|
0
|
1 <tool id="snpSift_dbnsfp" name="SnpSift dbNSFP" version="4.0.0">
|
|
|
2 <description>Add Annotations from dbNSFP</description>
|
|
|
3 <expand macro="requirements" />
|
|
|
4 <macros>
|
|
|
5 <import>snpSift_macros.xml</import>
|
|
|
6 </macros>
|
|
|
7 <command>
|
|
|
8 java -Xmx6G -jar \$SNPEFF_JAR_PATH/SnpSift.jar dbnsfp -v
|
|
|
9 #if $db.dbsrc == 'cached' :
|
|
|
10 -db $db.dbnsfp
|
|
|
11 #if $db.annotations and $db.annotations.__str__ != '':
|
|
|
12 -f "$db.annotations"
|
|
|
13 #end if
|
|
|
14 #else :
|
|
|
15 -db "${db.dbnsfpdb.extra_files_path}/${db.dbnsfpdb.metadata.bgzip}"
|
|
|
16 #if $db.annotations and $db.annotations.__str__ != '':
|
|
|
17 -f "$db.annotations"
|
|
|
18 #end if
|
|
|
19 #end if
|
|
|
20 $input > $output
|
|
|
21 2> tmp.err && grep -v file tmp.err
|
|
|
22 </command>
|
|
|
23 <inputs>
|
|
|
24 <param name="input" type="data" format="vcf" label="Variant input file in VCF format"/>
|
|
|
25 <conditional name="db">
|
|
|
26 <param name="dbsrc" type="select" label="dbNSFP ">
|
|
|
27 <option value="cached">Locally installed dbNSFP database </option>
|
|
|
28 <option value="history">dbNSFP database from your history</option>
|
|
|
29 </param>
|
|
|
30 <when value="cached">
|
|
|
31 <param name="dbnsfp" type="select" label="Genome">
|
|
|
32 <options from_data_table="snpsift_dbnsfp">
|
|
|
33 <column name="name" index="1"/>
|
|
|
34 <column name="value" index="2"/>
|
|
|
35 </options>
|
|
|
36 </param>
|
|
|
37 <param name="annotations" type="select" multiple="true" display="checkboxes" label="Annotate with">
|
|
|
38 <options from_data_table="snpsift_dbnsfp">
|
|
|
39 <column name="name" index="3"/>
|
|
|
40 <column name="value" index="3"/>
|
|
|
41 <filter type="param_value" ref="dbnsfp" column="2" />
|
|
|
42 <filter type="multiple_splitter" column="3" separator=","/>
|
|
|
43 </options>
|
|
|
44 </param>
|
|
|
45 </when>
|
|
|
46 <when value="history">
|
|
|
47 <param name="dbnsfpdb" type="data" format="snpsiftdbnsfp" label="DbNSFP"/>
|
|
|
48 <param name="annotations" type="select" multiple="true" display="checkboxes" label="Annotate with">
|
|
|
49 <options>
|
|
|
50 <filter type="data_meta" ref="dbnsfpdb" key="annotation" />
|
|
|
51 </options>
|
|
|
52 </param>
|
|
|
53 </when>
|
|
|
54 </conditional>
|
|
|
55 </inputs>
|
|
|
56 <expand macro="stdio" />
|
|
|
57 <outputs>
|
|
|
58 <data format="vcf" name="output" />
|
|
|
59 </outputs>
|
|
|
60 <tests>
|
|
|
61 <test>
|
|
|
62 <param name="input" ftype="vcf" value="test_annotate_in.vcf.vcf"/>
|
|
|
63 <param name="dbsrc" value="history"/>
|
|
|
64 <param name="dbnsfpdb" value="test_dbnsfpdb.tabular" ftype="dbnsfp.tabular" />
|
|
|
65 <annotations value="aaref,aaalt,genename,aapos,SIFT_score"/>
|
|
|
66 <output name="output">
|
|
|
67 <assert_contents>
|
|
|
68 <has_text text="dbNSFP_SIFT_score=0.15" />
|
|
|
69 </assert_contents>
|
|
|
70 </output>
|
|
|
71 </test>
|
|
|
72 </tests>
|
|
|
73 <help>
|
|
|
74
|
|
|
75 The dbNSFP is an integrated database of functional predictions from multiple algorithms (SIFT, Polyphen2, LRT and MutationTaster, PhyloP and GERP++, etc.).
