|
7
|
1 <tool id="create_annotation_sqlite" name="create annotation in sqlite for trips-viz" version="0.1.5conda">
|
|
6
|
2 <requirements>
|
|
7
|
3 <requirement type="package" version="3.1.0">python-intervaltree</requirement>
|
|
|
4 <requirement type="package" version="0.4.6">pysqlite3</requirement>
|
|
6
|
5 </requirements>
|
|
|
6 <command detect_errors="exit_code"><![CDATA[
|
|
7
|
7 python3 '$__tool_directory__/create_annotation_sqlite.py' $annotation $fasta $pseudo_utr_len $transcript $gene $output
|
|
6
|
8 ]]></command>
|
|
|
9 <inputs>
|
|
|
10 <param format="gtf,gff" name="annotation" type="data" label="GTF/GFF3 File"/>
|
|
|
11 <param format="fasta" name="fasta" type="data" label="Transcriptome FASTA file"/>
|
|
|
12 <param name="pseudo_utr_len" type="text" label="Pseudo UTR length"/>
|
|
|
13 <param name="transcript" type="text" label="Example transcript"/>
|
|
|
14 <param name="gene" type="text" label="Example gene"/>
|
|
|
15 </inputs>
|
|
|
16 <outputs>
|
|
|
17 <data format="sqlite" name="output" />
|
|
|
18 </outputs>
|
|
|
19 <tests>
|
|
|
20 <test>
|
|
|
21 <param name="fasta" value="sacCer3_transcripts.fasta"/>
|
|
|
22 <param name="annotation" value="saccharomyces_cerevisiae.R64-1-1.84.gtf"/>
|
|
|
23 <param name="pseudo_utr_len" value="300"/>
|
|
|
24 <param name="transcript" value="YDL248W"/>
|
|
|
25 <param name="gene" value="COS7"/>
|
|
|
26 <output name="output" file="output"/>
|
|
|
27 </test>
|
|
|
28 </tests>
|
|
|
29 <help><![CDATA[
|
|
|
30 **GTF/GFF3 File**
|
|
|
31
|
|
|
32 GFF lines have nine required fields that must be tab-separated.
|
|
|
33 The GFF3 format addresses the most common extensions to GFF, while preserving backward compatibility with previous formats.
|
|
|
34
|
|
|
35 Both transcript ids and gene names should be listed in the file.
|
|
|
36
|
|
|
37 -----
|
|
|
38
|
|
|
39 **Transcriptome FASTA file**
|
|
|
40
|
|
|
41 A FASTA file with an entry for every transcript. The headers should be the transcript id's as they appear in the GTF/GFF3 file.
|
|
|
42
|
|
|
43 -----
|
|
|
44
|
|
|
45 **Psuedo UTR length**
|
|
|
46 An integer representing the length (in nucleotides) to be added to the 5' end and 3' end of every transcript with an annotated
|
|
|
47 CDS. Useful for when an organism does not have any annotated UTR's, if it does use 0. If not 0, the extra nucleotides should
|
|
|
48 already be present in the FASTA file.
|
|
|
49
|
|
|
50 -----
|
|
|
51
|
|
|
52 **Example transcript**
|
|
|
53
|
|
|
54 An example of a transcript id that appears in the FASTA/GTF/GFF3 file, e.g ENST00000123456
|
|
|
55
|
|
|
56 -----
|
|
|
57
|
|
|
58 **Example Gene**
|
|
|
59
|
|
|
60 An example of a gene name as it appears in the GTF/GFF3 file, e.g BRCA1
|
|
|
61
|
|
|
62 -----
|
|
|
63
|
|
|
64 **Output**
|
|
|
65
|
|
|
66 The output of the script can be downloaded and uploaded to Trips-viz_. by signing in and going to the uploads page, then selecting
|
|
|
67 "Upload new transcriptome". When uploaded the new organism will appear on the home page of Trips-viz, or under the transcriptomes
|
|
|
68 page if the organism name used is already present on Trips-viz.
|
|
|
69
|
|
|
70
|
|
|
71
|
|
|
72 .. _Trips-viz: http://trips.ucc.ie
|
|
|
73
|
|
|
74 ]]></help>
|
|
|
75 <citations>
|
|
|
76 <citation type="bibtex">
|
|
|
77 @misc{githubTrips-Viz,
|
|
|
78 author = {LastTODO, FirstTODO},
|
|
|
79 year = {TODO},
|
|
|
80 title = {Trips-Viz},
|
|
|
81 publisher = {GitHub},
|
|
|
82 journal = {GitHub repository},
|
|
|
83 url = {https://github.com/skiniry/Trips-Viz},
|
|
|
84 }</citation>
|
|
|
85 </citations>
|
|
|
86 </tool>
|
