|
0
|
1 <tool id="get_orfs_or_cdss" name="Get open reading frames (ORFs) or coding sequences (CDSs)" version="19.1.0.0">
|
|
|
2 <description>e.g. to get peptides from ESTs</description>
|
|
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 <import>cpt-macros.xml</import>
|
|
|
6 </macros>
|
|
|
7 <expand macro="requirements">
|
|
1
|
8 <requirement type="package" version="2022.1.18">regex</requirement>
|
|
0
|
9 </expand>
|
|
|
10 <command interpreter="python" detect_errors="aggressive">
|
|
|
11 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
|
|
|
12 </command>
|
|
|
13 <inputs>
|
|
|
14 <param name="input_file" type="data" format="fasta,fastq,sff" label="Sequence file (nucleotides)" help="FASTA, FASTQ, or SFF format." />
|
|
|
15 <param name="table" type="select" label="Genetic code" help="Tables from the NCBI, these determine the start and stop codons">
|
|
|
16 <option value="1">1. Standard</option>
|
|
|
17 <option value="2">2. Vertebrate Mitochondrial</option>
|
|
|
18 <option value="3">3. Yeast Mitochondrial</option>
|
|
|
19 <option value="4">4. Mold, Protozoan, Coelenterate Mitochondrial and Mycoplasma/Spiroplasma</option>
|
|
|
20 <option value="5">5. Invertebrate Mitochondrial</option>
|
|
|
21 <option value="6">6. Ciliate Macronuclear and Dasycladacean</option>
|
|
|
22 <option value="9">9. Echinoderm Mitochondrial</option>
|
|
|
23 <option value="10">10. Euplotid Nuclear</option>
|
|
|
24 <option value="11">11. Bacterial</option>
|
|
|
25 <option value="12">12. Alternative Yeast Nuclear</option>
|
|
|
26 <option value="13">13. Ascidian Mitochondrial</option>
|
|
|
27 <option value="14">14. Flatworm Mitochondrial</option>
|
|
|
28 <option value="15">15. Blepharisma Macronuclear</option>
|
|
|
29 <option value="16">16. Chlorophycean Mitochondrial</option>
|
|
|
30 <option value="21">21. Trematode Mitochondrial</option>
|
|
|
31 <option value="22">22. Scenedesmus obliquus</option>
|
|
|
32 <option value="23">23. Thraustochytrium Mitochondrial</option>
|
|
|
33 <option value="24">24. Pterobranchia Mitochondrial</option>
|
|
|
34 </param>
|
|
|
35 <param name="ftype" type="select" value="True" label="Look for ORFs or CDSs">
|
|
|
36 <option value="ORF">Look for ORFs (check for stop codons only, ignore start codons)</option>
|
|
|
37 <option value="CDS">Look for CDSs (with start and stop codons)</option>
|
|
|
38 </param>
|
|
|
39 <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)" />
|
|
|
40 <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).">
|
|
|
41 <option value="both">Search both the forward and reverse strand</option>
|
|
|
42 <option value="forward">Only search the forward strand</option>
|
|
|
43 <option value="reverse">Only search the reverse strand</option>
|
|
|
44 </param>
|
|
|
45 </inputs>
|
|
|
46 <outputs>
|
|
|
47 <data name="out_nuc_file" format="fasta" label="${ftype.value}s (nucleotides)" />
|
|
|
48 <data name="out_prot_file" format="fasta" label="${ftype.value}s (amino acids)" />
|
|
|
49 <data name="out_bed_file" format="bed6" label="${ftype.value}s (bed)" />
|
|
|
50 <data name="out_gff3_file" format="gff3" label="${ftype.value}s (gff3)" />
|
|
|
51 </outputs>
|
|
|
52 <tests>
|
|
|
53 <test>
|
|
|
54 <param name="input_file" value="Orf_T7In.fasta" />
|
|
|
55 <param name="table" value="11" />
|
|
|
56 <param name="ftype" value="ORF" />
|
|
|
57 <param name="min_len" value="30" />
|
|
|
58 <param name="strand" value="both" />
|
|
|
59 <output name="out_nuc_file" file="Orf_T7Out_Nuc.fasta" />
|
|
|
60 <output name="out_prot_file" file="Orf_T7Out_AA.fasta" />
|
|
|
61 <output name="out_bed_file" file="Orf_T7Out_Bed.bed" />
|
|
|
62 <output name="out_gff3_file" file="Orf_T7Out_Gff.gff3" />
|
|
|
63 </test>
|
|
|
64 <test>
|
|
|
65 <param name="input_file" value="Orf_In2.fasta" />
|
|
|
66 <param name="table" value="1" />
|
|
|
67 <param name="ftype" value="CDS" />
|
|
|
68 <param name="min_len" value="10" />
|
|
|
69 <param name="strand" value="forward" />
|
|
|
70 <output name="out_nuc_file" file="Orf_Out2T1_Nuc.fasta" />
|
|
|
71 <output name="out_prot_file" file="Orf_Out2T1_AA.fasta" />
|
|
|
72 <output name="out_bed_file" file="Orf_Out2T1_Bed.bed" />
|
|
|
73 <output name="out_gff3_file" file="Orf_Out2T1_Gff.gff3" />
|
|
|
74 </test>
|
|
|
75 <test>
|
|
|
76 <param name="input_file" value="Orf_In2.fasta" />
|
|
|
77 <param name="table" value="11" />
|
|
|
78 <param name="ftype" value="CDS" />
|
|
|
79 <param name="min_len" value="10" />
|
|
|
80 <param name="strand" value="forward" />
|
|
|
81 <output name="out_nuc_file" file="Orf_Out2T11_Nuc.fasta" />
|
|
|
82 <output name="out_prot_file" file="Orf_Out2T11_AA.fasta" />
|
|
|
83 <output name="out_bed_file" file="Orf_Out2T11_Bed.bed" />
|
|
|
84 <output name="out_gff3_file" file="Orf_Out2T11_Gff.gff3" /> </test>
|
|
|
85 </tests>
|
|
|
86 <help>
|
|
|
87 **What it does**
|
|
|
88
|
|
|
89 Takes an input file of nucleotide sequences (typically FASTA, but also FASTQ
|
|
|
90 and Standard Flowgram Format (SFF) are supported), and searches each sequence
|
|
|
91 for open reading frames (ORFs) or potential coding sequences (CDSs) of the
|
|
|
92 given minimum length. These are returned as FASTA files of nucleotides and
|
|
|
93 protein sequences.
