Mercurial > repos > iuc > snpsift_dbnsfp_generic
annotate snpSift_dbnsfp.xml @ 2:a7cbaf3beadd draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit bd4fbe120288bf8452e479cbd82aa1bbf5c4bd31
| author | iuc |
|---|---|
| date | Mon, 19 Dec 2016 11:57:16 -0500 |
| parents | 1f4ee04c0841 |
| children |
| rev | line source |
|---|---|
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
1 <tool id="snpSift_dbnsfp_generic" name="SnpSift dbNSFP" version="@WRAPPER_VERSION@.1"> |
| 0 | 2 <description>Add Annotations from dbNSFP and similar annotation DBs</description> |
| 3 <macros> | |
| 4 <import>snpSift_macros.xml</import> | |
| 5 </macros> | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
6 <expand macro="requirements" /> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
7 <expand macro="stdio" /> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
8 <expand macro="version_command" /> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
9 <command><![CDATA[ |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
10 @CONDA_SNPSIFT_JAR_PATH@ && |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
11 java -Xmx6G -jar "\$SNPSIFT_JAR_PATH/SnpSift.jar" dbnsfp -v |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
12 #if $db.dbsrc == 'cached': |
| 0 | 13 -db $db.dbnsfp |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
14 #if $db.annotations and str($db.annotations) != '': |
| 0 | 15 -f "$db.annotations" |
| 16 #end if | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
17 #else: |
| 0 | 18 -db "${db.dbnsfpdb.extra_files_path}/${db.dbnsfpdb.metadata.bgzip}" |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
19 #if $db.annotations and str($db.annotations) != '': |
| 0 | 20 -f "$db.annotations" |
| 21 #end if | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
22 #end if |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
23 "$input" > "$output" |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
24 2> tmp.err && grep -v file tmp.err |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
25 ]]> |
| 0 | 26 </command> |
| 27 <inputs> | |
| 28 <param name="input" type="data" format="vcf" label="Variant input file in VCF format"/> | |
| 29 <conditional name="db"> | |
| 30 <param name="dbsrc" type="select" label="dbNSFP "> | |
| 31 <option value="cached">Locally installed dbNSFP database </option> | |
| 32 <option value="history">dbNSFP database from your history</option> | |
| 33 </param> | |
| 34 <when value="cached"> | |
| 35 <param name="dbnsfp" type="select" label="Genome"> | |
| 36 <options from_data_table="snpsift_dbnsfp"> | |
| 37 <column name="name" index="2"/> | |
| 38 <column name="value" index="3"/> | |
| 39 </options> | |
| 40 </param> | |
| 41 <param name="annotations" type="select" multiple="true" display="checkboxes" label="Annotate with"> | |
| 42 <options from_data_table="snpsift_dbnsfp"> | |
| 43 <column name="name" index="3"/> | |
| 44 <column name="value" index="3"/> | |
| 45 <filter type="param_value" ref="dbnsfp" column="2" /> | |
| 46 <filter type="multiple_splitter" column="3" separator=","/> | |
| 47 </options> | |
| 48 </param> | |
| 49 </when> | |
| 50 <when value="history"> | |
| 51 <param name="dbnsfpdb" type="data" format="snpsiftdbnsfp" label="DbNSFP"/> | |
| 52 <param name="annotations" type="select" multiple="true" display="checkboxes" label="Annotate with"> | |
| 53 <options> | |
| 54 <filter type="data_meta" ref="dbnsfpdb" key="annotation" /> | |
| 55 </options> | |
| 56 </param> | |
| 57 </when> | |
| 58 </conditional> | |
| 59 </inputs> | |
| 60 <outputs> | |
| 61 <data format="vcf" name="output" /> | |
| 62 </outputs> | |
| 63 <tests> | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
64 <!-- This cannot be tested at the moment because test_dbnsfpdb.tabular |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
65 is converted from dbnsfp.tabular to snpsiftdbnsfp format on-the-fly |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
66 when this tool is run and annotation metadata is not available |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
67 until after the conversion is completed. |
