Mercurial > repos > cpt > cpt_get_orfs
diff cpt_get_orfs/get_orfs_or_cdss.xml @ 0:daab1b0e68c1 draft
Uploaded
| author | cpt |
|---|---|
| date | Fri, 13 May 2022 04:52:44 +0000 |
| parents | |
| children | 77da06bc38f5 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_get_orfs/get_orfs_or_cdss.xml Fri May 13 04:52:44 2022 +0000 @@ -0,0 +1,153 @@ +<tool id="get_orfs_or_cdss" name="Get open reading frames (ORFs) or coding sequences (CDSs)" version="19.1.0.0"> + <description>e.g. to get peptides from ESTs</description> + <macros> + <import>macros.xml</import> + <import>cpt-macros.xml</import> + </macros> + <expand macro="requirements"> + <requirement type="package" version="2019.06.08">regex</requirement> + </expand> + <command interpreter="python" detect_errors="aggressive"> +get_orfs_or_cdss.py $input_file -f $input_file.ext --table $table -t $ftype -e "closed" -m "all" --min_len $min_len --strand $strand --on $out_nuc_file --op $out_prot_file --ob $out_bed_file --og $out_gff3_file + </command> + <inputs> + <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file (nucleotides)" help="FASTA, FASTQ, or SFF format." /> + <param name="table" type="select" label="Genetic code" help="Tables from the NCBI, these determine the start and stop codons"> + <option value="1">1. Standard</option> + <option value="2">2. Vertebrate Mitochondrial</option> + <option value="3">3. Yeast Mitochondrial</option> + <option value="4">4. Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option> + <option value="5">5. Invertebrate Mitochondrial</option> + <option value="6">6. Ciliate Macronuclear and Dasycladacean</option> + <option value="9">9. Echinoderm Mitochondrial</option> + <option value="10">10. Euplotid Nuclear</option> + <option value="11">11. Bacterial</option> + <option value="12">12. Alternative Yeast Nuclear</option> + <option value="13">13. Ascidian Mitochondrial</option> + <option value="14">14. Flatworm Mitochondrial</option> + <option value="15">15. Blepharisma Macronuclear</option> + <option value="16">16. Chlorophycean Mitochondrial</option> + <option value="21">21. Trematode Mitochondrial</option> + <option value="22">22. Scenedesmus obliquus</option> + <option value="23">23. Thraustochytrium Mitochondrial</option> + <option value="24">24. Pterobranchia Mitochondrial</option> + </param> + <param name="ftype" type="select" value="True" label="Look for ORFs or CDSs"> + <option value="ORF">Look for ORFs (check for stop codons only, ignore start codons)</option> + <option value="CDS">Look for CDSs (with start and stop codons)</option> + </param> + <param name="min_len" type="integer" size="5" value="30" label="Minimum length ORF/CDS (in amino acids, e.g. 30 aa = 90 bp plus any stop codon)" /> + <param name="strand" type="select" label="Strand to search" help="Use the forward only option if your sequence directionality is known (e.g. from poly-A tails, or strand specific RNA sequencing)."> + <option value="both">Search both the forward and reverse strand</option> + <option value="forward">Only search the forward strand</option> + <option value="reverse">Only search the reverse strand</option> + </param> + </inputs> + <outputs> + <data name="out_nuc_file" format="fasta" label="${ftype.value}s (nucleotides)" /> + <data name="out_prot_file" format="fasta" label="${ftype.value}s (amino acids)" /> + <data name="out_bed_file" format="bed6" label="${ftype.value}s (bed)" /> + <data name="out_gff3_file" format="gff3" label="${ftype.value}s (gff3)" /> + </outputs> + <tests> + <test> + <param name="input_file" value="Orf_T7In.fasta" /> + <param name="table" value="11" /> + <param name="ftype" value="ORF" /> + <param name="min_len" value="30" /> + <param name="strand" value="both" /> + <output name="out_nuc_file" file="Orf_T7Out_Nuc.fasta" /> + <output name="out_prot_file" file="Orf_T7Out_AA.fasta" /> + <output name="out_bed_file" file="Orf_T7Out_Bed.bed" /> + <output name="out_gff3_file" file="Orf_T7Out_Gff.gff3" /> + </test> + <test> + <param