<tool id="cfsan_cronology" name="cronology" version="0.2.0+galaxy23.1">
    <description>An automated workflow for Cronobacter isolate assembly, sequence typing and traceback.</description>
    <requirements>
        <container type="docker">quay.io/biocontainers/nextflow:24.04.3--hdfd78af_0</container>
    </requirements>    
    <version_command>nextflow -version</version_command>
    <command detect_errors="exit_code"><![CDATA[
	mkdir -p cpipes-input || exit 1;
    echo -e 'We attempted to create a tree and upload to microreact.org. The following is the log of that attempt\\nand contains the URL if it was successful.\\n\\n' > upload_to_microreact.txt || exit 1;
    pwd_path=\$(pwd);
    #import re
    #if (str($input_read_type_cond.input_read_type) == "single_long"):
	    #for _, $unpaired in enumerate($input_read_type_cond.input):
            #set read1 = str($unpaired.name)
            #if not str($unpaired.name).endswith(('.fastq', '.fastq.gz')):
                #set read1_ext = re.sub('fastqsanger', 'fastq', str($unpaired.ext))
                #set read1 = str($unpaired.name) + str('.') + $read1_ext
            #end if
            ln -sf '$unpaired' './cpipes-input/$read1';
	    #end for
    #elif (str($input_read_type_cond.input_read_type) == "paired"):
	    #for _, $pair in enumerate($input_read_type_cond.input_pair)
            #set read_R1 = re.sub('\:forward', '_forward', str($pair.forward.name))
            #set read_R2 = re.sub('\:reverse', '_reverse', str($pair.reverse.name))
            #set read_R1_ext = re.sub('fastqsanger', 'fastq', str($pair.forward.ext))
            #set read_R2_ext = re.sub('fastqsanger', 'fastq', str($pair.reverse.ext))
            #if not str($pair.forward.name).endswith(('.fastq', '.fastq.gz')):
	            #set read_R1 = $read_R1 + str('.') + $read_R1_ext
            #end if
            #if not str($pair.reverse.name).endswith(('.fastq', '.fastq.gz')):
                #set read_R2 = $read_R2 + str('.') + $read_R2_ext
            #end if
	        ln -sf '$pair.forward' './cpipes-input/$read_R1';
	        ln -sf '$pair.reverse' './cpipes-input/$read_R2';
	    #end for
    #end if
	$__tool_directory__/0.1.0/cpipes
    --pipeline cronology
    --input \${pwd_path}/cpipes-input
	--output \${pwd_path}/cpipes-output
    --fq_suffix '${input_read_type_cond.fq_suffix}'
    #if (str($input_read_type_cond.input_read_type) == "single_long"):
        --fq_single_end true
    #elif (str($input_read_type_cond.input_read_type) == "paired"):
        --fq_single_end false --fq2_suffix '${input_read_type_cond.fq2_suffix}'
    #end if
    --ref_acc $refgenome
    --tuspy_n $tuspy_n
	--fq_filename_delim '${fq_filename_delim}'
	--fq_filename_delim_idx $fq_filename_delim_idx
	-profile gxkubernetes;
    mv './cpipes-output/cronology-multiqc/multiqc_report.html' './multiqc_report.html' || exit 1;
    mv './cpipes-output/mashtree/hitsTree.dnd' './hitsTree.newick' > || exit 1;
    cat ./cpipes-output/upload_microreact/microreact_url.txt >> upload_to_microreact.txt || exit 1;
    ]]></command>
    <inputs>
        <conditional name="input_read_type_cond">
            <param name="input_read_type" type="select" label="Select the read collection type">
                <option value="single_long" selected="true">Single-End short reads</option>
                <option value="paired">Paired-End short reads</option>
            </param>
            <when value="single_long">
                <param name="input" type="data_collection" collection_type="list" format="fastq,fastq.gz"
                    label="Dataset list of unpaired short reads or long reads" />
                <param name="fq_suffix" value=".fastq.gz" type="text" label="Suffix of the Single-End FASTQ"/>
            </when>
            <when value="paired">
                <param name="input_pair" type="data_collection" collection_type="list:paired" format="fastq,fastq.gz" label="List of Dataset pairs" />
                <param name="fq_suffix" value="_R1_001.fastq.gz" type="text" label="Suffix of the R1 FASTQ"
                    help="For any data sets downloaded from NCBI into Galaxy, change this to _forward.fastq.gz suffix."/>
                <param name="fq2_suffix" value="_R2_001.fastq.gz" type="text" label="Suffix of the R2 FASTQ"
                    help="For any data sets downloaded from NCBI into Galaxy, change this to _reverse.fastq.gz suffix."/>
            </when>
        </conditional>
        <param name="refgenome" optional="true" value="GCF_003516125" type="text"
                label="NCBI reference genome accession"
                help="Is the reference genome other than Cronobacter sakazakii? Reference genome FASTA is used as a model for gene prediction. DO NOT ENTER THE DECIMAL PART (Ex: GCF_003516125.1)." />
        <param name="tuspy_n" optional="true" value="2" type="integer" label="Enter the number of top unique hits to retain after initial MASH screen step"
            help="These hits will be used to build a genome distance based tree for your experiment run. Default value of 2 is suitable for almost all scenarios."/>
        <param name="fq_filename_delim" type="text" value="_" label="File name delimitor by which samples are grouped together (--fq_filename_delim)" 
            help="This is the delimitor by which samples are grouped together to display in the final MultiQC report. For example, if your input data sets are mango_replicate1.fastq.gz, mango_replicate2.fastq.gz, orange_replicate1_maryland.fastq.gz, orange_replicate2_maryland.fastq.gz, then to create 2 samples mango and orange, the value for --fq_filename_delim would be _ (underscore) and the value for --fq_filename_delim_idx would be 1, since you want to group by the first word (i.e. mango or orange) after splitting the filename based on _ (underscore)."/>
        <param name="fq_filename_delim_idx" type="integer" value="1" label="File name delimitor index (--fq_filename_delim_idx)" />
    </inputs>
    <outputs>
        <data name="multiqc_report" format="html" label="cronology: MultiQC Report on ${on_string}" from_work_dir="multiqc_report.html"/>
        <data name="mashtree" format="nhx" label="cronology: Genome distance based tree on ${on_string}" from_work_dir="hitsTree.newick"/>
        <data name="microreact" format="txt" label="cronology: Tree result from microreact.org ${on_string}" from_work_dir="upload_to_microreact.txt"/>
        <collection name="itol_metadata" type="list" label="cronology: iTOL Metadata: ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.*)\.txt" ext="txt" directory="./cpipes-output/cat_unique" match_relative_path="true" />
        </collection>
        <collection name="gene_models" type="list" label="cronology: Predicted gene models: ${on_string}">
            <discover_datasets pattern=".*\/(?P&lt;name&gt;.*)\.gff" ext="gff" directory="./cpipes-output/prokka" recurse="true" match_relative_path="true" />
        </collection>
        <collection name="assemblies" type="list" label="cronology: Polished genome assemblies: ${on_string}">
            <discover_datasets pattern="(?P&lt;name&gt;.*)\.fa" ext="fa" directory="./cpipes-output/polypolish" match_relative_path="true" />
        </collection>
    </outputs>
    <tests>
        <!--Test 01: long reads-->
        <test expect_num_outputs="2">
            <param name="input">
                <collection type="list">
                    <element name="FAL11127.fastq.gz" value="FAL11127.fastq.gz" />
                    <element name="FAL11341.fastq.gz" value="FAL11341.fastq.gz" />
                    <element name="FAL11342.fastq.gz" value="FAL11342.fastq.gz" />
                </collection>
            </param>
            <param name="fq_suffix" value=".fastq.gz"/>
            <output name="multiqc_report" file="multiqc_report.html" ftype="html" compare="sim_size"/>
            <!-- <output name="assembled_mags" file="FAL11127.assembly_filtered.contigs.fasta" ftype="fasta" compare="sim_size"/> -->
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Purpose**

cronology is an automated workflow for Cronobacter isolate assembly,
sequencing typing and traceback. The workflow version 0.1.0 takes in single-end
or paired-end Illumina short read data, performs QC using fastp, assembly and polish using shovill and polypolish
and whole genome distance based clustering using mashtree based on NCBI Pathogen Detection DB for Cronobacter.

It is written in Nextflow and is part of the modular data analysis pipelines (CFSAN PIPELINES or CPIPES for short) at CFSAN.


----

.. class:: infomark

**Testing and Validation**

The CPIPES - cronology Nextflow pipeline has been wrapped to make it work in Galaxy. 
All the testing has been done on the command line on the CFSAN Raven2 HPC Cluster.


----

.. class:: infomark

**Outputs**

The main output files are:

    ::

        - MultiQC Report: Contains a brief summary report including any serotyping and AMR result tables.
                          Please note that due to MultiQC customizations, the preview (eye icon) will not
                          work within Galaxy for the MultiQC report. Please download the file by clicking
                          on the floppy icon and view it in your browser on your local desktop/workstation.
                          You can export the tables and plots from the downloaded MultiQC report.
        - Polished de novo assemblies (FASTA) for each sample.
        - Genome annotations (GFF) for each sample.
        - Whole genome distance based clustering tree (Newick).
        - Additional metadata useful for uploading the Newick tree into iTOL. 

  ]]></help>
    <citations>
        <citation type="bibtex">
            @article{cronology,
            author = {Konganti, Kranti},
            year = {2024},
            month = {May},
            title = {cronology: An automated workflow for Cronobacter isolate assembly, sequence typing and traceback},
            journal = {Unpublished},
            doi = {xx.xxxx/xxxxx.2024.xxxxxxxxxx},
            url = {https://github.com/CFSAN-Biostatistics/cronology}}
        </citation>
    </citations>
</tool>