Mercurial > repos > p.lucas > diamond_using_binary
changeset 63:f35c3ad107ab draft
Uploaded
| author | p.lucas |
|---|---|
| date | Mon, 10 Jun 2024 13:16:57 +0000 |
| parents | 3a186f337346 |
| children | 4c0effbfd084 |
| files | diamond.xml diamond_makedb.xml diamond_view.xml macros.xml tool-data/pl_diamond_database.loc tool-data/pl_diamond_database.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 6 files changed, 0 insertions(+), 707 deletions(-) [+] |
line wrap: on
line diff
--- a/diamond.xml Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,376 +0,0 @@ -<tool id="pl_diamond" name="PL_Diamond" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="19.01"> - <description>alignment tool for short sequences against a protein database</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="stdio" /> - <expand macro="version_command" /> - <command detect_errors="aggressive"> -<![CDATA[ - - #if $ref_db_source.db_source == "history": - ln -s $ref_db_source.reference_database ./database.dmnd< - #end if - - && - - /usr/bin/diamond - $method_cond.method_select - --quiet - --threads "\${GALAXY_SLOTS:-12}" - #if $ref_db_source.db_source == "history": - --db ./database - #else - --db $ref_db_source.index.fields.db_path - #end if - --query '$query' - #if $method_cond.method_select == "blastx" - --query-gencode '$method_cond.query_gencode' - --strand '$method_cond.query_strand' - --min-orf $method_cond.min_orf - #if $method_cond.frameshift_cond.frameshift_select == 'yes' - --frameshift $method_cond.frameshift_cond.frameshift - $method_cond.frameshift_cond.range_culling - #end if - #else if $method_cond.method_select == "blastp" - $method_cond.no_self_hits - #end if - - @OUTPUT_ARGS@ - - #if $output_section.output.outfmt != '100' - --compress '0' - #end if - $sens_cond.sensitivity - $iterate - --algo $algo - #if $global_ranking - --global-ranking $global_ranking - #end if - #if str($gapopen) != "": - --gapopen '$gapopen' - #end if - #if str($gapextend) != "": - --gapextend '$gapextend' - #end if - --matrix '$matrix' - --comp-based-stats '$method_cond.comp_based_stats' - --masking '$masking' - - @HITFILTER_ARGS@ - - #if str($filter_score.filter_score_select) == 'evalue': - --evalue '$filter_score.evalue' - #else: - --min-score '$filter_score.min_score' - #end if - - --id '$id' - --query-cover '$query_cover' - --subject-cover '$subject_cover' - --block-size '$sens_cond.block_size' - #if $output_section.output_unal - #if "--un" in $output_section.output_unal - --un '$unalqueries' - #if $query.ext.startswith("fasta"): - --unfmt fasta - #else - --unfmt fastq - #end if - #end if - #if "--al" in $output_section.output_unal - --al '$alqueries' - #if $query.ext.startswith("fasta"): - --alfmt fasta - #else - --alfmt fastq - #end if - #end if - #end if - #if $output_section.max_hsps - --max-hsps $output_section.max_hsps - #end if - #if $tax_cond.tax_select == 'file': - --taxonlist `cat '$tax_cond.taxonlistfile' | grep -v "^#" | grep -v "^$" | tr "\n" "," | sed 's/,$//'` - #else if $tax_cond.tax_select == 'list': - --taxonlist '$tax_cond.taxonlist' - #end if - #if $advanced_section.seed_cut - --seed-cut $advanced_section.seed_cut - #end if - $advanced_section.freq_masking - --motif-masking $advanced_section.motif_masking -]]> - </command> - <inputs> - <conditional name="method_cond"> - <param name="method_select" type="select" label="Alignment mode" help="(blastp/blastx)"> - <option value="blastp">Amino acid query sequences (blastp)</option> - <option value="blastx">DNA query sequences (blastx)</option> - </param> - <when value="blastx"> - <param argument="--query-gencode" type="select" label="Genetic code used for translation of query in BLASTX mode" help=""> - <option value="1">Standard Code</option> - <option value="2">Vertebrate Mitochondrial Code</option> - <option value="3">Yeast Mitochondrial Code</option> - <option value="4">Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option> - <option value="5">Invertebrate Mitochondrial Code</option> - <option value="6">Ciliate, Dasycladacean and Hexamita Nuclear Code</option> - <option value="9">Echinoderm and Flatworm Mitochondrial Code</option> - <option value="10">Euplotid Nuclear Code</option> - <option value="11">Bacterial, Archaeal and Plant Plastid Code</option> - <option value="12">Alternative Yeast Nuclear Code</option> - <option value="13">Ascidian Mitochondrial Code</option> - <option value="14">Alternative Flatworm Mitochondrial Code</option> - <option value="16">Chlorophycean Mitochondrial Code</option> - <option value="21">Trematode Mitochondrial Code</option> - <option value="22">Scenedesmus obliquus Mitochondrial Code</option> - <option value="23">Thraustochytrium Mitochondrial Code</option> - <option value="24">Pterobranchia Mitochondrial Code</option> - <option value="25">Candidate Division SR1 and Gracilibacteria Code</option> - <option value="26">Pachysolen tannophilus Nuclear Code</option> - </param> - <param argument="--min-orf" type="integer" value="1" label="ignore translated sequences without an open reading frame of at least this length" help="By default this feature is disabled for sequences of length below 30, set to 20 for sequences of length below 100, and set to 40 otherwise. Setting this option to 1 will disable this feature" /> - - <param name="query_strand" argument="--strand" type="select" label="query strands to search" help=""> - <option value="both" selected="True">Both</option> - <option value="plus">Plus</option> - <option value="minus">Minus</option> - </param> - <conditional name="frameshift_cond"> - <param name="frameshift_select" type="select" label="Allow for frameshifts?" help=""> - <option value="yes">yes</option> - <option value="no" selected="true">no</option> - </param> - <when value="yes"> - <param argument="--range-culling" type="boolean" truevalue="--range-culling" falsevalue="" checked="false" label="restrict hit culling to overlapping query ranges" help="This feature is designed for long query DNA sequences that may span several genes. In these cases, the default of reporting the 25 best overall hits could cause hits to a lower scoring gene to be overshadowed. But just increasing the number of alignments reported will bloat the output size and reduce performance. Using this feature along with -k 25 (default), a hit will only be deleted if at least 50% of its query range is spanned by at least 25 higher or equal scoring hits. Using this feature along with --top 10, a hit will only be deleted if its score is more than 10% lower than that of a higher scoring hit over at least 50% of its query range. The percentage is configurable using --range-cover. Note that this feature is currently only available in frameshift alignment mode"/> - <param argument="--frameshift" type="integer" value="0" label="frame shift penalty" help="Values around 15 are reasonable for this parameter. Enabling this feature will have the aligner tolerate missing bases in DNA sequences and is most recommended for long, error-prone sequences like MinION reads. In the pairwise output format, frameshifts will be indicated by \ and / for a shift by +1 and -1 nucleotide in the direction of translation respectively." /> - </when> - <when value="no"/> - </conditional> - - <param argument="--comp-based-stats" type="select" label="Composition based statistics" help="Compositionally biased sequences often cause false positive matches, which are effectively filtered by this algorithm in a way similar to the composition based statistics used by BLAST"> - <option value="0">Disable</option> - <option value="1" selected="True">Default mode (Hauser, 2016)</option> - </param> - </when> - <when value="blastp"> - <param argument="--no-self-hits" type="boolean" truevalue="--no-self-hits" falsevalue="" checked="true" - label="Suppress reporting of identical self-hits between sequences" - help="The FASTA sequence identifiers as well as the sequences of query and target need to be identical for a hit to be deleted"/> - - <param argument="--comp-based-stats" type="select" label="Composition based statistics" help="Compositionally biased sequences often cause false positive matches, which are effectively filtered by this algorithm in a way similar to the composition based statistics used by BLAST"> - <option value="0">Disable</option> - <option value="1" selected="True">Default mode (Hauser, 2016)</option> - <option value="2">Compositional matrix adjust conditioned on sequence properties, simplified (Yu, 2005)</option> - <option value="3">Compositional matrix adjust conditioned on sequence properties (Yu, 2005)</option> - <option value="4">Compositional matrix adjust unconditionally (Yu, 2005)</option> - </param> - </when> - </conditional> - <param argument="--query" type="data" format="fasta,fastq" label="Input query file in FASTA or FASTQ format" /> - <conditional name="ref_db_source"> - <param name="db_source" type="select" label="Will