|
3
|
1 <tool id="snpSift_dbnsfp_generic" name="SnpSift dbNSFP" version="4.0.0">
|
|
|
2 <description>Add Annotations from dbNSFP and similar annotation DBs</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="2"/>
|
|
|
34 <column name="value" index="3"/>
|
|
|
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 It contains variant annotations such as:
|
|
|
77
|
|
|
78
|
|
|
79 1000Gp1_AC
|
|
|
80 Alternative allele counts in the whole 1000 genomes phase 1 (1000Gp1) data
|
|
|
81 1000Gp1_AF
|
|
|
82 Alternative allele frequency in the whole 1000Gp1 data
|
|
|
83 1000Gp1_AFR_AC
|
|
|
84 Alternative allele counts in the 1000Gp1 African descendent samples
|
|
|
85 1000Gp1_AFR_AF
|
|
|
86 Alternative allele frequency in the 1000Gp1 African descendent samples
|
|
|
87 1000Gp1_AMR_AC
|
|
|
88 Alternative allele counts in the 1000Gp1 American descendent samples
|
|
|
89 1000Gp1_AMR_AF
|
|
|
90 Alternative allele frequency in the 1000Gp1 American descendent samples
|
|
|
91 1000Gp1_ASN_AC
|
|
|
92 Alternative allele counts in the 1000Gp1 Asian descendent samples
|
|
|
93 1000Gp1_ASN_AF
|
|
|
94 Alternative allele frequency in the 1000Gp1 Asian descendent samples
|
|
|
95 1000Gp1_EUR_AC
|
|
|
96 Alternative allele counts in the 1000Gp1 European descendent samples
|
|
|
97 1000Gp1_EUR_AF
|
|
|
98 Alternative allele frequency in the 1000Gp1 European descendent samples
|
|
|
99 aaalt
|
|
|
100 Alternative amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
101 aapos
|
|
|
102 Amino acid position as to the protein. "-1" if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
103 aapos_SIFT
|
|
|
104 ENSP id and amino acid positions corresponding to SIFT scores. Multiple entries separated by ";"
|
|
|
105 aapos_FATHMM
|
|
|
106 ENSP id and amino acid positions corresponding to FATHMM scores. Multiple entries separated by ";"
|
|
|
107 aaref
|
|
|
108 Reference amino acid. "." if the variant is a splicing site SNP (2bp on each end of an intron)
|
|
|
109 alt
|
|
|
110 Alternative nucleotide allele (as on the + strand)
|
|
|
111 Ancestral_allele
|
|
|
112 Ancestral allele (based on 1000 genomes reference data)
|
|
|
113 cds_strand
|
|
|
114 Coding sequence (CDS) strand (+ or -)
|
|
|
115 chr
|
|
|
116 Chromosome number
|
|
|
117 codonpos
|
|
|
118 Position on the codon (1, 2 or 3)
|
|
|
119 Ensembl_geneid
|
|
|
120 Ensembl gene ID
|
|
|
121 Ensembl_transcriptid
|
|
|
122 Ensembl transcript IDs (separated by ";")
|
|
|
123 ESP6500_AA_AF
|
|
|
124 Alternative allele frequency in the African American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set)
|
|
|
125 ESP6500_EA_AF
|
|
|
126 Alternative allele frequency in the European American samples of the NHLBI GO Exome Sequencing Project (ESP6500 data set)
|
|
|
127 FATHMM_pred
|
|
|
128 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 ";"
|
|
|
129 FATHMM_rankscore
|
|
|
130 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
|
|
|
131 FATHMM_score
|
|
|
132 FATHMM default score (FATHMMori)
|
|
|
133 fold-degenerate
|
|
|
134 Degenerate type (0, 2 or 3)
|
|
|
135 genename
|
|
|
136 Gene name; if the non-synonymous SNP can be assigned to multiple genes, gene names are separated by ";"
|
|
|
137 GERP++_NR
|
|
|
138 GERP++ neutral rate
|
|
|
139 GERP++_RS
|
|
|
140 GERP++ RS score, the larger the score, the more conserved the site
|
|
|
141 GERP++_RS_rankscore
|
|
|
142 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
|
|
|
143 hg18_pos(1-coor)
|
|
|
144 Physical position on the chromosome as to hg18 (1-based coordinate)
|
|
|
145 Interpro_domain
|
|
|
146 Domain or conserved site on which the variant locates
|
|
|
147 LR_pred
|
|
|
148 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
|
|
|
149 LR_rankscore
|
|
|
150 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
|
|
|
151 LR_score
|
|
|
152 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
|
|
|
153 LRT_Omega
|
|
|
154 Estimated nonsynonymous-to-synonymous-rate ratio (Omega, reported by LRT)
|
|
|
155 LRT_converted_rankscore
|
|
|
156 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
|
|
|
157 LRT_pred
|
|
|
158 LRT prediction, D(eleterious), N(eutral) or U(nknown), which is not solely determined by the score
|
|
|
159 LRT_score
|
|
|
160 The original LRT two-sided p-value (LRTori), ranges from 0 to 1
|
|
|
161 MutationAssessor_pred
|
|
|
162 MutationAssessor's functional impact of a variant
|
|
|
163 MutationAssessor_rankscore
|
|
|
164 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
|
|
|
165 MutationAssessor_score
|
|
|
166 MutationAssessor functional impact combined score (MAori)
|
|
|
167 MutationTaster_converted_rankscore
|
|
|
168 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
|
|
|
169 MutationTaster_pred
|
|
|
170 MutationTaster prediction
|
|
|
171 MutationTaster_score
|
|
|
172 MutationTaster p-value (MTori), ranges from 0 to 1
|
|
|
173 phastCons46way_placental
|
|
|
174 phastCons conservation score based on the multiple alignments of 33 placental mammal genomes (including human). The larger the score, the more conserved the site
|
|
|
175 phastCons46way_placental_rankscore
|
|
|
176 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
|
|
|
177 phastCons46way_primate
|
|
|
178 phastCons conservation score based on the multiple alignments of 10 primate genomes (including human). The larger the score, the more conserved the site
|
|
|
179 phastCons46way_primate_rankscore
|
|
|
180 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
|
|
|
181 phastCons100way_vertebrate
|
|
|
182 phastCons conservation score based on the multiple alignments of 100 vertebrate genomes (including human). The larger the score, the more conserved the site
|
|
|
183 phastCons100way_vertebrate_rankscore
|
|
|
184 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
|
|
|
185 phyloP46way_placental
|
|
|
186 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
|
|
|
187 phyloP46way_placental_rankscore
|
|
|
188 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
|
|
|
189 phyloP46way_primate
|
|
|
190 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
|
|
|
191 phyloP46way_primate_rankscore
|
|
|
192 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
|
|
|
193 phyloP100way_vertebrate
|
|
|
194 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
|
|
|
195 phyloP100way_vertebrate_rankscore
|
|
|
196 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
|
|
|
197 Polyphen2_HDIV_pred
|
|
|
198 Polyphen2 prediction based on HumDiv
|
|
|
199 Polyphen2_HDIV_rankscore
|
|
|
200 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
|
|
|
201 Polyphen2_HDIV_score
|
|
|
202 Polyphen2 score based on HumDiv, i.e. hdiv_prob. The score ranges from 0 to 1. Multiple entries separated by ";"
|
|
|
203 Polyphen2_HVAR_pred
|
|
|
204 Polyphen2 prediction based on HumVar
|
|
|
205 Polyphen2_HVAR_rankscore
|
|
|
206 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
|
|
|
207 Polyphen2_HVAR_score
|
|
|
208 Polyphen2 score based on HumVar, i.e. hvar_prob. The score ranges from 0 to 1. Multiple entries separated by ";"
|
|
|
209 pos(1-coor)
|
|
|
210 Physical position on the chromosome as to hg19 (1-based coordinate)
|
|
|
211 RadialSVM_pred
|
|
|
