/tools/human_genome_variation/sift.xml
XML | 174 lines | 145 code | 29 blank | 0 comment | 0 complexity | 070bfb2df8f01cd5fc2f5a791ad21d99 MD5 | raw file
1<tool id="hgv_sift" name="SIFT" version="1.0.0"> 2 <description>predictions of functional sites</description> 3 4 <command interpreter="bash"> 5 sift_variants_wrapper.sh "$input" "$output" "${input.metadata.dbkey}" "${GALAXY_DATA_INDEX_DIR}/sift_db.loc" "$chrom_col" "$pos_col" "$base" "$allele_col" "$strand_source.strand_col" "$comment_source.comment_col" "$output_opts" 6 </command> 7 8 <inputs> 9 <param name="input" type="data" format="tabular" label="Dataset"> 10 <validator type="unspecified_build"/> 11 <validator type="dataset_metadata_in_file" filename="sift_db.loc" metadata_name="dbkey" metadata_column="0" message="Data is currently not available for the specified build."/> 12 </param> 13 <param name="chrom_col" type="data_column" data_ref="input" label="Column with chromosome"/> 14 <param name="pos_col" type="data_column" data_ref="input" numerical="true" label="Column with position"/> 15 <param name="base" type="select" label="Position coordinates are"> 16 <option value="1" selected="true">one-based</option> 17 <option value="0">zero-based</option> 18 </param> 19 <param name="allele_col" type="data_column" data_ref="input" label="Column with allele"/> 20 <conditional name="strand_source"> 21 <param name="strand_choice" type="select" label="Strand info"> 22 <option value="data_column" selected="true">a column in the dataset</option> 23 <option value="all_pos">all on sense/forward/+ strand</option> 24 <option value="all_neg">all on antisense/reverse/- strand</option> 25 </param> 26 <when value="data_column"> 27 <param name="strand_col" type="data_column" data_ref="input" label="Column with strand"/> 28 </when> 29 <when value="all_pos"> 30 <param name="strand_col" type="hidden" value="+"/> 31 </when> 32 <when value="all_neg"> 33 <param name="strand_col" type="hidden" value="-"/> 34 </when> 35 </conditional> 36 <conditional name="comment_source"> 37 <param name="comment_choice" type="select" label="Include comment column"> 38 <option value="no" selected="true">no</option> 39 <option value="yes">yes</option> 40 </param> 41 <when value="no"> 42 <param name="comment_col" type="hidden" value="-"/> 43 </when> 44 <when value="yes"> 45 <param name="comment_col" type="data_column" data_ref="input" label="Column with comment"/> 46 </when> 47 </conditional> 48 <param name="output_opts" type="select" multiple="true" display="checkboxes" label="Include the following additional fields in the output"> 49 <option value="A">Ensembl Gene ID</option> 50 <option value="B">Gene Name</option> 51 <option value="C">Gene Description</option> 52 <option value="D">Ensembl Protein Family ID</option> 53 <option value="E">Ensembl Protein Family Description</option> 54 <option value="F">Ensembl Transcript Status (Known / Novel)</option> 55 <option value="G">Protein Family Size</option> 56 <option value="H">Ka/Ks (Human-mouse)</option> 57 <option value="I">Ka/Ks (Human-macaque)</option> 58 <option value="J">OMIM Disease</option> 59 <option value="K">Allele Frequencies (All Hapmap Populations - weighted average)</option> 60 <option value="L">Allele Frequencies (CEU Hapmap population)</option> 61 </param> 62 </inputs> 63 64 <outputs> 65 <data format="tabular" name="output" /> 66 </outputs> 67 68 <requirements> 69 <requirement type="binary">awk</requirement> 70 <requirement type="binary">rm</requirement> 71 <requirement type="binary">sed</requirement> 72 </requirements> 73 74 <tests> 75 <test> 76 <param name="input" value="sift_variants.tab" ftype="tabular" dbkey="hg18"/> 77 <param name="chrom_col" value="1"/> 78 <param name="pos_col" value="3"/> 79 <param name="base" value="1"/> 80 <param name="allele_col" value="5"/> 81 <param name="strand_choice" value="data_column"/> 82 <param name="strand_col" value="4"/> 83 <param name="output_opts" value="A"/> 84 <output name="output" file="sift_variants_result.tab"/> 85 </test> 86 </tests> 87 88 <help> 89.. class:: warningmark 90 91This currently works only for builds hg18 or hg19. 