| 0 | 68 <test> |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
69 <param name="input" ftype="vcf" value="test_annotate_in.vcf"/> |
| 0 | 70 <param name="dbsrc" value="history"/> |
| 71 <param name="dbnsfpdb" value="test_dbnsfpdb.tabular" ftype="dbnsfp.tabular" /> | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
72 <param name="annotations" value="aaref,aaalt,genename,aapos,SIFT_score"/> |
| 0 | 73 <output name="output"> |
| 74 <assert_contents> | |
| 75 <has_text text="dbNSFP_SIFT_score=0.15" /> | |
| 76 </assert_contents> | |
| 77 </output> | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
78 </test> --> |
| 0 | 79 </tests> |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
80 <help><![CDATA[ |
| 0 | 81 |
| 82 The dbNSFP is an integrated database of functional predictions from multiple algorithms (SIFT, Polyphen2, LRT and MutationTaster, PhyloP and GERP++, etc.). | |
| 83 It contains variant annotations such as: | |
| 84 | |
| 85 | |
| 86 1000Gp1_AC | |
| 87 Alternative allele counts in the whole 1000 genomes phase 1 (1000Gp1) data | |
| 88 1000Gp1_AF | |
| 89 Alternative allele frequency in the whole 1000Gp1 data | |
| 90 1000Gp1_AFR_AC | |
| 91 Alternative allele counts in the 1000Gp1 African descendent samples | |
| 92 1000Gp1_AFR_AF | |
| 93 Alternative allele frequency in the 1000Gp1 African descendent samples | |
| 94 1000Gp1_AMR_AC | |
| 95 Alternative allele counts in the 1000Gp1 American descendent samples | |
| 96 1000Gp1_AMR_AF | |
| 97 Alternative allele frequency in the 1000Gp1 American descendent samples | |
| 98 1000Gp1_ASN_AC | |
| 99 Alternative allele counts in the 1000Gp1 Asian descendent samples | |
| 100 1000Gp1_ASN_AF | |
| 101 Alternative allele frequency in the 1000Gp1 Asian descendent samples | |
| 102 1000Gp1_EUR_AC | |
| 103 Alternative allele counts in the 1000Gp1 European descendent samples | |
| 104 1000Gp1_EUR_AF | |
| 105 Alternative allele frequency in the 1000Gp1 European descendent samples | |
| 106 aaalt | |
| 107 Alternative amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron) | |
| 108 aapos | |
| 109 Amino acid position as to the protein. "-1" if the variant is a splicing site SNP (2bp on each end of an intron) | |
| 110 aapos_SIFT | |
| 111 ENSP id and amino acid positions corresponding to SIFT scores. Multiple entries separated by ";" | |
| 112 aapos_FATHMM | |
| 113 ENSP id and amino acid positions corresponding to FATHMM scores. Multiple entries separated by ";" | |
| 114 aaref | |
| 115 Reference amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron) | |
| 116 alt | |
| 117 Alternative nucleotide allele (as on the + strand) | |
| 118 Ancestral_allele | |
| 119 Ancestral allele (based on 1000 genomes reference data) | |
| 120 cds_strand | |
| 121 Coding sequence (CDS) strand (+ or -) | |
| 122 chr | |
| 123 Chromosome number | |
| 124 codonpos | |
| 125 Position on the codon (1, 2 or 3) | |
| 126 Ensembl_geneid | |
| 127 Ensembl gene ID | |
| 128 Ensembl_transcriptid | |
| 129 Ensembl transcript IDs (separated by ";") | |
| 130 ESP6500_AA_AF | |
| 131 Alternative allele frequency in the African American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set) | |
| 132 ESP6500_EA_AF | |
| 133 Alternative allele frequency in the European American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set) | |
| 134 FATHMM_pred | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
135 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 ";" |
| 0 | 136 FATHMM_rankscore |
| 137 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 | |
| 138 FATHMM_score | |
| 139 FATHMM default score (FATHMMori) | |
| 140 fold-degenerate | |
| 141 Degenerate type (0, 2 or 3) | |
| 142 genename | |
| 143 Gene name; if the non-synonymous SNP can be assigned to multiple genes, gene names are separated by ";" | |
| 144 GERP++_NR | |
| 145 GERP++ neutral rate | |
| 146 GERP++_RS | |
| 147 GERP++ RS score, the larger the score, the more conserved the site | |
| 148 GERP++_RS_rankscore | |
| 149 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 | |
| 150 hg18_pos(1-coor) | |