|
|
|
76
|
|
|
77
|
|
|
78 1000Gp1_AC
|
|
|
79 Alternative allele counts in the whole 1000 genomes phase 1 (1000Gp1) data
|
|
|
80 1000Gp1_AF
|
|
|
81 Alternative allele frequency in the whole 1000Gp1 data
|
|
|
82 1000Gp1_AFR_AC
|
|
|
83 Alternative allele counts in the 1000Gp1 African descendent samples
|
|
|
84 1000Gp1_AFR_AF
|
|
|
85 Alternative allele frequency in the 1000Gp1 African descendent samples
|
|
|
86 1000Gp1_AMR_AC
|
|
|
87 Alternative allele counts in the 1000Gp1 American descendent samples
|
|
|
88 1000Gp1_AMR_AF
|
|
|
89 Alternative allele frequency in the 1000Gp1 American descendent samples
|
|
|
90 1000Gp1_ASN_AC
|
|
|
91 Alternative allele counts in the 1000Gp1 Asian descendent samples
|
|
|
92 1000Gp1_ASN_AF
|
|
|
93 Alternative allele frequency in the 1000Gp1 Asian descendent samples
|
|
|
94 1000Gp1_EUR_AC
|
|
|
95 Alternative allele counts in the 1000Gp1 European descendent samples
|
|
|
96 1000Gp1_EUR_AF
|
|
|
97 Alternative allele frequency in the 1000Gp1 European descendent samples
|
|
|
98 aaalt
|
|
|
99 Alternative amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
100 aapos
|
|
|
101 Amino acid position as to the protein. "-1" if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
102 aapos_SIFT
|
|
|
103 ENSP id and amino acid positions corresponding to SIFT scores. Multiple entries separated by ";"
|
|
|
104 aapos_FATHMM
|
|
|
105 ENSP id and amino acid positions corresponding to FATHMM scores. Multiple entries separated by ";"
|
|
|
106 aaref
|
|
|
107 Reference amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
108 alt
|
|
|
109 Alternative nucleotide allele (as on the + strand)
|
|
|
110 Ancestral_allele
|
|
|
111 Ancestral allele (based on 1000 genomes reference data)
|
|
|
112 cds_strand
|
|
|
113 Coding sequence (CDS) strand (+ or -)
|
|
|
114 chr
|
|
|
115 Chromosome number
|
|
|
116 codonpos
|
|
|
117 Position on the codon (1, 2 or 3)
|
|
|
118 Ensembl_geneid
|
|
|
119 Ensembl gene ID
|
|
|
120 Ensembl_transcriptid
|
|
|
121 Ensembl transcript IDs (separated by ";")
|
|
|
122 ESP6500_AA_AF
|
|
|
123 Alternative allele frequency in the African American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set)
|
|
|
124 ESP6500_EA_AF
|
|
|
125 Alternative allele frequency in the European American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set)
|
|
|
126 FATHMM_pred
|
|
|
127 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 ";"
|
|
|
128 FATHMM_rankscore
|
|
|
129 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
|
|
|
130 FATHMM_score
|
|
|
131 FATHMM default score (FATHMMori)
|
|
|
132 fold-degenerate
|
|
|
133 Degenerate type (0, 2 or 3)
|
|
|
134 genename
|
|
|
135 Gene name; if the non-synonymous SNP can be assigned to multiple genes, gene names are separated by ";"
|
|
|
136 GERP++_NR
|
|
|
137 GERP++ neutral rate
|
|
|
138 GERP++_RS
|
|
|
139 GERP++ RS score, the larger the score, the more conserved the site
|
|
|
140 GERP++_RS_rankscore
|
|
|
141 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
|
|
|
142 hg18_pos(1-coor)
|
|
|
143 Physical position on the chromosome as to hg18 (1-based coordinate)
|
|
|
144 Interpro_domain
|
|
|
145 Domain or conserved site on which the variant locates
|
|
|
146 LR_pred
|
|
|
147 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
|
|
|
148 LR_rankscore
|
|
|
149 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
|
|
|
150 LR_score
|
|
|
151 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
|
|
|
152 LRT_Omega
|
|
|
153 Estimated nonsynonymous-to-synonymous-rate ratio (Omega, reported by LRT)
|
|
|
154 LRT_converted_rankscore
|
|
|
155 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
|
|
|
156 LRT_pred
|
|
|
157 LRT prediction, D(eleterious), N(eutral) or U(nknown), which is not solely determined by the score
|
|
|
158 LRT_score
|
|
|
159 The original LRT two-sided p-value (LRTori), ranges from 0 to 1
|
|
|
160 MutationAssessor_pred
|
|
|
161 MutationAssessor's functional impact of a variant
|
|
|
162 MutationAssessor_rankscore
|
|
|
163 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
|
|
|
164 MutationAssessor_score
|
|
|
165 MutationAssessor functional impact combined score (MAori)
|
|
|
166 MutationTaster_converted_rankscore
|
|
|
167 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
|
|
|
168 MutationTaster_pred
|
|
|
169 MutationTaster prediction
|
|
|
170 MutationTaster_score
|
|
|
171 MutationTaster p-value (MTori), ranges from 0 to 1
|
|
|
172 phastCons46way_placental
|
|
|
173 phastCons conservation score based on the multiple alignments of 33 placental mammal genomes (including human). The larger the score, the more conserved the site
|
|
|
174 phastCons46way_placental_rankscore
|
|
|
175 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
|
|
|
176 phastCons46way_primate
|
|
|