name="input_file" value="Orf_In2.fasta" /> + <param name="table" value="1" /> + <param name="ftype" value="CDS" /> + <param name="min_len" value="10" /> + <param name="strand" value="forward" /> + <output name="out_nuc_file" file="Orf_Out2T1_Nuc.fasta" /> + <output name="out_prot_file" file="Orf_Out2T1_AA.fasta" /> + <output name="out_bed_file" file="Orf_Out2T1_Bed.bed" /> + <output name="out_gff3_file" file="Orf_Out2T1_Gff.gff3" /> + </test> + <test> + <param name="input_file" value="Orf_In2.fasta" /> + <param name="table" value="11" /> + <param name="ftype" value="CDS" /> + <param name="min_len" value="10" /> + <param name="strand" value="forward" /> + <output name="out_nuc_file" file="Orf_Out2T11_Nuc.fasta" /> + <output name="out_prot_file" file="Orf_Out2T11_AA.fasta" /> + <output name="out_bed_file" file="Orf_Out2T11_Bed.bed" /> + <output name="out_gff3_file" file="Orf_Out2T11_Gff.gff3" /> </test> + </tests> + <help> +**What it does** + +Takes an input file of nucleotide sequences (typically FASTA, but also FASTQ +and Standard Flowgram Format (SFF) are supported), and searches each sequence +for open reading frames (ORFs) or potential coding sequences (CDSs) of the +given minimum length. These are returned as FASTA files of nucleotides and +protein sequences. + +You can choose to have all the ORFs/CDSs above the minimum length for each +sequence (similar to the EMBOSS getorf tool), those with the longest length +equal, or the first ORF/CDS with the longest length (in the special case +where a sequence encodes two or more long ORFs/CDSs of the same length). The +last option is a reasonable choice when the input sequences represent EST or +mRNA sequences, where only one ORF/CDS is expected. + +Note that if no ORFs/CDSs in a sequence match the criteria, there will be no +output for that sequence. + +Also note that the ORFs/CDSs are assigned modified identifiers to distinguish +them from the original full length sequences, by appending a suffix. + +The start and stop codons are taken from the `NCBI Genetic Codes +<http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi>`_. +When searching for ORFs, the sequences will run from stop codon to stop +codon, and any start codons are ignored. When searching for CDSs, the first +potential start codon will be used, giving the longest possible CDS within +each ORF, and thus the longest possible protein sequence. This is useful +for things like BLAST or domain searching, but since this may not be the +correct start codon, it may not be appropriate for signal peptide detection +etc. + +**Example Usage** + +Given some EST sequences (Sanger capillary reads) assembled into unigenes, +or a transcriptome assembly from some RNA-Seq, each of your nucleotide +sequences should (barring sequencing, assembly errors, frame-shifts etc) +encode one protein as a single ORF/CDS, which you wish to extract (and +perhaps translate into amino acids). + +If your RNA-Seq data was strand specific, and assembled taking this into +account, you should only search for ORFs/CDSs on the forward strand. + +**Citation** + +If you use this Galaxy tool in work leading to a scientific publication please +cite the following paper: + +Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013). +Galaxy tools and workflows for sequence analysis with applications +in molecular plant pathology. PeerJ 1:e167 +http://dx.doi.org/10.7717/peerj.167 + +This tool uses Biopython, so you may also wish to cite the Biopython +application note (and Galaxy too of course): + +Cock et al (2009). Biopython: freely available Python tools for computational +molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3. +http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878. + +This tool is available to install into other Galaxy Instances via the Galaxy +Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/get_orfs_or_cdss + </help> + <citations> + <citation type="doi">10.7717/peerj.167</citation> + <citation type="doi">10.1093/bioinformatics/btp163</citation> + </citations> +</tool>