Mercurial > repos > iuc > snpsift_dbnsfp
changeset 4:4e21e4f2bc48 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp commit fbc18d9128669e461e76ed13307ee88dd774afa5
| author | iuc |
|---|---|
| date | Mon, 12 Jun 2017 10:25:44 -0400 |
| parents | 563d1bdb7b80 |
| children | |
| files | snpSift_dbnsfp.xml snpSift_macros.xml |
| diffstat | 2 files changed, 154 insertions(+), 167 deletions(-) [+] |
line wrap: on
line diff
--- a/snpSift_dbnsfp.xml Mon Dec 19 11:57:06 2016 -0500 +++ b/snpSift_dbnsfp.xml Mon Jun 12 10:25:44 2017 -0400 @@ -1,5 +1,5 @@ -<tool id="snpSift_dbnsfp" name="SnpSift dbNSFP" version="@WRAPPER_VERSION@.1"> - <description>Add Annotations from dbNSFP or similar annotation DBs</description> +<tool id="snpSift_dbnsfp" name="SnpSift dbNSFP" version="@WRAPPER_VERSION@.0"> + <description>Add annotations from dbNSFP or similar annotation DBs</description> <macros> <import>snpSift_macros.xml</import> </macros> @@ -7,23 +7,21 @@ <expand macro="stdio" /> <expand macro="version_command" /> <command><![CDATA[ - @CONDA_SNPSIFT_JAR_PATH@ && - java -Xmx6G -jar "\$SNPSIFT_JAR_PATH/SnpSift.jar" dbnsfp -v - #if $db.dbsrc == 'cached': - -db "$db.dbnsfp" - #if $db.annotations and str($db.annotations) != '': - -f "$db.annotations" - #end if - #else: - -db "${db.dbnsfpdb.extra_files_path}/${db.dbnsfpdb.metadata.bgzip}" - #if $db.annotations and str($db.annotations) != '': - -f "$db.annotations" - #end if - #end if - "$input" > "$output" - 2> tmp.err && grep -v file tmp.err -]]> - </command> +SnpSift -Xmx6G dbnsfp -v +#if $db.dbsrc == 'cached': + -db '$db.dbnsfp' + #if $db.annotations and str($db.annotations) != '': + -f '$db.annotations' + #end if +#else: + -db '${db.dbnsfpdb.extra_files_path}/${db.dbnsfpdb.metadata.bgzip}' + #if $db.annotations and str($db.annotations) != '': + -f '$db.annotations' + #end if +#end if +'$input' > '$output' +2> tmp.err && grep -v file tmp.err + ]]></command> <inputs> <param name="input" type="data" format="vcf" label="Variant input file in VCF format"/> <conditional name="db"> @@ -50,15 +48,15 @@ <when value="history"> <param name="dbnsfpdb" type="data" format="snpsiftdbnsfp" label="DbNSFP"/> <param name="annotations" type="select" multiple="true" display="checkboxes" label="Annotate with"> - <options> - <filter type="data_meta" ref="dbnsfpdb" key="annotation" /> - </options> + <options> + <filter type="data_meta" ref="dbnsfpdb" key="annotation" /> + </options> </param> </when> </conditional> </inputs> <outputs> - <data format="vcf" name="output" /> + <data name="output" format="vcf" /> </outputs> <tests> <!-- This cannot be tested at the moment because test_dbnsfpdb.tabular @@ -78,220 +76,211 @@ </test> --> </tests> <help><![CDATA[ - The dbNSFP is an integrated database of functional predictions from multiple algorithms (SIFT, Polyphen2, LRT and MutationTaster, PhyloP and GERP++, etc.). It contains variant annotations such as: - - 1000Gp1_AC +1000Gp1_AC Alternative allele counts in the whole 1000 genomes phase 1 (1000Gp1) data - 1000Gp1_AF +1000Gp1_AF Alternative allele frequency in the whole 1000Gp1 data - 1000Gp1_AFR_AC +1000Gp1_AFR_AC Alternative allele counts in the 1000Gp1 African descendent samples - 1000Gp1_AFR_AF +1000Gp1_AFR_AF Alternative allele frequency in the 1000Gp1 African descendent samples - 1000Gp1_AMR_AC +1000Gp1_AMR_AC Alternative allele counts in the 1000Gp1 American descendent samples - 1000Gp1_AMR_AF +1000Gp1_AMR_AF Alternative allele frequency in the 1000Gp1 American descendent samples - 1000Gp1_ASN_AC +1000Gp1_ASN_AC Alternative allele counts in the 1000Gp1 Asian descendent samples - 1000Gp1_ASN_AF +1000Gp1_ASN_AF Alternative allele frequency in the 1000Gp1 Asian descendent samples - 1000Gp1_EUR_AC +1000Gp1_EUR_AC Alternative allele counts in the 1000Gp1 European descendent samples - 1000Gp1_EUR_AF +1000Gp1_EUR_AF Alternative allele frequency in the 1000Gp1 European descendent samples - aaalt +aaalt Alternative amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron) - aapos +aapos Amino acid position as to the protein. "-1" if the variant is a splicing site SNP (2bp on each end of an intron) - aapos_SIFT +aapos_SIFT ENSP id and amino acid positions corresponding to SIFT scores. Multiple entries separated by ";" - aapos_FATHMM +aapos_FATHMM ENSP id and amino acid positions corresponding to FATHMM scores. Multiple entries separated by ";" - aaref +aaref Reference amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron) - alt +alt Alternative nucleotide allele (as on the + strand) - Ancestral_allele +Ancestral_allele Ancestral allele (based on 1000 genomes reference data) - cds_strand +cds_strand Coding sequence (CDS) strand (+ or -) - chr +chr Chromosome number - codonpos +codonpos Position on the codon (1, 2 or 3) - Ensembl_geneid +Ensembl_geneid Ensembl gene ID - Ensembl_transcriptid +Ensembl_transcriptid Ensembl transcript IDs (separated by ";") - ESP6500_AA_AF +ESP6500_AA_AF Alternative allele frequency in the African American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set) - ESP6500_EA_AF +ESP6500_EA_AF Alternative allele frequency in the European American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set) - FATHMM_pred +FATHMM_pred If a FATHMM_score is <=-1.5 (or rankscore <=0.81415) the corresponding non-synonymous SNP is predicted as "D(AMAGING)"; otherwise it is predicted as "T(OLERATED)". Multiple predictions separated by ";" - FATHMM_rankscore +FATHMM_rankscore FATHMMori scores were ranked among all FATHMMori scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of FATHMMori scores in dbNSFP. If there are multiple scores, only the most damaging (largest) rankscore is presented. The scores range from 0 to 1 - FATHMM_score +FATHMM_score FATHMM default score (FATHMMori) - fold-degenerate +fold-degenerate Degenerate type (0, 2 or 3) - genename +genename Gene name; if the non-synonymous SNP can be assigned to multiple genes, gene names are separated by ";" - GERP++_NR +GERP++_NR GERP++ neutral rate - GERP++_RS +GERP++_RS GERP++ RS score, the larger the score, the more conserved the site - GERP++_RS_rankscore +GERP++_RS_rankscore GERP++ RS scores were ranked among all GERP++ RS scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of GERP++ RS scores in dbNSFP - hg18_pos(1-coor) +hg18_pos(1-coor) Physical position on the chromosome as to hg18 (1-based coordinate) - Interpro_domain +Interpro_domain Domain or conserved site on which the variant locates - LR_pred +LR_pred Prediction of our LR based ensemble prediction score, "T(olerated)" or "D(amaging)". The score cutoff between "D" and "T" is 0.5. The rankscore cutoff between "D" and "T" is 0.82268 - LR_rankscore +LR_rankscore LR scores were ranked among all LR scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of LR scores in dbNSFP. The scores range from 0 to 1 - LR_score +LR_score Our logistic regression (LR) based ensemble prediction score, which incorporated 10 scores (SIFT, PolyPhen-2 HDIV, PolyPhen-2 HVAR, GERP++, MutationTaster, Mutation Assessor, FATHMM, LRT, SiPhy, PhyloP) and the maximum frequency observed in the 1000 genomes populations. Larger value means the SNV is more likely to be damaging. Scores range from 0 to 1 - LRT_Omega +LRT_Omega Estimated nonsynonymous-to-synonymous-rate ratio (Omega, reported by LRT) - LRT_converted_rankscore +LRT_converted_rankscore LRTori scores were first converted as LRTnew=1-LRTori*0.5 if Omega<1, or LRTnew=LRTori*0.5 if Omega>=1. Then LRTnew scores were ranked among all LRTnew scores in dbNSFP. The rankscore is the ratio of the rank over the total number of the scores in dbNSFP. The scores range from 0.00166 to 0.85682 - LRT_pred +LRT_pred LRT prediction, D(eleterious), N(eutral) or U(nknown), which is not solely determined by the score - LRT_score +LRT_score The original LRT two-sided p-value (LRTori), ranges from 0 to 1 - MutationAssessor_pred +MutationAssessor_pred MutationAssessor's functional impact of a variant - MutationAssessor_rankscore +MutationAssessor_rankscore MAori scores were ranked among all MAori scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of MAori scores in dbNSFP. The scores range from 0 to 1 - MutationAssessor_score +MutationAssessor_score MutationAssessor functional impact combined score (MAori) - MutationTaster_converted_rankscore +MutationTaster_converted_rankscore The MTori scores were first converted: if the prediction is "A" or "D" MTnew=MTori; if the prediction is "N" or "P", MTnew=1-MTori. Then MTnew scores were ranked among all MTnew scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of MTnew scores in dbNSFP. The scores range from 0.0931 to 0.80722 - MutationTaster_pred +MutationTaster_pred MutationTaster prediction - MutationTaster_score +MutationTaster_score MutationTaster p-value (MTori), ranges from 0 to 1 - phastCons46way_placental +phastCons46way_placental phastCons conservation score based on the multiple alignments of 33 placental mammal genomes (including human). The larger the score, the more conserved the site - phastCons46way_placental_rankscore +phastCons46way_placental_rankscore phastCons46way_placental scores were ranked among all phastCons46way_placental scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phastCons46way_placental scores in dbNSFP - phastCons46way_primate +phastCons46way_primate phastCons conservation score based on the multiple alignments of 10 primate genomes (including human). The larger the score, the more conserved the site - phastCons46way_primate_rankscore +phastCons46way_primate_rankscore phastCons46way_primate scores were ranked among all phastCons46way_primate scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phastCons46way_primate scores in dbNSFP - phastCons100way_vertebrate +phastCons100way_vertebrate phastCons conservation score based on the multiple alignments of 100 vertebrate genomes (including human). The larger the score, the more conserved the site - phastCons100way_vertebrate_rankscore +phastCons100way_vertebrate_rankscore phastCons100way_vertebrate scores were ranked among all phastCons100way_vertebrate scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phastCons100way_vertebrate scores in dbNSFP - phyloP46way_placental +phyloP46way_placental phyloP (phylogenetic p-values) conservation score based on the multiple alignments of 33 placental mammal genomes (including human). The larger the score, the more conserved the site - phyloP46way_placental_rankscore +phyloP46way_placental_rankscore phyloP46way_placental scores were ranked among all phyloP46way_placental scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phyloP46way_placental scores in dbNSFP - phyloP46way_primate +phyloP46way_primate phyloP (phylogenetic p-values) conservation score based on the multiple alignments of 10 primate genomes (including human). The larger the score, the more conserved the site - phyloP46way_primate_rankscore +phyloP46way_primate_rankscore phyloP46way_primate scores were ranked among all phyloP46way_primate scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phyloP46way_primate scores in dbNSFP - phyloP100way_vertebrate +phyloP100way_vertebrate phyloP (phylogenetic p-values) conservation score based on the multiple alignments of 100 vertebrate genomes (including human). The larger the score, the more conserved the site - phyloP100way_vertebrate_rankscore +phyloP100way_vertebrate_rankscore phyloP100way_vertebrate scores were ranked among all phyloP100way_vertebrate scores in dbNSFP. The rankscore is the ratio of the rank of the score over the total number of phyloP100way_vertebrate scores in dbNSFP - Polyphen2_HDIV_pred +Polyphen2_HDIV_pred Polyphen2 prediction based on HumDiv - Polyphen2_HDIV_rankscore +Polyphen2_HDIV_rankscore Polyphen2 HDIV scores were first ranked among all HDIV scores in dbNSFP. The rankscore is the ratio of the rank the score over the total number of the scores in dbNSFP. If there are multiple scores, only the most damaging (largest) rankscore is presented. The scores range from 0.02656 to 0.89917 - Polyphen2_HDIV_score +Polyphen2_HDIV_score Polyphen2 score based on HumDiv, i.e. hdiv_prob. The score ranges from 0 to 1. Multiple entries separated by ";" - Polyphen2_HVAR_pred +Polyphen2_HVAR_pred Polyphen2 prediction based on HumVar - Polyphen2_HVAR_rankscore +Polyphen2_HVAR_rankscore Polyphen2 HVAR scores were first ranked among all HVAR scores in dbNSFP. The rankscore is the ratio of the rank the score over the total number of the scores in dbNSFP. If there are multiple scores, only the most damaging (largest) rankscore is presented. The scores range from 0.01281 to 0.9711 - Polyphen2_HVAR_score +Polyphen2_HVAR_score Polyphen2 score based on HumVar, i.e. hvar_prob. The score ranges from 0 to 1. Multiple entries separated by ";" - pos(1-coor) +pos(1-coor) Physical position on the chromosome as to hg19 (1-based coordinate) - RadialSVM_pred +RadialSVM_pred Prediction of our SVM based ensemble prediction score, "T(olerated)" or "D(amaging)". The score cutoff between "D" and "T" is 0. The rankscore cutoff between "D" and "T" is 0.83357 - RadialSVM_rankscore +RadialSVM_rankscore RadialSVM scores were ranked among all RadialSVM scores in dbNSFP. The rankscore is the ratio of the rank of the screo over the total number of RadialSVM scores in dbNSFP. The scores range from 0 to 1 - RadialSVM_score +RadialSVM_score Our support vector machine (SVM) based ensemble prediction score, which incorporated 10 scores (SIFT, PolyPhen-2 HDIV, PolyPhen-2 HVAR, GERP++, MutationTaster, Mutation Assessor, FATHMM, LRT, SiPhy, PhyloP) and the maximum frequency observed in the 1000 genomes populations. Larger value means the SNV is more likely to be damaging. Scores range from -2 to 3 in dbNSFP - ref +ref Reference nucleotide allele (as on the + strand) - refcodon +refcodon Reference codon - Reliability_index +Reliability_index Number of observed component scores (except the maximum frequency in the 1000 genomes populations) for RadialSVM and LR. Ranges from 1 to 10. As RadialSVM and LR scores are calculated based on imputed data, the less missing component scores, the higher the reliability of the scores and predictions - SIFT_converted_rankscore +SIFT_converted_rankscore SIFTori scores were first converted to SIFTnew=1-SIFTori, then ranked among all SIFTnew scores in dbNSFP. The rankscore is the ratio of the rank the SIFTnew score over the total number of SIFTnew scores in dbNSFP. If there are multiple scores, only the most damaging (largest) rankscore is presented. The rankscores range from 0.02654 to 0.87932 - SIFT_pred +SIFT_pred If SIFTori is smaller than 0.05 (rankscore>0.55) the corresponding non-synonymous SNP is predicted as "D(amaging)"; otherwise it is predicted as "T(olerated)". Multiple predictions separated by ";" - SIFT_score +SIFT_score SIFT score (SIFTori). Scores range from 0 to 1. The smaller the score the more likely the SNP has damaging effect. Multiple scores separated by ";" - SiPhy_29way_logOdds +SiPhy_29way_logOdds SiPhy score based on 29 mammals genomes. The larger the score, the more conserved the site - SiPhy_29way_pi +SiPhy_29way_pi The estimated stationary distribution of A, C, G and T at the site, using SiPhy algorithm based on 29 mammals genomes - SLR_test_statistic +SLR_test_statistic SLR test statistic for testing natural selection on codons. A negative value indicates negative selection, and a positive value indicates positive selection. Larger magnitude of the value suggests stronger evidence - Uniprot_aapos +Uniprot_aapos Amino acid position as to Uniprot. Multiple entries separated by ";" - Uniprot_acc +Uniprot_acc Uniprot accession number. Multiple entries separated by ";" - Uniprot_id +Uniprot_id Uniprot ID number. Multiple entries separated by ";" - UniSNP_ids +UniSNP_ids rs numbers from UniSNP, which is a cleaned version of dbSNP build 129, in format: rs number1;rs number2;... - -The website for dbNSFP database is https://sites.google.com/site/jpopgen/dbNSFP and there is only annotation for human genome builds. +The dbNSFP database is available from https://sites.google.com/site/jpopgen/dbNSFP and there is only annotation for human genome builds. -The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp is in the SnpSift documentation: -*( It also provides links for dbNSFP databases prebuilt for SnpSift )* +The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp and a couple of prebuilt dbNSFP databases are available at: http://snpeff.sourceforge.net/SnpSift.html#dbNSFP -However, any dbNSFP-like tabular file that be can used with SnpSift dbnsfp if it has:: +However, any dbNSFP-like tabular file that be can used with SnpSift dbnsfp if it has: + +- The first line of the file must be column headers that name the annotations. +- The first 4 columns are required and must be: - - The first line of the file must be column headers that name the annotations. - - The first 4 columns are required and must be:: - 1. chromosome - 2. position in chromosome - 3. reference base - 4. alternate base + 1. chr: chromosome + 2. pos(1-coor): position in chromosome + 3. ref: reference base + 4. alt: alternate base -For example: - -:: +For example:: - #chr pos(1-coor) ref alt aaref aaalt genename SIFT_score - 1 69134 A C E A OR4F5 0.03 - 1 69134 A G E G OR4F5 0.09 - 1 69134 A T E V OR4F5 0.03 - 4 100239319 T A H L ADH1B 0 - 4 100239319 T C H R ADH1B 0.15 - 4 100239319 T G H P ADH1B 0 + #chr pos(1-coor) ref alt aaref aaalt genename SIFT_score + 1 69134 A C E A OR4F5 0.03 + 1 69134 A G E G OR4F5 0.09 + 1 69134 A T E V OR4F5 0.03 + 4 100239319 T A H L ADH1B 0 + 4 100239319 T C H R ADH1B 0.15 + 4 100239319 T G H P ADH1B 0 +The Galaxy datatypes for dbNSFP can automatically convert the specially formatted tabular file for use by SnpSift dbNSFP: -The galaxy datatypes for dbNSFP can automatically convert the specially formatted tabular file for use by SnpSift dbNSFP: - 1. Upload the tabular file, set the datatype as: **"dbnsfp.tabular"** - 2. Edit the history dataset attributes (pencil icon): Use "Convert Format" to convert the **"dbnsfp.tabular"** to the correct format for SnpSift dbnsfp: **"snpsiftdbnsfp"**. - +1. Upload the tabular file, set the datatype as: **"dbnsfp.tabular"** +2. Edit the history dataset attributes (pencil icon): Use "Convert Format" to convert the **"dbnsfp.tabular"** to the correct format for SnpSift dbnsfp: **"snpsiftdbnsfp"**. @EXTERNAL_DOCUMENTATION@ - http://snpeff.sourceforge.net/SnpSift.html#dbNSFP -]]> - </help> +- http://snpeff.sourceforge.net/SnpSift.html#dbNSFP + ]]></help> <expand macro="citations"> - <citation type="doi">DOI: 10.1002/humu.21517</citation> - <citation type="doi">DOI: 10.1002/humu.22376</citation> - <citation type="doi">DOI: 10.1002/humu.22932</citation> - <citation type="doi">doi: 10.1093/hmg/ddu733</citation> - <citation type="doi">doi: 10.1093/nar/gku1206</citation> - <citation type="doi">doi: 10.3389/fgene.2012.00035</citation> + <citation type="doi">10.1002/humu.21517</citation> + <citation type="doi">10.1002/humu.22932</citation> + <citation type="doi">10.1093/hmg/ddu733</citation> + <citation type="doi">10.3389/fgene.2012.00035</citation> </expand> </tool>
--- a/snpSift_macros.xml Mon Dec 19 11:57:06 2016 -0500 +++ b/snpSift_macros.xml Mon Jun 12 10:25:44 2017 -0400 @@ -1,33 +1,31 @@ <macros> <xml name="requirements"> <requirements> - <requirement type="package" version="4.1">snpsift</requirement> + <requirement type="package" version="4.3.1p">snpsift</requirement> </requirements> </xml> - <xml name="stdio"> - <stdio> - <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> - <exit_code range="1:" level="fatal" description="Error" /> - </stdio> - </xml> - <token name="@CONDA_SNPSIFT_JAR_PATH@">if [ -z "\$SNPSIFT_JAR_PATH" ]; then export SNPSIFT_JAR_PATH=\$(dirname \$(readlink -e \$(which SnpSift))); fi</token> - <xml name="version_command"> - <version_command><![CDATA[ - if [ -z "$SNPSIFT_JAR_PATH" ]; then export SNPSIFT_JAR_PATH=$(dirname $(readlink -e $(which SnpSift))); fi && - java -jar "$SNPSIFT_JAR_PATH/SnpSift.jar" dbnsfp 2>&1|head -n 1 - ]]></version_command> - </xml> - <token name="@WRAPPER_VERSION@">4.1</token> - <token name="@EXTERNAL_DOCUMENTATION@"> + <xml name="stdio"> + <stdio> + <exit_code range=":-1" level="fatal" description="Error: Cannot open file" /> + <exit_code range="1:" level="fatal" description="Error" /> + </stdio> + </xml> + <token name="@CONDA_SNPSIFT_JAR_PATH@">if [ -z "\$SNPSIFT_JAR_PATH" ]; then export SNPSIFT_JAR_PATH=\$(dirname \$(readlink -e \$(which SnpSift))); fi</token> + <xml name="version_command"> + <version_command><![CDATA[ +SnpSift dbnsfp 2>&1|head -n 1 + ]]></version_command> + </xml> + <token name="@WRAPPER_VERSION@">4.3</token> + <token name="@EXTERNAL_DOCUMENTATION@"> +For details about this tool, please go to: -For details about this tool, please go to: - http://snpeff.sourceforge.net/SnpEff_manual.html - - </token> - <xml name="citations"> - <citations> - <citation type="doi">10.3389/fgene.2012.00035</citation> - <yield /> - </citations> - </xml> +- http://snpeff.sourceforge.net/SnpEff_manual.html + </token> + <xml name="citations"> + <citations> + <citation type="doi">10.3389/fgene.2012.00035</citation> + <yield /> + </citations> + </xml> </macros>