Mercurial > repos > iuc > prodigal
view prodigal.xml @ 0:91791b6ecd38 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/prodigal commit fc5c69375318ffee0a71a69378d51c97003427b6
| author | iuc |
|---|---|
| date | Thu, 14 Mar 2024 16:49:04 +0000 |
| parents | |
| children |
line wrap: on
line source
<tool id="prodigal" name="Prodigal Gene Predictor" version="@VERSION@+galaxy0" profile="22.05"> <description>A tool for gene prediction in microbial genomes</description> <macros> <token name="@VERSION@">2.6.3</token> </macros> <xrefs> <xref type="bio.tools">prodigal</xref> </xrefs> <requirements> <requirement type="package" version="@VERSION@">prodigal</requirement> </requirements> <command detect_errors="exit_code"><![CDATA[ prodigal -i '$input_fa' #if $input_train -t '$input_train' #end if -o '$output' -f '$out_format' -p '$procedure' -g '$trans_table' -a '$output_faa' -d '$output_fnn' -s '$output_start' $closed $force_nonsd $masked_seq ]]></command> <inputs> <param type="data" name="input_fa" format="fasta" label="Specify input file" help="-i" /> <param type="data" name="input_train" format="fasta" label="Specify training file" optional="true" help="Read and use the specified training file (-t)" /> <param type="select" name="out_format" label="Specify output format" help="-f" > <option value="gbk" selected="true">GBK (default)</option> <option value="gff">GFF</option> <option value="sqn">SQN</option> <option value="sco">SCO</option> </param> <param type="select" name="procedure" label="Specify mode" help="-p" > <option value="single" selected="true">Single : Single genome, any number of sequences (default)</option> <option value="meta">Meta : Anonymous sequences, analyze using preset training files, ideal for metagenomic data or single short sequences</option> </param> <param type="select" name="trans_table" label="Specify a translation table to use" help="-g" > <option value="11">11 : Standard Bacteria/Archaea (default)</option> <option value="4">4 : Mycoplasma/Spiroplasma</option> <option value="#"># : Other genetic codes 1-25</option> </param> <param name="closed" type="boolean" label="Closed ends" truevalue="-c" falsevalue="" optional="true" help="Closed ends. Do not allow partial genes at edges of sequence (-c)" /> <param name="force_nonsd" type="boolean" label="Force Prodigal to scan for motifs" truevalue="-n" falsevalue="" optional="true" help="Do not use the Shine-Dalgarno RBS finder and instead force Prodigal to scan for motifs (-n)" /> <param name="masked_seq" type="boolean" label="Treat runs of N as masked sequence" truevalue="-m" falsevalue="" optional="true" help="Treat runs of N as masked sequence; don't build genes across them (-m)" /> </inputs> <outputs> <data name="output" format="genbank" label="${tool.name} on ${on_string} : coordinates"> <change_format> <when input="out_format" value="gff" format="gff3" /> <when input="out_format" value="sqn" format="asn1" /> <when input="out_format" value="sco" format="genbank" /> </change_format> </data> <data name="output_faa" format="fasta" label="${tool.name} on ${on_string} : protein translations file" /> <data name="output_fnn" format="fasta" label="${tool.name} on ${on_string} : nucleotide sequences file" /> <data name="output_start" format="tabular" label="${tool.name} on ${on_string} : complete starts file" /> </outputs> <tests> <test> <param name="input_fa" value="input.fna"/> <output name="output" file="output"/> </test> <test> <param name="input_fa" value="input.fna"/> <output name="output" file="output" ftype="genbank"/> <output name="output_faa" file="output.faa"/> <output name="output_fnn" file="output.fnn"/> <output name="output_start" file="output.start"/> </test> <test> <param name="input_fa" value="input.fna"/> <param name="out_format" value="gff"/> <output name="output" file="output.gff" ftype="gff3" /> <output name="output_faa" file="output.faa"/> <output name="output_fnn" file="output.fnn"/> <output name="output_start" file="output.start"/> </test> <test> <param name="input_fa" value="input.fna"/> <param name="trans_table" value="4"/> <output name="output" file="output_tt" ftype="genbank"/> <output name="output_faa" file="output_tt.faa"/> <output name="output_fnn" file="output_tt.fnn"/> <output name="output_start" file="output_tt.start"/> </test> <test> <param name="input_fa" value="input.fna"/> <param name="procedure" value="single"/> <param name="closed" value="true"/> <param name="force_nonsd" value="true"/> <param name="masked_seq" value="true"/> <output name="output" file="output_c_n_m" ftype="genbank"/> <output name="output_faa" file="output_c_n_m.faa"/> <output name="output_fnn" file="output_c_n_m.fnn"/> <output name="output_start" file="output_c_n_m.start"/> </test> <test> <param name="input_fa" value="input.fna"/> <param name="input_train" value="train_file.trn"/> <output name="output" file="output_train" ftype="genbank"/> <output name="output_faa" file="output_train.faa"/> <output name="output_fnn" file="output_train.fnn"/> <output name="output_start" file="output_train.start"/> </test> </tests> <help><![CDATA[ Fast, reliable protein-coding gene prediction for prokaryotic genomes. Features: * Predicts protein-coding genes: Prodigal provides fast, accurate protein-coding gene predictions in GFF3, Genbank, or Sequin table format. * Handles draft genomes and metagenomes: Prodigal runs smoothly on finished genomes, draft genomes, and metagenomes. * Runs quickly: Prodigal analyzes the E. coli K-12 genome in 10 seconds on a modern MacBook Pro. * Runs unsupervised: Prodigal is an unsupervised machine learning algorithm. It does not need to be provided with any training data, and instead automatically learns the properties of the genome from the sequence itself, including RBS motif usage, start codon usage, and coding statistics. * Handles gaps and partial genes: The user can specify if Prodigal should build genes across runs of N's as well as how to handle genes at the edges of contigs. * Identifies translation initiation sites: Prodigal predicts the correct translation initiation site for most genes, and can output information about every potential start site in the genome, including confidence score, RBS motif, and much more. ]]></help> <citations> <citation type="doi">10.1186/1471-2105-11-119</citation> </citations> </tool>
