Previous changeset 5:84becfc8c803 (2018-02-09) Next changeset 7:22aee300afdf (2018-04-18) |
Commit message:
planemo upload commit 475f4d7d8442a0d75e103af326ae5881c4d2a4ac |
modified:
Snmf.pl snmf.xml |
added:
test-data/snmf_groups test-data/snmf_input.vcf test-data/snmf_output test-data/snmf_outputs.Q |
removed:
test-data/groups test-data/input.vcf test-data/output test-data/outputs.Q |
b |
diff -r 84becfc8c803 -r 0ba60156e25f snmf.xml --- a/snmf.xml Fri Feb 09 01:30:26 2018 -0500 +++ b/snmf.xml Mon Apr 16 08:57:17 2018 -0400 |
[ |
@@ -1,5 +1,5 @@ -<tool id="snmf" name="sNMF" version="1.2"> - <description>a population structure from large SNP genotype datasets</description> +<tool id="snmf" name="sNMF" version="2.0.0"> + <description>Fast and efficient program for estimating individual ancestry coefficients</description> <requirements> <requirement type="binary">perl</requirement> <requirement type="package" version="1.6.924">perl-bioperl</requirement> @@ -28,22 +28,22 @@ <tests> <test> - <param name="vcf" value="input.vcf" /> + <param name="vcf" value="snmf_input.vcf" /> <param name="kmin" value="2" /> <param name="kmax" value="5" /> <param name="threshold_group" value="50" /> - <output name="best_k_output" file="output" compare="sim_size" > + <output name="best_k_output" file="snmf_output" compare="sim_size" > <assert_contents> <has_n_columns n="4" /> <has_line_matching expression=".*\s\d\..*" /> </assert_contents> </output> - <output name="best_k_groups" file="groups" compare="sim_size" > + <output name="best_k_groups" file="snmf_groups" compare="sim_size" > <assert_contents> <has_line_matching expression=".*;.*" /> </assert_contents> </output> - <output name="outputs" file="outputs.Q" compare="sim_size" > + <output name="outputs" file="snmf_outputs.Q" compare="sim_size" > <assert_contents> <has_line_matching expression=".*\s\d\..*" /> </assert_contents> @@ -52,33 +52,52 @@ </test> </tests> - <help> - + <help><![CDATA[ .. class:: infomark -**Program encapsulated in Galaxy by Southgreen** +**sNMF** version 1.2 + +.. class:: infomark + +**Galaxy integration** Provided by Southgreen & Dereeper Alexis (IRD) & Marcon Valentin (IFB & INRA) .. class:: infomark -**sNMF version 1.2** +**Support** For any questions about Galaxy integration, please send an e-mail to alexis.dereeper@ird.fr ------ +--------------------------------------------------- -=========== - Overview: -=========== +==== +sNMF +==== -Fast and efficient program for estimating individual admixture coefficients based on sparse non-negative matrix factorization and population genetics. +----------- +Description +----------- ------ - -For further informations, please visite the sNMF_ website. + | Fast and efficient program for estimating individual admixture coefficients based on sparse non-negative matrix factorization and population genetics. + | For further informations, please visit the sNMF website_. -.. _sNMF: http://membres-timc.imag.fr/Olivier.Francois/snmf/index.htm - </help> +.. _website: http://membres-timc.imag.fr/Olivier.Francois/snmf/index.htm + +------------ +Dependencies +------------ +sNMF + snmf_ 1.2, Conda version +PLINK + plink_ 1.90b4, Conda version +Bioperl + perl-bioperl_ 1.6.924, Conda version + +.. _snmf: https://anaconda.org/bioconda/snmf +.. _plink: https://anaconda.org/bioconda/plink +.. _perl-bioperl: https://anaconda.org/bioconda/perl-bioperl + + ]]></help> <citations> -<citation type="doi" >10.1534/genetics.113.160572</citation> + <citation type="doi">10.1534/genetics.113.160572</citation> </citations> </tool> |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/groups --- a/test-data/groups Fri Feb 09 01:30:26 2018 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,19 +0,0 @@ -Indiv;Group -sativa;Q0 -RS2;Q1 -RS3;Q1 -RS4;Q1 -RS5;Q1 -RS6;Q1 -RS7;Q1 -RS8;Q1 -RS9;Q1 -RS10;Q1 -RC1;Q2 -RC2;Q2 -RC3;Q2 -RC4;Q2 -RC5;Q2 -RC6;Q2 -RC7;Q2 -RC10;Q2 |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/input.vcf --- a/test-data/input.vcf Fri Feb 09 01:30:26 2018 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
