def mkdup(self, input_bam, output_prefix):
output_bam = "%s.bam" % output_prefix
stat_file = "%s.stat" % output_prefix
options = self.parse_options(input_bam, output_bam, stat_file)
self.execute(options=options)
SamtoolsV1.index(output_bam)
def clipoverlap(self, input, output, poolsize=None):
from RouToolPa.Tools.Samtools import SamtoolsV1
options = self.parse_options(input, output, poolsize=poolsize)
self.execute(options=options, cmd="bam clipOverlap")
SamtoolsV1.index(output)
sort_by_name=False,
max_per_sorting_thread_memory="10G")
if args.add_read_groups_by_picard:
sorted_alignment_picard_groups = "%s.picard_groups.%s" % (
args.prefix, args.alignment_format)
AddOrReplaceReadGroups.add_read_groups(sorted_alignment,
sorted_alignment_picard_groups,
RGID=args.prefix,
RGLB=args.prefix,
RGPL=args.prefix,
RGSM=args.prefix,
RGPU=args.prefix)
if args.alignment_format == "bam":
SamtoolsV1.index(sorted_alignment_picard_groups
if sorted_alignment_picard_groups else sorted_alignment)
MarkDuplicates.run(
sorted_alignment_picard_groups if sorted_alignment_picard_groups else
sorted_alignment, final_alignment, duplicates_stat_file)
if args.alignment_format == "bam":
SamtoolsV1.index(final_alignment)
"""
GenomeCov.get_coverage(final_alignment, genome_bed, coverage_file)
if not args.retain_temp:
os.remove(sorted_alignment)
if args.add_read_groups_by_picard:
os.remove(sorted_alignment_picard_groups)
if args.calculate_median_coverage or args.calculate_mean_coverage:
def align(self,
genome_dir,
forward_read_list,
reverse_read_list=None,
annotation_gtf=None,
sample=None,
feature_from_gtf_to_use_as_exon=None,
exon_tag_to_use_as_transcript_id=None,
exon_tag_to_use_as_gene_id=None,
length_of_sequences_flanking_junction=None,
junction_tab_file_list=None,
three_prime_trim=None,
five_prime_trim=None,
adapter_seq_for_three_prime_clip=None,
max_mismatch_percent_for_adapter_trimming=None,
three_prime_trim_after_adapter_clip=None,
output_type="BAM",
sort_bam=True,
max_memory_per_thread_for_bam_sorting="4G",
include_unmapped_reads_in_bam=True,
output_unmapped_reads=True,
output_dir="./",
two_pass_mode=False,
max_intron_length=None):
if reverse_read_list:
if len(forward_read_list) != len(reverse_read_list):
raise ValueError("Wrong read file pairing")
options = " --runThreadN %i" % self.threads
options += " --genomeDir %s" % os.path.abspath(genome_dir)
options += " --sjdbGTFfile %s" % annotation_gtf if annotation_gtf else ""
options += " --sjdbGTFtagExonParentTranscript %s" % exon_tag_to_use_as_transcript_id if exon_tag_to_use_as_transcript_id else ""
options += " --sjdbGTFtagExonParentGene %s" % exon_tag_to_use_as_gene_id if exon_tag_to_use_as_gene_id else ""
options += " --sjdbGTFfeatureExon %s" % feature_from_gtf_to_use_as_exon if feature_from_gtf_to_use_as_exon else ""
options += " --sjdbOverhang %i" % length_of_sequences_flanking_junction if length_of_sequences_flanking_junction else ""
options += (" --sjdbFileChrStartEnd %s" %
(os.path.abspath(junction_tab_file_list) if isinstance(
junction_tab_file_list, str) else " ".join(
map(os.path.abspath, junction_tab_file_list)))
) if junction_tab_file_list else ""
#print(forward_read_list)
forward_read_abs_path_list = [
os.path.abspath(forward_read_list)
] if isinstance(forward_read_list, str) else list(
map(os.path.abspath, forward_read_list))
reverse_read_abs_path_list = (
[os.path.abspath(reverse_read_list)] if isinstance(
reverse_read_list, str) else list(
map(os.path.abspath,
reverse_read_list))) if reverse_read_list else None
#print(forward_read_abs_path_list)
forward_read_abs_path_list = self.add_external_extraction_to_filelist(
forward_read_abs_path_list)
reverse_read_abs_path_list = self.add_external_extraction_to_filelist(
reverse_read_abs_path_list) if reverse_read_list else None
#print(forward_read_abs_path_list)
options += " --readFilesIn %s" % " ".join(forward_read_abs_path_list)
options += (
" %s" %
" ".join(reverse_read_abs_path_list) if reverse_read_abs_path_list
else "") if reverse_read_abs_path_list else ""
options += " --clip3pNbases %i" % three_prime_trim if three_prime_trim else ""
options += " --clip5pNbases %i" % five_prime_trim if five_prime_trim else ""
options += " --clip3pAdapterSeq %s" % adapter_seq_for_three_prime_clip if adapter_seq_for_three_prime_clip else ""
options += " --clip3pAdapterMMp %f" % max_mismatch_percent_for_adapter_trimming if max_mismatch_percent_for_adapter_trimming else ""
options += " --clip3pAfterAdapterNbases %i" % three_prime_trim_after_adapter_clip if three_prime_trim_after_adapter_clip else ""
options += " --outSAMtype %s %s" % (
output_type, "Unsorted"
) # "SortedByCoordinate" if sort_bam else "Unsorted")
#options += " --limitBAMsortRAM %i" % max_memory_for_bam_sorting if max_memory_for_bam_sorting else ""
options += " --outSAMunmapped Within" if include_unmapped_reads_in_bam else ""
options += " --outReadsUnmapped Fastx" if output_unmapped_reads else ""
options += " --outFileNamePrefix %s" % output_dir if output_dir else ""
options += " --twopassMode Basic" if two_pass_mode else ""
options += " --alignIntronMax %i" % max_intron_length if max_intron_length else ""
self.execute(options)
if sort_bam:
print("\tSorting...")