| 151 Physical position on the chromosome as to hg18 (1-based coordinate) | |
| 152 Interpro_domain | |
| 153 Domain or conserved site on which the variant locates | |
| 154 LR_pred | |
| 155 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 | |
| 156 LR_rankscore | |
| 157 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 | |
| 158 LR_score | |
| 159 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 | |
| 160 LRT_Omega | |
| 161 Estimated nonsynonymous-to-synonymous-rate ratio (Omega, reported by LRT) | |
| 162 LRT_converted_rankscore | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
163 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 |
| 0 | 164 LRT_pred |
| 165 LRT prediction, D(eleterious), N(eutral) or U(nknown), which is not solely determined by the score | |
| 166 LRT_score | |
| 167 The original LRT two-sided p-value (LRTori), ranges from 0 to 1 | |
| 168 MutationAssessor_pred | |
| 169 MutationAssessor's functional impact of a variant | |
| 170 MutationAssessor_rankscore | |
| 171 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 | |
| 172 MutationAssessor_score | |
| 173 MutationAssessor functional impact combined score (MAori) | |
| 174 MutationTaster_converted_rankscore | |
| 175 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 | |
| 176 MutationTaster_pred | |
| 177 MutationTaster prediction | |
| 178 MutationTaster_score | |
| 179 MutationTaster p-value (MTori), ranges from 0 to 1 | |
| 180 phastCons46way_placental | |
| 181 phastCons conservation score based on the multiple alignments of 33 placental mammal genomes (including human). The larger the score, the more conserved the site | |
| 182 phastCons46way_placental_rankscore | |
| 183 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 | |
| 184 phastCons46way_primate | |
| 185 phastCons conservation score based on the multiple alignments of 10 primate genomes (including human). The larger the score, the more conserved the site | |
| 186 phastCons46way_primate_rankscore | |
| 187 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 | |
| 188 phastCons100way_vertebrate | |
| 189 phastCons conservation score based on the multiple alignments of 100 vertebrate genomes (including human). The larger the score, the more conserved the site | |
| 190 phastCons100way_vertebrate_rankscore | |
| 191 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 | |
| 192 phyloP46way_placental | |
| 193 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 | |
| 194 phyloP46way_placental_rankscore | |
| 195 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 | |
| 196 phyloP46way_primate | |
| 197 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 | |
| 198 phyloP46way_primate_rankscore | |
| 199 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 | |
| 200 phyloP100way_vertebrate | |
| 201 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 | |
| 202 phyloP100way_vertebrate_rankscore | |
| 203 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 | |
| 204 Polyphen2_HDIV_pred | |
| 205 Polyphen2 prediction based on HumDiv | |
| 206 Polyphen2_HDIV_rankscore | |
| 207 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 | |
| 208 Polyphen2_HDIV_score | |
| 209 Polyphen2 score based on HumDiv, i.e. hdiv_prob. The score ranges from 0 to 1. Multiple entries separated by ";" | |
| 210 Polyphen2_HVAR_pred | |
| 211 Polyphen2 prediction based on HumVar | |
| 212 Polyphen2_HVAR_rankscore | |
| 213 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 | |
| 214 Polyphen2_HVAR_score | |
| 215 Polyphen2 score based on HumVar, i.e. hvar_prob. The score ranges from 0 to 1. Multiple entries separated by ";" | |
| 216 pos(1-coor) | |
| 217 Physical position on the chromosome as to hg19 (1-based coordinate) | |
| 218 RadialSVM_pred | |
| 219 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 | |
| 220 RadialSVM_rankscore | |
| 221 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 | |
| 222 RadialSVM_score | |
| 223 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 | |
| 224 ref | |
| 225 Reference nucleotide allele (as on the + strand) | |
| 226 refcodon | |
| 227 Reference codon | |
