Mercurial > repos > galaxyp > eggnog_mapper
changeset 8:96cac424c870 draft
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/eggnog_mapper/eggnog_mapper commit e45c15081260025e470d23975ef5a734d3f8fc66"
author | galaxyp |
---|---|
date | Tue, 25 Jan 2022 13:51:50 +0000 |
parents | 4e4c6329f6cd |
children | 63662ae295d6 |
files | eggnog_macros.xml eggnog_mapper.xml test-data/DIA_nlim.emapper.annotations test-data/DIA_nlim.emapper.annotations_orthologs test-data/DIA_nlim.emapper.seed_orthologs test-data/README test-data/cached_locally/eggnog.db test-data/cached_locally/eggnog.taxa.db test-data/cached_locally/eggnog_mapper_db_versioned.loc test-data/eggnogg_tiny.sh test-data/eggnogg_tiny_taxa.sh test-data/scoped.emapper.annotations test-data/scoped.emapper.annotations_orthologs test-data/scoped.emapper.seed_orthologs tool-data/eggnog_mapper_db_versioned.loc.sample |
diffstat | 15 files changed, 329 insertions(+), 157 deletions(-) [+] |
line wrap: on
line diff
--- a/eggnog_macros.xml Fri Feb 19 18:54:25 2021 +0000 +++ b/eggnog_macros.xml Tue Jan 25 13:51:50 2022 +0000 @@ -1,14 +1,15 @@ <?xml version="1.0"?> <macros> - <token name="@VERSION@">2.0.1</token> - <token name="@EGGNOG_DB_VERSION@">2.0</token> + <token name="@VERSION@">2.1.6</token> + <token name="@EGGNOG_DB_VERSION@">5.0.2</token> <!-- - # Versionning is super confusing: + # DB versionning was super confusing for eggnog-mapper 2.0.x: # eggnog-mapper 1.* needed a db v4.5 (based on eggnog v4.5) - # eggnog-mapper 2.0 needs a db v2.0 (based on eggnog v5.0) - # db v4.5 are not compatible with eggnog-mapper 2.0 + # eggnog-mapper 2.x needed a db v2.0 (based on eggnog v5.0) + # (db v4.5 are not compatible with eggnog-mapper 2.0) + # Starting with eggnog-mapper 2.1.* db versioning looks better: 2.1.0 requires db v5.0.2 --> - <token name="@IDX_VERSION@">2.0</token> + <token name="@IDX_VERSION@">5.0.2</token> <xml name="citations"> <citations> <citation type="doi">10.1093/nar/gkv1248</citation> @@ -26,6 +27,8 @@ <xml name="data_manager_params"> <param name="test" type="hidden" value="false" /> <param name="diamond_database" type="boolean" truevalue="" falsevalue="-D" checked="true" label="Install the diamond database" help="Takes ~9Gb, you most probably want it."/> + <param name="mmseqs_database" type="boolean" truevalue="-M" falsevalue="" checked="true" label="Install the MMseqs2 database" help="Required for mmseqs seed ortholog search mode. Takes ~11Gb, you most probably want it."/> + <param name="pfam_database" type="boolean" truevalue="-P" falsevalue="" checked="true" label="Install the Pfam database" help="Rquired for de novo annotation or realignment. Takes ~3Gb, you most probably want it."/> </xml> <xml name="data_manager_outputs"> <outputs> @@ -40,7 +43,7 @@ #end if mkdir -p '${install_path}' && download_eggnog_data.py - $diamond_database -y -q + $diamond_database $mmseqs_database $pfam_database -y -q #if $test == 'true' -s #end if
--- a/eggnog_mapper.xml Fri Feb 19 18:54:25 2021 +0000 +++ b/eggnog_mapper.xml Tue Jan 25 13:51:50 2022 +0000 @@ -8,14 +8,38 @@ <command detect_errors="aggressive"><![CDATA[ emapper.py --data_dir '$eggnog_data.fields.path' - -m diamond - $translate + -m '$seed_ortho_options.ortho_method.m' + --itype '${input_trans.itype}' + #if $input_trans.itype in ['CDS', 'genome', 'metagenome']: + $input_trans.translate + #end if + #if $input_trans.itype in ['genome', 'metagenome']: + $input_trans.genepred + #end if ## Diamond option - --matrix '$diamond.matrix_gapcosts.matrix' - $diamond.matrix_gapcosts.gap_costs - --query-cover $diamond.query_cover - --subject-cover $diamond.subject_cover + #if $seed_ortho_options.ortho_method.m == "diamond": + --matrix '$seed_ortho_options.ortho_method.matrix_gapcosts.matrix' + $seed_ortho_options.ortho_method.matrix_gapcosts.gap_costs + --sensmode $seed_ortho_options.ortho_method.sensmode + $seed_ortho_options.ortho_method.dmnd_iterate + $seed_ortho_options.ortho_method.dmnd_ignore_warnings + #elif $seed_ortho_options.ortho_method.m == "mmseqs": + --start_sens $seed_ortho_options.ortho_method.start_sens + --sens_steps $seed_ortho_options.ortho_method.sens_steps + --final_sens $seed_ortho_options.ortho_method.final_sens + #end if + + ## Common options for search filtering + #if $seed_ortho_options.query_cover: + --query_cover $seed_ortho_options.query_cover + #end if + #if $seed_ortho_options.subject_cover: + --subject_cover $seed_ortho_options.subject_cover + #end if + #if $seed_ortho_options.pident: + --pident $seed_ortho_options.pident + #end if #if $annotation_options.tax_scope: --tax_scope=$annotation_options.tax_scope @@ -27,10 +51,10 @@ --go_evidence=$annotation_options.go_evidence #end if #if $seed_ortholog_options.seed_ortholog_evalue: - --seed_ortholog_evalue=$seed_ortholog_options.seed_ortholog_evalue + --evalue=$seed_ortholog_options.seed_ortholog_evalue #end if #if str($seed_ortholog_options.seed_ortholog_score): - --seed_ortholog_score=$seed_ortholog_options.seed_ortholog_score + --score=$seed_ortholog_options.seed_ortholog_score #end if $output_options.no_file_comments $output_options.no_annot @@ -41,145 +65,199 @@ ]]></command> <inputs> <param name="input" type="data" format="fasta" label="Fasta sequences to annotate"/> + <conditional name="input_trans"> + <param argument="--itype" type="select" label="Type of sequences"> + <option value="proteins" selected="true">proteins</option> + <option value="CDS">CDS</option> + <option value="genome">genome</option> + <option value="metagenome">metagenome</option> + </param> + <when value="proteins"/> + <when value="CDS"> + <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" + label="Translate CDS to proteins before search"/> + </when> + <when value="genome"> + <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" + label="Translate predicted CDS from blastx hits to proteins"/> + <param argument="--genepred" type="select" label="Type of sequences"> + <option value="search" selected="true">Inferred from Diamond/MMseqs2 blastx hits</option> + <option value="prodigal">Performed using Prodigal</option> + </param> + </when> + <when value="metagenome"> + <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" + label="Translate predicted CDS from blastx hits to proteins"/> + <param argument="--genepred" type="select" label="Type of sequences"> + <option value="search" selected="true">Inferred from Diamond/MMseqs2 blastx hits</option> + <option value="prodigal">Performed using Prodigal</option> + </param> + </when> + </conditional> <param name="eggnog_data" type="select" label="Version of eggNOG Database"> <options from_data_table="eggnog_mapper_db_versioned"> <filter type="static_value" column="3" value="@IDX_VERSION@" /> </options> </param> - <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" - label="Are these coding DNA sequences that need to be translated?"/> - <section name="diamond" expanded="true" title="Diamond Options"> - <conditional name="matrix_gapcosts"> - <param argument="--matrix" type="select" label="Scoring matrix and gap costs"> - <option value="BLOSUM90">BLOSUM90</option> - <option value="BLOSUM80">BLOSUM80</option> - <option value="BLOSUM62" selected="true">BLOSUM62</option> - <option value="BLOSUM50">BLOSUM50</option> - <option value="BLOSUM45">BLOSUM45</option> - <option value="PAM250">PAM250</option> - <option value="PAM70">PAM70</option> - <option value="PAM30">PAM30</option> + <section name="seed_ortho_options" expanded="true" title="Seed orthologs search options"> + <conditional name="ortho_method"> + <param argument="-m" type="select" label="Method to search seed orthologs"> + <option value="diamond" selected="true">Diamond</option> + <option value="mmseqs">MMseqs2</option> </param> - <when value="BLOSUM90"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option> - <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> - <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> - <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> - <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> - <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> - <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> + <when value="diamond"> + <conditional name="matrix_gapcosts"> + <param argument="--matrix" type="select" label="Scoring matrix and gap costs"> + <option value="BLOSUM90">BLOSUM90</option> + <option value="BLOSUM80">BLOSUM80</option> + <option value="BLOSUM62" selected="true">BLOSUM62</option> + <option value="BLOSUM50">BLOSUM50</option> + <option value="BLOSUM45">BLOSUM45</option> + <option value="PAM250">PAM250</option> + <option value="PAM70">PAM70</option> + <option value="PAM30">PAM30</option> + </param> + <when value="BLOSUM90"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option> + <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> + <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> + <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> + <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> + <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> + <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> + </param> + </when> + <when value="BLOSUM80"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> + <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> + <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> + <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> + <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> + <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> + </param> + </when> + <when value="BLOSUM62"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option> + <option value="--gapopen 10 --gapextend 2">Existence: 10 Extension: 2</option> + <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option> + <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> + <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> + <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> + <option value="--gapopen 13 --gapextend 1">Existence: 13 Extension: 1</option> + <option value="--gapopen 12 --gapextend 1">Existence: 12 Extension: 1</option> + <option value="--gapopen 11 --gapextend 1" selected="true">Existence: 11 Extension: 1</option> + <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option> + <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> + </param> + </when> + <when value="BLOSUM50"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> + <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> + <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option> + <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option> + <option value="--gapopen 9 --gapextend 3">Existence: 9 Extension: 3</option> + <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option> + <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option> + <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> + <option value="--gapopen 13 --gapextend 2" selected="true">Existence: 13 Extension: 2</option> + <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option> + <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> + <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> + <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> + <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option> + <option value="--gapopen 15 --gapextend 1">Existence: 15 Extension: 1</option> + </param> + </when> + <when value="BLOSUM45"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> + <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> + <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option> + <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option> + <option value="--gapopen 15 --gapextend 2" selected="true">Existence: 15 Extension: 2</option> + <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> + <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option> + <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option> + <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> + <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> + <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> + <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option> + </param> + </when> + <when value="PAM250"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option> + <option value="--gapopen 14 --gapextend 3">Existence: 14 Extension: 3</option> + <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> + <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> + <option value="--gapopen 17 --gapextend 2">Existence: 17 Extension: 2</option> + <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option> + <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option> + <option value="--gapopen 14 --gapextend 2" selected="true">Existence: 14 Extension: 2</option> + <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option> + <option value="--gapopen 21 --gapextend 1">Existence: 21 Extension: 1</option> + <option value="--gapopen 20 --gapextend 1">Existence: 20 Extension: 1</option> + <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> + <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> + <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> + </param> + </when> + <when value="PAM70"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> + <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option> + <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> + <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> + <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> + <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> + <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> + <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> + </param> + </when> + <when value="PAM30"> + <param name="gap_costs" type="select" label="Gap Costs"> + <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option> + <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> + <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> + <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> + <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> + <option value="--gapopen 5 --gapextend 2">Existence: 5 Extension: 2</option> + <option value="--gapopen 14 --gapextend 1">Existence: 14 Extension: 1</option> + <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option> + <option value="--gapopen 9 --gapextend 1" selected="true">Existence: 9 Extension: 1</option> + <option value="--gapopen 8 --gapextend 1">Existence: 8 Extension: 1</option> + </param> + </when> + </conditional> + <param name="sensmode" type="select" label="Gap Costs"> + <option value="default">default</option> + <option value="fast">fast</option> + <option value="mid-sensitive">mid-sensitive</option> + <option value="sensitive" selected="true">sensitive</option> + <option value="more-sensitive">more-sensitive</option> + <option value="very-sensitive">very-sensitive</option> + <option value="ultra-sensitive">ultra-sensitive</option> </param> - </when> - <when value="BLOSUM80"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> - <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> - <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> - <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> - <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> - <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> - </param> - </when> - <when value="BLOSUM62"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option> - <option