Mercurial > repos > bgruening > hifiasm
changeset 12:da9d8bf98802 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/hifiasm commit 2bb01c64e79df856fbcb12afde62f7c14a5f59fa
author | bgruening |
---|---|
date | Fri, 24 Feb 2023 17:34:21 +0000 |
parents | cd7936c5a9a5 |
children | ec9e21e9c71b |
files | hifiasm.xml test-data/hifiasm-out13.ovlp.source.bin |
diffstat | 2 files changed, 33 insertions(+), 14 deletions(-) [+] |
line wrap: on
line diff
--- a/hifiasm.xml Thu Feb 23 22:34:21 2023 +0000 +++ b/hifiasm.xml Fri Feb 24 17:34:21 2023 +0000 @@ -2,7 +2,7 @@ <description>haplotype-resolved de novo assembler for PacBio Hifi reads</description> <macros> <token name="@TOOL_VERSION@">0.18.8</token> - <token name="@VERSION_SUFFIX@">0</token> + <token name="@VERSION_SUFFIX@">1</token> <token name="@FORMATS@">fasta,fasta.gz,fastq,fastq.gz</token> <xml name="reads"> <param name="reads" type="data" format="@FORMATS@" multiple="true" label="Input reads" /> @@ -150,7 +150,12 @@ #if $log_out: 2> output.log #end if - && mkdir noseq_files && mv *.noseq.gfa noseq_files + + && mkdir noseq_files && mv *.noseq.gfa noseq_files + + #if $bins_out: + && mkdir bin_files && mv *.bin bin_files + #end if ]]> </command> <inputs> @@ -268,7 +273,8 @@ </param> </when> </conditional> - <param name="log_out" type="boolean" label="Output log file?" truevalue="yes" falsevalue="no"/> + <param name="log_out" type="boolean" label="Output log file?" truevalue="yes" falsevalue="no" /> + <param name="bins_out" type="boolean" label="Output .bin files (used for development and debugging)?" truevalue="yes" falsevalue="no" /> </inputs> <outputs> <!--Standard mode--> @@ -320,13 +326,17 @@ <data name="hap2_contigs_hic" format="gfa1" from_work_dir="output.hic.bench.p_utg.gfa" label="${tool.name} on ${on_string}: processsed unitig graph"> <filter>mode['mode_selector'] == 'trio' and hic_partition['hic_partition_selector'] == 'set'</filter> </data> - <!--Log output--> + <!--Log, noseq, and bin output--> <data name="log_file" format="txt" from_work_dir="output.log" label="${tool.name} ${on_string}: log file"> <filter>log_out</filter> </data> <collection name="noseq_files" type="list" label="${tool.name} on ${on_string}: noseq files"> <discover_datasets pattern="__name_and_ext__" format="gfa1" directory="noseq_files" /> </collection> + <collection name="bin_files" type="list" label="${tool.name} on ${on_string}: bin files"> + <filter>bins_out</filter> + <discover_datasets pattern="__name_and_ext__" format="gfa1" directory="bin_files" /> + </collection> </outputs> <tests> <!-- TEST 1 --> @@ -496,7 +506,7 @@ <test expect_num_outputs="5"> <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" /> <param name="mode_selector" value="standard" /> - <param name="filter_bits" value="0" /> + <param name="filter_bits" value="0" /> <conditional name="ont_integration"> <param name="ont_integration_selector" value="set" /> <param name="ul" value="nanopore.fasta.gz" /> @@ -509,7 +519,7 @@ <test expect_num_outputs="6"> <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" /> <param name="mode_selector" value="standard" /> - <param name="filter_bits" value="0" /> + <param name="filter_bits" value="0" /> <param name="log_out" value="yes" /> <conditional name="ont_integration"> <param name="ont_integration_selector" value="set" /> @@ -522,6 +532,14 @@ </assert_contents> </output> </test> + <!-- TEST 14: test bin files --> + <test expect_num_outputs="6"> + <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" /> + <param name="filter_bits" value="0" /> + <param name="mode_selector" value="standard" /> + <param name="bins_out" value="yes" /> + <output_collection name="bin_files" type="list" count="3" /> + </test> </tests> <help><![CDATA[ .. class:: infomark @@ -529,7 +547,7 @@ **HiFiASM - a fast de novo assembler** -Hifiasm is a fast haplotype-resolved de novo assembler for PacBio Hifi reads. It can assemble a human genome in several hours and works with the California redwood genome, one of the most complex genomes sequenced so far. Hifiasm can produce primary/alternate assemblies of quality competitive with the best assemblers. It also introduces a new graph binning algorithm and achieves the best haplotype-resolved assembly given trio data. +Hifiasm is a fast haplotype-resolved *de novo* assembler for PacBio Hifi reads. It can assemble a human genome in several hours and works with the California redwood genome, one of the most complex genomes sequenced so far. Hifiasm can produce primary/alternate assemblies of quality competitive with the best assemblers. It also introduces a new graph binning algorithm and achieves the best haplotype-resolved assembly given trio data. ---- @@ -537,8 +555,8 @@ **Assembly mode** -- *Standard* -- *Trio* When parental short reads are available, hifiasm can generate a pair of haplotype-resolved assemblies with trio binning. +- *Standard*: Standard assembly can be run in pseudohaplotype mode, or with Hi-C phasing using Hi-C reads from the same individual. +- *Trio*: When parental short reads are available, hifiasm can generate a pair of haplotype-resolved assemblies with trio binning. ---- @@ -546,12 +564,13 @@ **Outputs** -Non Trio assembly: +Non-Trio assembly: -- Haplotype-resolved raw unitig graph in GFA format. This graph keeps all haplotype information, including somatic mutations and recurrent sequencing errors. -- Haplotype-resolved processed unitig graph without small bubbles : Small bubbles might be caused by somatic mutations or noise in data, which are not the real haplotype information. -- Primary assembly contig graph : This graph collapses different haplotypes. -- Alternate assembly contig graph : This graph consists of all assemblies that are discarded in primary contig graph. +- Haplotype-resolved raw unitig graph: This graph keeps all haplotype information, including somatic mutations and recurrent sequencing errors. +- Haplotype-resolved processed unitig graph without small bubbles: This graph 'pops' small bubbles in the raw unitig graph; small bubbles might be caused by somatic mutations or noise in data, which are not the real haplotype information. +- Primary assembly contig graph: This graph includes a complete assembly with long stretches of phased blocks, though there may be some haplotype collapse. +- Alternate assembly contig graph: This graph consists of all contigs that are discarded from the primary contig graph. +- [hap1]/[hap2] contig graph: Each graph consists of phased contigs (output only with Hi-C phasing enabled). Trio assembly: