gffread: gffread.xml comparison

comparison gffread.xml @ 2:12aeae6d8587 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/cufflinks/gffread commit 3bc5271145f939d85bb709fc95197be66b348328

author	devteam
date	Tue, 07 Jun 2016 17:58:15 -0400
parents	48fe74f391ab
children	9f243677c4c6

comparison

equal deleted inserted replaced

-:48fe74f391ab
+:12aeae6d8587
 <param name="ref_filtering" type="select" display="checkboxes" multiple="true" label="reference based filters">
 <option value="-N">discard multi-exon mRNAs that have any intron with a non-canonical splice site consensus, i.e. not GT-AG, GC-AG or AT-AC (-N)</option>
 <option value="-J">discard any mRNAs that either lack initial START codon or the terminal STOP codon, or have an in-frame stop codon (-J)</option>
 <option value="-V">discard any mRNAs with CDS having in-frame stop codons (-V)</option>
 <option value="-H">check and adjust the starting CDS phase if the original phase leads to a translation with an in-frame stop codon (-H with -V)</option>
 <!-- gffread bug: B not in  missing from param to the arg parser
 <option value="-B">single-exon transcripts are also checked on the opposite strand (-B with -V)</option>
 -->
 </param>
 </xml>
 <xml name="trackname">
 <command>
 <![CDATA[
 #if $reference_genome.source == 'history':
 ln -s $reference_genome.genome_fasta genomeref.fa &&
 #end if
 gffread $input
 #if $reference_genome.source == 'cached':
 -g "${reference_genome.fasta_indexes.fields.path}"
 #if $reference_genome.ref_filtering and str($reference_genome.ref_filtering) != '':
 #echo ' '.join(str($reference_genome.ref_filtering).split(','))
 #end if
 <option value="-U">discard single-exon transcripts (-U)</option>
 <option value="-C">coding only: discard mRNAs that have no CDS feature (-C)</option>
 <option value="-G">only parse additional exon attributes from the first exon and move them to the mRNA level (useful for GTF input) (-G)</option>
 <option value="-O">process also non-transcript GFF records (by default non-transcript records are ignored) (-O)</option>
 <option value="--no-pseudo">filter out records matching the 'pseudo' keyword (--no-pseudo)</option>
 </param>
 <conditional name="region">
 <param name="region_filter" type="select" label="Filter by genome region">
 <option value="none">No</option>
 <option value="filter">Yes</option>
 </param>
 <when value="none"/>
 <when value="filter">
 <param name="range" type="text" value="" label="Only show transcripts overlapping coordinate range">
 <help><![CDATA[
 (-r [['strand']'chr':]'start'..'end') <br>
 examples: <br>
 1000..500000 <br>
 chr1:1000..500000 <br>
 +chr1:1000..500000 <br>
 -chr1:1000..500000
 ]]>
 </help>
 <validator type="regex">(([+-])?(\w+:))?\d+\.\.\d+</validator>
 </param>
 <param name="discard_partial" type="boolean" truevalue="-R" falsevalue="" check="false"
 label="discard all transcripts that are not fully contained within the given range" help="(-R)"/>
 </when>
 </conditional>
 <param name="maxintron" type="integer" value="" optional="true" min="0" label="Filter out transcipts with large introns"
 help="If set, discard transcripts having an intron larger (-i max_intron)"/>
 <param name="chr_replace" type="data" format="tabular" optional="true" label="Replace reference sequence names" >
 <help><![CDATA[(-m chr_replace) <br>
 chr_replace is a reference sequence replacement table consisting of 2 columns: "original_ref_ID"  "new_ref_ID"<br>
 It is useful for switching between Ensembl and UCSC naming conventions <br>
 NOTE: GFF records on reference sequences that are not found among the "original_ref_ID" entries in this file will be filtered out
 ]]>
 </help>
 </param>
 <!-- Although documented, does not appear to be used in the gffread code
 <param name="seq_info" type="data" format="tabular" optional="true" label="Use the description field as the value for a 'descr' attribute to the GFF record">
 <help>
 (-s seq_info.fsize -A)  useful with mRNA/EST/protein mappings &lt;br&gt;
 seq_info input file is a 3 column tab-delimited file providing this info for each of the mapped sequences: &lt;br&gt;
 "seq-name" "seq-length" "seq-description" &lt;br&gt;
 </help>
 </param>
 -->
 <!-- merging -->
 <conditional name="merging">
 <param name="merge_sel" type="select" label="Transcript merging" help="(-M/--merge or --cluster-only)">
 </param>
 <expand macro="ref_filtering_select" />
 <expand macro="fasta_output_select" />
 </when>
 <when value="history">
 <param name="genome_fasta" type="data" format="fasta" label="Genome Reference Fasta"/>
