| Previous changeset 5:ff4031bfaa22 (2024-08-01) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/yahs commit ab918ac1eab72932e78c6e45e46d745543eac810 |
|
modified:
yahs.xml |
|
added:
test-data/test2.unsorted.bam test-data/test3.qname_sorted.bam |
| b |
| diff -r ff4031bfaa22 -r 6756b34312cd test-data/test2.unsorted.bam |
| b |
| Binary file test-data/test2.unsorted.bam has changed |
| b |
| diff -r ff4031bfaa22 -r 6756b34312cd test-data/test3.qname_sorted.bam |
| b |
| Binary file test-data/test3.qname_sorted.bam has changed |
| b |
| diff -r ff4031bfaa22 -r 6756b34312cd yahs.xml --- a/yahs.xml Thu Aug 01 11:41:41 2024 +0000 +++ b/yahs.xml Wed Sep 17 06:28:08 2025 +0000 |
| [ |
| b'@@ -2,7 +2,7 @@\n <description>yet another HI-C scaffolding tool</description>\n <macros>\n <token name="@VERSION@">1.2a.2</token>\n- <token name="@VERSION_SUFFIX@">2</token>\n+ <token name="@VERSION_SUFFIX@">3</token>\n </macros>\n <requirements>\n <requirement type="package" version="@VERSION@">yahs</requirement>\n@@ -12,22 +12,13 @@\n <command detect_errors="exit_code"><![CDATA[\n #if $function.function_select == "yahs":\n ln -s \'$function.fasta\' input.fasta &&\n- #if $function.bfile.ext == "bam":\n- ln -s \'$function.bfile\' input.bam &&\n- #else if $function.bfile.ext == "bed":\n- ln -s \'$function.bfile\' input.bed &&\n- #end if\n+ ln -s \'$function.bfile\' input.$function.bfile.ext &&\n #if $function.agp:\n ln -s \'$function.agp\' input.agp &&\n #end if\n samtools faidx input.fasta &&\n mkdir initial_break agp_out agp_break final_outs &&\n- yahs --no-mem-check input.fasta \n- #if $function.bfile.ext == "bam":\n- input.bam\n- #else if $function.bfile.ext == "bed":\n- input.bed\n- #end if\n+ yahs --no-mem-check input.fasta input.$function.bfile.ext\n #if $agp:\n -a input.agp\n #end if\n@@ -83,16 +74,16 @@\n </param>\n <when value="yahs">\n <param name="fasta" type="data" format="fasta" label="Input contig sequences"/>\n- <param name="bfile" type="data" format="bam,bed" label="Alignment file of Hi-C reads to contigs"/>\n- <param name="agp" argument="-a" type="data" format="agp" optional="true" label="Input AGP file (for rescaffolding)"\n- help="You can specify a AGP format file to ask YaHS to do scaffolding with the scaffolds in the AGP file as the start point"/>\n- <param name="res" argument="-r" type="text" label="Resolutions" optional="true" \n- help="Comma separated, ascending list of range of resolutions with no spaces. Ex. 50000,100000,200000,500000,1000000,2000000,5000000. By default and the upper limit is automatically adjusted with the genome size"/>\n+ <param name="bfile" type="data" format="bam,bed,qname_sorted.bam,unsorted.bam" label="Alignment file of Hi-C reads to contigs. NOTE: The input BAM could either be sorted by read names (qname_sorted.bam) or not. The behaviours of the program are slightly different, which might lead to slightly different scaffolding results. For a BAM input sorted by read names, with each mapped read pair, a Hi-C link is counted between the middle positions of the read alignments; while for a BAM input sorted by coordinates or unsorted, Hi-C links are counted between the start positions of the read alignments. Also, for a BAM input not sorted by read names, the mapping quality filtering is suppressed (-q option). If a bed file is provided: the BAM file used to genereate BED file need to be filtered out unmapped reads, supplementary/secondary alignment records, and PCR/optical duplicates, and sorted by read names (otherwise the resulted BED file need to be sorted by the read name column)."/>\n+ <param name="agp" argument="-a" type="data" format="agp" optional="true" label="Input AGP file (for rescaffolding)" help="You can specify a AGP format file to ask YaHS to do scaffolding with the scaffolds in the AGP file as the start point"/>\n+ <param name="res" argument="-r" type="text" label="Resolutions" optional="true" help="Comma separated, ascending list of range of resolutions with no spaces. Ex. 50000,100000,200000,500000,1000000,2000000,5000000. By default and the upper limit is automatically adjusted with the genome size">\n+ <validator type="regex" message="Only Numbers and commas can be used in to define the list of range'..b'nzymes" value="omnic"/>\n+ <param name="fasta" value="test.fasta" ftype="fasta"/>\n+ <param name="bfile" value="test.bed" ftype="bed"/>\n+ <conditional name="enzyme_conditional">\n+ <param name="enzyme_options" value="preconfigured"/>\n+ <param name="preconfigured_enzymes" value="omnic"/>\n+ </conditional>\n </conditional>\n <param name="log_out" value="yes"/>\n <output name="log_file" ftype="txt">\n@@ -269,9 +259,46 @@\n </assert_contents>\n </output>\n </test>\n+ <!-- TEST 8: qname_sorted-->\n+ <test expect_num_outputs="6">\n+ <conditional name="function">\n+ <param name="function_select" value="yahs"/>\n+ <param name="fasta" value="test2.fasta" ftype="fasta"/>\n+ <param name="bfile" value="test3.qname_sorted.bam" ftype="qname_sorted.bam"/>\n+ <param name="res" value="1000,2000,5000,10000,20000,50000,100000,200000,500000"/>\n+ <conditional name="enzyme_conditional">\n+ <param name="enzyme_options" value="not_specified"/>\n+ </conditional>\n+ </conditional>\n+ <param name="log_out" value="yes"/>\n+ <output name="log_file" ftype="txt">\n+ <assert_contents>\n+ <has_text text="[I::dump_links_from_bam_file] dumped 6399 read pairs from 17675 records: 6399 intra links + 0 inter links"/>\n+ </assert_contents>\n+ </output>\n+ </test>\n+ <!-- TEST 9: unsorted-->\n+ <test expect_num_outputs="6">\n+ <conditional name="function">\n+ <param name="function_select" value="yahs"/>\n+ <param name="fasta" value="test2.fasta" ftype="fasta"/>\n+ <param name="bfile" value="test2.unsorted.bam" ftype="bam"/>\n+ <param name="res" value="1000,2000,5000,10000,20000,50000,100000,200000,500000"/>\n+ <conditional name="enzyme_conditional">\n+ <param name="enzyme_options" value="not_specified"/>\n+ </conditional>\n+ </conditional>\n+ <param name="log_out" value="yes"/>\n+ <output name="log_file" ftype="txt">\n+ <assert_contents>\n+ <has_text text="[I::dump_links_from_bam_file] dumped 6399 read pairs from 17675 records: 6297 intra links + 102 inter links"/>\n+ </assert_contents>\n+ </output>\n+ <!-- COMMAND: yahs test.fasta test.bam -r 1000,2000,5000,10000,20000,50000,100000,200000,500000 -o test_3 -->\n+ </test>\n </tests>\n <help><![CDATA[\n- YaHS is scaffolding tool using Hi-C data. It relies on a new algothrim for contig joining detection which considers the topological distribution of Hi-C signals aiming to distingush real interaction signals from mapping nosies. YaHS has been tested in a wide range of genome assemblies. Compared to other Hi-C scaffolding tools, it usually generates more contiguous scaffolds - especially with a higher N90 and L90 statistics. It is also super fast - takes less than 5 minutes to reconstruct the human genome from an assembly of 5,483 contigs with ~45X Hi-C data.\n+ YaHS is scaffolding tool using Hi-C data. It relies on a new algorithm for contig joining detection which considers the topological distribution of Hi-C signals aiming to distingush real interaction signals from mapping nosies. YaHS has been tested in a wide range of genome assemblies. Compared to other Hi-C scaffolding tools, it usually generates more contiguous scaffolds - especially with a higher N90 and L90 statistics. It is also super fast - takes less than 5 minutes to reconstruct the human genome from an assembly of 5,483 contigs with ~45X Hi-C data.\n ]]></help>\n <citations>\n <citation type="doi">10.5281/zenodo.5848772</citation>\n' |