you select a reference database from your history or use a built-in index?" help="Built-ins were indexed using default options"> - <option value="indexed">Use a built-in index</option> - <option value="history">Use one from the history</option> - </param> - <when value="indexed"> - <param name="index" type="select" label="Select a reference database" help="If your database of interest is not listed, contact your Galaxy admin"> - <options from_data_table="pl_diamond_database"> - <filter type="sort_by" column="2"/> - <validator type="no_options" message="No indexes are available for the selected input dataset"/> - </options> - </param> - </when> - <when value="history"> - <param name="reference_database" argument="--db" type="data" format="dmnd" label="Select the reference database" /> - </when> - </conditional> - <conditional name="tax_cond"> - <param name="tax_select" type="select" label="Restrict search taxonomically?" help="Any taxonomic rank can be used, and only reference sequences matching one of the specified taxon ids will be searched against."> - <option value="no" selected="True">No</option> - <option value="list">List of taxids entered manually</option> - <option value="file">List of taxids from single column tabular file</option> - </param> - <when value="no"/> - <when value="list"> - <param name="taxonlist" argument="--taxonlist" type="text" value="" label="Comma separated list of taxon ids" help=""> - <validator type="regex" message="Taxonlist needs to be a comma separated list of integers">[0-9,]*</validator> - </param> - </when> - <when value="file"> - <param name="taxonlistfile" argument="--taxonlist" type="data" format="tabular" label="Keep alignments within the given percentage range of the top alignment score for a quer" help="" /> - </when> - </conditional> - <conditional name="sens_cond"> - <param name='sensitivity' type="select" label="Sensitivity Mode" help="Choose one of the sensitivity modes. The default mode is mainly designed for short read alignment, i.e. finding significant matches of >50 bits on 30-40aa fragments. The sensitive mode is a lot more sensitive than the default and generally recommended for aligning longer sequences. The more sensitive mode provides even more sensitivity. More sensitivity may increase computation time."> - <option value="--fast">Fast (--fast)</option> - <option value="" selected="True">Default</option> - <option value="--mid-sensitive">Mid Sensitive (--mid-sensitive)</option> - <option value="--sensitive">Sensitive (--sensitive)</option> - <option value="--more-sensitive">More Sensitive (--more-sensitive)</option> - <option value="--very-sensitive">Very Sensitive (--very-sensitive)</option> - <option value="--ultra-sensitive">Ultra Sensitive (--ultra-sensitive)</option> - </param> - <when value="--fast"> - <expand macro="block_size_low_sens"/> - </when> - <when value=""> - <expand macro="block_size_low_sens"/> - </when> - <when value="--mid-sensitive"> - <expand macro="block_size_low_sens"/> - </when> - <when value="--sensitive"> - <expand macro="block_size_low_sens"/> - </when> - <when value="--more-sensitive"> - <expand macro="block_size_low_sens"/> - </when> - <when value="--very-sensitive"> - <expand macro="block_size_hi_sens"/> - </when> - <when value="--ultra-sensitive"> - <expand macro="block_size_hi_sens"/> - </when> - </conditional> - <param argument="--matrix" type="select" label="Scoring matrix" help="In parentheses are the supported values for (gap open)/(gap extend). In brackets are default gap penalties"> - <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1) [14/2]</option> - <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1) [13/2]</option> - <option value="BLOSUM62" selected="True">BLOSUM62 ((6-11)/2; (9-13)/1) [11/1]</option> - <option value="BLOSUM80">BLOSUM80 ((6-9)/2; 13/2; 25/2; (9-11)/1) [10/1]</option> - <option value="BLOSUM90">BLOSUM90 ((6-9)/2; (9-11)/1) [10/1]</option> - <option value="PAM250">PAM250 ((11-15)/3; (13-17)/2; (17-21)/1) [14/2]</option> - <option value="PAM70">PAM70 ((6-8)/2; (9-11)/1) [10/1]</option> - <option value="PAM30">PAM30 ((5-7)/2; (8-10)/1) [9/1]</option> - </param> - <param argument="--gapopen" type="integer" optional="True" value="" label="Gap open penalty" help="Leave empty for default (see scoring matrix)" /> - <param argument="--gapextend" type="integer" optional="True" value="" label="Gap extension penalty" help="Leave empty for default (see scoring matrix)" /> - <param argument="--masking" type="select" label="Masking algorithm" help="DIAMOND by default applies the tantan repeat masking algorithm to the query and target sequences as described in (Frith, 2011). - This masking procedure increases the specificity of alignments and serves to filter out spurious hits. Note that when using --comp-based-stats (2,3,4), tantan masking is disabled by default."> - <option value="0">Disabled</option> - <option value="1" selected="true">Tantan</option> - <option value="seg">SEG</option> - </param> - <conditional name="filter_score"> - <param name="filter_score_select" type="select" label="Method to filter?" help="(--evalue/--min-score)"> - <option value="evalue" selected="True">Maximum e-value to report alignments</option> - <option value="min-score">Minimum bit score to report alignments</option> - </param> - <when value="evalue"> - <param argument="--evalue" type="float" value="0.001" label="Maximum expected value to keep an alignment" /> - </when> - <when value="min-score"> - <param name="min_score" argument="--min-score" type="integer" value="0" label="Minimum bit score to keep an alignment" help="(--min-score)" /> - </when> - </conditional> - <param argument="--iterate" type="boolean" truevalue="--iterate" falsevalue="" checked="false" - label="Run multiple rounds of searches with increasing sensitivity" help="he query dataset will first be searched at a lower sensitivity setting, only searching those query sequences at - the target sensitivity that fail to produce a significant alignment at a lower sensitivity." /> - <param argument="--algo" type="select" label="Algorithm for seed search" help="Double-indexed is the main algorithm of the program, designed for large input files but less efficient for small - query files. Query-indexed and improves performance for small query files. This mode will be automatically triggered based on the input. Contiguous-seed mode and further improves performance - for small query files. The modes differ slightly in their sensitivity, so results are not guaranteed to be 100% identical for different settings of this option."> - <option value="0">Doble-indexed (0)</option> - <option value="1">Query-indexed (1)</option> - <option value="ctg">Contiguous-seed mode (ctg)</option> - </param> - <expand macro="hit_filter_macro" /> - <param argument="--global-ranking" type="integer" min="0" value="" optional="true" - label="Limit on the number of Smith Waterman extensions" help="Target sequences will be ranked according to their ungapped extension scores at seed hits, and gapped extensions will only - be computed for the best N targets for each query. Note that this option increases memory use." /> - <param argument="--id" type="integer" value="0" label="Minimum identity percentage to report an alignment" help="Report only alignments above the given percentage of sequence identity" /> - <param argument="--query-cover" type="integer" value="0" label="Minimum query cover percentage to report an alignment" help="Report only alignments above the given percentage of query cover" /> - <param argument="--subject-cover" type="integer" value="0" label="Minimum subject cover percentage to report an alignment" help="Report only alignments above the given percentage of subject cover"/> - <section name="output_section" title="Output options"> - <param argument="--max-hsps" type="integer" min="0" optional="true" label="Maximum number of HSPs" - help="The maximum number of HSPs (High-Scoring Segment Pairs) per target sequence to report for each query. The default policy is to report only the highest-scoring - HSP for each target, while disregarding alternative, lower-scoring HSPs that are contained in the same target." /> - <expand macro="output_type_macro"> - <!-- Taxonomy features are not supported for the DAA format (i.e. - can't be used in diamond view) --> - <option value="staxids">unique Subject Taxonomy ID(s), separated by a ';' (in numerical order)</option> - <option value="sskingdoms">Subject super kingdoms</option> - <option value="skingdoms">Subject kingdoms</option> - <option value="sphylums">Subject phylums</option> - </expand> - <param name="output_unal" type="select" optional="true" multiple="true" label="Output aligned/unaligned queries to separate file" help=""> - <option value="--un">Output unaligned queries (--un)</option> - <option value="--al">Output alaligned queries (--al)</option> - </param> - </section> - <section name="advanced_section" title="Advanced options" expanded="false"> - <param argument="--seed-cut" type="float" min="0" optional="true" label="Set a complexity cutoff for indexed seeds"/> - <param argument="--freq-masking" type="boolean" truevalue="--freq-masking" falsevalue="" checked="false" label="Enable masking seeds based on frequency" help="This option is incompatible with --sed-cut" /> - <param argument="--motif-masking" type="select" label="Softmask abundant motifs" help="Enable or disable motif masking"> - <option value="0">Disabled</option> - <option value="1">Enabled</option> - </param> - </section> - </inputs> - <outputs> - <expand macro="output_macro" /> - <data format_source="query" name="unalqueries" label="${tool.name} on ${on_string}: unaligned queries"> - <filter>output_section['output_unal'] and "--un" in output_section['output_unal']</filter> - </data> - <data format_source="query" name="alqueries" label="${tool.name} on ${on_string}: aligned queries"> - <filter>output_section['output_unal'] and "--un" in output_section['output_unal']</filter> - </data> - </outputs> - <help> -<![CDATA[ - -**What it does** - -DIAMOND_ is a new alignment tool for aligning short DNA sequencing reads to a protein reference database such as NCBI-NR. -On Illumina reads of length 100-150bp, in fast mode, DIAMOND is about 20,000 times faster than BLASTX, while reporting -about 80-90% of all matches that BLASTX finds, with an e-value of at most 1e-5. In sensitive mode, DIAMOND ist about 2,500 -times faster than BLASTX, finding more than 94% of all matches. - -The DIAMOND algorithm is designed for the alignment of large datasets. The algorithm is not efficient for a small number of query sequences or only a single one of them, and speed will be low. BLAST is recommended for small datasets. - -.. _DIAMOND: http://ab.inf.uni-tuebingen.de/software/diamond/ - -**Input** - -Input data is a large protein or nucleotide sequence file. - - -**Output** - -Diamond gives you a tabular output file with 12 columns: - -Column Description -1 Query Seq-id (ID of your sequence) -2 Subject Seq-id (ID of the database hit) -3 Percentage of identical matches -4 Alignment length -5 Number of mismatches -6 Number of gap openings -7 Start of alignment in query -8 End of alignment in query -9 Start of alignment in subject (database hit) -10 End of alignment in subject (database hit) -11 Expectation value (E-value) -12 Bit score - - -Supported values for gap open and gap extend parameters depending on the selected scoring matrix. - -======== ============================================ -Matrix Supported values for (gap open)/(gap extend) -======== ============================================ -BLOSUM45 (10-13)/3; (12-16)/2; (16-19)/1 -BLOSUM50 (9-13)/3; (12-16)/2; (15-19)/1 -BLOSUM62 (6-11)/2; (9-13)/1 -BLOSUM80 (6-9)/2; 13/2; 25/2; (9-11)/1 -BLOSUM90 (6-9)/2; (9-11)/1 -PAM250 (11-15)/3; (13-17)/2; (17-21)/1 -PAM70 (6-8)/2; (9-11)/1 -PAM30 (5-7)/2; (8-10)/1 -======== ============================================ - - -]]> - </help> - <expand macro="citations" /> -</tool>
--- a/diamond_makedb.xml Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,73 +0,0 @@ -<tool id="pl_diamond_makedb" name="PL_Diamond makedb" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="19.01"> - <description>Build database from a FASTA file</description> - <macros> - <import>macros.xml</import> - </macros> - - <expand macro="stdio" /> - <expand macro="version_command" /> - - <command detect_errors="aggressive"> - <!-- DB has two files, *.dmnd and *.tx --> - <![CDATA[ - /usr/bin/diamond makedb - --threads "\${GALAXY_SLOTS:-12}" - --in '$infile' - --db ./database - - #if str($tax_cond.tax_select) == 'yes': - --taxonmap '$tax_cond.taxonmap' - --taxonnodes '$tax_cond.taxonnodes' - --taxonnames '$tax_cond.taxonnames' - #end if - ]]> - </command> - - <inputs> - <param name="infile" type="data" format="fasta" label="Input reference file in FASTA format" /> - <conditional name="tax_cond"> - <param name="tax_select" type="select" label="Add taxonomic data?" help="Needs to be supplied in order to provide taxonomy features of the aligner"> - <option value="yes">Yes</option> - <option value="no" selected="true">No</option> - </param> - <when value="yes"> - <param argument="--taxonmap" type="data" format="tabular" - label="Protein accession to taxid mapping file" - help="Path to mapping file that maps NCBI protein accession numbers to taxon ids (gzip compressed). This parameter is optional and needs to be supplied in order to provide taxonomy features. - A custom file following the same format may be supplied here. Note that the first line of this file is assumed to contain headings and will be ignored" /> - <param argument="--taxonnodes" type="data" format="tabular" label="Taxonomy nodes.dmp from NCBI" help="This parameter is optional and needs to be supplied in order to provide taxonomy features" /> - <param argument="--taxonnames" type="data" format="tabular" label="Taxonomy names.dmp from NCBI" help="This parameter is optional and needs to be supplied in order to provide taxonomy features" /> - </when> - <when value="no"/> - </conditional> - </inputs> - - <outputs> - <data format="dmnd" name="outfile" from_work_dir="database.dmnd" label="${tool.name} on ${on_string}"/> - </outputs> - - <help> -<![CDATA[ - -.. class:: infomark - -**What it does** - -DIAMOND_ is a new alignment tool for aligning short DNA sequencing reads to a protein reference database such as NCBI-NR. -On Illumina reads of length 100-150bp, in fast mode, DIAMOND is about 20,000 times faster than BLASTX, while reporting -about 80-90% of all matches that BLASTX finds, with an e-value of at most 1e-5. In sensitive mode, DIAMOND is about 2,500 -times faster than BLASTX, finding more than 94% of all matches. - -.. _DIAMOND: http://ab.inf.uni-tuebingen.de/software/diamond/ - - -- taxonmap: Path to mapping file that maps NCBI protein accession numbers to taxon ids (gzip compressed). This parameter is optional and needs to be supplied in order to provide taxonomy features. The file can be downloaded from NCBI: ftp://ftp.ncbi.nlm.nih.gov/pub/taxonomy/accession2taxid/prot.accession2taxid.gz - -- taxonnames: Path to the names.dmp file from the NCBI taxonomy. This parameter is optional and needs to be supplied in order to provide taxonomy features. The file is contained within this archive downloadable at NCBI: ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdmp.zip - -- taxonnodes: Path to the nodes.dmp file from the NCBI taxonomy. This parameter is optional and needs to be supplied in order to provide taxonomy features. The file is contained within this archive downloadable at NCBI: ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdmp.zip -]]> - </help> - - <expand macro="citations" /> -</tool>
--- a/diamond_view.xml Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,66 +0,0 @@ -<tool id="pl_diamond_view" name="PL_Diamond view" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="19.01"> - <description>generate formatted output from DAA files</description> - <macros> - <import>macros.xml</import> - </macros> - <expand macro="stdio" /> - <expand macro="version_command" /> - <command detect_errors="aggressive"><![CDATA[ - ## need to link because diamont tries to open dataset_xxx.dat.daa - ln -s '$daa' input.daa && - /usr/bin/diamond - view - --threads \${GALAXY_SLOTS:-1} - --daa input.daa - @OUTPUT_ARGS@ - @HITFILTER_ARGS@ - $forwardonly - --compress '0' - ]]> - </command> - <inputs> - <param argument="--daa" type="data" format="daa" label="input file in DAA format" /> - <section name="output_section" title="Output options"> - <expand macro="output_type_macro" /> - </section> - <expand macro="hit_filter_macro" /> - <param argument="--forwardonly" type="boolean" truevalue="--forwardonly" falsevalue="" checked="false" label="only show alignments of forward strand" help=""/> - </inputs> - <outputs> - <expand macro="output_macro" /> - </outputs> - <help> -<![CDATA[ - -**What it does** - -Converts diamond daa files to multiple other formats. - -**Input** - -Input data is a daa file. - - -**Output** - -Alignment results in BLAST format (pairwise/tabular), xml, sam, taxonomic (Note the latter does not work with the current diamond version. ) - -BLAST tables contain the following columns. - -Column Description -1 Query Seq-id (ID of your sequence) -2 Subject Seq-id (ID of the database hit) -3 Percentage of identical matches -4 Alignment length -5 Number of mismatches -6 Number of gap openings -7 Start of alignment in query -8 End of alignment in query -9 Start of alignment in subject (database hit) -10 End of alignment in subject (database hit) -11 Expectation value (E-value) -12 Bit score -]]> - </help> - <expand macro="citations" /> -</tool>
