def produce_bowtie2_alignments_old(reads,
sam_fn,
index_prefix,
genome_dir,
score_min,
):
bowtie2_options = {'local': True,
#'report_all': True,
'report_up_to': 10,
'seed_mismatches': 1,
'seed_interval_function': 'C,1,0',
'seed_length': 10,
#'threads': 12,
}
mapping_tools.map_bowtie2(index_prefix,
None,
None,
sam_fn,
unpaired_Reads=reads,
custom_binary=True,
score_min=score_min,
**bowtie2_options)
sam_file = pysam.Samfile(sam_fn)
region_fetcher = genomes.build_region_fetcher(genome_dir, load_references=True)
mapping_groups = utilities.group_by(sam_file, lambda m: m.qname)
for qname, group in mapping_groups:
alignments = [mapping_to_alignment(mapping, sam_file, region_fetcher)
for mapping in group if not mapping.is_unmapped]
yield qname, alignments
def produce_bowtie2_alignments(
reads,
index_prefix,
genome_dir,
score_min,
):
bowtie2_options = {
'local': True,
'report_up_to': 10,
'seed_mismatches': 1,
'seed_interval_function': 'C,1,0',
'seed_length': 10,
}
sam_file, mappings = mapping_tools.map_bowtie2(index_prefix,
reads=reads,
custom_binary=True,
score_min=score_min,
yield_mappings=True,
**bowtie2_options)
base_lookup = genomes.build_base_lookup(genome_dir, sam_file)
mapping_groups = utilities.group_by(mappings, lambda m: m.qname)
for qname, group in mapping_groups:
group = sorted(group, key=lambda m: (m.tid, m.pos))
alignments = [
mapping_to_alignment(mapping, sam_file, base_lookup)
for mapping in group if not mapping.is_unmapped
]
yield qname, alignments
def produce_bowtie2_alignments(reads,
index_prefix,
genome_dir,
score_min,
):
bowtie2_options = {'local': True,
#'report_all': True,
'report_up_to': 10,
'seed_mismatches': 1,
'seed_interval_function': 'C,1,0',
'seed_length': 10,
}
sam_file, mappings = mapping_tools.map_bowtie2(index_prefix,
reads=reads,
custom_binary=True,
score_min=score_min,
yield_mappings=True,
**bowtie2_options)
region_fetcher = genomes.build_region_fetcher(genome_dir, load_references=True)
mapping_groups = utilities.group_by(mappings, lambda m: m.qname)
for qname, group in mapping_groups:
group = sorted(group, key=lambda m: (m.tid, m.pos))
alignments = [mapping_to_alignment(mapping, sam_file, region_fetcher)
for mapping in group if not mapping.is_unmapped]
yield qname, alignments
def pre_filter_paired(contaminant_index, read_pairs, bam_fn, error_fn):
unmapped_pairs = mapping_tools.map_bowtie2(
contaminant_index,
output_file_name=bam_fn,
bam_output=True,
read_pairs=read_pairs,
max_insert_size=1500,
suppress_unaligned_SAM=True,
report_all=True,
error_file_name=error_fn,
yield_unaligned=True,
)
return unmapped_pairs
def pre_filter(contaminant_index, reads, bam_fn, error_fn='/dev/null'):
''' Maps reads to contaminant_index. Return an iterator over reads that
don't map.
'''
unmapped_reads = mapping_tools.map_bowtie2(
contaminant_index,
output_file_name=bam_fn,
reads=reads,
bam_output=True,
report_all=True,
omit_secondary_seq=True,
suppress_unaligned_SAM=True,
error_file_name=error_fn,
yield_unaligned=True,
)
return unmapped_reads
def pre_filter(contaminant_index, reads, bam_fn, error_fn="/dev/null"):
""" Maps reads to contaminant_index. Return an iterator over reads that
don't map.
