Mercurial > repos > xuebing > sharplabtool
diff tools/evolution/codingSnps.xml @ 0:9071e359b9a3
Uploaded
author | xuebing |
---|---|
date | Fri, 09 Mar 2012 19:37:19 -0500 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/evolution/codingSnps.xml Fri Mar 09 19:37:19 2012 -0500 @@ -0,0 +1,139 @@ +<tool id="hgv_codingSnps" name="aaChanges" version="1.0.0"> + <description>amino-acid changes caused by a set of SNPs</description> + + <command interpreter="perl"> + codingSnps.pl $input1 $input2 Galaxy build=${input1.metadata.dbkey} loc=${GALAXY_DATA_INDEX_DIR}/codingSnps.loc chr=${input1.metadata.chromCol} start=${input1.metadata.startCol} end=${input1.metadata.endCol} snp=$col1 > $out_file1 + </command> + + <inputs> + <param format="interval" name="input1" type="data" label="SNP dataset"> + <validator type="dataset_metadata_in_file" filename="codingSnps.loc" metadata_name="dbkey" metadata_column="0" message="Sequences are not currently available for the specified build." split="\t" /> + </param> + <param name="col1" type="data_column" data_ref="input1" label="Column with SNPs" /> + <param format="interval" name="input2" type="data" label="Gene dataset"> + <validator type="dataset_metadata_in_file" filename="codingSnps.loc" metadata_name="dbkey" metadata_column="0" message="Sequences are not currently available for the specified build." split="\t" /> + </param> + </inputs> + + <outputs> + <data format="tabular" name="out_file1" /> + </outputs> + + <code file="codingSnps_filter.py"></code> + + <requirements> + <requirement type="binary">cat</requirement> + <requirement type="binary">sort</requirement> + <requirement type="package">ucsc_tools</requirement> + </requirements> + + <tests> + <test> + <param name="input1" ftype="interval" value="codingSnps_input1.interval" dbkey="hg18" /> + <param name="col1" value="6" /> + <param name="input2" ftype="interval" value="codingSnps_inputGenes1.bed" dbkey="hg18" /> + <output name="output" file="codingSnps_output1.interval" /> + </test> + <test> + <param name="input1" ftype="interval" value="codingSnps_input2.interval" dbkey="hg18" /> + <param name="input2" ftype="interval" value="codingSnps_inputGenes2.bed" dbkey="hg18" /> + <param name="col1" value="4" /> + <output name="output" file="codingSnps_output2.interval" /> + </test> + </tests> + + <help> +.. class:: infomark + +The build must be defined for the input files and must be the same for both files. +Use the pencil icon to add the build to the files if necessary. + +----- + +**Dataset formats** + +The SNP dataset is in interval_ format, with a column of SNPs as described below. +The gene dataset is in BED_ format with 12 columns. The output dataset is also interval. +(`Dataset missing?`_) + +.. _interval: ./static/formatHelp.html#interval +.. _BED: ./static/formatHelp.html#bed +.. _Dataset missing?: ./static/formatHelp.html + +----- + +**What it does** + +This tool identifies which SNPs create amino-acid changes in the specified +coding regions. The first input file contains the SNPs and must be an interval file. +It needs the chromosome, start, and end position as well as the SNP. The +SNP can be given using ambiguous-nucleotide symbols or a list of two to four +alleles +separated by '/'. Any other columns in the first input file will not be +used but will be kept for the output. The second input file contains the genes +to be used for defining the coding regions. This file must be a BED file with +the first 12 columns standard BED columns. The output is the same as the +first input file with +several columns added: the name field from the line of the gene input file +used, the amino acids, the codon number, and the reference nucleotide that +changed in the amino acid. +The amino acids are listed with the reference amino acid first, then a colon, +and then the amino acids for the alleles. If a SNP is not in a coding region +or is synonymous then it is not included in the output file. + +----- + +**Example** + +- first input file, with SNPs:: + + chr22 15660821 15660822 A/G + chr22 15825725 15825726 G/T + chr22 15827035 15827036 G + chr22 15827135 15827136 C/G + chr22 15830928 15830929 A/G + chr22 15830951 15830952 G + chr22 15830955 15830956 C/T + chr22 15848885 15848886 C/T + chr22 15849048 15849049 A/C + chr22 15919711 15919712 A/G + etc. + + or, indicating polymorphisms using ambiguous-nucleotide symbols:: + + chr22 15660821 15660822 R + chr22 15825725 15825726 K + chr22 15827035 15827036 G + chr22 15827135 15827136 S + chr22 15830928 15830929 R + chr22 15830951 15830952 G + chr22 15830955 15830956 Y + chr22 15848885 15848886 Y + chr22 15849048 15849049 M + chr22 15919711 15919712 R + etc. + +- second input file, with UCSC annotations for human genes:: + + chr22 15688363 15690225 uc010gqr.1 0 + 15688363 15688363 0 2 587,794, 0,1068, + chr22 15822826 15869112 uc002zlw.1 0 - 15823622 15869004 0 10 940,105,97,91,265,86,251,208,304,282, 0,1788,2829,3241,4163,6361,8006,26023,29936,46004, + chr22 15826991 15869112 uc010gqs.1 0 - 15829218 15869004 0 5 1380,86,157,304,282, 0,2196,21858,25771,41839, + chr22 15897459 15919682 uc002zlx.1 0 + 15897459 15897459 0 4 775,128,103,1720, 0,8303,10754,20503, + chr22 15945848 15971389 uc002zly.1 0 + 15945981 15970710 0 13 271,25,147,113,127,48,164,84,85,12,102,42,2193, 0,12103,12838,13816,15396,17037,17180,18535,19767,20632,20894,22768,23348, + etc. + +- output file, showing non-synonymous substitutions in coding regions:: + + chr22 15825725 15825726 G/T uc002zlw.1 Gln:Pro/Gln 469 T + chr22 15827035 15827036 G uc002zlw.1 Glu:Asp 414 C + chr22 15827135 15827136 C/G uc002zlw.1 Gly:Gly/Ala 381 C + chr22 15830928 15830929 A/G uc002zlw.1 Ala:Ser/Pro 281 C + chr22 15830951 15830952 G uc002zlw.1 Leu:Pro 273 A + chr22 15830955 15830956 C/T uc002zlw.1 Ser:Gly/Ser 272 T + chr22 15848885 15848886 C/T uc002zlw.1 Ser:Trp/Stop 217 G + chr22 15848885 15848886 C/T uc010gqs.1 Ser:Trp/Stop 200 G + chr22 15849048 15849049 A/C uc002zlw.1 Gly:Stop/Gly 163 C + etc. + + </help> +</tool>