Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Prepend chromosomes with chr to match the SAM/BAM files. #132

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion chanjo/annotator/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
from __future__ import absolute_import

from .cli import annotate
from .core import annotate_bed_stream
from .core import annotate_bed_stream, apply_bed_stream
from .stages import (
assign_relative_positions,
calculate_metrics,
Expand Down
50 changes: 37 additions & 13 deletions chanjo/annotator/core.py
Original file line number Diff line number Diff line change
Expand Up @@ -22,17 +22,15 @@
)
from ..utils import bed_to_interval, split, validate_bed_format


def annotate_bed_stream(bed_stream, bam_path, cutoff=10, extension=0,
contig_prefix='', bp_threshold=17000):
"""Annotate all intervals from a BED-file stream.

Yields tuple data for each interval with calculated coverage and
completeness.

def apply_bed_stream(bed_stream, bam_path, fn, extension=0,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a nice addition!

contig_prefix='', bp_threshold=17000):
"""Maps a function to all intervals of a BED stream
Args:
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would be awesome with a simple description of the fn argument here!

bed_stream (sequence): usually a BED-file handle to read from
bam_path (str): path to BAM-file
fn: function that takes a list of intervals and read depths
and computes a summary statistic over them. See
annotator.stages.calculate_metrics for an example.
cutoff (int, optional): threshold for completeness calculation,
defaults to 10
extension (int, optional): number of bases to extend each interval
Expand All @@ -41,10 +39,6 @@ def annotate_bed_stream(bed_stream, bam_path, cutoff=10, extension=0,
defaults to empty string
bp_threshold (int, optional): optimization threshold for reading
BAM-file in chunks, default to 17000

Yields:
tuple: :class:`chanjo.BaseInterval`, coverage (float), and
completeness (float)
"""
# setup: connect to BAM-file
bam = BamFile(bam_path)
Expand All @@ -62,5 +56,35 @@ def annotate_bed_stream(bed_stream, bam_path, cutoff=10, extension=0,
group_intervals(bp_threshold=bp_threshold), # group by threshold
map(process_interval_group(bam)), # read coverage
concat, # flatten list of lists
map(calculate_metrics(threshold=cutoff)) # calculate cov./compl.
map(fn) # map provided function
)


def annotate_bed_stream(bed_stream, bam_path, cutoff=10, extension=0,
contig_prefix='', bp_threshold=17000):
"""Annotate all intervals from a BED-file stream.

Yields tuple data for each interval with calculated coverage and
completeness.

Args:
bed_stream (sequence): usually a BED-file handle to read from
bam_path (str): path to BAM-file
cutoff (int, optional): threshold for completeness calculation,
defaults to 10
extension (int, optional): number of bases to extend each interval
with (+/-), defaults to 0
contig_prefix (str, optional): rename contigs by prefixing,
defaults to empty string
bp_threshold (int, optional): optimization threshold for reading
BAM-file in chunks, default to 17000

Yields:
tuple: :class:`chanjo.BaseInterval`, coverage (float), and
completeness (float)
"""
# setup: connect to BAM-file
fn = calculate_metrics(threshold=cutoff)

return apply_bed_stream(bed_stream, bam_path, fn, extension,
contig_prefix, bp_threshold)
12 changes: 6 additions & 6 deletions chanjo/demo/files/CCDS.mini.txt
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#chromosome nc_accession gene gene_id ccds_id ccds_status cds_strand cds_from cds_to cds_locations match_type
1 NC_000001.8 LINC00115 79854 CCDS1.1 Withdrawn - 801942 802433 [801942-802433] Identical
1 NC_000001.10 SAMD11 148398 CCDS2.2 Public + 11 35 [11-18, 25-30, 32-35] Identical
22 NC_000022.10 RFPL2 10739 CCDS54521.1 Public - 32586758 32589173 [32586758-32587338, 32588888-32589173] Identical
22 NC_000022.10 RFPL2 10739 CCDS46694.1 Public - 32586758 32589260 [32586758-32587338, 32588888-32589260] Identical
X NC_000023.10 TRO 7216 CCDS59529.1 Public + 54951423 54957452 [54951423-54951500, 54952024-54952115, 54952842-54952921, 54953015-54953057, 54953475-54953537, 54954099-54954213, 54955035-54957452] Identical
Y NC_000024.9 TSPY8 728403 CCDS59533.1 Public + 9195451 9198013 [9195451-9195936, 9196544-9196621, 9196750-9196861, 9196963-9197108, 9197215-9197296, 9197991-9198013] Identical
chr1 NC_000001.8 LINC00115 79854 CCDS1.1 Withdrawn - 801942 802433 [801942-802433] Identical
chr1 NC_000001.10 SAMD11 148398 CCDS2.2 Public + 11 35 [11-18, 25-30, 32-35] Identical
chr22 NC_000022.10 RFPL2 10739 CCDS54521.1 Public - 32586758 32589173 [32586758-32587338, 32588888-32589173] Identical
chr22 NC_000022.10 RFPL2 10739 CCDS46694.1 Public - 32586758 32589260 [32586758-32587338, 32588888-32589260] Identical
chrX NC_000023.10 TRO 7216 CCDS59529.1 Public + 54951423 54957452 [54951423-54951500, 54952024-54952115, 54952842-54952921, 54953015-54953057, 54953475-54953537, 54954099-54954213, 54955035-54957452] Identical
chrY NC_000024.9 TSPY8 728403 CCDS59533.1 Public + 9195451 9198013 [9195451-9195936, 9196544-9196621, 9196750-9196861, 9196963-9197108, 9197215-9197296, 9197991-9198013] Identical
38 changes: 19 additions & 19 deletions tests/fixtures/CCDS.mini.bed
Original file line number Diff line number Diff line change
@@ -1,19 +1,19 @@
1 11 18 1-11-18 0 + CCDS2.2 SAMD11
1 25 30 1-25-30 0 + CCDS2.2 SAMD11
1 32 35 1-32-35 0 + CCDS2.2 SAMD11
22 32586758 32587338 22-32586758-32587338 0 - CCDS54521.1,CCDS46694.1 RFPL2,RFPL2
22 32588888 32589260 22-32588888-32589260 0 - CCDS46694.1 RFPL2
22 32588888 32589173 22-32588888-32589173 0 - CCDS54521.1 RFPL2
X 54951423 54951500 X-54951423-54951500 0 + X-CCDS59529.1 X-TRO
X 54952024 54952115 X-54952024-54952115 0 + X-CCDS59529.1 X-TRO
X 54952842 54952921 X-54952842-54952921 0 + X-CCDS59529.1 X-TRO
X 54953015 54953057 X-54953015-54953057 0 + X-CCDS59529.1 X-TRO
X 54953475 54953537 X-54953475-54953537 0 + X-CCDS59529.1 X-TRO
X 54954099 54954213 X-54954099-54954213 0 + X-CCDS59529.1 X-TRO
X 54955035 54957452 X-54955035-54957452 0 + X-CCDS59529.1 X-TRO
Y 9195451 9195936 Y-9195451-9195936 0 + Y-CCDS59533.1 Y-TSPY8
Y 9196544 9196621 Y-9196544-9196621 0 + Y-CCDS59533.1 Y-TSPY8
Y 9196750 9196861 Y-9196750-9196861 0 + Y-CCDS59533.1 Y-TSPY8
Y 9196963 9197108 Y-9196963-9197108 0 + Y-CCDS59533.1 Y-TSPY8
Y 9197215 9197296 Y-9197215-9197296 0 + Y-CCDS59533.1 Y-TSPY8
Y 9197991 9198013 Y-9197991-9198013 0 + Y-CCDS59533.1 Y-TSPY8
chr1 11 18 1-11-18 0 + CCDS2.2 SAMD11
chr1 25 30 1-25-30 0 + CCDS2.2 SAMD11
chr1 32 35 1-32-35 0 + CCDS2.2 SAMD11
chr22 32586758 32587338 22-32586758-32587338 0 - CCDS54521.1,CCDS46694.1 RFPL2,RFPL2
chr22 32588888 32589260 22-32588888-32589260 0 - CCDS46694.1 RFPL2
chr22 32588888 32589173 22-32588888-32589173 0 - CCDS54521.1 RFPL2
chrX 54951423 54951500 X-54951423-54951500 0 + X-CCDS59529.1 X-TRO
chrX 54952024 54952115 X-54952024-54952115 0 + X-CCDS59529.1 X-TRO
chrX 54952842 54952921 X-54952842-54952921 0 + X-CCDS59529.1 X-TRO
chrX 54953015 54953057 X-54953015-54953057 0 + X-CCDS59529.1 X-TRO
chrX 54953475 54953537 X-54953475-54953537 0 + X-CCDS59529.1 X-TRO
