|
0
|
1 <?xml version="1.0"?>
|
|
|
2 <tool id="snpeff_to_peptides" name="SnpEff to Peptide fasta" version="0.0.1">
|
|
|
3 <description> to create a Search DB fasta for variant SAP peptides</description>
|
|
|
4 <command interpreter="python">snpeff_to_peptides.py --input "$snpeff_vcf" --protein_fasta "$all_pep_fasta" --output "$peptide_variant_fasta"
|
|
|
5 #if $leading_aa_num:
|
|
|
6 --leading_aa_num $leading_aa_num
|
|
|
7 #end if
|
|
|
8 #if $trailing_aa_num:
|
|
|
9 --trailing_aa_num $trailing_aa_num
|
|
|
10 #end if
|
|
|
11 </command>
|
|
|
12 <inputs>
|
|
|
13 <param name="snpeff_vcf" type="data" format="vcf" label="SnpEff generated VCF file with NON_SYNONYMOUS_CODING annotations"/>
|
|
|
14 <param name="all_pep_fasta" type="data" format="fasta,tabular" label="Ensembl all_pep.fa"
|
|
|
15 help="An Ensembl all_pep.fa file corresponding to the genome build used for SnpEff (May be converted to tabular fasta format)"/>
|
|
|
16 <param name="leading_aa_num" type="integer" value="30" min="0" optional="true" label="Preceeding AAs"
|
|
|
17 help="The number of Amino Acids to include before the variant position (leave blank to include all)"/>
|
|
|
18 <param name="trailing_aa_num" type="integer" value="30" min="0" optional="true" label="Following AAs"
|
|
|
19 help="The number of Amino Acids to include after the variant position (leave blank to include all)"/>
|
|
|
20 </inputs>
|
|
|
21 <stdio>
|
|
|
22 <exit_code range="1:" level="fatal" description="Error" />
|
|
|
23 </stdio>
|
|
|
24 <outputs>
|
|
|
25 <data name="peptide_variant_fasta" metadata_source="all_pep_fasta" format="fasta"/>
|
|
|
26 </outputs>
|
|
|
27 <tests>
|
|
|
28 <test>
|
|
|
29 <param name="snpeff_vcf" value="snpeff.vcf" ftype="vcf" dbkey="hg19"/>
|
|
|
30 <param name="all_pep_fasta" value="all_pep.fa" ftype="fasta" dbkey="hg19"/>
|
|
|
31 <param name="leading_aa_num" value="10"/>
|
|
|
32 <param name="trailing_aa_num" value="10"/>
|
|
|
33 <output name="peptide_variant_fasta" file="peptides_10_10.fa"/>
|
|
|
34 </test>
|
|
|
35 <test>
|
|
|
36 <param name="snpeff_vcf" value="snpeff.vcf" ftype="vcf" dbkey="hg19"/>
|
|
|
37 <param name="all_pep_fasta" value="all_pep.tabular" ftype="tabular" dbkey="hg19"/>
|
|
|
38 <param name="leading_aa_num" value="10"/>
|
|
|
39 <param name="trailing_aa_num" value="10"/>
|
|
|
40 <output name="peptide_variant_fasta" file="peptides_10_10.fa"/>
|
|
|
41 </test>
|
|
|
42 </tests>
|
|
|
43 <help>
|
|
|
44 **SnpEff to Peptide Fasta**
|
|
|
45
|
|
|
46 This generates a fasta file of peptide sequences with SAPs ( Single Amino acid Polymorphisms )
|
|
|
47 from the NON_SYNONYMOUS_CODING EFF annnotations from the SnpEff_ application.
|
|
|
48 The SnpEff VCF may be filtered or annotated using SnpSift.
|
|
|
49
|
|
|
50 The following is appended to the fasta ID line: snp_location:chr:position codon_change:nnn/nnn sap:AposA
|
|
|
51
|
|
|
52 For VCF entry::
|
|
|
53
|
|
|
54 chr1 22846709 . G A 9.31 . DP=2;VDB=0.0174;AF1=1;AC1=2;DP4=0,0,1,1;MQ=20;FQ=-33;EFF=NON_SYNONYMOUS_CODING(MODERATE|MISSENSE|Gtg/Atg|V885M|1127|ZBTB40|protein_coding|CODING|ENST00000374651|12|1) PL 40,6,0
|
|
|
55
|
|
|
56 The peptide fasta entry that matches transcript ID: ENST00000374651 would be::
|
|
|
57
|
|
|
58 >ENSP00000363782 pep:known chromosome:GRCh37:1:22778472:22853855:1 gene:ENSG00000184677 transcript:ENST00000374651 gene_biotype:protein_coding transcript_biotype:protein_coding
|
|
|
59
|
|
|
60 The ID of the output peptide fasta ID would be::
|
|
|
61
|
|
|
62 >ENSP00000363782 pep:sap chromosome:GRCh37:1:22778472:22853855:1 gene:ENSG00000184677 transcript:ENST00000374651 gene_biotype:protein_coding transcript_biotype:protein_coding snp_location:chr1:22846709 codon_change:Gtg/Atg sap:V885M
|
|
|
63
|
|
|
64
|
|
|
65 .. _SnpEff: http://snpeff.sourceforge.net/index.html
|
|
|
66
|
|
|
67 **Citation**
|
|
|
68
|
|
|
69 SnpEff citation:
|
|
|
70 "A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process]
|
|
|
71
|
|
|
72 SnpSift citation:
|
|
|
73 "Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3, 2012.
|
|
|
74
|
|
|
75 </help>
|
|
|
76 </tool>
|