unsorted_bam = "%s/Aligned.out.bam" % output_dir
sorted_bam = "%s/%s.bam" % (output_dir,
("%s.sorted" % sample if sample else
"Aligned.sortedByCoord.out"))
SamtoolsV1.threads = self.threads
SamtoolsV1.sort(
unsorted_bam,
sorted_bam,
max_memory_per_thread=max_memory_per_thread_for_bam_sorting)
print("\tIndexing bam file...")
SamtoolsV1.index(sorted_bam)
def align(self,
sample_dir,
reference_index,
aligner="bwa",
sample_list=None,
outdir="./",
quality_score_type="phred33",
read_suffix="",
read_extension="fastq",
alignment_format="bam",
threads=None,
mark_duplicates=True,
platform="Illumina",
add_read_groups_by_picard=False,
gzipped_reads=False):
self.init_tools(threads=threads)
samples = self.get_sample_list(sample_dir, sample_list=sample_list)
self.prepare_dirs(samples, outdir=outdir)
if aligner == "bowtie2":
aligner_tool = Bowtie2
elif aligner == "bwa":
aligner_tool = BWA
else:
raise ValueError("")
for sample in samples:
read_prefix = "%s/%s/%s%s" % (sample_dir, sample, sample,
read_suffix)
forward_reads = "%s_1.%s%s" % (read_prefix, read_extension,
".gz" if gzipped_reads else "")
reverse_reads = "%s_2.%s%s" % (read_prefix, read_extension,
".gz" if gzipped_reads else "")
output_prefix = "%s/%s/%s" % (outdir, sample, sample)
raw_alignment = "%s.%s" % (output_prefix, alignment_format)
final_alignment = "%s.mkdup.%s" % (output_prefix, alignment_format)
duplicates_stat_file = "%s.duplicates.stat" % output_prefix
coverage_file = "%s.coverage.bed" % output_prefix
sorted_alignment_picard_groups = None
aligner_tool.align(
reference_index,
forward_reads_list=forward_reads,
reverse_reads_list=reverse_reads,
unpaired_reads_list=None,
quality_score=quality_score_type,
output_prefix=output_prefix,
output_format=alignment_format,
read_group_name=sample,
PU="x",
SM=sample,
platform=platform,
LB="x",
sort_by_coordinate=True,
sort_by_name=False,
max_per_sorting_thread_memory=str(
max(int(self.max_memory / self.threads), 1)) + "G")
if add_read_groups_by_picard:
sorted_alignment_picard_groups = "%s.picard_groups.%s" % (
output_prefix, alignment_format)
AddOrReplaceReadGroups.add_read_groups(
raw_alignment,
sorted_alignment_picard_groups,
RGID=sample,
RGLB=sample,
RGPL=platform,
RGSM=sample,
RGPU=sample)
if alignment_format == "bam":
SamtoolsV1.index(
sorted_alignment_picard_groups
if sorted_alignment_picard_groups else raw_alignment)
if mark_duplicates:
MarkDuplicates.run(
sorted_alignment_picard_groups
if sorted_alignment_picard_groups else raw_alignment,
final_alignment, duplicates_stat_file)
if alignment_format == "bam":
SamtoolsV1.index(final_alignment)
sample_list = args.samples if args.samples else Pipeline.get_sample_list(
args.samples_dir)
FileRoutines.safe_mkdir(args.output_dir)
for sample in sample_list:
print("Handling %s" % sample)
sample_dir = "%s/%s/" % (args.samples_dir, sample)
alignment_sample_dir = "%s/%s/" % (args.output_dir, sample)
FileRoutines.safe_mkdir(alignment_sample_dir)
filetypes, forward_files, reverse_files, se_files = FileRoutines.make_lists_forward_and_reverse_files(
sample_dir)
print("\tAligning reads...")
STAR.align_miRNA(
args.genome_dir,
se_files,
output_dir=alignment_sample_dir,
annotation_gtf=args.annotation_gtf if not args.genome_fasta else None,
max_memory_for_bam_sorting=args.max_memory_for_bam_sorting,
max_alignments_per_read=args.max_number_of_alignments_per_read,
no_soft_clip=args.enable_soft_clipping,
max_number_of_mismatches=args.max_number_of_mismatches,
max_relative_number_of_mismatches=args.
max_relative_number_of_mismatches)
print("\tIndexing bam file...")
resulting_bam_file = "%s/Aligned.sortedByCoord.out.bam" % alignment_sample_dir
SamtoolsV1.index(resulting_bam_file)