annotate lexicmap.xml @ 4:feedc23590ad draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/lexicmap commit eceb4b3a69c5a755feac55801e85eb914a669042

<tool id="lexicmap_search" name="LexicMap Search" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE_VERSION@">
    <description>nucleotide sequence tool for querying genomes</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>

    <command detect_errors="exit_code"><![CDATA[
#if $db_opts.db_opts_selector == "histdb"
    #set INDICES = [db.extra_files_path for db in $db_opts.histdb]
#else:
    #set INDICES = $db_opts.lexicmap_index.fields.path.split(",")
#end if

extract_query_ids() {
    local input_files="\$1";
    local query_ids="";
    IFS=',' read -ra files <<< "\$input_files";
    query_ids="";
    for query_file in "\${files[@]}"; do
        if file --mime-type "\$query_file" | grep -q "gzip"; then
            query_ids+=\$(zcat "\$query_file" | grep '^>' | while IFS= read -r line; do clean="\${line#>}"; echo "\${clean%% *}>"; done);
        else
            query_ids+=\$(cat "\$query_file" | grep '^>' | while IFS= read -r line; do clean="\${line#>}"; echo "\${clean%% *}>"; done);
        fi
    done;
    declare -g -a query_array=();
    IFS='>' read -r -a query_array <<< "\$query_ids";
}
&&
#for $counter, $index in enumerate($INDICES):
    lexicmap search

        --threads "\${GALAXY_SLOTS:-1}"

        ${load_whole_seeds}
        ${all}

        --index '${index}'

        #for $q in $query
            '$q'
        #end for

        --out-file 'lexicmap_search_result__index${counter}.tsv'

        --top-n-genomes '$top_n_genomes'

        --align-band '$align_band'
        --align-ext-len '$align_ext_len'
        --align-max-gap '$align_max_gap'
        --align-min-match-len '$align_min_match_len'
        --align-min-match-pident '$align_min_match_pident'
        --max-evalue '$max_evalue'
        --max-query-conc '$max_query_conc'
        --seed-max-dist '$seed_max_dist'
        --seed-max-gap '$seed_max_gap'
        --seed-min-prefix '$seed_min_prefix'
        --seed-min-single-prefix '$seed_min_single_prefix'

        #if $min_qcov_per_genome
            --min-qcov-per-genome '$min_qcov_per_genome'
        #end if

        #if $min_qcov_per_hsp
            --min-qcov-per-hsp '$min_qcov_per_hsp'
        #end if
        &&
#end for

#if len($INDICES) > 1
    counter=0 &&
    extract_query_ids '$query' &&
    for ((i=0; i<\${#query_array[@]}; i++)); do
        counter=\$((counter + 1));
        lexicmap utils merge-search-results
            --out-file "combined_result.\${counter}.tsv"
            -q "\${query_array[\$i]}" lexicmap_search_result__index*.tsv
            -j "\${GALAXY_SLOTS:-1}";
    done &&
    cat combined_result.*.tsv | awk 'NR==1 || $0 !~ /^query\tqlen\thits/' > '$out_file'
#else
    mv lexicmap_search_result__index0.tsv '$out_file'
#end if
    ]]></command>
    <inputs>
        <param name="query" type="data" format="fasta.gz" label="LexicMap query file" multiple="true"  help=""/>
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="LexiMap index source">
              <option value="histdb">From your history</option>
              <option value="db" selected="true">Locally installed LexicMap indexes</option>
            </param>
            <when value="histdb">
                <param name="histdb" type="data" format="lexicmap_index" optional="false" multiple="true" label="LexicMap index" />
            </when>
            <when value="db">
                <param name="lexicmap_index" type="select" optional="false" multiple="true" label="LexicMap index file">
                    <options from_data_table="lexicmap_index"/>
                </param>
            </when>
        </conditional>
        <param argument="--top-n-genomes" type="integer" value="0" label="Keep top N genome matches for a query (0 for all)" />
        <section name="advanced_settings" title="Advanced settings" expanded="false">
            <param argument="--align-band" value="100" type="integer" label="Align band" help="Band size in backtracking the score matrix (pseudo alignment" />
            <param argument="-align-ext-len" min="0" value="1000" type="integer" label="Align extend length" help="Extend length of upstream and downstream of seed regions, for extracting query and target sequences for alignment. It should be &lt;= contig interval length in database." />
            <param argument="-align-max-gap" value="20" type="integer" label="Align max gap" help="Maximum gap in a HSP segment." />
            <param argument="--align-min-match-len" value="50" type="integer" label="Align min match length" help="Minimum aligned length in a HSP segment." />
            <param argument="--align-min-match-pident" value="70" type="float" label="Align min match pident" help="Minimum base identity (percentage) in a HSP segment." />
            <param argument="--all" type="boolean" truevalue="--all" falsevalue="" checked="false" label="All all columns" help="Output more columns, e.g., matched sequences. Use this if you want to output blast-style format with 'lexicmap utils 2blast'." />
            <param argument="--load-whole-seeds" type="boolean" truevalue="--load-whole-seeds" falsevalue="" checked="false" label="Load whole seeds" help="Load the whole seed data into memory for faster search" />
            <param argument="--max-evalue" value="10" type="float" label="Max evalue" help="Maximum evalue of a HSP segment." />
            <param argument="--max-query-conc" value="12" type="integer" label="Max query conc" help="Maximum number of concurrent queries. Bigger values do not improve the batch searching speed and consume much memory." />
            <param argument="--min-qcov-per-genome" type="float" optional="true" help="Minimum query coverage (percentage) per genome." />
            <param argument="--min-qcov-per-hsp" type="float" optional="true" help="Minimum query coverage (percentage) per HSP." />
            <param argument="--seed-max-dist" value="1000" type="integer" label="Seed max dist" help="Minimum distance between seeds in seed chaining. It should be &lt;= contig interval length in database." />
            <param argument="--seed-max-gap" value="1000" type="integer" label="Seed max gap" help="Minimum gap in seed chaining." />
            <param argument="--seed-min-prefix" value="17" type="integer" label="Seed min prefix" help="Minimum (prefix/suffix) length of matched seeds (anchors)." />
            <param argument="--seed-min-single-prefix" value="19" type="integer" label="Seed min single prefix" help="Minimum (prefix/suffix) length of matched seeds (anchors) if there's only one pair of seeds matched." />
        </section>
    </inputs>
    <outputs>
        <data name="out_file" format="tabular">
            <actions>
                <conditional name="advanced_settings.all">
                    <when value="true">
                        <action name="column_names" type="metadata" default="Qquery,qlen,hits,sgenome,sseqid,qcovGnm,cls,hsp,qcovHSP,alenHSP,pident,gaps,qstart,qend,sstart,send,sstr,slen,evalue,bitscore,cigar,qseq,sseq,align" />
                    </when>
                    <when value="false">
                        <action name="column_names" type="metadata" default="Qquery,qlen,hits,sgenome,sseqid,qcovGnm,cls,hsp,qcovHSP,alenHSP,pident,gaps,qstart,qend,sstart,send,sstr,slen,evalue,bitscore" />
                    </when>
                </conditional>
            </actions>
        </data>
    </outputs>
    <tests>
        <!-- Test 1 - query one local index with one query -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndex1" />
            </conditional>
            <param name="query" value="lexicmap_query.fasta.gz" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result.tsv" />
        </test>
        <!-- Test 2 - query one local index with multiple query files -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndex1" />
            </conditional>
            <param name="query" value="lexicmap_query.fasta.gz,lexicmap_query2.fasta.gz" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result2.tsv" />
        </test>
        <!-- Test 3 - query two local index with one query file -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndexCombined" />
            </conditional>
            <param name="query" value="lexicmap_query.fasta.gz" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result.tsv" />
        </test>
        <!-- Test 4 - query two local index with multiple query files -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndexCombined" />
            </conditional>
            <param name="query" value="lexicmap_query.fasta.gz,lexicmap_query2.fasta.gz,lexicmap_query3.fasta" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result4.tsv" />
        </test>
        <!-- Test 5 - query one local index with multiple query files, where only one query will get hits -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndex2" />
            </conditional>
            <param name="query" value="lexicmap_query.fasta.gz,lexicmap_query2.fasta.gz,lexicmap_query3.fasta" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result3.tsv" />
        </test>
        <!-- Test 6 - query multiple local index with multiple query files -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="db"/>
                <param name="lexicmap_index" value="LexicMapIndex1,LexicMapIndex2,LexicMapIndexCombined" />
            </conditional>

