[2] | 1 | <tool id="hgv_codingSnps" name="aaChanges" version="1.0.0"> |
---|
| 2 | <description>amino-acid changes caused by a set of SNPs</description> |
---|
| 3 | |
---|
| 4 | <command interpreter="perl"> |
---|
| 5 | 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 |
---|
| 6 | </command> |
---|
| 7 | |
---|
| 8 | <inputs> |
---|
| 9 | <param format="interval" name="input1" type="data" label="SNP dataset"> |
---|
| 10 | <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" /> |
---|
| 11 | </param> |
---|
| 12 | <param name="col1" type="data_column" data_ref="input1" label="Column with SNPs" /> |
---|
| 13 | <param format="interval" name="input2" type="data" label="Gene dataset"> |
---|
| 14 | <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" /> |
---|
| 15 | </param> |
---|
| 16 | </inputs> |
---|
| 17 | |
---|
| 18 | <outputs> |
---|
| 19 | <data format="tabular" name="out_file1" /> |
---|
| 20 | </outputs> |
---|
| 21 | |
---|
| 22 | <code file="codingSnps_filter.py"></code> |
---|
| 23 | |
---|
| 24 | <requirements> |
---|
| 25 | <requirement type="binary">cat</requirement> |
---|
| 26 | <requirement type="binary">sort</requirement> |
---|
| 27 | <requirement type="package">ucsc_tools</requirement> |
---|
| 28 | </requirements> |
---|
| 29 | |
---|
| 30 | <tests> |
---|
| 31 | <test> |
---|
| 32 | <param name="input1" ftype="interval" value="codingSnps_input1.interval" dbkey="hg18" /> |
---|
| 33 | <param name="col1" value="6" /> |
---|
| 34 | <param name="input2" ftype="interval" value="codingSnps_inputGenes1.bed" dbkey="hg18" /> |
---|
| 35 | <output name="output" file="codingSnps_output1.interval" /> |
---|
| 36 | </test> |
---|
| 37 | <test> |
---|
| 38 | <param name="input1" ftype="interval" value="codingSnps_input2.interval" dbkey="hg18" /> |
---|
| 39 | <param name="input2" ftype="interval" value="codingSnps_inputGenes2.bed" dbkey="hg18" /> |
---|
| 40 | <param name="col1" value="4" /> |
---|
| 41 | <output name="output" file="codingSnps_output2.interval" /> |
---|
| 42 | </test> |
---|
| 43 | </tests> |
---|
| 44 | |
---|
| 45 | <help> |
---|
| 46 | .. class:: infomark |
---|
| 47 | |
---|
| 48 | The build must be defined for the input files and must be the same for both files. |
---|
| 49 | Use the pencil icon to add the build to the files if necessary. |
---|
| 50 | |
---|
| 51 | ----- |
---|
| 52 | |
---|
| 53 | **Dataset formats** |
---|
| 54 | |
---|
| 55 | The SNP dataset is in interval_ format, with a column of SNPs as described below. |
---|
| 56 | The gene dataset is in BED_ format with 12 columns. The output dataset is also interval. |
---|
| 57 | (`Dataset missing?`_) |
---|
| 58 | |
---|
| 59 | .. _interval: ./static/formatHelp.html#interval |
---|
| 60 | .. _BED: ./static/formatHelp.html#bed |
---|
| 61 | .. _Dataset missing?: ./static/formatHelp.html |
---|
| 62 | |
---|
| 63 | ----- |
---|
| 64 | |
---|
| 65 | **What it does** |
---|
| 66 | |
---|
| 67 | This tool identifies which SNPs create amino-acid changes in the specified |
---|
| 68 | coding regions. The first input file contains the SNPs and must be an interval file. |
---|
| 69 | It needs the chromosome, start, and end position as well as the SNP. The |
---|
| 70 | SNP can be given using ambiguous-nucleotide symbols or a list of two to four |
---|
| 71 | alleles |
---|
| 72 | separated by '/'. Any other columns in the first input file will not be |
