Mercurial > repos > galaxyp > peptide_to_gff
annotate peptide_to_gff.xml @ 2:4c87b4cc1176
Add simple label to output files for IGV display application (it does not handle punctuation in URLs)
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Mon, 15 Jun 2015 15:22:59 -0500 |
| parents | 0cd177bc347d |
| children | 42c89c1bbda9 |
| rev | line source |
|---|---|
| 0 | 1 <tool id="peptide_to_gff" name="Peptide to GFF" version="1.0"> |
| 2 <description>Map peptide to reference genome</description> | |
| 3 <requirements> | |
| 1 | 4 <requirement type="package" version="35x1">blat</requirement> |
| 5 <requirement type="package" version="1.61">biopython</requirement> | |
| 6 <requirement type="package" version="0.1">bcbb_gff</requirement> | |
| 7 <requirement type="package" version="0.1">peptide_to_gff</requirement> | |
| 0 | 8 </requirements> |
| 9 <command>peptide_to_gff | |
| 10 #if $peptide_src.inputFormat == 'protein_pilot' or $peptide_src.inputFormat == 'tabular': | |
| 11 --skip_lines $peptide_src.input_file.metadata.comment_lines | |
| 12 --input $peptide_src.input_file | |
| 13 --peptide_column $peptide_src.peptide_col | |
| 14 --accession_column $peptide_src.accession_col | |
| 15 #end if | |
| 16 #for $ref in $ref_mappings: | |
| 17 #if $ref.mapping.ref_selector =='cdna_gtf': | |
| 18 --cdna_fasta $ref.mapping.seqs | |
| 19 --cdna_gtf $ref.mapping.feature_ref | |
| 20 #elif $ref.mapping.ref_selector =='cdna_ref': | |
| 21 --cdna_fasta $ref.mapping.seqs | |
| 22 #if $ref.mapping.genome.ref_src == 'indexed': | |
| 23 --reference $ref.mapping.genome.reference.fields.path | |
| 24 #else : | |
| 25 --reference $ref.mapping.genome.reference | |
| 26 #end if | |
| 27 #elif $ref.mapping.ref_selector =='cds_gff': | |
| 28 --cds_fasta $ref.mapping.seqs | |
| 29 --cds_gff $ref.mapping.feature_ref | |
| 30 #elif $ref.mapping.ref_selector =='eej': | |
| 31 --cdna_gtf $ref.mapping.feature_ref | |
| 32 #end if | |
| 33 #end for | |
| 34 #if $show_unmapped: | |
| 35 --unmapped $unmapped | |
| 36 #end if | |
| 37 --output $output_gff | |
| 38 </command> | |
| 39 <inputs> | |
| 40 <conditional name="peptide_src" > | |
| 41 <param name="inputFormat" type="select" label="Peptide Source Format"> | |
| 42 <option value="protein_pilot">Protein Pilot Tabular</option> | |
| 43 <option value="tabular">Generic Tabular (with peptide and accession columns)</option> | |
| 44 <!-- future formats --> | |
| 45 </param> | |
| 46 <when value="protein_pilot"> | |
| 47 <param name="input_file" type="data" format="tabular" label="Source File" | |
| 48 help="A tabular file that contains a peptide in a column and a accession name in another column."/> | |
| 49 <param name="peptide_col" type="hidden" value="13" label="Peptide Column"/> | |
| 50 <param name="accession_col" type="hidden" value="7" label="Accession Identifier Column"/> | |
| 51 <!-- | |
| 52 <param name="info_cols" type="data_column" data_ref="input_file" label="Columns to include in the GTF INFO" multiple="true" optional="true"/> | |
| 53 --> | |
| 54 </when> | |
| 55 <when value="tabular"> | |
| 56 <param name="input_file" type="data" format="tabular" label="Source File" | |
| 57 help="A tabular file that contains a peptide in a column and a accession name in another column."/> | |