"""
unmapped_reads = mapping_tools.map_bowtie2(
contaminant_index,
output_file_name=bam_fn,
reads=reads,
bam_output=True,
report_all=True,
omit_secondary_seq=True,
suppress_unaligned_SAM=True,
error_file_name=error_fn,
yield_unaligned=True,
)
return unmapped_reads
def pre_filter_paired(
contaminant_index,
read_pairs,
bam_fn,
error_fn,
):
unmapped_pairs = mapping_tools.map_bowtie2(
contaminant_index,
output_file_name=bam_fn,
bam_output=True,
read_pairs=read_pairs,
max_insert_size=1500,
suppress_unaligned_SAM=True,
report_all=True,
error_file_name=error_fn,
yield_unaligned=True,
)
return unmapped_pairs
#fastq_fn = '/home/jah/projects/arlen/experiments/lareau_elife/Cycloheximide_replicate_1/data/SRR1363415.fastq'
#fastq_fn = '/home/jah/projects/arlen/experiments/arribere_gr/S288C_TLSeq2/data/SRR825166.fastq'
#fastq_fn = '/home/jah/projects/arlen/experiments/baudin-baillieu_cell_reports/traductome_PSI-_rep_2/data/SRR594901.fastq'
fastq_fn = '/home/jah/projects/arlen/experiments/baudin-baillieu_cell_reports/Ribo-seq_[PSI+]_rep1/data/SRR1190356.fastq'
index_prefix = '/home/jah/projects/arlen/data/organisms/saccharomyces_cerevisiae/EF4/genome/genome'
root, ext = os.path.splitext(fastq_fn)
small_fastq_fn = '{0}_small.fastq'.format(root)
small_sam_fn = '{0}_small.sam'.format(root)
head_command = ['head', '-n', '100000', fastq_fn]
subprocess.check_call(head_command, stdout=open(small_fastq_fn, 'w'))
mapping_tools.map_bowtie2(small_fastq_fn,
index_prefix,
small_sam_fn,
seed_length=12,
local=True)
positions = [Counter() for i in range(40)]
qlens = Counter()
for read in pysam.Samfile(small_sam_fn):
if read.is_unmapped:
continue
qlens[read.qlen] += 1
trimmed = read.seq[read.qend:]
for p, b in zip(positions, trimmed):
p[b] += 1
#fastq_fn = '/home/jah/projects/arlen/experiments/belgium_3_5_14/wt/data/wt_cDNA.140219.HiSeq2500.FCB.lane1.R1.fastq'
#fastq_fn = '/home/jah/projects/arlen/experiments/dunn_elife/YCF182_110222_HiSeq.fq'
#fastq_fn = '/home/jah/projects/arlen/experiments/lareau_elife/Cycloheximide_replicate_1/data/SRR1363415.fastq'
#fastq_fn = '/home/jah/projects/arlen/experiments/arribere_gr/S288C_TLSeq2/data/SRR825166.fastq'
#fastq_fn = '/home/jah/projects/arlen/experiments/baudin-baillieu_cell_reports/traductome_PSI-_rep_2/data/SRR594901.fastq'
fastq_fn = '/home/jah/projects/arlen/experiments/baudin-baillieu_cell_reports/Ribo-seq_[PSI+]_rep1/data/SRR1190356.fastq'
index_prefix = '/home/jah/projects/arlen/data/organisms/saccharomyces_cerevisiae/EF4/genome/genome'
root, ext = os.path.splitext(fastq_fn)
small_fastq_fn = '{0}_small.fastq'.format(root)
small_sam_fn = '{0}_small.sam'.format(root)
head_command = ['head', '-n', '100000', fastq_fn]
subprocess.check_call(head_command, stdout=open(small_fastq_fn, 'w'))
mapping_tools.map_bowtie2(small_fastq_fn, index_prefix, small_sam_fn, seed_length=12, local=True)
positions = [Counter() for i in range(40)]
qlens = Counter()
for read in pysam.Samfile(small_sam_fn):
if read.is_unmapped:
continue
qlens[read.qlen] += 1
trimmed = read.seq[read.qend:]
for p, b in zip(positions, trimmed):
p[b] += 1
for p in positions:
if not p:
