sylph_profile.xml

<tool id="sylph_profile" name="sylph profile" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0">
    <expand macro='description'/>
    <macros>
       <import>macros.xml</import> 
    </macros>
    <expand macro='requirements'/>
    <command detect_errors='exit_code'><![CDATA[
#import re
##SYMLINK SYLPH DB
@DB_SELECTOR@
##Single input
        #if $sketch.type == 'single':
            @SINGLE_INPUT@
##Single group
        #else if $sketch.type == 'single_group':
            @SINGLE_GROUP@
##Paired input
        #else if $sketch.type == 'paired':
            @PAIRED@
##Paired  group
        #else if $sketch.type == 'paired_group':
            @PAIRED_GROUP@
        #end if
##SKETCHING
        sylph sketch
        #if $sketch.type == 'single':
            $input
        #else if $sketch.type == 'single_group':
            -r $input
        #else if $sketch.type == 'paired': 
            -1 $read1
            -2 $read2
        #else if $sketch.type == 'paired_group': 
            -1 $read1
            -2 $read2
        #end if
        -t \${GALAXY_SLOTS:-4}
        -d sylph_sketches &&
##MAIN COMMAND
        sylph profile
        database.syldb
        sylph_sketches/*.sylsp
        #if $min_num_kmers:
            --min-number-kmers ${min_num_kmers}
        #end if
        -t \${GALAXY_SLOTS:-4}
        -o $output

        #if $outputs:
            #if $database_select.select == 'cached':
                && ln -s '$database_select.sylph_database.fields.path/database.tsv.gz' 'database.tsv.gz'
            #else:
                && ln -s '$database_select.metadata' 'database.tsv.gz'
            #end if
            && python '$__tool_directory__/sylph_to_taxprof.py' -s $output -m database.tsv.gz -o metaphlan_
            #if 'krona' in $outputs:
                && python '$__tool_directory__/sylphformatoutput.py' format_for_krona --metaphlan_output *.sylphmpa --krona_output krona.tsv
                && mkdir krona_out && mv *krona.tsv krona_out
            #end if
            && mkdir metaphlan_out && mv *.sylphmpa metaphlan_out
        #end if
    ]]></command>
    <inputs>
        <conditional name="sketch">
            <param name="type" type="select" label="Select the type of reads used">
                <option value="single">Individual single-end reads</option>
                <option value="single_group">Group of single-ended reads</option>
                <option value="paired">One set of paired-end reads</option>
                <option value="paired_group"> Group of paired-ended reads</option>
            </param>
        <!-- Only permitting fastq as tool input only allows fastq and fastq.gz as file ext -->
            <when value="single">
                <param name="input" type="data" format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" label="Single-end input reads"/>
            </when>
            <when value="single_group">
                <param name="input" type="data" format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" label="Single-end input reads" multiple="true"/>
            </when>            
            <when value="paired">
                <param name="input_1" type="data" format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" label="Paired-end input reads 1"/>
                <param name="input_2" type="data" format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" label="Paired-end input reads 2"/>
            </when>
            <when value="paired_group">
                <param name="input" type="data_collection" format="fastq,fastq.gz,fastqsanger,fastqsanger.gz" label="Paired-end input reads" collection_type="paired"/>
            </when>
        </conditional>
        <param name="min_num_kmers" type="integer" min="1" value="50" label="Minimum number of k-mers for Sylph to output a result." help="States the minimum number of k-mers needed for sylph to output a result.This is (approximately) the contig length divided by -c. With default settings, --min-number-kmers 10 can work with contigs ~2500 bp. For smaller contigs, consider -c 100."/>
        <expand macro="output_format"/>
        <expand macro="input_database"/>
    </inputs>
    <outputs>
        <data format="tabular" name="output" label="${tool.name} on ${on_string}"/>
        <collection  name="metaphlan_out" type="list" label="${tool.name} on ${on_string}: MetaPhlAn-style output">
            <filter> outputs and 'metaphlan' in outputs</filter>
            <discover_datasets pattern="__name_and_ext__"  directory="metaphlan_out/" />
        </collection>
        <collection  name="krona_out" type="list" label="${tool.name} on ${on_string}: Krona-useable output">
            <filter>outputs and 'krona' in outputs</filter>
            <discover_datasets pattern="__name_and_ext__"  directory="krona_out/" />
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="sylph_database" value="sylph_db"/>
            <conditional name="sketch">
                <param name="type" value="single"/>
                <param name="input" value="single_1.fastq.gz" ftype="fastq"/>
            </conditional>
            <output name="output" value="output_1.tabular"/>
        </test>

        <!--Test 2  Group of Single-end Inputs-->
        <test expect_num_outputs="1">
            <param name="sylph_database" value="sylph_db"/>
            <conditional name="sketch">
                <param name="type" value="single_group"/>
                <param name="input" value="single_1.fastq.gz,single_2.fastq.gz" ftype="fastq"/>
            </conditional>
            <param name="min_num_kmers" value="49"/>
            <output name="output" value="output_2.tabular" compare="sim_size"/>
        </test>

        <!-- Test 3 Paired-end reads -->
        <test expect_num_outputs="1">
            <param name="sylph_database" value="sylph_db"/>
            <conditional name="sketch">
                <param name="type" value="paired"/>
                <param name="input_1" value="test R1.fq" ftype="fastq"/>
                <param name="input_2" value="test R2.fq" ftype="fastqsanger"/>
            </conditional>
            <output name="output" value="output_3.tabular"/>
        </test>

        <!-- Test 4 Collection of Paired-end Reads -->
        <test expect_num_outputs="1">
            <param name="sylph_database" value="sylph_db"/>
            <conditional name="sketch">
                <param name="type" value="paired_group"/>
                <param name="input">
                    <collection type="paired" name="test">
                        <element name="forward" ftype="fastq" value="test R1.fq"/>
                        <element name="reverse" ftype="fastq" value="test R2.fq"/>
                    </collection>
                </param>
            </conditional>
            <output name="output" value="output_4.tabular"/>
        </test>
        <!-- Test 5 output format conversion -->
        <test expect_num_outputs="3">
            <param name="sylph_database" value="sylph_db"/>
            <conditional name="sketch">
                <param name="type" value="single"/>
                <param name="input" value="single_1.fastq.gz" ftype="fastq"/>
            </conditional>
            <param name="outputs" value="metaphlan,krona"/>
            <!-- With test data, output will be empty for krona tool so only check against metaphlan converter, but keep num_outputs-->
            <output_collection name="metaphlan_out" type="list">
                <element name="metaphlan_single_1.fastq.gz" value="test.sylphmpa"/>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
**What is sylph?**

Sylph is an extremely fast and memory efficient program for profiling and searching metagenomic samples against databases. It is 10-100x faster than other popular software such as MetaPhlAn or Kraken and more memory efficient too. 

**What can sylph do?**

- Profile metagenomes: sylph can calculate the abundances of genomes in a sample using a reference database. This is the same type of output as Kraken or MetaPhlAn. 
- Search genomes against metagenomes: sylph can check if a genome is contained in your sample (e.g. is this E. coli genome in my sample?).
- ANI querying: sylph can estimate the containment average nucleotide identity (ANI) of a reference genome to the genomes in your sample.
- Use custom reference databases: Eukaryotes, viruses, and any collections of fasta files are ok.
- Long-reads are usable: sylph is primarily optimized for short-reads, but it can utilize nanopore or PacBio reads with high precision.
- Calculate coverage: sylph can estimate the coverage (not just the abundance) of genomes in your database.

`[See here for more information on what sylph can and can not do]. <https://github.com/bluenote-1577/sylph/wiki/Introduction:-what-is-sylph-and-how-does-it-work%3F>`_

----

**Output**

Sylph profile outputs a TSV (tab-separated values) file. Each row is one genome detected in the metagenome sample.
    - Sample_file: the filename of the reads/sample.
    - Genome_file: the filename of the detected genome.
    - Taxonomic_abundance: normalized taxonomic abundance as a percentage. Coverage-normalized - same as MetaPhlAn abundance
    - Sequence_abundance: normalized sequence abundance as a percentage. The "number of reads" assigned to each genome - same as Kraken abundance
    - Adjusted_ANI: adjusted containment ANI estimate.
        - If coverage adjustment is possible (cov is < 3x cov): returns coverage-adjusted ANI
        - If coverage is too low/high: returns Naive_ANI (see below)
    - Eff_cov/True_cov: an estimate of the effective, or if -u specified, the true coverage. Always a decimal number.
    - ANI_5-95_percentile: [5%,95%] confidence intervals. Not always a decimal number.
        - If coverage adjustment is possible: float-float e.g. 98.52-99.55
        - If coverage is too low/high: NA-NA is given.
    - Eff_lambda: estimate of the effective coverage parameter. Not always a decimal number.
        - If coverage adjustment is possible: lambda estimate is given
        - If coverage is too low/high: LOW or HIGH is output
    - Lambda_5-95_percentile: [5%, 95%] confidence intervals for lambda. Same format rules as ANI_5-95_percentile.
    - Median_cov: median k-mer multiplicity for k-mers with >= 1 multiplicity.
    - Mean_cov_geq1: mean k-mer multiplicity for k-mers with >= 1 multiplicity.
    - Containment_ind: int/int showing the containment index (number of k-mers found in sample divided by total k-mers), e.g. 959/1053.
    - Naive_ANI: containment ANI without coverage adjustment.
    - kmers_reassigned: the number of k-mers reassigned away from the genome.
    - Contig_name: name of the first contig in the genome

Additional files are able to be output. The metaphlan-style output is formatted similarly to that output by the `[Metaphlan <toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.1.1+galaxy3>`_ 
This output is *NOT* compatible with Krona directly. For that, please select the Krona-style output option.


    ]]></help>
    <expand macro="citation"/>
</tool>