177 phastCons conservation score based on the multiple alignments of 10 primate genomes (including human). The larger the score, the more conserved the site
|
|
|
178 phastCons46way_primate_rankscore
|
|
|
179 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
|
|
|
180 phastCons100way_vertebrate
|
|
|
181 phastCons conservation score based on the multiple alignments of 100 vertebrate genomes (including human). The larger the score, the more conserved the site
|
|
|
182 phastCons100way_vertebrate_rankscore
|
|
|
183 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
|
|
|
184 phyloP46way_placental
|
|
|
185 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
|
|
|
186 phyloP46way_placental_rankscore
|
|
|
187 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
|
|
|
188 phyloP46way_primate
|
|
|
189 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
|
|
|
190 phyloP46way_primate_rankscore
|
|
|
191 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
|
|
|
192 phyloP100way_vertebrate
|
|
|
193 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
|
|
|
194 phyloP100way_vertebrate_rankscore
|
|
|
195 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
|
|
|
196 Polyphen2_HDIV_pred
|
|
|
197 Polyphen2 prediction based on HumDiv
|
|
|
198 Polyphen2_HDIV_rankscore
|
|
|
199 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
|
|
|
200 Polyphen2_HDIV_score
|
|
|
201 Polyphen2 score based on HumDiv, i.e. hdiv_prob. The score ranges from 0 to 1. Multiple entries separated by ";"
|
|
|
202 Polyphen2_HVAR_pred
|
|
|
203 Polyphen2 prediction based on HumVar
|
|
|
204 Polyphen2_HVAR_rankscore
|
|
|
205 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
|
|
|
206 Polyphen2_HVAR_score
|
|
|
207 Polyphen2 score based on HumVar, i.e. hvar_prob. The score ranges from 0 to 1. Multiple entries separated by ";"
|
|
|
208 pos(1-coor)
|
|
|
209 Physical position on the chromosome as to hg19 (1-based coordinate)
|
|
|
210 RadialSVM_pred
|
|
|
211 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
|
|
|
212 RadialSVM_rankscore
|
|
|
213 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
|
|
|
214 RadialSVM_score
|
|
|
215 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
|
|
|
216 ref
|
|
|
217 Reference nucleotide allele (as on the + strand)
|
|
|
218 refcodon
|
|
|
219 Reference codon
|
|
|
220 Reliability_index
|
|
|
221 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
|
|
|
222 SIFT_converted_rankscore
|
|
|
223 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
|
|
|
224 SIFT_pred
|
|
|
225 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 ";"
|
|
|
226 SIFT_score
|
|
|
227 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 ";"
|
|
|
228 SiPhy_29way_logOdds
|
|
|
229 SiPhy score based on 29 mammals genomes. The larger the score, the more conserved the site
|
|
|
230 SiPhy_29way_pi
|
|
|
231 The estimated stationary distribution of A, C, G and T at the site, using SiPhy algorithm based on 29 mammals genomes
|
|
|
232 SLR_test_statistic
|
|
|
233 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
|
|
|
234 Uniprot_aapos
|
|
|
235 Amino acid position as to Uniprot. Multiple entries separated by ";"
|
|
|
236 Uniprot_acc
|
|
|
237 Uniprot accession number. Multiple entries separated by ";"
|
|
|
238 Uniprot_id
|
|
|
239 Uniprot ID number. Multiple entries separated by ";"
|
|
|
240 UniSNP_ids
|
|
|
241 rs numbers from UniSNP, which is a cleaned version of dbSNP build 129, in format: rs number1;rs number2;...
|
|
|
242
|
|
|
243
|
|
|
244 The website for dbNSFP database is https://sites.google.com/site/jpopgen/dbNSFP and there is only annotation for human hg18 and hg19 genome builds.
|
|
|
245
|
|
|
246 However, any dbNSFP-like tabular file that be can used with SnpSift dbnsfp if it has::
|
|
|
247
|
|
|
248 - The first line of the file must be column headers that name the annotations.
|
|
|
249 - The first 4 columns are required and must be::
|
|
|
250 1. chromosome
|
|
|
251 2. position in chromosome
|
|
|
252 3. reference base
|
|
|
253 4. alternate base
|
|
|
254
|
|
|
255 For example:
|
|
|
256
|
|
|
257 ::
|
|
|
258
|
|
|
259 #chr pos(1-coor) ref alt aaref aaalt genename SIFT_score
|
|
|
260 1 69134 A C E A OR4F5 0.03
|
|
|
261 1 69134 A G E G OR4F5 0.09
|
|
|
262 1 69134 A T E V OR4F5 0.03
|
|
|
263 4 100239319 T A H L ADH1B 0
|
|
|
264 4 100239319 T C H R ADH1B 0.15
|
|
|
265 4 100239319 T G H P ADH1B 0
|
|
|
266
|
|
|
267
|
|
|
268 The uploaded tabular file should be set to datatype: "dbnsfp.tabular"
|
|
|
269 Using "Convert Format" the "dbnsfp.tabular" can be converted to the correct format for SnpSift dbnsfp.
|
|
|
270
|
|
|
271 The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp is in the SnpSift documentation.
|
|
|
272
|
|
|
273
|
|
|
274 @EXTERNAL_DOCUMENTATION@
|
|
|
275 http://snpeff.sourceforge.net/SnpSift.html#dbNSFP
|
|
|
276
|
|
|
277 @CITATION_SECTION@
|
|
|
278
|
|
|
279
|
|
|
280 </help>
|
|
|
281 </tool>
|
