Mercurial > repos > triasteran > trips_create_new_organism
diff final/create_annotation_sqlite.xml @ 4:9482a43a3d83 draft
Uploaded
| author | triasteran |
|---|---|
| date | Tue, 01 Mar 2022 12:40:17 +0000 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/final/create_annotation_sqlite.xml Tue Mar 01 12:40:17 2022 +0000 @@ -0,0 +1,85 @@ +<tool id="create_annotation_sqlite" name="create annotation in sqlite for trips-viz" version="0.1.4"> + <requirements> + <container type="docker">triasteran/trips_create_annotation:latest</container> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + create_annotation_sqlite $annotation $fasta $pseudo_utr_len $transcript $gene $output + ]]></command> + <inputs> + <param format="gtf,gff" name="annotation" type="data" label="GTF/GFF3 File"/> + <param format="fasta" name="fasta" type="data" label="Transcriptome FASTA file"/> + <param name="pseudo_utr_len" type="text" label="Pseudo UTR length"/> + <param name="transcript" type="text" label="Example transcript"/> + <param name="gene" type="text" label="Example gene"/> + </inputs> + <outputs> + <data format="sqlite" name="output" /> + </outputs> + <tests> + <test> + <param name="fasta" value="sacCer3_transcripts.fasta"/> + <param name="annotation" value="saccharomyces_cerevisiae.R64-1-1.84.gtf"/> + <param name="pseudo_utr_len" value="300"/> + <param name="transcript" value="YDL248W"/> + <param name="gene" value="COS7"/> + <output name="output" file="output"/> + </test> + </tests> + <help><![CDATA[ + **GTF/GFF3 File** + +GFF lines have nine required fields that must be tab-separated. +The GFF3 format addresses the most common extensions to GFF, while preserving backward compatibility with previous formats. + +Both transcript ids and gene names should be listed in the file. + +----- + +**Transcriptome FASTA file** + +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. + +----- + +**Psuedo UTR length** +An integer representing the length (in nucleotides) to be added to the 5' end and 3' end of every transcript with an annotated +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 +already be present in the FASTA file. + +----- + +**Example transcript** + +An example of a transcript id that appears in the FASTA/GTF/GFF3 file, e.g ENST00000123456 + +----- + +**Example Gene** + +An example of a gene name as it appears in the GTF/GFF3 file, e.g BRCA1 + +----- + +**Output** + +The output of the script can be downloaded and uploaded to Trips-viz_. by signing in and going to the uploads page, then selecting +"Upload new transcriptome". When uploaded the new organism will appear on the home page of Trips-viz, or under the transcriptomes +page if the organism name used is already present on Trips-viz. + + + +.. _Trips-viz: http://trips.ucc.ie + + ]]></help> + <citations> + <citation type="bibtex"> +@misc{githubTrips-Viz, + author = {LastTODO, FirstTODO}, + year = {TODO}, + title = {Trips-Viz}, + publisher = {GitHub}, + journal = {GitHub repository}, + url = {https://github.com/skiniry/Trips-Viz}, +}</citation> + </citations> +</tool>
