sequence-formats 1.3.1 → 1.3.2

raw patch · 10 files changed

+92/−1 lines, 10 files

Files

Changelog.md +2/−0
sequence-formats.cabal +9/−1
testDat/example.bim +7/−0
testDat/example.eigenstratgeno +7/−0
testDat/example.fasta +10/−0
testDat/example.freqsum +8/−0
testDat/example.histogram.txt +10/−0
testDat/example.ind +5/−0
testDat/example.snp +7/−0
testDat/example.vcf +27/−0

Changelog.md view

@@ -21,3 +21,5 @@ V 1.3.0: Removed pipes-text, text and turtle dependencies and some more. Restructured all datatypes to use Bytestring instead of text.   V 1.3.1: Moved test suite outside of the main library into the test source directory. Cleaner setup.++V 1.3.2: Added testDat to Cabal file to make tests work off the tarball.

sequence-formats.cabal view

@@ -1,6 +1,6 @@ cabal-version: >=1.10 name: sequence-formats-version: 1.3.1+version: 1.3.2 license: GPL-3 license-file: LICENSE maintainer: stephan.schiffels@mac.com@@ -13,6 +13,14 @@ extra-source-files:     README.md     Changelog.md+    testDat/example.bim+    testDat/example.eigenstratgeno+    testDat/example.fasta+    testDat/example.freqsum+    testDat/example.histogram.txt+    testDat/example.ind+    testDat/example.snp+    testDat/example.vcf  library     exposed-modules:

+ testDat/example.bim view

@@ -0,0 +1,7 @@+11       rs0000     0.000000            0 A C+11       rs1111     0.001000       100000 A G+11       rs2222     0.002000       200000 A T+11       rs3333     0.003000       300000 C A+11       rs4444     0.004000       400000 G A+11       rs5555     0.005000       500000 T A+11       rs6666     0.006000       600000 G T

+ testDat/example.eigenstratgeno view

@@ -0,0 +1,7 @@+11100+01212+21101+09122+21100+00191+22199

+ testDat/example.fasta view

@@ -0,0 +1,10 @@+>chr1 bla bla bla+ACCAATTTCCCTTTAATATAAG+ACCCTTTCGGGGAAA+>chr2 dsasdfas+ACTACTACTACTACTACTACTACGGGGG+AAAAAAAAACCCCCCCCCGGGGGGGG+>chr3 kflfksja+ACGACGACGACGGGGTTTAAA+AAGGGTTTCCTCTCTCTCTGGG+

+ testDat/example.freqsum view

@@ -0,0 +1,8 @@+#CHROM	POS	REF	ALT	SAMPLE0(2)	SAMPLE1(2)	SAMPLE2(2)	SAMPLE3(1)	SAMPLE4(1)+11	0	A	C	1	1	1	1	1+11	100000	A	G	2	1	0	0	0+11	200000	A	T	0	1	1	1	1+11	300000	C	A	2	-1	1	0	0+11	400000	G	A	0	1	1	1	1+11	500000	T	A	2	2	1	-1	1+11	600000	G	T	0	0	1	-1	-1

+ testDat/example.histogram.txt view

@@ -0,0 +1,10 @@+NAMES=EUR,SEA,SIB,CHK,SAM+N=66,42,44,8,28+MAX_M=10+TOTAL_SITES=1146826657+1,0,0,0,0 773148 6.7e-4 3.6e-6+0,1,0,0,0 527207 4.5e-4 2.5e-6+0,0,1,0,0 368640 3.2e-4 2.4e-6+0,0,0,0,1 213918 1.8e-4 3.6e-6+2,0,0,0,0 158795 1.3e-4 1.4e-6+0,2,0,0,0 73241 6.3e-5 7.3e-7

+ testDat/example.ind view

@@ -0,0 +1,5 @@+	     SAMPLE0 F       Case+             SAMPLE1 M       Case+             SAMPLE2 F    Control+             SAMPLE3 M    Control+             SAMPLE4 F    Control

+ testDat/example.snp view

@@ -0,0 +1,7 @@+              rs0000  11        0.000000               0 A C+              rs1111  11        0.001000          100000 A G+              rs2222  11        0.002000          200000 A T+              rs3333  11        0.003000          300000 C A+              rs4444  11        0.004000          400000 G A+              rs5555  11        0.005000          500000 T A+              rs6666  11        0.006000          600000 G T

+ testDat/example.vcf view

@@ -0,0 +1,27 @@+##fileformat=VCFv4.2+##FILTER=<ID=PASS,Description="All filters passed">+##samtoolsVersion=1.3+htslib-1.3+##samtoolsCommand=samtools mpileup -vI -f /projects1/Reference_Genomes/Human/hs37d5/hs37d5.fa -r 1:1-200000 12880A.bam 12881A.bam 12883A.bam 12884A.bam 12885A.bam+##reference=file:///projects1/Reference_Genomes/Human/hs37d5/hs37d5.fa+##contig=<ID=1,length=249250621>+##contig=<ID=2,length=243199373>+##contig=<ID=3,length=198022430>+##contig=<ID=4,length=191154276>+##contig=<ID=5,length=180915260>+##contig=<ID=hs37d5,length=35477943>+##ALT=<ID=*,Description="Represents allele(s) other than observed.">+##INFO=<ID=INDEL,Number=0,Type=Flag,Description="Indicates that the variant is an INDEL.">+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="List of Phred-scaled genotype likelihoods">+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">+##INFO=<ID=AF1,Number=1,Type=Float,Description="Max-likelihood estimate of the first ALT allele frequency (assuming HWE)">+##INFO=<ID=DP4,Number=4,Type=Integer,Description="Number of high-quality ref-forward , ref-reverse, alt-forward and alt-reverse bases">+##bcftools_callVersion=1.3+htslib-1.3+##bcftools_callCommand=call -c -v+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	12880A	12881A	12883A	12884A	12885A+1	10492	.	C	T	15.0302	.	DP=28;PV4=1,1,0.30985,1	GT:PL	0/0:0,3,37	0/0:0,6,67	0/1:51,0,28	0/0:0,54,255	0/0:0,9,83+1	14907	.	A	G	146.092	.	DP=55.526787;AC1=5;DP4=19,16,8,12;PV4=0.403198,0.000983733,1,0.0348559	GT:PL	0/1:0,0,0	0/0:0,9,42	0/1:51,0,0	0/1:70,0,123	1/1:68,5,0+1	14930	.	A	G	999	.	DP=61.545999;AC1=6;;FQ=999;PV4=0.602167,0.240103,1,1	GT:PL	0/1:0,3,20	0/1:22,0,47	0/1:70,0,26	0/1:188,0,121	1/1:80,12,0+2	14933	.	G	A	51.2451	.	DP=60.215796;PV4=0.49427,1,1,1	GT:PL	0/0:0,6,39	0/1:25,0,48	0/0:0,18,118	0/1:69,0,163	0/0:0,12,80+2	16495	.	G	C	7.29715	.	DP=47.27107;AC1=2;PV4=0.540781,0.244272,1,0.0352549	GT:PL	0/0:0,9,9	0/1:23,3,0	0/0:0,4,9	0/1:27,0,46	0/0:0,9,21+2	20144	.	G	A	15.7039	.	DP=121;AC1=3;PV4=1,1,1,1	GT:PL	0/0:0,5,81	0/1:33,0,47	0/1:9,0,21	0/0:0,182,122	0/1:18,0,27+2	30923	rs12345	G	.	110.112	.	DP=5;FQ=-28.9619	GT:PL	1/1:0,0,0	1/1:0,0,0	1/1:40,6,0	1/1:105,9,0	1/1:0,0,0