--- a/macros.xml Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,173 +0,0 @@ -<macros> - <token name="@TOOL_VERSION@">2.1.9</token> - <token name="@VERSION_SUFFIX@">0</token> - - <xml name="stdio"> - <stdio> - <regex match="Failed to allocate" source="stderr" level="fatal_oom" /> - </stdio> - </xml> - - <xml name="version_command"> - <version_command>/usr/bin/diamond version | cut -d" " -f 3</version_command> - </xml> - - <xml name="output_type_macro"> - <conditional name="output"> - <param argument="--outfmt" type="select" label="Format of output file" help=""> - <option value="0">BLAST pairwise</option> - <option value="5">BLAST XML</option> - <option value="6">BLAST tabular</option> - <option value="100">DAA</option> - <option value="101">SAM</option> - <option value="102">Taxonomic classification</option> - </param> - <when value="0"/> - <when value="5"/> - <when value="6"> - <param name="fields" type="select" label="Tabular fields" help="" multiple="true"> - <option value="qseqid" selected="true">Query Seq - id</option> - <option value="sseqid" selected="true">Subject Seq - id</option> - <option value="sallseqid">All subject Seq - id(s)</option> - <option value="qlen">Query sequence length</option> - <option value="slen">Subject sequence length</option> - <option value="pident" selected="true">Percentage of identical matches</option> - <option value="length" selected="true">Alignment length</option> - <option value="nident">Number of identical matches</option> - <option value="mismatch" selected="true">Number of mismatches</option> - <option value="positive">Number of positive - scoring matches</option> - <option value="gapopen" selected="true">Number of gap openings</option> - <option value="gaps">Total number of gaps</option> - <option value="ppos">Percentage of positive - scoring matches</option> - <option value="qstart" selected="true">Start of alignment in query</option> - <option value="qend" selected="true">End of alignment in query</option> - <option value="sstart" selected="true">Start of alignment in subject</option> - <option value="send" selected="true">End of alignment in subject</option> - <option value="qseq">Aligned part of query sequence</option> - <option value="sseq">Aligned part of subject sequence</option> - <option value="qseq_translated">Translation of the aligned part of query sequence</option> - <option value="evalue" selected="true">Expect value</option> - <option value="bitscore" selected="true">Bit score</option> - <option value="score">Raw score</option> - <option value="qframe">Query frame</option> - <option value="btop">Blast traceback operations(BTOP)</option> - <option value="scovhsp">Subject coverage per HSP</option> - <option value="stitle">Subject Title</option> - <option value="salltitles">All Subject Title(s)</option> - <option value="qcovhsp">Query Coverage Per HSP</option> - <option value="qtitle">Query title</option> - <option value="full_qseq">Query sequence</option> - <option value="full_sseq">Subject sequence</option> - <option value="qqual">Query quality values for the aligned part of the query</option> - <option value="full_qqual">Query quality values</option> - <option value="qstrand">Query strand</option> - <option value="cigar">Cigar</option> - <yield/> - </param> - <param argument="--unal" type="boolean" label="Report unaligned queries" truevalue="1" falsevalue="0" checked="false"/> - </when> - <when value="100"> - <param argument="--salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="true" label="Include full subject titles in DAA file?" help=""/> - <param argument="--sallseqid" type="boolean" truevalue="--sallseqid" falsevalue="" checked="true" label="Include all subject ids in DAA file?" help=""/> - </when> - <when value="101"> - <param argument="--salltitles" type="boolean" truevalue="--salltitles" falsevalue="" checked="true" label="Include full subject titles in DAA file?" help=""/> - <param argument="--sallseqid" type="boolean" truevalue="--sallseqid" falsevalue="" checked="true" label="Include all subject ids in DAA file?" help=""/> - </when> - <when value="102"/> - </conditional> - </xml> - - <xml name="hit_filter_macro"> - <conditional name="hit_filter"> - <param name="hit_filter_select" type="select" label="Method to restrict the number of hits?"> - <option value="max">Maximum number of target sequences</option> - <option value="top">Percentage of top alignment score</option> - </param> - <when value="max"> - <param name="max_target_seqs" argument="--max-target-seqs" type="integer" value="25" label="The maximum number of target sequences per query to report alignments for" - help="Setting this to 0 will report all alignments that were found." /> - </when> - <when value="top"> - <param argument="--top" type="integer" value="0" label="Keep alignments within the given percentage range of the top alignment score for a query" - help="For example, setting this to 10 will report all alignments whose score is at most 10% lower than the best alignment score for a query." /> - </when> - </conditional> - </xml> - - <xml name="block_size_low_sens"> - <param argument="--block-size" type="float" value="2" label="Block size in billions of sequence letters to be processed at a time" - help="This is the main parameter for controlling the program’s memory and disk space usage. Bigger numbers will increase the use of memory and temporary - disk space, but also improve performance" /> - </xml> - - <xml name="block_size_hi_sens"> - <param argument="--block-size" type="float" value="0.4" label="Block size in billions of sequence letters to be processed at a time" - help="This is the main parameter for controlling the program’s memory and disk space usage. Bigger numbers will increase the use of memory and temporary - disk space, but also improve performance" /> - </xml> - - <xml name="citations"> - <citations> - <citation type="doi">10.1038/nmeth.3176</citation> - </citations> - </xml> - - - <xml name="output_macro"> - <data format="txt" name="blast_pairw" label="${tool.name} on ${on_string}"> - <filter>output_section["output"]["outfmt"] == "0"</filter> - </data> - <data format="xml" name="blast_xml" label="${tool.name} on ${on_string}"> - <filter>output_section["output"]["outfmt"] == "5"</filter> - </data> - <data format="tabular" name="blast_tabular" label="${tool.name} on ${on_string}"> - <filter>output_section["output"]["outfmt"] == "6"</filter> - </data> - <!-- for daa diamond appends the .daa extension -> hence from_work_dir --> - <data format="daa" name="daa_output" label="${tool.name} on ${on_string}" from_work_dir="output.daa"> - <filter>output_section["output"]["outfmt"] == "100"</filter> - </data> - <data format="sam" name="sam_output" label="${tool.name} on ${on_string}"> - <filter>output_section["output"]["outfmt"] == "101"</filter> - </data> - <data format="tabular" name="tax_output" label="${tool.name} on ${on_string}"> - <filter>output_section["output"]["outfmt"] == "102"</filter> - </data> - </xml> - - <token name="@OUTPUT_ARGS@"> - #if $output_section.output.outfmt == "0" - --outfmt '0' - --out '$blast_pairw' - #else if $output_section.output.outfmt == "5" - --outfmt '5' - --out '$blast_xml' - #else if $output_section.output.outfmt == "6" - --outfmt '6' #echo ' '.join(str($output_section.output.fields).split(',')) - --out '$blast_tabular' - --unal $output_section.output.unal - #else if $output_section.output.outfmt == "100" - --outfmt '100' - $output_section.output.salltitles - $output_section.output.sallseqid - --out output.daa - #else if $output_section.output.outfmt == "101" - --outfmt '101' - $output_section.output.salltitles - $output_section.output.sallseqid - --out '$sam_output' - #else if $output_section.output.outfmt == "102" - --outfmt '102' - --out '$tax_output' - #end if - </token> - - <token name="@HITFILTER_ARGS@"> - #if str($hit_filter.hit_filter_select) == 'max': - --max-target-seqs '$hit_filter.max_target_seqs' - #else: - --top '$hit_filter.top' - #end if - </token> -</macros>
--- a/tool-data/pl_diamond_database.loc Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ -#This is a sample file that enables the diamind to find the protein databases -#You will need to create these data files and then create -#a diamond_database.loc file similar to this one (store it in this directory) -#that points to the directories in which those files are stored. -#The diamond_database_indices.loc file has this format (longer white space characters are TAB characters): -# -#<unique_build_id> <display_name> <file_base_path> -# -#So, for example: -#ncbi_nr NCBI NR database (1-1-2015) /data/db/diamond/1-1-2015/nr.dmnd -
--- a/tool_data_table_conf.xml.sample Mon Jun 10 13:16:20 2024 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,8 +0,0 @@ -<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc--> -<tables> - <!-- Locations of indexes in the Bowtie mapper format --> - <table name="pl_diamond_database" comment_char="#"> - <columns>value, name, db_path</columns> - <file path="tool-data/pl_diamond_database.loc" /> - </table> -</tables>