| 228 Reliability_index | |
| 229 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 | |
| 230 SIFT_converted_rankscore | |
| 231 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 | |
| 232 SIFT_pred | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
233 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 ";" |
| 0 | 234 SIFT_score |
| 235 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 ";" | |
| 236 SiPhy_29way_logOdds | |
| 237 SiPhy score based on 29 mammals genomes. The larger the score, the more conserved the site | |
| 238 SiPhy_29way_pi | |
| 239 The estimated stationary distribution of A, C, G and T at the site, using SiPhy algorithm based on 29 mammals genomes | |
| 240 SLR_test_statistic | |
| 241 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 | |
| 242 Uniprot_aapos | |
| 243 Amino acid position as to Uniprot. Multiple entries separated by ";" | |
| 244 Uniprot_acc | |
| 245 Uniprot accession number. Multiple entries separated by ";" | |
| 246 Uniprot_id | |
| 247 Uniprot ID number. Multiple entries separated by ";" | |
| 248 UniSNP_ids | |
| 249 rs numbers from UniSNP, which is a cleaned version of dbSNP build 129, in format: rs number1;rs number2;... | |
| 250 | |
| 251 | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
252 The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp and a couple of prebuilt dbNSFP databases are available at: |
| 0 | 253 http://snpeff.sourceforge.net/SnpSift.html#dbNSFP |
| 254 | |
| 255 | |
| 256 **Uploading Your Own Annotations for any Genome** | |
| 257 | |
| 258 The website for dbNSFP databases releases is: | |
| 259 https://sites.google.com/site/jpopgen/dbNSFP | |
| 260 | |
| 261 But there is only annotation for human hg18, hg19, and hg38 genome builds. | |
| 262 | |
| 263 However, any dbNSFP-like tabular file that be can used with SnpSift dbnsfp if it has: | |
| 264 | |
| 265 - The first line of the file must be column headers that name the annotations. | |
| 266 - The first 4 columns are required and must be: | |
| 267 | |
| 268 1. #chr - chromosome | |
| 269 2. pos(1-coor) - position in chromosome | |
| 270 3. ref - reference base | |
| 271 4. alt - alternate base | |
| 272 | |
| 273 | |
| 274 For example: | |
| 275 | |
| 276 :: | |
| 277 | |
| 278 #chr pos(1-coor) ref alt aaref aaalt genename SIFT_score | |
| 279 4 100239319 T A H L ADH1B 0 | |
| 280 4 100239319 T C H R ADH1B 0.15 | |
| 281 4 100239319 T G H P ADH1B 0 | |
| 282 | |
| 283 | |
| 284 The custom galaxy datatypes for dbNSFP can automatically convert the specially formatted tabular file for use by SnpSift dbNSFP: | |
| 285 1. Upload the tabular file, set the datatype as: **"dbnsfp.tabular"** | |
| 286 2. Edit the history dataset attributes (pencil icon): Use "Convert Format" to convert the **"dbnsfp.tabular"** to the correct format for SnpSift dbnsfp: **"snpsiftdbnsfp"**. | |
| 287 | |
| 288 The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp is in the SnpSift documentation. | |
| 289 | |
| 290 | |
| 291 @EXTERNAL_DOCUMENTATION@ | |
| 292 http://snpeff.sourceforge.net/SnpSift.html#dbNSFP | |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
293 ]]> |
| 0 | 294 </help> |
|
1
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
295 <expand macro="citations"> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
296 <citation type="doi">DOI: 10.1002/humu.21517</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
297 <citation type="doi">DOI: 10.1002/humu.22376</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
298 <citation type="doi">DOI: 10.1002/humu.22932</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
299 <citation type="doi">doi: 10.1093/hmg/ddu733</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
300 <citation type="doi">doi: 10.1093/nar/gku1206</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
301 <citation type="doi">doi: 10.3389/fgene.2012.00035</citation> |
|
1f4ee04c0841
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tool_collections/snpsift/snpsift_dbnsfp_generic/ commit d12355cea76843e3ed6f09d96c3e9fe22afe4a4f
iuc
parents:
0
diff
changeset
|
302 </expand> |
| 0 | 303 </tool> |