b'@@ -1,92993 +0,0 @@\n-##fileformat=VCFv4.1\n-##ALT=<ID=NON_REF,Description="Represents any possible alternative allele at this location">\n-##FILTER=<ID=LowQual,Description="Low quality">\n-##FILTER=<ID=XAB,Description="Fails user-input genotype-level AB filter">\n-##FILTER=<ID=XDP,Description="Fails user-input genotype-level DP filter">\n-##FORMAT=<ID=AB,Number=1,Type=Float,Description="Allele balance for each het genotype">\n-##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n-##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n-##FORMAT=<ID=FT,Number=1,Type=String,Description="Genotype-level filter">\n-##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">\n-##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n-##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another">\n-##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">\n-##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n-##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher\'s Exact Test to detect strand bias.">\n-##INFO=<ID=ABHet,Number=1,Type=Float,Description="Allele Balance for hets (ref/(ref+alt))">\n-##INFO=<ID=ABHom,Number=1,Type=Float,Description="Allele Balance for homs (A/(A+O))">\n-##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n-##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n-##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n-##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n-##INFO=<ID=CCC,Number=1,Type=Integer,Description="Number of called chromosomes">\n-##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">\n-##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n-##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n-##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n-##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n-##INFO=<ID=GC,Number=1,Type=Integer,Description="GC content around the variant (see docs for window size details)">\n-##INFO=<ID=GQ_MEAN,Number=1,Type=Float,Description="Mean of all GQ values">\n-##INFO=<ID=GQ_STDDEV,Number=1,Type=Float,Description="Standard deviation of all GQ values">\n-##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n-##INFO=<ID=HW,Number=1,Type=Float,Description="Phred-scaled p-value for Hardy-Weinberg violation">\n-##INFO=<ID=HWP,Number=1,Type=Float,Description="P value from test of Hardy Weinberg Equilibrium">\n-##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n-##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n-##INFO=<ID=LikelihoodRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref haplotype likelihoods">\n-##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts '..b'0\t0/0\n-chr09\t22793753\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n-chr09\t22796602\t.\tA\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t1/1\t./.\t./.\t./.\t0/0\n-chr09\t22796605\t.\tT\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/1\t./.\t./.\t./.\t./.\t0/0\t./.\t./.\t./.\t0/0\n-chr09\t22810017\t.\tC\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n-chr09\t22810194\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22811118\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/0\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\n-chr09\t22811315\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t./.