212 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
|
|
|
213 RadialSVM_rankscore
|
|
|
214 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
|
|
|
215 RadialSVM_score
|
|
|
216 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
|
|
|
217 ref
|
|
|
218 Reference nucleotide allele (as on the + strand)
|
|
|
219 refcodon
|
|
|
220 Reference codon
|
|
|
221 Reliability_index
|
|
|
222 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
|
|
|
223 SIFT_converted_rankscore
|
|
|
224 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
|
|
|
225 SIFT_pred
|
|
|
226 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 ";"
|
|
|
227 SIFT_score
|
|
|
228 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 ";"
|
|
|
229 SiPhy_29way_logOdds
|
|
|
230 SiPhy score based on 29 mammals genomes. The larger the score, the more conserved the site
|
|
|
231 SiPhy_29way_pi
|
|
|
232 The estimated stationary distribution of A, C, G and T at the site, using SiPhy algorithm based on 29 mammals genomes
|
|
|
233 SLR_test_statistic
|
|
|
234 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
|
|
|
235 Uniprot_aapos
|
|
|
236 Amino acid position as to Uniprot. Multiple entries separated by ";"
|
|
|
237 Uniprot_acc
|
|
|
238 Uniprot accession number. Multiple entries separated by ";"
|
|
|
239 Uniprot_id
|
|
|
240 Uniprot ID number. Multiple entries separated by ";"
|
|
|
241 UniSNP_ids
|
|
|
242 rs numbers from UniSNP, which is a cleaned version of dbSNP build 129, in format: rs number1;rs number2;...
|
|
|
243
|
|
|
244
|
|
|
245
|
|
|
246 The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp is in the SnpSift documentation:
|
|
|
247 http://snpeff.sourceforge.net/SnpSift.html#dbNSFP
|
|
|
248
|
|
|
249 A couple dbNSFP databases are prebuilt for SnpSift at:
|
|
|
250 http://sourceforge.net/projects/snpeff/files/databases/dbNSFP/
|
|
|
251
|
|
|
252
|
|
|
253
|
|
|
254
|
|
|
255 **Uploading Your Own Annotations for any Genome**
|
|
|
256
|
|
|
257 The website for dbNSFP databases releases is:
|
|
|
258 https://sites.google.com/site/jpopgen/dbNSFP
|
|
|
259
|
|
|
260 But there is only annotation for human hg18, hg19, and hg38 genome builds.
|
|
|
261
|
|
|
262 However, any dbNSFP-like tabular file that be can used with SnpSift dbnsfp if it has:
|
|
|
263
|
|
|
264 - The first line of the file must be column headers that name the annotations.
|
|
|
265 - The first 4 columns are required and must be:
|
|
|
266
|
|
|
267 1. #chr - chromosome
|
|
|
268 2. pos(1-coor) - position in chromosome
|
|
|
269 3. ref - reference base
|
|
|
270 4. alt - alternate base
|
|
|
271
|
|
|
272
|
|
|
273 For example:
|
|
|
274
|
|
|
275 ::
|
|
|
276
|
|
|
277 #chr pos(1-coor) ref alt aaref aaalt genename SIFT_score
|
|
|
278 4 100239319 T A H L ADH1B 0
|
|
|
279 4 100239319 T C H R ADH1B 0.15
|
|
|
280 4 100239319 T G H P ADH1B 0
|
|
|
281
|
|
|
282
|
|
|
283 The custom galaxy datatypes for dbNSFP can automatically convert the specially formatted tabular file for use by SnpSift dbNSFP:
|
|
|
284 1. Upload the tabular file, set the datatype as: **"dbnsfp.tabular"**
|
|
|
285 2. Edit the history dataset attributes (pencil icon): Use "Convert Format" to convert the **"dbnsfp.tabular"** to the correct format for SnpSift dbnsfp: **"snpsiftdbnsfp"**.
|
|
|
286
|
|
|
287 The procedure for preparing the dbNSFP data for use in SnpSift dbnsfp is in the SnpSift documentation.
|
|
|
288
|
|
|
289
|
|
|
290 @EXTERNAL_DOCUMENTATION@
|
|
|
291 http://snpeff.sourceforge.net/SnpSift.html#dbNSFP
|
|
|
292
|
|
|
293 @CITATION_SECTION@
|
|
|
294
|
|
|
295
|
|
|
296 </help>
|
|
|
297 </tool>
|
