add COMEBin utility script #7285
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,14 @@ | ||
| name: comebin_bam | ||
| owner: iuc | ||
| description: Generate bam file for COMEBin | ||
| homepage_url: https://github.com/ziyewang/COMEBin | ||
| long_description: | | ||
| COMEBin, a binning method based on contrastive multi-view representation learning. | ||
| COMEBin utilizes data augmentation to generate multiple fragments (views) of each | ||
| contig and obtains high-quality embeddings of heterogeneous features | ||
| (sequence coverage and k-mer distribution) through contrastive learning. | ||
| This script generate the bam file input for COMEBin. | ||
| remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/main/tools/comebin_bam/ | ||
| type: unrestricted | ||
| categories: | ||
| - Metagenomics |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,175 @@ | ||
| <tool id="comebin_bam" name="Generate BAM file for COMEBin" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> | ||
| <description>COMEBin utility script to generate BAM files using modified MetaWRAP</description> | ||
| <macros> | ||
| <import>macros.xml</import> | ||
| </macros> | ||
| <expand macro="requirements"/> | ||
| <command detect_errors="exit_code"> | ||
| <![CDATA[ | ||
|
|
||
| mkdir 'outputs' && | ||
|
|
||
| #if $assembly.ext.endswith('.gz'): | ||
| ln -s '$assembly' 'assembly.fasta.gz' && | ||
| gunzip 'assembly.fasta.gz' && | ||
| #else: | ||
| ln -s '$assembly' 'assembly.fasta' && | ||
| #end if | ||
|
|
||
| #if $read_typ.is_select == "normal": | ||
| #if $input_typ.is_select == "paired": | ||
| #if $paired_reads.forward.ext.endswith('.gz'): | ||
| ln -s '$paired_reads.forward' 'read_1.fastq.gz' && | ||
| ln -s '$paired_reads.reverse' 'read_2.fastq.gz' && | ||
| gunzip 'read_1.fastq.gz' && | ||
| gunzip 'read_2.fastq.gz' && | ||
| #else: | ||
| ln -s '$paired_reads.forward' 'read_1.fastq' && | ||
| ln -s '$paired_reads.reverse' 'read_2.fastq' && | ||
| #end if | ||
| #else: | ||
| #if $forward.ext.endswith('.gz'): | ||
| ln -s '$forward' 'read_1.fastq.gz' && | ||
| ln -s '$reverse' 'read_2.fastq.gz' && | ||
| gunzip 'read_1.fastq.gz' && | ||
| gunzip 'read_2.fastq.gz' && | ||
| #else: | ||
| ln -s '$forward' 'read_1.fastq' && | ||
| ln -s '$reverse' 'read_2.fastq' && | ||
| #end if | ||
| #end if | ||
| #else: | ||
| #if $single_reads.ext.endswith('.gz'): | ||
| ln -s '$single_reads' 'read.fastq.gz' && | ||
| gunzip 'read.fastq.gz' && | ||
| #else: | ||
| ln -s '$single_reads' 'read.fastq' && | ||
| #end if | ||
| #end if | ||
|
|
||
| gen_cov_file.sh | ||
| -a 'assembly.fasta' | ||
| -o 'outputs' | ||
| -t \${GALAXY_SLOTS:-1} | ||
| -l ${length} | ||
| #if $read_typ.is_select == "normal": | ||
| 'read_1.fastq' | ||
| 'read_2.fastq' | ||
| #else: | ||
| --single-end 'read.fastq' | ||
| #end if | ||
|
|
||
| && | ||
|
|
||
| mv 'outputs/work_files/read.bam' '$bam_file' | ||
|
|
||
| ]]> | ||
| </command> | ||
| <inputs> | ||
| <param name="assembly" type="data" format="fasta,fasta.gz" label="Input assembly file"/> | ||
| <conditional name="read_typ"> | ||
| <param name="is_select" type="select" label="Type of reads"> | ||
| <option value="normal" selected="true">Paired-end non-interleaved</option> | ||
| <option value="single">Single-end</option> | ||
| </param> | ||
| <when value="normal"> | ||
| <conditional name="input_typ"> | ||
| <param name="is_select" type="select" label="Input type"> | ||
| <option value="paired">Paired collection</option> | ||
| <option value="single">No collection</option> | ||
| </param> | ||
| <when value="paired"> | ||
| <param name="paired_reads" type="data_collection" collection_type="paired" format="fastq,fastq.gz" label="Input paired reads collection"/> | ||
| </when> | ||
| <when value="single"> | ||
| <param name="forward" type="data" format="fastq,fastq.gz" label="Input forward reads"/> | ||
| <param name="reverse" type="data" format="fastq,fastq.gz" label="Input reverse reads"/> | ||
| </when> | ||
| </conditional> | ||
| </when> | ||
| <when value="single"> | ||
| <param name="single_reads" type="data" format="fastq,fastq.gz" label="Input single-end reads"/> | ||
| </when> | ||
| </conditional> | ||
| <param name="length" type="integer" value="1000" label="Set minimum contig length"/> | ||
| </inputs> | ||
| <outputs> | ||
| <data name="bam_file" format="bam" label="COMEBin bam file"/> | ||
| </outputs> | ||
| <tests> | ||
| <test expect_num_outputs="1"> | ||
| <param name="assembly" value="bowtie2-ref.fasta" ftype="fasta"/> | ||
| <conditional name="read_typ"> | ||
| <param name="is_select" value="normal"/> | ||
| <conditional name="input_typ"> | ||
| <param name="is_select" value="paired"/> | ||
| <param name="paired_reads"> | ||
| <collection type="paired"> | ||
| <element name="forward" value="bowtie2-fq_1.fastq" ftype="fastq"/> | ||
| <element name="reverse" value="bowtie2-fq_2.fastq" ftype="fastq"/> | ||
| </collection> | ||
| </param> | ||
| </conditional> | ||
| </conditional> | ||
| <output name="bam_file"> | ||
| <assert_contents> | ||
| <has_size size="17000" delta="1000"/> | ||
| </assert_contents> | ||
| </output> | ||
| </test> | ||
| <test expect_num_outputs="1"> | ||
| <param name="assembly" value="bowtie2-ref.fasta" ftype="fasta"/> | ||
| <conditional name="read_typ"> | ||
| <param name="is_select" value="normal"/> | ||
| <conditional name="input_typ"> | ||
| <param name="is_select" value="single"/> | ||
| <param name="forward" value="bowtie2-fq_1.fastq" ftype="fastq"/> | ||
| <param name="reverse" value="bowtie2-fq_2.fastq" ftype="fastq"/> | ||
| </conditional> | ||
| </conditional> | ||
| <output name="bam_file"> | ||
| <assert_contents> | ||
| <has_size size="17000" delta="1000"/> | ||
| </assert_contents> | ||
| </output> | ||
| </test> | ||
| <test expect_num_outputs="1"> | ||
| <param name="assembly" value="bowtie2-ref.fasta" ftype="fasta"/> | ||
| <conditional name="read_typ"> | ||
| <param name="is_select" value="normal"/> | ||
| <conditional name="input_typ"> | ||
| <param name="is_select" value="single"/> | ||
| <param name="forward" value="bowtie2-fq_1.fastq.gz" ftype="fastq.gz"/> | ||
| <param name="reverse" value="bowtie2-fq_2.fastq.gz" ftype="fastq.gz"/> | ||
| </conditional> | ||
| </conditional> | ||
| <output name="bam_file"> | ||
| <assert_contents> | ||
| <has_size size="17000" delta="1000"/> | ||
| </assert_contents> | ||
| </output> | ||
| </test> | ||
| </tests> | ||
| <help> | ||
|
There was a problem hiding this comment. What is this bash script doing? Why is bowtie2 not good enough? This looks a bit suspicious to me :) There was a problem hiding this comment. I did change the help to answer this question. This script was build using a modified version of the binning.sh of MetaWRAP and i assume the tool itself was build to fit to the these generated BAM files which means that other could work but i will not bet on this. Since BAM files are binary it is hard to see the difference but i could link you a history where 2 Comebin runs did run 1 with the BAM file generated by the the utitlity script and one with the Bowtie2 output: https://usegalaxy.eu/u/santinof/h/metagenome-assembled-genomes-mags-generation-imported-from-uploaded-file There was a problem hiding this comment. @SantaMcCloud I still feel there is still room to update the help text. As of now, it lacks quite a lot of information. Maybe you could add what does the script does? Why is this script preferred over Bowtie2? What are inputs, expected outputs? That would be much helpful for the users. There was a problem hiding this comment. I added the help section a little bit. There si not a lot left what i could write there since this scritp use case is only the preprocessing for COMEBin. Bowtie2 doesnt work here and this script output doesnt work for other binnner. If this still is not enought since i can not write more detailed since i dont know metaWRAP i have to read a bit into it. |
||
| <![CDATA[ | ||
|
|
||
| **Why using this tool instead of Bowtie2** | ||
|
|
||
| COMEBin used modified from the "binning.sh" of MetaWRAP which means a complete pipeline is running to generate BAM files fit for COMEBin to use. | ||
|
|
||
| Other BAM file tools might also work but it is recommended to use this utility script because some test showed that using Bowtie2 COMEBin always failed since certain IDs are not contain in COMEBins data. | ||
|
|
||
| This tool only serve one use case which is when using COMEBin as binner other binner can use and it is recommended to use Bowtie2 in this case. Only use this script when the binner is COMEBin! | ||
|
|
||
| **Input** | ||
|
|
||
| - Single-end reads or Paired-end (non-)interleaved reads | ||
|
|
||
| **Output** | ||
|
|
||
| - One BAM file build for use for COMEBin (no other binner can use this file so please run Bowtie2 for other binner!) | ||
|
|
||
| ]]> | ||
| </help> | ||
| <expand macro="citations"/> | ||
| </tool> | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,15 @@ | ||
| <macros> | ||
| <xml name="requirements"> | ||
| <requirements> | ||
| <requirement type="package" version="@TOOL_VERSION@">comebin</requirement> | ||
| </requirements> | ||
| </xml> | ||
| <token name="@TOOL_VERSION@">1.0.4</token> | ||
| <token name="@VERSION_SUFFIX@">0</token> | ||
| <token name="@PROFILE@">24.2</token> | ||
| <xml name="citations"> | ||
| <citations> | ||
| <citation type="doi">10.1038/s41467-023-44290-z</citation> | ||
| </citations> | ||
| </xml> | ||
| </macros> |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.