\t0/0\t1/1\t./.\t1/1\t0/0\t0/0\t0/0\n-chr09\t22812158\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22812406\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\n-chr09\t22812464\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t./.\t1/1\t0/0\t0/0\t0/0\n-chr09\t22813028\t.\tT\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/1\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t0/0\n-chr09\t22813451\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n-chr09\t22855055\t.\tC\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t0/0\t0/0\t./.\t./.\t./.\t./.\t./.\t1/1\t./.\t0/0\t0/0\t./.\t./.\t0/0\n-chr09\t22855307\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t0/0\t./.\t./.\t0/0\t./.\t./.\t./.\t./.\t./.\t0/1\t./.\t./.\t0/0\t0/0\n-chr09\t22856093\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22856094\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22856129\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t./.\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n-chr09\t22856586\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22856616\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n-chr09\t22856876\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n-chr09\t22885420\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t./.\t./.\t./.\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n-chr09\t22925510\t.\tG\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\n-chr09\t22926202\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\n-chr09\t22927491\t.\tA\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22928133\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/1\t./.\t0/0\t0/0\n-chr09\t22933637\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/1\t0/0\t0/0\n-chr09\t22933673\t.\tA\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t./.\t./.\t0/1\t./.\t./.\t./.\t0/0\t0/0\t0/0\n-chr09\t22933742\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t1/1\t1/1\t1/1\t0/0\n-chr09\t22933958\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t1/1\t0/0\n-chr09\t22934365\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n-chr09\t22934694\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n-chr09\t22936535\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n-chr09\t22936727\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n' |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/output --- a/test-data/output Fri Feb 09 01:30:26 2018 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,19 +0,0 @@ -Indiv Q0 Q1 Q2 -RC1 0.9998 9.999E-05 9.999E-05 -RC2 0.997792 0.00210825 9.9991E-05 -RC3 0.992815 0.0070846 9.9991E-05 -RC4 0.98779 0.00447419 0.00773612 -RC5 0.9998 9.999E-05 9.999E-05 -RC6 0.986189 9.9991E-05 0.0137112 -RC7 0.998607 0.00129292 9.9991E-05 -RC10 0.9998 9.999E-05 9.999E-05 -sativa 9.999E-05 0.9998 9.999E-05 -RS2 9.9991E-05 0.0113303 0.98857 -RS3 0.17463 0.00506838 0.820301 -RS4 9.9991E-05 0.00303564 0.996864 -RS5 0.0699589 9.9991E-05 0.929941 -RS6 0.101322 0.00547481 0.893203 -RS7 0.215161 9.9991E-05 0.784739 -RS8 0.2832 0.0062863 0.710513 -RS9 9.999E-05 9.999E-05 0.9998 -RS10 9.999E-05 9.999E-05 0.9998 |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/outputs.Q --- a/test-data/outputs.Q Fri Feb 09 01:30:26 2018 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,96 +0,0 @@ -Indiv Q0 Q1 -sativa 0.9999 0.0001 -RC1 0.0001 0.9999 -RC2 0.0001 0.9999 -RC3 0.0001 0.9999 -RC4 0.0001 0.9999 -RC5 0.0001 0.9999 -RC6 0.0001 0.9999 -RC7 0.0001 0.9999 -RC10 0.0001 0.9999 -RS2 0.0276489 0.972351 -RS3 0.0122501 0.98775 -RS4 0.0159128 0.984087 -RS5 0.00798707 0.992013 -RS6 0.0166237 0.983376 -RS7 0.00395985 0.99604 -RS8 0.00927791 0.990722 -RS9 0.00587378 0.994126 -RS10 0.0001 0.9999 - - -==================================== - - -Indiv Q0 Q1 Q2 -sativa 0.9998 9.999E-05 9.999E-05 -RC1 0.000456703 0.999443 9.9991E-05 -RC2 0.00172354 0.998176 9.9991E-05 -RC3 0.00506151 0.994838 9.9991E-05 -RC4 0.0042728 0.989246 0.00648157 -RC5 9.999E-05 0.9998 9.999E-05 -RC6 9.999E-05 0.99109 0.00881015 -RC7 0.000969241 0.998931 9.9991E-05 -RC10 9.999E-05 0.9998 9.999E-05 -RS2 0.0140148 9.9991E-05 0.985885 -RS3 0.00439008 0.168521 0.827089 -RS4 0.0035241 9.9991E-05 0.996376 -RS5 9.9991E-05 0.0628424 0.937058 -RS6 0.00467646 0.105235 0.890089 -RS7 9.9991E-05 0.215856 0.784044 -RS8 0.0056373 0.28324 0.711123 -RS9 9.999E-05 9.999E-05 0.9998 -RS10 9.999E-05 9.999E-05 0.9998 - - -==================================== - - -Indiv Q0 Q1 Q2 Q3 -RS8 0.9997 9.998E-05 9.998E-05 9.998E-05 -RC1 9.9982E-05 0.999473 9.9982E-05 0.000327325 -RC2 0.000489532 0.997332 9.9991E-05 0.00207839 -RC3 0.000110686 0.993536 9.9991E-05 0.00625299 -RC4 0.00501773 0.982068 0.00946016 0.00345434 -RC5 9.998E-05 0.9997 9.998E-05 9.998E-05 -RC6 9.9982E-05 0.986574 0.0132258 9.9982E-05 -RC7 9.9982E-05 0.999456 9.9982E-05 0.000344078 -RC10 0.000620147 0.99918 9.9982E-05 9.9982E-05 -RS2 0.0360548 9.9991E-05 0.948924 0.0149213 -RS3 9.999E-05 0.1692 0.825102 0.00559822 -RS4 0.00179797 9.9991E-05 0.994733 0.00336903 -RS5 9.9982E-05 0.0652871 0.934513 9.9982E-05 -RS6 9.999E-05 0.10355 0.889024 0.00732619 -RS7 0.00490876 0.210563 0.784428 9.9991E-05 -RS9 9.998E-05 9.998E-05 0.9997 9.998E-05 -RS10 9.998E-05 9.998E-05 0.9997 9.998E-05 -sativa 9.998E-05 9.998E-05 9.998E-05 0.9997 - - -==================================== - - -Indiv Q0 Q1 Q2 Q3 Q4 -RS8 0.9996 9.997E-05 9.997E-05 9.997E-05 9.997E-05 -sativa 9.997E-05 0.9996 9.997E-05 9.997E-05 9.997E-05 -RS2 9.997E-05 9.997E-05 0.9996 9.997E-05 9.997E-05 -RS3 0.0113257 0.0044246 9.9991E-05 0.838311 0.145839 -RS4 0.00651095 0.00350823 0.0868845 0.902996 9.9991E-05 -RS5 0.0024032 0.00136572 0.00134543 0.955104 0.0397821 -RS6 9.9982E-05 0.00880184 9.9982E-05 0.917804 0.0731939 -RS7 0.001644 0.000287288 9.9991E-05 0.822929 0.17504 -RS9 9.997E-05 9.997E-05 0.0285941 0.971106 9.997E-05 -RS10 9.997E-05 9.997E-05 0.0113093 0.988391 9.997E-05 -RC1 9.997E-05 9.997E-05 9.997E-05 9.997E-05 0.9996 -RC2 0.00194482 0.00191543 9.9982E-05 9.9982E-05 0.99594 -RC3 9.9991E-05 0.00484461 0.00132366 0.00596324 0.987769 -RC4 0.00194057 0.00543494 0.00369552 0.00852023 0.980409 -RC5 9.997E-05 9.997E-05 9.997E-05 9.997E-05 0.9996 -RC6 0.00650254 9.9991E-05 0.00718994 0.000224601 0.985983 -RC7 9.9973E-05 0.000781725 9.9973E-05 9.9973E-05 0.998918 -RC10 0.00244461 9.9982E-05 9.9982E-05 0.000887377 0.996468 - - -==================================== - - |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/snmf_groups --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/snmf_groups Mon Apr 16 08:57:17 2018 -0400 |
b |
@@ -0,0 +1,19 @@ +Indiv;Group +sativa;Q0 +RS2;Q1 +RS3;Q1 +RS4;Q1 +RS5;Q1 +RS6;Q1 +RS7;Q1 +RS8;Q1 +RS9;Q1 +RS10;Q1 +RC1;Q2 +RC2;Q2 +RC3;Q2 +RC4;Q2 +RC5;Q2 +RC6;Q2 +RC7;Q2 +RC10;Q2 |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/snmf_input.vcf --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/snmf_input.vcf Mon Apr 16 08:57:17 2018 -0400 |
b |
