Merge pull request #63 from standage/cli/sum

Added simple summary script to CLI

CHANGELOG.md

@@ -2,6 +2,14 @@
 All notable changes to this project will be documented in this file.
 This project adheres to [Semantic Versioning](http://semver.org/).
 
+## [0.3.3] - 2017-06-21
+### Fixed
+- Missing `extent` query from the index implementation.
+- Aliased `index.keys()` to `index.seqids`.
+
+### Added
+- Script `tag sum` to provide very basic summaries of genomic GFF3 files.
+
 ## [0.3.2] - 2017-04-19
 ### Added
 - Pseudo-features for better handling and sorting of top-level multi-features.

tag/__main__.py

@@ -15,6 +15,7 @@
     'gff3': tag.cli.gff3.main,
     'occ': tag.cli.occ.main,
     'pmrna': tag.cli.pmrna.main,
+    'sum': tag.cli.sum.main,
 }
 
 

tag/cli/__init__.py

@@ -13,6 +13,7 @@
 from . import gff3
 from . import occ
 from . import pmrna
+from . import sum
 
 
 def parser():
@@ -22,9 +23,10 @@ def parser():
     parser.add_argument('-l', '--logfile', metavar='FILE', default=sys.stderr,
                         type=argparse.FileType('w'))
     subparsers = parser.add_subparsers(dest='cmd', metavar='cmd',
-                                       help='gff3 | occ | pmrna')
+                                       help='gff3 | occ | pmrna | sum')
     tag.cli.gff3.subparser(subparsers)
     tag.cli.occ.subparser(subparsers)
     tag.cli.pmrna.subparser(subparsers)
+    tag.cli.sum.subparser(subparsers)
 
     return parser

tag/cli/sum.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python
+#
+# -----------------------------------------------------------------------------
+# Copyright (C) 2017 Daniel Standage <[email protected]>
+#
+# This file is part of tag (http://github.com/standage/tag) and is licensed
+# under the BSD 3-clause license: see LICENSE.
+# -----------------------------------------------------------------------------
+
+from __future__ import print_function
+import argparse
+from collections import defaultdict
+import tag
+
+
+def subparser(subparsers):
+    desc = 'Briefly summarize a GFF3 file'
+    subparser = subparsers.add_parser('sum', description=desc)
+    subparser.add_argument('gff3', help='input file')
+
+
+def main(args):
+    annot = tag.index.Index()
+    annot.consume_file(args.gff3)
+    annot.yield_inferred = False
+
+    seqs = list(annot.seqids)
+    size = 0
+    for seqid in seqs:
+        start, end = annot.extent(seqid)
+        size += end - start
+
+    counts = defaultdict(int)
+    maxlens = defaultdict(int)
+    for feature in tag.select.features(annot):
+        for subfeat in feature:
+            counts[subfeat.type] += 1
+            maxlens[subfeat.type] = max(len(subfeat), maxlens[subfeat.type])
+
+    sumstr = 'Summary for file "{}":\n'.format(args.gff3)
+    sumstr += '    - {} annotated sequences'.format(len(seqs))
+    sumstr += ' for a total length of {} bp\n'.format(size)
+    sumstr += '    - {} annotated features'.format(sum(counts.values()))
+    sumstr += ' (or feature entries)\n'
+    for ft in sorted(counts):
+        sumstr += '        - {} entries of type {}'.format(counts[ft], ft)
+        sumstr += ', maximum length: {} bp\n'.format(maxlens[ft])
+
+    print(sumstr.strip())

tests/test_cli.py

@@ -98,3 +98,12 @@ def test_pmrna(capsys):
     out, err = capsys.readouterr()
     exp_out = tag.pkgdata('nanosplice-primary.gff3').read()
     assert out.strip() == exp_out.strip()
+
+
+def test_sum(capsys):
+    infile = 'tests/testdata/GCF_001639295.1_ASM163929v1_genomic.gff.gz'
+    args = tag.cli.parser().parse_args(['sum', infile])
+    tag.cli.sum.main(args)
+
+    out, err = capsys.readouterr()
+    assert out.strip() == tag.pkgdata('sum-test-out.txt').read().strip()

tests/testdata/sum-test-out.txt

@@ -0,0 +1,12 @@
+Summary for file "tests/testdata/GCF_001639295.1_ASM163929v1_genomic.gff.gz":
+    - 232 annotated sequences for a total length of 2414608 bp
+    - 4298 annotated features (or feature entries)
+        - 1973 entries of type CDS, maximum length: 12025 bp
+        - 1 entries of type RNase_P_RNA, maximum length: 274 bp
+        - 1 entries of type SRP_RNA, maximum length: 316 bp
+        - 40 entries of type exon, maximum length: 2857 bp
+        - 2012 entries of type gene, maximum length: 12025 bp
+        - 4 entries of type rRNA, maximum length: 2857 bp
+        - 232 entries of type region, maximum length: 74332 bp
+        - 2 entries of type repeat_region, maximum length: 3602 bp
+        - 33 entries of type tRNA, maximum length: 107 bp