| 58 <param name="peptide_col" type="data_column" data_ref="input_file" label="Peptide Column"/> | |
| 59 <param name="accession_col" type="data_column" data_ref="input_file" label="Accession Identifier Column"/> | |
| 60 <!-- | |
| 61 <param name="info_cols" type="data_column" data_ref="input_file" label="Columns to include in the GTF INFO" multiple="true" optional="true"/> | |
| 62 --> | |
| 63 </when> | |
| 64 </conditional> | |
| 65 <repeat name="ref_mappings" title="Sequence and Feature References for mapping the peptides" min="1" help="" > | |
| 66 <conditional name="mapping" > | |
| 67 <param name="ref_selector" type="select" label="Select Peptide Mapping File Formats"> | |
| 68 <option value="cdna_gtf">cdna sequence with GTF feature reference (Ensembl)</option> | |
| 69 <option value="cdna_ref">cdna sequence with genome sequence reference (ECgene)</option> | |
| 70 <option value="cds_gff">protein sequence with GFF feature reference (Augustus)</option> | |
| 71 <!-- Eventually may want to include putative exon-exon junctions | |
| 72 <option value="eej">putative exon exon junctions</option> | |
| 73 --> | |
| 74 </param> | |
| 75 <when value="cdna_gtf"> | |
| 76 <param name="seqs" type="data" format="fasta" label="CDNA Transcripts Fasta" | |
| 77 help="Example: ftp://ftp.ensembl.org/pub/release-71/fasta/homo_saPiens/cdna/Homo_sapiens.GRCh37.71.cdna.all.fa.gz"/> | |
| 78 <param name="feature_ref" type="data" format="gtf" label=" GTF feature file for the cdna transcipts" | |
| 79 help="Example: ftp://ftp.ensembl.org/pub/release-71/gtf/homo_sapiens/Homo_sapiens.GRCh37.71.gtf.gz"/> | |
| 80 </when> | |
| 81 <when value="cdna_ref"> | |
| 82 <param name="seqs" type="data" format="fasta" label="CDNA Transcripts Fasta" | |
| 83 help="Example: http://genome.ewha.ac.kr/ECgene/download/hg18/hg18_b1_low_fasta.txt.gz"/> | |
| 84 <conditional name="genome"> | |
| 85 <param name="ref_src" type="select" label="Reference Genome Source for mapping"> | |
| 86 <option value="indexed">Use a built-in index</option> | |
| 87 <option value="history">Use one in your history </option> | |
| 88 </param> | |
| 89 <when value="indexed"> | |
| 90 <param name="reference" type="select" label="Genome Reference"> | |
| 91 <options from_data_table="all_fasta"> | |
| 92 </options> | |
| 93 </param> | |
| 94 </when> | |
| 95 <when value="history"> | |
| 96 <param name="reference" type="data" format="fasta" label="Reference Genome Fasta"/> | |
| 97 </when> | |
| 98 </conditional> | |
| 99 </when> | |
| 100 <when value="cds_gff"> | |
| 101 <param name="seqs" type="data" format="fasta" label="Protein Sequence Fasta" | |
| 102 help="Example: http://gbi.agrsci.dk/pig/sscrofa10_2_annotation/ssc10.2.RNA.hints.augustus.gff.prot.faa.gz"/> | |
| 103 <param name="feature_ref" type="data" format="gff3,gtf" label="GFF Feature file for the Protein Sequences" | |
| 104 help="Example: http://gbi.agrsci.dk/pig/sscrofa10_2_annotation/ssc10.2.RNA.hints.augustus.gff.gz"/> | |
| 105 </when> | |
| 106 <!-- Eventually may want to include putative exon-exon junctions | |
| 107 <when value="eej"> | |
| 108 <param name="feature_ref" type="data" format="gtf" label=" The Ensembl GTF feature file corresponding to the EEJ build" | |