b'@@ -0,0 +1,92993 @@\n+##fileformat=VCFv4.1\n+##ALT=<ID=NON_REF,Description="Represents any possible alternative allele at this location">\n+##FILTER=<ID=LowQual,Description="Low quality">\n+##FILTER=<ID=XAB,Description="Fails user-input genotype-level AB filter">\n+##FILTER=<ID=XDP,Description="Fails user-input genotype-level DP filter">\n+##FORMAT=<ID=AB,Number=1,Type=Float,Description="Allele balance for each het genotype">\n+##FORMAT=<ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">\n+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">\n+##FORMAT=<ID=FT,Number=1,Type=String,Description="Genotype-level filter">\n+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">\n+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">\n+##FORMAT=<ID=PGT,Number=1,Type=String,Description="Physical phasing haplotype information, describing how the alternate alleles are phased in relation to one another">\n+##FORMAT=<ID=PID,Number=1,Type=String,Description="Physical phasing ID information, where each unique ID within a given sample (but not across samples) connects records within a phasing group">\n+##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Normalized, Phred-scaled likelihoods for genotypes as defined in the VCF specification">\n+##FORMAT=<ID=SB,Number=4,Type=Integer,Description="Per-sample component statistics which comprise the Fisher\'s Exact Test to detect strand bias.">\n+##INFO=<ID=ABHet,Number=1,Type=Float,Description="Allele Balance for hets (ref/(ref+alt))">\n+##INFO=<ID=ABHom,Number=1,Type=Float,Description="Allele Balance for homs (A/(A+O))">\n+##INFO=<ID=AC,Number=A,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AF,Number=A,Type=Float,Description="Allele Frequency, for each ALT allele, in the same order as listed">\n+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">\n+##INFO=<ID=BaseQRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref base qualities">\n+##INFO=<ID=CCC,Number=1,Type=Integer,Description="Number of called chromosomes">\n+##INFO=<ID=ClippingRankSum,Number=1,Type=Float,Description="Z-score From Wilcoxon rank sum test of Alt vs. Ref number of hard clipped bases">\n+##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">\n+##INFO=<ID=DS,Number=0,Type=Flag,Description="Were any of the samples downsampled?">\n+##INFO=<ID=Dels,Number=1,Type=Float,Description="Fraction of Reads Containing Spanning Deletions">\n+##INFO=<ID=FS,Number=1,Type=Float,Description="Phred-scaled p-value using Fisher\'s exact test to detect strand bias">\n+##INFO=<ID=GC,Number=1,Type=Integer,Description="GC content around the variant (see docs for window size details)">\n+##INFO=<ID=GQ_MEAN,Number=1,Type=Float,Description="Mean of all GQ values">\n+##INFO=<ID=GQ_STDDEV,Number=1,Type=Float,Description="Standard deviation of all GQ values">\n+##INFO=<ID=HRun,Number=1,Type=Integer,Description="Largest Contiguous Homopolymer Run of Variant Allele In Either Direction">\n+##INFO=<ID=HW,Number=1,Type=Float,Description="Phred-scaled p-value for Hardy-Weinberg violation">\n+##INFO=<ID=HWP,Number=1,Type=Float,Description="P value from test of Hardy Weinberg Equilibrium">\n+##INFO=<ID=HaplotypeScore,Number=1,Type=Float,Description="Consistency of the site with at most two segregating haplotypes">\n+##INFO=<ID=InbreedingCoeff,Number=1,Type=Float,Description="Inbreeding coefficient as estimated from the genotype likelihoods per-sample when compared against the Hardy-Weinberg expectation">\n+##INFO=<ID=LikelihoodRankSum,Number=1,Type=Float,Description="Z-score from Wilcoxon rank sum test of Alt Vs. Ref haplotype likelihoods">\n+##INFO=<ID=MLEAC,Number=A,Type=Integer,Description="Maximum likelihood expectation (MLE) for the allele counts '..b'0\t0/0\n+chr09\t22793753\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n+chr09\t22796602\t.\tA\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t1/1\t./.\t./.\t./.\t0/0\n+chr09\t22796605\t.\tT\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/1\t./.\t./.\t./.\t./.\t0/0\t./.\t./.\t./.\t0/0\n+chr09\t22810017\t.\tC\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n+chr09\t22810194\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22811118\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/0\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\n+chr09\t22811315\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t./.\t0/0\t1/1\t./.\t1/1\t0/0\t0/0\t0/0\n+chr09\t22812158\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22812406\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\n+chr09\t22812464\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t./.\t1/1\t0/0\t0/0\t0/0\n+chr09\t22813028\t.\tT\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/1\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t0/0\n+chr09\t22813451\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n+chr09\t22855055\t.\tC\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t0/0\t0/0\t./.\t./.\t./.\t./.\t./.\t1/1\t./.\t0/0\t0/0\t./.\t./.\t0/0\n+chr09\t22855307\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t0/0\t./.\t./.\t0/0\t./.\t./.\t./.\t./.\t./.\t0/1\t./.\t./.\t0/0\t0/0\n+chr09\t22856093\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22856094\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22856129\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t./.\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n+chr09\t22856586\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22856616\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n+chr09\t22856876\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t0/0\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n+chr09\t22885420\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t1/1\t./.\t./.\t./.\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/0\n+chr09\t22925510\t.\tG\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\n+chr09\t22926202\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\n+chr09\t22927491\t.\tA\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22928133\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/1\t./.\t0/0\t0/0\n+chr09\t22933637\t.\tC\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t./.\t0/1\t0/0\t0/0\n+chr09\t22933673\t.\tA\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t./.\t./.\t0/1\t./.\t./.\t./.\t0/0\t0/0\t0/0\n+chr09\t22933742\t.\tT\tC\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t./.\t./.\t./.\t./.\t./.\t./.\t1/1\t1/1\t1/1\t0/0\n+chr09\t22933958\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t./.\t0/0\t0/0\t0/0\t1/1\t0/0\n+chr09\t22934365\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\n+chr09\t22934694\t.\tA\tG\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t1/1\t0/0\t1/1\t0/0\t0/0\t1/1\t1/1\t1/1\t0/0\t0/0\t0/0\n+chr09\t22936535\t.\tC\tT\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n+chr09\t22936727\t.\tG\tA\t10\tPASS\tAC=2;AF=1;AN=10\tGT\t./.\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t0/0\t1/1\t0/0\t1/1\t1/1\t0/0\t0/0\t0/0\t1/1\t1/1\t0/0\n' |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/snmf_output --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/snmf_output Mon Apr 16 08:57:17 2018 -0400 |
b |