chrX 54954099 54954213 X-54954099-54954213 0 + X-CCDS59529.1 X-TRO
chrX 54955035 54957452 X-54955035-54957452 0 + X-CCDS59529.1 X-TRO
chrY 9195451 9195936 Y-9195451-9195936 0 + Y-CCDS59533.1 Y-TSPY8
chrY 9196544 9196621 Y-9196544-9196621 0 + Y-CCDS59533.1 Y-TSPY8
chrY 9196750 9196861 Y-9196750-9196861 0 + Y-CCDS59533.1 Y-TSPY8
chrY 9196963 9197108 Y-9196963-9197108 0 + Y-CCDS59533.1 Y-TSPY8
chrY 9197215 9197296 Y-9197215-9197296 0 + Y-CCDS59533.1 Y-TSPY8
chrY 9197991 9198013 Y-9197991-9198013 0 + Y-CCDS59533.1 Y-TSPY8
38 changes: 19 additions & 19 deletions tests/fixtures/CCDS.mini.coverage.bed
Original file line number Diff line number Diff line change
@@ -1,20 +1,20 @@
#{"group_id": null, "sample_id": "tiriwiro", "coverage_source": "/Users/robinandeer/Projects/clinical-genomics/qxt/bam/Sample_E2-QXT-prep2/sorted.bam", "cutoff": 10, "extension": 0}
1 12 18 1-11-18 0 + CCDS2.2 SAMD11 0.0 0.0
1 26 30 1-25-30 0 + CCDS2.2 SAMD11 0.0 0.0
1 33 35 1-32-35 0 + CCDS2.2 SAMD11 0.0 0.0
22 32586759 32587338 22-32586758-32587338 0 - CCDS54521.1,CCDS46694.1 RFPL2,RFPL2 139.862068966 1.0
22 32588889 32589260 22-32588888-32589260 0 - CCDS46694.1 RFPL2 146.86827957 1.0
22 32588889 32589173 22-32588888-32589173 0 - CCDS54521.1 RFPL2 140.631578947 1.0
X 54951424 54951500 X-54951423-54951500 0 + X-CCDS59529.1 X-TRO 13.8961038961 1.0
X 54952025 54952115 X-54952024-54952115 0 + X-CCDS59529.1 X-TRO 81.5714285714 1.0
X 54952843 54952921 X-54952842-54952921 0 + X-CCDS59529.1 X-TRO 37.7974683544 1.0
X 54953016 54953057 X-54953015-54953057 0 + X-CCDS59529.1 X-TRO 13.0714285714 0.9523809523809523
X 54953476 54953537 X-54953475-54953537 0 + X-CCDS59529.1 X-TRO 19.5 1.0
X 54954100 54954213 X-54954099-54954213 0 + X-CCDS59529.1 X-TRO 23.5350877193 1.0
X 54955036 54957452 X-54955035-54957452 0 + X-CCDS59529.1 X-TRO 43.4224244932 1.0
Y 9195452 9195936 Y-9195451-9195936 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
Y 9196545 9196621 Y-9196544-9196621 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
Y 9196751 9196861 Y-9196750-9196861 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
Y 9196964 9197108 Y-9196963-9197108 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
Y 9197216 9197296 Y-9197215-9197296 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
Y 9197992 9198013 Y-9197991-9198013 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chr1 12 18 1-11-18 0 + CCDS2.2 SAMD11 0.0 0.0
chr1 26 30 1-25-30 0 + CCDS2.2 SAMD11 0.0 0.0
chr1 33 35 1-32-35 0 + CCDS2.2 SAMD11 0.0 0.0
chr22 32586759 32587338 22-32586758-32587338 0 - CCDS54521.1,CCDS46694.1 RFPL2,RFPL2 139.862068966 1.0
chr22 32588889 32589260 22-32588888-32589260 0 - CCDS46694.1 RFPL2 146.86827957 1.0
chr22 32588889 32589173 22-32588888-32589173 0 - CCDS54521.1 RFPL2 140.631578947 1.0
chrX 54951424 54951500 X-54951423-54951500 0 + X-CCDS59529.1 X-TRO 13.8961038961 1.0
chrX 54952025 54952115 X-54952024-54952115 0 + X-CCDS59529.1 X-TRO 81.5714285714 1.0
chrX 54952843 54952921 X-54952842-54952921 0 + X-CCDS59529.1 X-TRO 37.7974683544 1.0
chrX 54953016 54953057 X-54953015-54953057 0 + X-CCDS59529.1 X-TRO 13.0714285714 0.9523809523809523
chrX 54953476 54953537 X-54953475-54953537 0 + X-CCDS59529.1 X-TRO 19.5 1.0
chrX 54954100 54954213 X-54954099-54954213 0 + X-CCDS59529.1 X-TRO 23.5350877193 1.0
chrX 54955036 54957452 X-54955035-54957452 0 + X-CCDS59529.1 X-TRO 43.4224244932 1.0
chrY 9195452 9195936 Y-9195451-9195936 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chrY 9196545 9196621 Y-9196544-9196621 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chrY 9196751 9196861 Y-9196750-9196861 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chrY 9196964 9197108 Y-9196963-9197108 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chrY 9197216 9197296 Y-9197215-9197296 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0
chrY 9197992 9198013 Y-9197991-9198013 0 + Y-CCDS59533.1 Y-TSPY8 0.0 0.0