 1):
nread_name = infiles[i].split('/')[1].split('.')[0]
if bam_name == nread_name:
readsfile = infiles[i]
break
else:
continue
nreads = ModuleTrna.getNumReadsFromReadsFile(readsfile)
track = P.snip(os.path.basename(readsfile), ".nreads")
# if a fastq file exists, submit for counting
if os.path.exists(track + ".fastq.gz"):
fastqfile = track + ".fastq.gz"
elif os.path.exists(track + ".fastq.1.gz"):
fastqfile = track + ".fastq.1.gz"
else:
fastqfile = None
if fastqfile is not None:
fastq_option = "--fastq-file=%s" % fastqfile
else:
fastq_option = ""
statement = '''
cgat bam2stats
%(fastq_option)s
--force-output
--mask-bed-file=%(rna_file)s
--ignore-masked-reads
--num-reads=%(nreads)i
--output-filename-pattern=%(outfile)s.%%s
< %(bamfile)s
> %(outfile)s
'''
P.run(statement)