@@ -0,0 +1,19 @@ +Indiv Q0 Q1 Q2 +RC1 0.9998 9.999E-05 9.999E-05 +RC2 0.997792 0.00210825 9.9991E-05 +RC3 0.992815 0.0070846 9.9991E-05 +RC4 0.98779 0.00447419 0.00773612 +RC5 0.9998 9.999E-05 9.999E-05 +RC6 0.986189 9.9991E-05 0.0137112 +RC7 0.998607 0.00129292 9.9991E-05 +RC10 0.9998 9.999E-05 9.999E-05 +sativa 9.999E-05 0.9998 9.999E-05 +RS2 9.9991E-05 0.0113303 0.98857 +RS3 0.17463 0.00506838 0.820301 +RS4 9.9991E-05 0.00303564 0.996864 +RS5 0.0699589 9.9991E-05 0.929941 +RS6 0.101322 0.00547481 0.893203 +RS7 0.215161 9.9991E-05 0.784739 +RS8 0.2832 0.0062863 0.710513 +RS9 9.999E-05 9.999E-05 0.9998 +RS10 9.999E-05 9.999E-05 0.9998 |
b |
diff -r 84becfc8c803 -r 0ba60156e25f test-data/snmf_outputs.Q --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/snmf_outputs.Q Mon Apr 16 08:57:17 2018 -0400 |
b |
@@ -0,0 +1,96 @@ +Indiv Q0 Q1 +sativa 0.9999 0.0001 +RC1 0.0001 0.9999 +RC2 0.0001 0.9999 +RC3 0.0001 0.9999 +RC4 0.0001 0.9999 +RC5 0.0001 0.9999 +RC6 0.0001 0.9999 +RC7 0.0001 0.9999 +RC10 0.0001 0.9999 +RS2 0.0276489 0.972351 +RS3 0.0122501 0.98775 +RS4 0.0159128 0.984087 +RS5 0.00798707 0.992013 +RS6 0.0166237 0.983376 +RS7 0.00395985 0.99604 +RS8 0.00927791 0.990722 +RS9 0.00587378 0.994126 +RS10 0.0001 0.9999 + + +==================================== + + +Indiv Q0 Q1 Q2 +sativa 0.9998 9.999E-05 9.999E-05 +RC1 0.000456703 0.999443 9.9991E-05 +RC2 0.00172354 0.998176 9.9991E-05 +RC3 0.00506151 0.994838 9.9991E-05 +RC4 0.0042728 0.989246 0.00648157 +RC5 9.999E-05 0.9998 9.999E-05 +RC6 9.999E-05 0.99109 0.00881015 +RC7 0.000969241 0.998931 9.9991E-05 +RC10 9.999E-05 0.9998 9.999E-05 +RS2 0.0140148 9.9991E-05 0.985885 +RS3 0.00439008 0.168521 0.827089 +RS4 0.0035241 9.9991E-05 0.996376 +RS5 9.9991E-05 0.0628424 0.937058 +RS6 0.00467646 0.105235 0.890089 +RS7 9.9991E-05 0.215856 0.784044 +RS8 0.0056373 0.28324 0.711123 +RS9 9.999E-05 9.999E-05 0.9998 +RS10 9.999E-05 9.999E-05 0.9998 + + +==================================== + + +Indiv Q0 Q1 Q2 Q3 +RS8 0.9997 9.998E-05 9.998E-05 9.998E-05 +RC1 9.9982E-05 0.999473 9.9982E-05 0.000327325 +RC2 0.000489532 0.997332 9.9991E-05 0.00207839 +RC3 0.000110686 0.993536 9.9991E-05 0.00625299 +RC4 0.00501773 0.982068 0.00946016 0.00345434 +RC5 9.998E-05 0.9997 9.998E-05 9.998E-05 +RC6 9.9982E-05 0.986574 0.0132258 9.9982E-05 +RC7 9.9982E-05 0.999456 9.9982E-05 0.000344078 +RC10 0.000620147 0.99918 9.9982E-05 9.9982E-05 +RS2 0.0360548 9.9991E-05 0.948924 0.0149213 +RS3 9.999E-05 0.1692 0.825102 0.00559822 +RS4 0.00179797 9.9991E-05 0.994733 0.00336903 +RS5 9.9982E-05 0.0652871 0.934513 9.9982E-05 +RS6 9.999E-05 0.10355 0.889024 0.00732619 +RS7 0.00490876 0.210563 0.784428 9.9991E-05 +RS9 9.998E-05 9.998E-05 0.9997 9.998E-05 +RS10 9.998E-05 9.998E-05 0.9997 9.998E-05 +sativa 9.998E-05 9.998E-05 9.998E-05 0.9997 + + +==================================== + + +Indiv Q0 Q1 Q2 Q3 Q4 +RS8 0.9996 9.997E-05 9.997E-05 9.997E-05 9.997E-05 +sativa 9.997E-05 0.9996 9.997E-05 9.997E-05 9.997E-05 +RS2 9.997E-05 9.997E-05 0.9996 9.997E-05 9.997E-05 +RS3 0.0113257 0.0044246 9.9991E-05 0.838311 0.145839 +RS4 0.00651095 0.00350823 0.0868845 0.902996 9.9991E-05 +RS5 0.0024032 0.00136572 0.00134543 0.955104 0.0397821 +RS6 9.9982E-05 0.00880184 9.9982E-05 0.917804 0.0731939 +RS7 0.001644 0.000287288 9.9991E-05 0.822929 0.17504 +RS9 9.997E-05 9.997E-05 0.0285941 0.971106 9.997E-05 +RS10 9.997E-05 9.997E-05 0.0113093 0.988391 9.997E-05 +RC1 9.997E-05 9.997E-05 9.997E-05 9.997E-05 0.9996 +RC2 0.00194482 0.00191543 9.9982E-05 9.9982E-05 0.99594 +RC3 9.9991E-05 0.00484461 0.00132366 0.00596324 0.987769 +RC4 0.00194057 0.00543494 0.00369552 0.00852023 0.980409 +RC5 9.997E-05 9.997E-05 9.997E-05 9.997E-05 0.9996 +RC6 0.00650254 9.9991E-05 0.00718994 0.000224601 0.985983 +RC7 9.9973E-05 0.000781725 9.9973E-05 9.9973E-05 0.998918 +RC10 0.00244461 9.9982E-05 9.9982E-05 0.000887377 0.996468 + + +==================================== + + |