            <param name="query" value="lexicmap_query.fasta.gz,lexicmap_query2.fasta.gz,lexicmap_query3.fasta" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result6.tsv" />
        </test>
        <!-- Test 7 - query one index found in the history with one query -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="histdb"/>
                <param name="histdb" ftype="lexicmap_index" class="Directory" value="db.lmi" />
            </conditional>
            <param name="top_n_genomes" value="0" />
            <param name="query" value="lexicmap_query.fasta.gz" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result.tsv" />
        </test>
        <!-- Test 8 - query two index found in the history with one query -->
        <test expect_num_outputs="1">
            <conditional name="db_opts">
                <param name="db_opts_selector" value="histdb"/>
                <param name="histdb" ftype="lexicmap_index" class="Directory" value="db.lmi,db2.lmi" />
            </conditional>
            <param name="top_n_genomes" value="0" />
            <param name="query" value="lexicmap_query.fasta.gz,lexicmap_query3.fasta" />
            <section name="advanced_settings">
                <param name="load_whole_seeds" value="true" />
            </section>
            <output name="out_file" value="lexicmap_query_result5.tsv" />
        </test>
    </tests>
    <help><![CDATA[
    
    Search sequences against an LexicMap index Database. For more information about settings
    please visit: https://bioinf.shenwei.me/LexicMap/usage/search

    Output format:
    Tab-delimited format with 20+ columns, with 1-based positions.

    1.  query,    Query sequence ID.
    2.  qlen,     Query sequence length.
    3.  hits,     Number of subject genomes.
    4.  sgenome,  Subject genome ID.
    5.  sseqid,   Subject sequence ID.
    6.  qcovGnm,  Query coverage (percentage) per genome: $(aligned bases in the genome)/$qlen.
    7.  cls,      Nth HSP cluster in the genome. (just for improving readability)
                  It's useful to show if multiple adjacent HSPs are collinear.
    8.  hsp,      Nth HSP in the genome.         (just for improving readability)
    9.  qcovHSP   Query coverage (percentage) per HSP: $(aligned bases in a HSP)/$qlen.
    10. alenHSP,  Aligned length in the current HSP.
    11. pident,   Percentage of identical matches in the current HSP.
    12. gaps,     Gaps in the current HSP.
    13. qstart,   Start of alignment in query sequence.
    14. qend,     End of alignment in query sequence.
    15. sstart,   Start of alignment in subject sequence.
    16. send,     End of alignment in subject sequence.
    17. sstr,     Subject strand.
    18. slen,     Subject sequence length.
    19. evalue,   Expect value.
    20. bitscore, Bit score.
    21. cigar,    CIGAR string of the alignment.                      (optional with --all)
    22. qseq,     Aligned part of query sequence.                     (optional with --all)
    23. sseq,     Aligned part of subject sequence.                   (optional with --all)
    24. align,    Alignment text ("|" and " ") between qseq and sseq. (optional with --all)

    When running against multiple indices lexicmap utils merge-search-results will be used to
    merge the search results. For more information please visit:
    https://bioinf.shenwei.me/LexicMap/usage/utils/merge-search-results/

    Note: if the query id contains spaces, only the first part (before the first space) will be kept as the query id.
    @info@
        ]]></help>
    <expand macro="citations" />
</tool>