|
|
|
94
|
|
|
95 You can choose to have all the ORFs/CDSs above the minimum length for each
|
|
|
96 sequence (similar to the EMBOSS getorf tool), those with the longest length
|
|
|
97 equal, or the first ORF/CDS with the longest length (in the special case
|
|
|
98 where a sequence encodes two or more long ORFs/CDSs of the same length). The
|
|
|
99 last option is a reasonable choice when the input sequences represent EST or
|
|
|
100 mRNA sequences, where only one ORF/CDS is expected.
|
|
|
101
|
|
|
102 Note that if no ORFs/CDSs in a sequence match the criteria, there will be no
|
|
|
103 output for that sequence.
|
|
|
104
|
|
|
105 Also note that the ORFs/CDSs are assigned modified identifiers to distinguish
|
|
|
106 them from the original full length sequences, by appending a suffix.
|
|
|
107
|
|
|
108 The start and stop codons are taken from the `NCBI Genetic Codes
|
|
|
109 <http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi>`_.
|
|
|
110 When searching for ORFs, the sequences will run from stop codon to stop
|
|
|
111 codon, and any start codons are ignored. When searching for CDSs, the first
|
|
|
112 potential start codon will be used, giving the longest possible CDS within
|
|
|
113 each ORF, and thus the longest possible protein sequence. This is useful
|
|
|
114 for things like BLAST or domain searching, but since this may not be the
|
|
|
115 correct start codon, it may not be appropriate for signal peptide detection
|
|
|
116 etc.
|
|
|
117
|
|
|
118 **Example Usage**
|
|
|
119
|
|
|
120 Given some EST sequences (Sanger capillary reads) assembled into unigenes,
|
|
|
121 or a transcriptome assembly from some RNA-Seq, each of your nucleotide
|
|
|
122 sequences should (barring sequencing, assembly errors, frame-shifts etc)
|
|
|
123 encode one protein as a single ORF/CDS, which you wish to extract (and
|
|
|
124 perhaps translate into amino acids).
|
|
|
125
|
|
|
126 If your RNA-Seq data was strand specific, and assembled taking this into
|
|
|
127 account, you should only search for ORFs/CDSs on the forward strand.
|
|
|
128
|
|
|
129 **Citation**
|
|
|
130
|
|
|
131 If you use this Galaxy tool in work leading to a scientific publication please
|
|
|
132 cite the following paper:
|
|
|
133
|
|
|
134 Peter J.A. Cock, Björn A. Grüning, Konrad Paszkiewicz and Leighton Pritchard (2013).
|
|
|
135 Galaxy tools and workflows for sequence analysis with applications
|
|
|
136 in molecular plant pathology. PeerJ 1:e167
|
|
|
137 http://dx.doi.org/10.7717/peerj.167
|
|
|
138
|
|
|
139 This tool uses Biopython, so you may also wish to cite the Biopython
|
|
|
140 application note (and Galaxy too of course):
|
|
|
141
|
|
|
142 Cock et al (2009). Biopython: freely available Python tools for computational
|
|
|
143 molecular biology and bioinformatics. Bioinformatics 25(11) 1422-3.
|
|
|
144 http://dx.doi.org/10.1093/bioinformatics/btp163 pmid:19304878.
|
|
|
145
|
|
|
146 This tool is available to install into other Galaxy Instances via the Galaxy
|
|
|
147 Tool Shed at http://toolshed.g2.bx.psu.edu/view/peterjc/get_orfs_or_cdss
|
|
|
148 </help>
|
|
|
149 <citations>
|
|
|
150 <citation type="doi">10.7717/peerj.167</citation>
|
|
|
151 <citation type="doi">10.1093/bioinformatics/btp163</citation>
|
|
|
152 </citations>
|
|
|
153 </tool>
|