 <expand macro="ref_filtering_select" />
 <expand macro="fasta_output_select" />
 </when>
 </conditional>
 <!-- outputs -->
 <conditional name="gffs">
-<param name="gff_fmt" type="select" optional="true" label="Feature File Output" help="(-o output.gff3|output.gtf)">
+<param name="gff_fmt" type="select" label="Feature File Output" help="(-o output.gff3|output.gtf)">
 <option value="none">none</option>
 <option value="gff">GFF</option>
 <option value="gtf">GTF</option>
 </param>
 <when value="none">
 <param name="output_cmd" type="hidden" value="-T -o output.gtf"/>
 <expand macro="trackname" />
 </when>
 </conditional>
 <param name="full_gff_attribute_preservation" type="boolean" truevalue="-F" falsevalue="" check="false"
 label="full GFF attribute preservation (all attributes are shown)" help="(-F)"/>
 <param name="decode_url" type="boolean" truevalue="-D" falsevalue="" check="false"
 label="decode url encoded characters within attributes" help="(-D)"/>
 <param name="expose" type="boolean" truevalue="-E" falsevalue="" check="false"
 label="warn about duplicate transcript IDs and other potential problems with the given GFF/GTF records" help="(-E)"/>
 </inputs>
 <outputs>
 <data name="output_gff" format="gff3" metadata_source="input" label="${tool.name} on ${on_string}: gff3" from_work_dir="output.gff3">
 .. _cufflinks: http://cole-trapnell-lab.github.io/cufflinks/
 Usage: ::
 gffread "input_gff" [-g "genomic_seqs_fasta" | "dir"][-s "seq_info.fsize"]
 [-o "outfile.gff"] [-t "tname"] [-r [["strand"]"chr":]"start".."end" [-R]]
 [-CTVNJMKQAFGUBHZWTOLE] [-w "exons.fa"] [-x "cds.fa"] [-y "tr_cds.fa"]
 [-i "maxintron"]
 Options: ::
 -g  full path to a multi-fasta file with the genomic sequences
 for all input mappings, OR a directory with single-fasta files
 (one per genomic sequence, with file names matching sequence names)
 <seq-name> <seq-length> <seq-description>
 (useful for -A option with mRNA/EST/protein mappings)
 -i  discard transcripts having an intron larger than <maxintron>
 -r  only show transcripts overlapping coordinate range <start>..<end>
 (on chromosome/contig <chr>, strand <strand> if provided)
 -R  for -r option, discard all transcripts that are not fully
 contained within the given range
 -U  discard single-exon transcripts
 -C  coding only: discard mRNAs that have no CDS feature
 -F  full GFF attribute preservation (all attributes are shown)
 -G  only parse additional exon attributes from the first exon
 and move them to the mRNA level (useful for GTF input)
 -A  use the description field from <seq_info.fsize> and add it
 as the value for a 'descr' attribute to the GFF record
 -O  process also non-transcript GFF records (by default non-transcript
 records are ignored)
 -V  discard any mRNAs with CDS having in-frame stop codons
 -H  for -V option, check and adjust the starting CDS phase
 if the original phase leads to a translation with an
 in-frame stop codon
 -B  for -V option, single-exon transcripts are also checked on the
 opposite strand
 -N  discard multi-exon mRNAs that have any intron with a non-canonical
 splice site consensus (i.e. not GT-AG, GC-AG or AT-AC)
 -J  discard any mRNAs that either lack initial START codon
 or the terminal STOP codon, or have an in-frame stop codon
 (only print mRNAs with a fulll, valid CDS)
 --no-pseudo: filter out records matching the 'pseudo' keyword
 -M/--merge : cluster the input transcripts into loci, collapsing matching
 transcripts (those with the same exact introns and fully contained)
 -d <dupinfo> : for -M option, write collapsing info to file <dupinfo>
 --cluster-only: same as --merge but without collapsing matching transcripts
 -K  for -M option: also collapse shorter, fully contained transcripts
 with fewer introns than the container
 -Q  for -M option, remove the containment restriction:
 (multi-exon transcripts will be collapsed if just their introns match,
 while single-exon transcripts can partially overlap (80%))
 --force-exons: make sure that the lowest level GFF features are printed as
 "exon" features
 -E  expose (warn about) duplicate transcript IDs and other potential
 problems with the given GFF/GTF records
 -D  decode url encoded characters within attributes
 -Z  merge close exons into a single exon (for intron size<4)
 -w  write a fasta file with spliced exons for each GFF transcript
 -x  write a fasta file with spliced CDS for each GFF transcript

Mercurial > repos > devteam > gffread

comparison gffread.xml @ 2:12aeae6d8587 draft