---|
| 73 | used but will be kept for the output. The second input file contains the genes |
---|
| 74 | to be used for defining the coding regions. This file must be a BED file with |
---|
| 75 | the first 12 columns standard BED columns. The output is the same as the |
---|
| 76 | first input file with |
---|
| 77 | several columns added: the name field from the line of the gene input file |
---|
| 78 | used, the amino acids, the codon number, and the reference nucleotide that |
---|
| 79 | changed in the amino acid. |
---|
| 80 | The amino acids are listed with the reference amino acid first, then a colon, |
---|
| 81 | and then the amino acids for the alleles. If a SNP is not in a coding region |
---|
| 82 | or is synonymous then it is not included in the output file. |
---|
| 83 | |
---|
| 84 | ----- |
---|
| 85 | |
---|
| 86 | **Example** |
---|
| 87 | |
---|
| 88 | - first input file, with SNPs:: |
---|
| 89 | |
---|
| 90 | chr22 15660821 15660822 A/G |
---|
| 91 | chr22 15825725 15825726 G/T |
---|
| 92 | chr22 15827035 15827036 G |
---|
| 93 | chr22 15827135 15827136 C/G |
---|
| 94 | chr22 15830928 15830929 A/G |
---|
| 95 | chr22 15830951 15830952 G |
---|
| 96 | chr22 15830955 15830956 C/T |
---|
| 97 | chr22 15848885 15848886 C/T |
---|
| 98 | chr22 15849048 15849049 A/C |
---|
| 99 | chr22 15919711 15919712 A/G |
---|
| 100 | etc. |
---|
| 101 | |
---|
| 102 | or, indicating polymorphisms using ambiguous-nucleotide symbols:: |
---|
| 103 | |
---|
| 104 | chr22 15660821 15660822 R |
---|
| 105 | chr22 15825725 15825726 K |
---|
| 106 | chr22 15827035 15827036 G |
---|
| 107 | chr22 15827135 15827136 S |
---|
| 108 | chr22 15830928 15830929 R |
---|
| 109 | chr22 15830951 15830952 G |
---|
| 110 | chr22 15830955 15830956 Y |
---|
| 111 | chr22 15848885 15848886 Y |
---|
| 112 | chr22 15849048 15849049 M |
---|
| 113 | chr22 15919711 15919712 R |
---|
| 114 | etc. |
---|
| 115 | |
---|
| 116 | - second input file, with UCSC annotations for human genes:: |
---|
| 117 | |
---|
| 118 | chr22 15688363 15690225 uc010gqr.1 0 + 15688363 15688363 0 2 587,794, 0,1068, |
---|
| 119 | 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, |
---|
| 120 | chr22 15826991 15869112 uc010gqs.1 0 - 15829218 15869004 0 5 1380,86,157,304,282, 0,2196,21858,25771,41839, |
---|
| 121 | chr22 15897459 15919682 uc002zlx.1 0 + 15897459 15897459 0 4 775,128,103,1720, 0,8303,10754,20503, |
---|
| 122 | 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, |
---|
| 123 | etc. |
---|
| 124 | |
---|
| 125 | - output file, showing non-synonymous substitutions in coding regions:: |
---|
| 126 | |
---|
| 127 | chr22 15825725 15825726 G/T uc002zlw.1 Gln:Pro/Gln 469 T |
---|
| 128 | chr22 15827035 15827036 G uc002zlw.1 Glu:Asp 414 C |
---|
| 129 | chr22 15827135 15827136 C/G uc002zlw.1 Gly:Gly/Ala 381 C |
---|
| 130 | chr22 15830928 15830929 A/G uc002zlw.1 Ala:Ser/Pro 281 C |
---|
| 131 | chr22 15830951 15830952 G uc002zlw.1 Leu:Pro 273 A |
---|
| 132 | chr22 15830955 15830956 C/T uc002zlw.1 Ser:Gly/Ser 272 T |
---|
| 133 | chr22 15848885 15848886 C/T uc002zlw.1 Ser:Trp/Stop 217 G |
---|
| 134 | chr22 15848885 15848886 C/T uc010gqs.1 Ser:Trp/Stop 200 G |
---|
| 135 | chr22 15849048 15849049 A/C uc002zlw.1 Gly:Stop/Gly 163 C |
---|
| 136 | etc. |
---|
| 137 | |
---|
| 138 | </help> |
---|
| 139 | </tool> |
---|