comparison arriba.xml @ 2:7420753b0671 draft

"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit 7dbe725aaa7b4b84d7b14ea52f38f63d362bf09c"
author jjohnson
date Fri, 08 Oct 2021 19:23:48 +0000
parents 9f2665b32c45
children 2d32e6c86c48
comparison
equal deleted inserted replaced
1:9f2665b32c45 2:7420753b0671
17 #set read2 = 'input_2.fastq.gz' 17 #set read2 = 'input_2.fastq.gz'
18 #else: 18 #else:
19 #set read2 = 'input_2.fastq' 19 #set read2 = 'input_2.fastq'
20 #end if 20 #end if
21 ln -f -s '${input_params.right_fq}' ${read2} && 21 ln -f -s '${input_params.right_fq}' ${read2} &&
22 #if str($input_params.index.index_source) == "history"
23 #set $star_index_dir = $input_params.index.star_index.files_path
24 #end if
22 STAR 25 STAR
23 --runThreadN \${GALAXY_SLOTS:-1} 26 --runThreadN \${GALAXY_SLOTS:-1}
24 --genomeDir /path/to/STAR_index 27 --genomeDir $star_index_dir
25 --genomeLoad NoSharedMemory 28 --genomeLoad NoSharedMemory
26 --readFilesIn $read1 $read2 29 --readFilesIn $read1 $read2
27 --readFilesCommand zcat 30 --readFilesCommand zcat
28 --outStd BAM_Unsorted 31 --outStd BAM_Unsorted
29 --outSAMtype BAM Unsorted 32 --outSAMtype BAM Unsorted
68 -o fusions.tsv 71 -o fusions.tsv
69 -O fusions.discarded.tsv 72 -O fusions.discarded.tsv
70 ]]></command> 73 ]]></command>
71 <inputs> 74 <inputs>
72 <conditional name="input_params"> 75 <conditional name="input_params">
73 <param name="input_source" 76 <param name="input_source" type="select" label="Use output from earlier STAR run or let Arriba running STAR">
74 type="select"
75 label="Use output from earlier STAR run or let Arriba running STAR">
76 <option value="use_star">Use output from earlier STAR</option> 77 <option value="use_star">Use output from earlier STAR</option>
77 <option value="use_fastq">Let Arriba control running STAR</option> 78 <option value="use_fastq">Let Arriba control running STAR</option>
78 </param> 79 </param>
79 <when value="use_star"> 80 <when value="use_star">
80 <param name="input" argument="-x" type="data" format="sam,bam,cram" label="STAR Aligned.out.sam"/> 81 <param name="input" argument="-x" type="data" format="sam,bam,cram" label="STAR Aligned.out.sam"/>
91 <param name="right_fq" 92 <param name="right_fq"
92 type="data" 93 type="data"
93 format="fastqsanger,fastqsanger.gz" 94 format="fastqsanger,fastqsanger.gz"
94 argument="--right_fq" 95 argument="--right_fq"
95 label="right.fq file"/> 96 label="right.fq file"/>
97 <conditional name="index">
98 <param name="index_source" type="select" label="Arriba STAR index source">
99 <option value="history">Arriba STAR index from your history</option>
100 </param>
101 <when value="history">
102 <param name="star_index" argument="--genomeDir" type="data" format="txt" label="Arriba STAR index"
103 help="generated by: Arriba Reference"/>
104 </when>
105 </conditional>
96 </when> 106 </when>
97 </conditional> 107 </conditional>
98 <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/> 108 <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/>
99 <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/> 109 <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/>
100 <param name="blacklist" argument="-b" type="data" format="tabular" label="File containing blacklisted ranges."/> 110 <param name="blacklist" argument="-b" type="data" format="tabular" label="File containing blacklisted ranges."/>
217 227
218 The file must be in GFF3 format and may optionally be gzip-compressed. The ninth column must at least contain the following attributes: 228 The file must be in GFF3 format and may optionally be gzip-compressed. The ninth column must at least contain the following attributes:
219 * Name=PROTEIN_DOMAIN_NAME; 229 * Name=PROTEIN_DOMAIN_NAME;
220 * gene_id=GENE_ID; 230 * gene_id=GENE_ID;
221 * gene_name=GENE_NAME 231 * gene_name=GENE_NAME
232
222 The attribute Name is reported in the column retained_protein_domains of Arriba's output file. Some special characters in the name are replaced with underscores (_). The columns gene_id and gene_name are used to match the protein domains to the genes given in the gene annotation. If a match cannot be found, Arriba cannot determine the retained protein domains of the respective gene and a warning is issued. There may be many warnings if RefSeq annotation is used, because the protein domains file distributed with Arriba uses ENSEMBL gene names/IDs. 233 The attribute Name is reported in the column retained_protein_domains of Arriba's output file. Some special characters in the name are replaced with underscores (_). The columns gene_id and gene_name are used to match the protein domains to the genes given in the gene annotation. If a match cannot be found, Arriba cannot determine the retained protein domains of the respective gene and a warning is issued. There may be many warnings if RefSeq annotation is used, because the protein domains file distributed with Arriba uses ENSEMBL gene names/IDs.
223 234
224 - Structural variant calls from WGS 235 - Structural variant calls from WGS
225 236
226 If whole-genome sequencing (WGS) data is available, the sensitivity and specificity of Arriba can be improved by passing a list of structural variants detected from WGS to Arriba via the parameter -d. This has the following effects: 237 If whole-genome sequencing (WGS) data is available, the sensitivity and specificity of Arriba can be improved by passing a list of structural variants detected from WGS to Arriba via the parameter -d. This has the following effects: