annotate tests/artificial-nofilt.vcf.in @ 6:df3b28364cd2

allele-counts.{py,xml}: Add strand bias, documentation updates.
author nicksto <nmapsy@gmail.com>
date Wed, 09 Dec 2015 11:20:51 -0500
parents 31361191d2d2
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
1 ##fileformat=VCFv4.1
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
2 ##comment="ARGS=-H -r 1 -f 0 -c 0"
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
3 ##comment="This is a test set of made-up sites, each created in order to test certain functionality. It's meant to be run with -f 10 -c 10"
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
4 ##fileDate=19700101
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
5 ##source=Dan
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
6 ##reference=file:///scratch/dan/galaxy/galaxy-central/database/files/002/dataset_0000.dat
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
7 ##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
8 ##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
9 ##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
10 ##FORMAT=<ID=AC,Number=.,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
11 ##FORMAT=<ID=AF,Number=.,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
12 ##FORMAT=<ID=NC,Number=.,Type=String,Description="Nucleotide and indel counts">
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
13 #CHROM POS ID REF ALT QUAL FILTER INFO FORMAT THYROID
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
14 # General note: the only data made consistent is the CHROM, POS, REF, ALT, and the variant data (after the ':'). The other stuff isn't supposed to be consistent.
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
15 # Simplest case, but POS 0 and no minor allele
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
16 chr1 0 . A . . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=15,-A=15,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
17 # Simple, normal cases of A/G variants: above/below threshold x strand bias/no strand bias (2 x 2 = 4 cases)
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
18 chr1 10 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=15,+G=1,-A=15,-G=1,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
19 chr1 20 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=15,+G=1,-A=16,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
20 chr1 30 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=10,+G=2,-A=11,-G=2,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
21 chr1 40 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=11,+G=3,-A=11,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
22 # Really low coverage
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
23 chr1 50 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=2,-A=1,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
24 chr1 60 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=1,+G=1,-A=1,-G=1
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
25 chr1 70 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=1,+G=1,-G=2,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
26 chr1 80 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=102,+G=3,-A=2,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
27 # Very low frequency tertiary allele
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
28 chr1 90 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=50,+G=5,+C=1,-A=50,-G=6,-C=1,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
29 chr1 100 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=50,+G=5,-A=50,-G=6,-C=1,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
30 # Only non-canonical alleles
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
31 chr1 120 . d1 . . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+d1=15,-d1=15,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
32 # Same 4 cases, but with non-canonical major allele (d1)
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
33 chr1 130 . d1 G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+d1=15,+G=1,-d1=15,-G=1,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
34 chr1 140 . d1 G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+d1=15,+G=1,-d1=16,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
35 chr1 150 . d1 G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+d1=10,+G=2,-d1=11,-G=2,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
36 chr1 160 . d1 G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+d1=11,+G=3,-d1=11,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
37 # Test case where minor allele is above threshold on only one strand because of different coverage. Also, a long decimal minor allele frequency.
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
38 chr1 260 . A G . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=13,+G=7,-A=93,-G=7,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
39 # Test case where minor alleles have equal frequency: Above/below threshold, +/- strand bias
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
40 chr1 300 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=1,+G=1,+T=38,-A=1,-G=1,-T=38,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
41 chr1 310 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=6,+G=6,+T=38,-A=6,-G=6,-T=38,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
42 chr1 320 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=6,+G=6,+T=38,-A=6,-G=6,-T=18,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
43 chr1 330 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=6,+G=6,+T=38,-A=1,-G=1,-T=28,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
44 chr1 340 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=1,+T=80,-G=1,-T=18,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
45 chr1 350 . T G,A . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=11,+T=60,-G=11,-T=18,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
46 # Case where + and - variants are interleaved with each other. Also, a long decimal result for the minor allele frequency.
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
47 chr1 400 . A N . . AC=;AF= GT:AC:AF:NC 0/0:1:1:+A=16,-A=16,+G=4,-G=4,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
48 # Test complex data in the ALT, INFO, and sample (before the ':') columns
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
49 chr1 410 . T G,A . . AC=1,1;AF=0.0111111111111,0.0111111111111 GT:AC:AF:NC 0/0:1,1:0.0111111111111,0.0111111111111:+A=1,+T=81,-T=16,-G=2,
31361191d2d2 Uploaded tarball.
nick
parents:
diff changeset
50 chr1 420 . A . . . AC=;AF= GT:AC:AF:NC 0/0:::+A=82,-A=22,