| 109 help="Example: ftp://ftp.ensembl.org/pub/release-71/gtf/homo_sapiens/Homo_sapiens.GRCh37.71.gtf.gz"/> | |
| 110 </when> | |
| 111 --> | |
| 112 </conditional> | |
| 113 </repeat> | |
| 114 <param name="show_unmapped" type="boolean" truevalue="yes" falsevalue="no" checked="False" label="Show unmapped lines"/> | |
| 115 </inputs> | |
| 116 <outputs> | |
|
2
4c87b4cc1176
Add simple label to output files for IGV display application (it does not handle punctuation in URLs)
Jim Johnson <jj@umn.edu>
parents:
1
diff
changeset
|
117 <data format="gff3" metadata_source="input_file" name="output_gff" label="peptides.gff3"/> |
|
4c87b4cc1176
Add simple label to output files for IGV display application (it does not handle punctuation in URLs)
Jim Johnson <jj@umn.edu>
parents:
1
diff
changeset
|
118 <data format_source="input_file" metadata_source="input_file" name="unmapped" label="peptides.unmapped"> |
| 0 | 119 <filter>show_unmapped == True</filter> |
| 120 </data> | |
| 121 </outputs> | |
| 122 <stdio> | |
| 123 <exit_code range="1:" level="fatal" description="Bad input dataset" /> | |
| 124 </stdio> | |
| 125 <tests> | |
| 126 <test> | |
| 127 <param name="inputFormat" value="protein_pilot"/> | |
| 128 <param name="input_file" value="ProtData.tsv" ftype="tabular"/> | |
| 129 <!-- | |
| 130 <param name="info_cols" value=""/> | |
| 131 --> | |
| 132 <param name="ref_selector" value="cdna_gtf"/> | |
| 133 <param name="seqs" value="GRCh37.69.cdna.19.fa" ftype="fasta"/> | |
| 134 <param name="feature_ref" value="Homo_sapiens.GRCh37_19.71.gtf" ftype="gtf"/> | |
| 135 <param name="show_unmapped" value="False"/> | |
| 136 <output name="output_gff" file="ProtData.gff3" ftype="gff3"/> | |
| 137 </test> | |
| 138 <!-- These values work when entered into a history, but aren't handled correctly by the function test environment. | |
| 139 <test> | |
| 140 <param name="inputFormat" value="protein_pilot"/> | |
| 141 <param name="input_file" value="ProtData.tsv" ftype="tabular"/> | |
| 142 <param name="ref_selector" value="cdna_ref"/> | |
| 143 <param name="seqs" value="GRCh37.69.cdna.19.fa" ftype="fasta"/> | |
| 144 <param name="ref_src" value="history"/> | |
| 145 <param name="reference" value="Homo_sapiens.GRCh37.71.dna.chromosome.19.fa" ftype="fasta"/> | |
| 146 <param name="show_unmapped" value="False"/> | |
| 147 <output name="output_gff" file="ProtData.gff3" ftype="gff3"/> | |
| 148 </test> | |
| 149 --> | |
| 150 | |
| 151 </tests> | |
| 152 <help> | |
| 153 **Peptide to GFF** | |
| 154 | |
| 155 Maps peptide sequences that have a known transcript or protein-coding sequence to a reference genome. | |
| 156 | |
| 157 Inputs: | |
| 158 | |
| 159 - A tabular file that contains a peptide column and a sequence accession column. | |
| 160 | |
| 161 - One or more fasta files of transcript or protein sequences that match the accession column entries | |
| 162 | |
| 163 - Either GTF, GFF, or a genome reference fasta for mapping the accession sequences to the genome. | |
| 164 | |
| 165 Output: | |
| 166 | |
| 167 - A GFF3 file with that gives the mapping of the peptide to the reference genome | |
| 168 | |
| 169 - Optionally, a dataset with the unmapped lines from the input file. | |
| 170 | |
| 171 </help> | |
| 172 </tool> | |
| 173 |