92 93----- 94 95**Dataset formats** 96 97The input and output datasets are tabular_. 98(`Dataset missing?`_) 99 100.. _tabular: ./static/formatHelp.html#tab 101.. _Dataset missing?: ./static/formatHelp.html 102 103----- 104 105**What it does** 106 107SIFT predicts whether an amino-acid substitution affects protein function, 108based on sequence homology and the physical properties of amino acids. 109SIFT can be applied to naturally occurring non-synonymous polymorphisms 110and laboratory-induced missense mutations. This tool uses SQLite databases 111containing pre-computed SIFT scores and annotations for all possible nucleotide 112substitutions at each position in the human exome. Allele frequency data 113are from the HapMap frequency database, and additional transcript and 114gene-level data are from Ensembl BioMart. 115 116The input dataset must contain columns for the chromosome, position, and 117alleles. The alleles must be two nucleotides separated by '/', 118usually the reference allele and the allele of interest. 119The strand must either be in another column or all the same. 120The output contains a standard set of columns plus the additional ones that 121have been selected from the list above. 122 123Website: http://sift.jcvi.org/ 124 125----- 126 127**Example** 128 129- input file:: 130 131 chr3 81780820 + T/C 132 chr2 230341630 + G/A 133 chr2 43881517 + A/T 134 chr2 43857514 + T/C 135 chr6 88375602 + G/A 136 chr22 29307353 - T/A 137 chr10 115912482 - G/T 138 chr10 115900918 - C/T 139 chr16 69875502 + G/T 140 etc. 141 142- output file:: 143 144 #Chrom Position Strand Allele Codons Transcript ID Protein ID Substitution Region dbSNP ID SNP Type Prediction Score Median Info Num seqs at position User Comment 145 chr3 81780820 + T/C AGA-gGA ENST00000264326 ENSP00000264326 R190G EXON CDS rs2229519:C Nonsynonymous DAMAGING 0.04 3.06 149 146 chr2 230341630 + G/T - ENST00000389045 ENSP00000373697 NA EXON CDS rs1803846:A Unknown Not scored NA NA NA 147 chr2 43881517 + A/T ATA-tTA ENST00000260605 ENSP00000260605 I230L EXON CDS rs11556157:T Nonsynonymous TOLERATED 0.47 3.19 7 148 chr2 43857514 + T/C TTT-TcT ENST00000260605 ENSP00000260605 F33S EXON CDS rs2288709:C Nonsynonymous TOLERATED 0.61 3.33 6 149 chr6 88375602 + G/A GTT-aTT ENST00000257789 ENSP00000257789 V217I EXON CDS rs2307389:A Nonsynonymous TOLERATED 0.75 3.17 13 150 chr22 29307353 + T/A ACC-tCC ENST00000335214 ENSP00000334612 T264S EXON CDS rs42942:A Nonsynonymous TOLERATED 0.4 3.14 23 151 chr10 115912482 + C/A CGA-CtA ENST00000369285 ENSP00000358291 R179L EXON CDS rs12782946:T Nonsynonymous TOLERATED 0.06 4.32 2 152 chr10 115900918 + G/A CAA-tAA ENST00000369287 ENSP00000358293 Q271* EXON CDS rs7095762:T Nonsynonymous N/A N/A N/A N/A 153 chr16 69875502 + G/T ACA-AaA ENST00000338099 ENSP00000337512 T608K EXON CDS rs3096381:T Nonsynonymous TOLERATED 0.12 3.41 3 154 etc. 155 156----- 157 158**References** 159 160Ng PC, Henikoff S. (2001) Predicting deleterious amino acid substitutions. 161Genome Res. 11(5):863-74. 162 163Ng PC, Henikoff S. (2002) Accounting for human polymorphisms predicted to affect protein function. 164Genome Res. 12(3):436-46. 165 166Ng PC, Henikoff S. (2003) SIFT: Predicting amino acid changes that affect protein function. 167Nucleic Acids Res. 31(13):3812-4. 168 169Kumar P, Henikoff S, Ng PC. (2009) Predicting the effects of coding non-synonymous variants 170on protein function using the SIFT algorithm. 171Nat Protoc. 4(7):1073-81. Epub 2009 Jun 25. 172 173 </help> 174</tool>