Skip to content

Update chewbbaca with manual species ID #7870

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
nilchia wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Update chewbbaca with manual species ID #7870

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
39dbfd8
update chewi
nilchia Apr 9, 2026
7569fad
bump version
nilchia Apr 9, 2026
e6b3f94
add conditional
nilchia Apr 9, 2026
480d9cb
add unzipp
nilchia Apr 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions tools/chewbbaca/AlleleCall.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,16 +53,16 @@
-i 'input' -g 'schema/schema_seed/' -o 'output'
]]></command>
<inputs>
<param format="fasta" name="input_file" type="data" multiple="true" label="Genome assemblies in FASTA format"/>
<param format="zip" name="input_schema" type="data" label="Schema Files in zip format" help="The schema directory contains the loci FASTA files and a folder named 'short' that contains the FASTA files with the loci representative alleles."/>
<param name="input_file" type="data" format="fasta" multiple="true" label="Genome assemblies in FASTA format"/>
<param name="input_schema" type="data" format="zip" label="Schema Files in zip format" help="The schema directory contains the loci FASTA files and a folder named 'short' that contains the FASTA files with the loci representative alleles."/>
<section name="advanced" title="Advanced options">
<param argument="--genes-list" type="data" format="txt" label="Gene list" optional="true" />
<param argument="--training-file" type="data" format="binary" label="Prodigal training file" optional="true" help="By default, gets the training file from the schema"/>
<param argument="--cds-input" type="boolean" truevalue="--cds-input" falsevalue="" checked="false" label="CDS input" optional="true"/>
<param argument="--blast-score-ratio" type="float" min="0.0" max="1.0" value="" optional="true" label="BLAST Score Ratio value" />
<param argument="--minimum-length" type="integer" min="0" value="" optional="true" label="Minimum sequence length value"/>
<param argument="--translation-table" type="integer" min="0" value="" optional="true" help="Must match the genetic code used to create the training file (default: uses value defined in schema config)." label="Genetic code used to predict genes and to translate coding sequences"/>
<param argument="--size-threshold" type="float" min="0" value="" optional="true" label="CDS size variation threshold"/>
<param argument="--blast-score-ratio" type="float" min="0.0" max="1.0" optional="true" label="BLAST Score Ratio value" />
<param argument="--minimum-length" type="integer" min="0" optional="true" label="Minimum sequence length value"/>
<param argument="--translation-table" type="integer" min="0" optional="true" help="Must match the genetic code used to create the training file (default: uses value defined in schema config)." label="Genetic code used to predict genes and to translate coding sequences"/>
<param argument="--size-threshold" type="float" min="0" optional="true" label="CDS size variation threshold"/>
<param argument="--no-inferred" type="boolean" truevalue="--no-inferred" falsevalue="" checked="false" optional="true" label="Add the sequences of inferred alleles (INF) to the schema" help="Use this parameter if the schema is being accessed by multiple processes/users simultaneously." />
<param argument="--prodigal-mode" type="select" optional="true" label="Prodigal Mode" help="&quot;single&quot; for finished genomes, reasonable quality draft genomes and big viruses. &quot;meta&quot; for metagenomes, low quality draft genomes, small viruses, and small plasmids">
<option value="single" selected="true">
Expand All @@ -76,7 +76,7 @@
<option value="1">Only exact matches at DNA level</option>
<option value="2">Exact matches at DNA and Protein level </option>
<option value="3">Exact matches and minimizer-based clustering to find similar alleles based on BSR+0.1 </option>
<option value="4" selected="true">Exact matches and minimizer-based clustering to find similar alleles based on BSR+0.1 </option>
<option value="4" selected="true">Run the full process to find exact matches and similar matches based on BSR value</option>
</param>
</section>
<section name="output" title="Output Options">
Expand Down
25 changes: 4 additions & 21 deletions tools/chewbbaca/DownloadSchema.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,32 +6,15 @@
<expand macro="requirements" />
<command detect_errors="exit_code"><![CDATA[
chewBBACA.py DownloadSchema
-sp $species_id
-sp $species_id
-sc $schema_id
-o 'output' &&
## The output is named based on the species name. Rename it to schema_seed so it is compatible for other chewbbaca tools.
mv output/* 'schema_seed' &&
zip -r schema_seed.zip 'schema_seed'
]]></command>
<inputs>
<param argument="--species-id" type="select" label="Species ID">
<option value="1">Streptococcus pyogenes</option>
<option value="2">Acinetobacter baumannii</option>
<option value="3">Arcobacter butzleri</option>
<option value="4">Campylobacter jejuni</option>
<option value="5">Escherichia coli</option>
<option value="6">Listeria monocytogenes</option>
<option value="7">Yersinia enterocolitica</option>
<option value="8">Salmonella enterica</option>
<option value="9">Streptococcus agalactiae</option>
<option value="10">Brucella melitensis</option>
<option value="11">Brucella</option>
<option value="12">Clostridium perfringens</option>
<option value="13">Clostridium chauvoei</option>
<option value="14">Bacillus anthracis</option>
<option value="15">Klebsiella oxytoca</option>
<option value="16">Clostridium neonatale</option>
</param>
<expand macro="species_id"/>
<!-- Currently,the schema id can only be set to 1. Maybe in the next versions other values possible -->
<param argument="--schema-id" type="integer" min="1" value="1" label="Schema ID"/>
</inputs>
Expand All @@ -57,13 +40,13 @@
</test>
</tests>
<help>

chewBBACA is a software suite for the creation and evaluation of core genome and whole genome MultiLocus Sequence Typing (cg/wgMLST) schemas and results.

The DownloadSchema module enables the download of schemas from the Chewie-NS server.


.. class:: infomark
.. class:: infomark

**Note**

Expand Down
8 changes: 4 additions & 4 deletions tools/chewbbaca/ExtractCgMLST.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,14 +9,14 @@
--t $threshold
#if $genes2remove:
--r '$genes2remove'
#end if
#end if
#if $genomes2remove:
--g '$genomes2remove'
#end if
#end if
-i '$input_file' -o 'output'
]]></command>
<inputs>
<param argument="--input-file" type="data" label="Allelic Profiles" format="tabular"/>
<param argument="--input-file" type="data" format="tabular" label="Allelic Profiles"/>
<section name="advanced" title="Advanced options">
<param argument="--genomes2remove" type="data" format="txt" label="Genomes/rows to remove from the matrix" optional="true" help="One genome identifier per line"/>
<param argument="--threshold" type="text" value="0.95 0.99 1" label="threshold" help="Genes that constitute the core genome must be in a proportion of genomes that is at least equal to this value. Users can provide multiple values as a space-separated list.">
Expand Down Expand Up @@ -50,7 +50,7 @@
<help>
chewBBACA is a software suite for the creation and evaluation of core genome and whole genome MultiLocus Sequence Typing (cg/wgMLST) schemas and results.

cgMLST schemas are defined as the set of loci that are present in all strains under analysis or, due to sequencing/assembly limitations, >95% of strains analyzed. In order to have a robust definition of a cgMLST schema for a given bacterial species, a set of representative strains of the diversity of a given species should be selected.
cgMLST schemas are defined as the set of loci that are present in all strains under analysis or, due to sequencing/assembly limitations, >95% of strains analyzed. In order to have a robust definition of a cgMLST schema for a given bacterial species, a set of representative strains of the diversity of a given species should be selected.

.. class:: infomark

Expand Down
50 changes: 34 additions & 16 deletions tools/chewbbaca/NSStats.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,39 +6,57 @@
<expand macro="requirements" />
<command detect_errors="exit_code"><![CDATA[
chewBBACA.py NSStats
-m $mode
#if $species_id != ""
--sp $species_id
#end if
#if $schema_id != ""
--sc $schema_id
#if $species_or_schemas.select_mode == "species"
-m species
#else
-m schemas
--sp $species_id
#if $schema_id != ""
--sc $schema_id
#end if
#end if
> 'NSStats.txt'
]]></command>
<inputs>
<param argument="--mode" type="select" label="Mode" optional="false">
<option value="species">species</option>
<option value="schemas">schemas</option>
</param>
<param argument="--species-id" type="select" label="Species ID" value="" optional="true">
<expand macro="species_id"/>
</param>
<!-- Currently,the schema id can only be set to 1. Maybe in the next versions other values possible -->
<param argument="--schema-id" type="integer" min="1" value="" label="Schema ID" optional="true"/>
<conditional name="species_or_schemas">
<param name="select_mode" type="select" label="Retrieve information for">
<option value="species">Species</option>
<option value="schemas">Schemas</option>
</param>
<when value="species"/>
<when value="schemas">
<expand macro="species_id"/>
<param argument="--schema-id" type="integer" min="1" label="Schema ID" optional="true"/>
</when>
</conditional>
</inputs>
<outputs>
<data format="txt" name="NSStats" from_work_dir="NSStats.txt" label="${tool.name}"/>
</outputs>
<tests>
<test expect_exit_code="0">
<param name="mode" value="species" />
<conditional name="species_or_schemas">
<param name="select_mode" value="species"/>
</conditional>
<output name="NSStats">
<assert_contents>
<has_text_matching expression="Streptococcus pyogenes\s+\d+\s+1\s+\d+\s+\d+"/>
<has_text_matching expression="Clostridium neonatale\s+\d+\s+1\s+\d+\s+\d+"/>
</assert_contents>
</output>
</test>
<test expect_exit_code="0">
<conditional name="species_or_schemas">
<param name="select_mode" value="schemas"/>
<param name="species_id" value="1"/>
</conditional>
<output name="NSStats">
<assert_contents>
<has_text_matching expression="Streptococcus pyogenes"/>
<has_text_matching expression="wgMLST"/>
</assert_contents>
</output>
</test>
</tests>
<help>
chewBBACA is a software suite for the creation and evaluation of core genome and whole genome MultiLocus Sequence Typing (cg/wgMLST) schemas and results.
Expand Down
25 changes: 6 additions & 19 deletions tools/chewbbaca/macros.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,15 @@
<macros>
<token name="@TOOL_VERSION@">3.3.10</token>
<token name="@VERSION_SUFFIX@">1</token>
<token name="@PROFILE@">24.2</token>
<token name="@VERSION_SUFFIX@">2</token>
<token name="@PROFILE@">25.0</token>
<xml name="requirements">
<requirements>
<requirement type="package" version="@TOOL_VERSION@">chewbbaca</requirement>
<requirement type="package" version="2.15.0">blast</requirement>
<requirement type="package" version="3.0">zip</requirement>
<requirement type="package" version="2.1.11">fasttree</requirement>
<!-- Unzip is needed because the unzip that comes with Busybox docker image can support to standard zip files with max of 4G in size. If it is larger than 4GB it comes under zip64 specification but also has .zip extension. -->
<requirement type="package" version="6.0">unzip</requirement>
<yield/>
</requirements>
</xml>
Expand All @@ -17,22 +19,7 @@
</citations>
</xml>
<xml name="species_id">
<option value="1">Streptococcus pyogenes</option>
<option value="2">Acinetobacter baumannii</option>
<option value="3">Arcobacter butzleri</option>
<option value="4">Campylobacter jejuni</option>
<option value="5">Escherichia coli</option>
<option value="6">Listeria monocytogenes</option>
<option value="7">Yersinia enterocolitica</option>
<option value="8">Salmonella enterica</option>
<option value="9">Streptococcus agalactiae</option>
<option value="10">Brucella melitensis</option>
<option value="11">Brucella</option>
<option value="12">Clostridium perfringens</option>
<option value="13">Clostridium chauvoei</option>
<option value="14">Bacillus anthracis</option>
<option value="15">Klebsiella oxytoca</option>
<option value="16">Clostridium neonatale</option>
<param argument="--species-id" type="integer" min="1" value="1" optional="False" label="Species ID" help="To see avaialble species and their IDs, please run chewBBACA NSStats with Mode = species"/>
</xml>
<token name="@COMMON_INPUT@">
--bsr $blast_score_ratio
Expand All @@ -41,7 +28,7 @@
--st $size_threshold
</token>
<xml name="common_param">
<param argument="--blast_score-ratio" type="float" min="0.0" max="1.0" value="0.6" label="BLAST Score Ratio value" />
<param argument="--blast_score-ratio" type="float" min="0.0" max="1.0" value="0.6" label="BLAST Score Ratio value" />
<param argument="--translation-table" type="integer" min="0" value="11" label="Genetic code used to predict genes and to translate coding sequences"/>
<param argument="--size-threshold" type="float" min="0" value="0.2" label="CDS size variation threshold"/>
</xml>
Expand Down
Loading