value="--gapopen 10 --gapextend 2">Existence: 10 Extension: 2</option> - <option value="--gapopen 9 --gapextend 2">Existence: 9 Extension: 2</option> - <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> - <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> - <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> - <option value="--gapopen 13 --gapextend 1">Existence: 13 Extension: 1</option> - <option value="--gapopen 12 --gapextend 1">Existence: 12 Extension: 1</option> - <option value="--gapopen 11 --gapextend 1" selected="true">Existence: 11 Extension: 1</option> - <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option> - <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> - </param> + <param argument="--dmnd_iterate" type="boolean" truevalue="--dmnd_iterate yes" falsevalue="--dmnd_iterate no" checked="false" + label="Run diamond in iterative mode, up to the sensitivity level"/> + <param argument="--dmnd_ignore_warnings" type="boolean" truevalue="--dmnd_ignore_warnings" falsevalue="" checked="false" + label="Ignore Diamond warnings on sequence content (e.g. when a protein contains only ATGC symbols)"/> </when> - <when value="BLOSUM50"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> - <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> - <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option> - <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option> - <option value="--gapopen 9 --gapextend 3">Existence: 9 Extension: 3</option> - <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option> - <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option> - <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> - <option value="--gapopen 13 --gapextend 2" selected="true">Existence: 13 Extension: 2</option> - <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option> - <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> - <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> - <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> - <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option> - <option value="--gapopen 15 --gapextend 1">Existence: 15 Extension: 1</option> - </param> - </when> - <when value="BLOSUM45"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> - <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> - <option value="--gapopen 11 --gapextend 3">Existence: 11 Extension: 3</option> - <option value="--gapopen 10 --gapextend 3">Existence: 10 Extension: 3</option> - <option value="--gapopen 15 --gapextend 2" selected="true">Existence: 15 Extension: 2</option> - <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> - <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option> - <option value="--gapopen 12 --gapextend 2">Existence: 12 Extension: 2</option> - <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> - <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> - <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> - <option value="--gapopen 16 --gapextend 1">Existence: 16 Extension: 1</option> - </param> - </when> - <when value="PAM250"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option> - <option value="--gapopen 14 --gapextend 3">Existence: 14 Extension: 3</option> - <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> - <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> - <option value="--gapopen 17 --gapextend 2">Existence: 17 Extension: 2</option> - <option value="--gapopen 16 --gapextend 2">Existence: 16 Extension: 2</option> - <option value="--gapopen 15 --gapextend 2">Existence: 15 Extension: 2</option> - <option value="--gapopen 14 --gapextend 2" selected="true">Existence: 14 Extension: 2</option> - <option value="--gapopen 13 --gapextend 2">Existence: 13 Extension: 2</option> - <option value="--gapopen 21 --gapextend 1">Existence: 21 Extension: 1</option> - <option value="--gapopen 20 --gapextend 1">Existence: 20 Extension: 1</option> - <option value="--gapopen 19 --gapextend 1">Existence: 19 Extension: 1</option> - <option value="--gapopen 18 --gapextend 1">Existence: 18 Extension: 1</option> - <option value="--gapopen 17 --gapextend 1">Existence: 17 Extension: 1</option> - </param> - </when> - <when value="PAM70"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 12 --gapextend 3">Existence: 12 Extension: 3</option> - <option value="--gapopen 11 --gapextend 2">Existence: 11 Extension: 2</option> - <option value="--gapopen 8 --gapextend 2">Existence: 8 Extension: 2</option> - <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> - <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> - <option value="--gapopen 11 --gapextend 1">Existence: 11 Extension: 1</option> - <option value="--gapopen 10 --gapextend 1" selected="true">Existence: 10 Extension: 1</option> - <option value="--gapopen 9 --gapextend 1">Existence: 9 Extension: 1</option> - </param> - </when> - <when value="PAM30"> - <param name="gap_costs" type="select" label="Gap Costs"> - <option value="--gapopen 15 --gapextend 3">Existence: 15 Extension: 3</option> - <option value="--gapopen 13 --gapextend 3">Existence: 13 Extension: 3</option> - <option value="--gapopen 14 --gapextend 2">Existence: 14 Extension: 2</option> - <option value="--gapopen 7 --gapextend 2">Existence: 7 Extension: 2</option> - <option value="--gapopen 6 --gapextend 2">Existence: 6 Extension: 2</option> - <option value="--gapopen 5 --gapextend 2">Existence: 5 Extension: 2</option> - <option value="--gapopen 14 --gapextend 1">Existence: 14 Extension: 1</option> - <option value="--gapopen 10 --gapextend 1">Existence: 10 Extension: 1</option> - <option value="--gapopen 9 --gapextend 1" selected="true">Existence: 9 Extension: 1</option> - <option value="--gapopen 8 --gapextend 1">Existence: 8 Extension: 1</option> - </param> + <when value="mmseqs"> + <param argument="--start_sens" type="integer" value="3" min="0" max="100" label="Starting sensitivity" /> + <param argument="--sens_steps" type="integer" value="3" min="0" max="100" label="Number of sensitivity steps" /> + <param argument="--final_sens" type="integer" value="7" min="0" max="100" label="Final sensititivy step" /> </when> </conditional> - <param name="query_cover" type="integer" value="0" min="0" max="100" label="Minimum query coverage" help="Report only alignments above the given percentage of query cover" /> - <param name="subject_cover" type="integer" value="0" min="0" max="100" label="Minimum subject coverage" help="Report only alignments above the given percentage of subject cover" /> + <param argument="--query_cover" type="integer" optional="true" min="0" max="100" label="Minimum query coverage" help="Report only alignments above the given percentage of query cover" /> + <param argument="--subject_cover" type="integer" optional="true" min="0" max="100" label="Minimum subject coverage" help="Report only alignments above the given percentage of subject cover" /> + <param argument="--pident" type="integer" optional="true" min="0" max="100" label="Minimum query coverage" help="Report only alignments above the given percentage of identity" /> </section> <section name="annotation_options" expanded="false" title="Annotation Options"> @@ -195,6 +273,7 @@ label="Select the set of GO terms that should be used for annotation"> <option value="experimental">experimental = Use only terms inferred from experimental evidence</option> <option value="non-electronic" selected="true">non-electronic = Use only non-electronically curated terms</option> + <option value="all" selected="true">All (experimental + non-electronic)</option> </param> </section> <section name="seed_ortholog_options" expanded="false" title="Seed Ortholog Search Options"> @@ -204,7 +283,7 @@ Queries not having a significant seed orthologs (E-value less than threshold) will not be annotated. </help> </param> - <param name="seed_ortholog_score" type="integer" value="60" min="0" label="Minimum bit score threshold"> + <param name="seed_ortholog_score" type="integer" optional="true" min="0" label="Minimum bit score threshold"> <help> Min bit score expected when searching for seed eggNOG ortholog. Queries not having a significant seed orthologs will not be annotated. @@ -223,19 +302,19 @@ <outputs> <data name="seed_orthologs" format="tabular" label="${tool.name} on ${on_string}: seed_orthologs" from_work_dir="results.emapper.seed_orthologs"> <actions> - <action name="column_names" type="metadata" default="query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score"/> + <action name="column_names" type="metadata" default="query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,query_start,query_end,seed_start,seed_end,pident,query_cov,seed_cov"/> </actions> </data> <data name="annotations" format="tabular" label="${tool.name} on ${on_string}: annotations" from_work_dir="results.emapper.annotations"> <filter>not output_options['no_annot']</filter> <actions> - <action name="column_names" type="metadata" default="query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,predicted_taxonomic_group,predicted_protein_name,GO_terms,EC_number,KEGG_KO,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reactions,Annotation_tax_scope,Matching_OGs,best_OG|evalue|score,COG_functional_categories,eggNOG_free_text_description"/> + <action name="column_names" type="metadata" default="query,seed_ortholog,evalue,score,max_annot_lvl,COG_category,Description,Preferred_name,GOs,EC,KEGG_ko,KEGG_Pathway,KEGG_Module,KEGG_Reaction,KEGG_rclass,BRITE,KEGG_TC,CAZy,BiGG_Reaction,PFAMseggNOG_OGs"/> </actions> </data> - <data name="annotations_orthologs" format="tabular" label="${tool.name} on ${on_string}: annotations.orthologs" from_work_dir="results.emapper.annotations.orthologs"> + <data name="annotations_orthologs" format="tabular" label="${tool.name} on ${on_string}: orthologs" from_work_dir="results.emapper.orthologs"> <filter>output_options['report_orthologs']</filter> <actions> - <action name="column_names" type="metadata" default="query_name,orthologs"/> + <action name="column_names" type="metadata" default="query,orth_type,species,orthologs"/> </actions> </data> </outputs> @@ -268,6 +347,37 @@ <output name="annotations" file="scoped.emapper.annotations" ftype="tabular" compare="sim_size"/> <output name="annotations_orthologs" file="scoped.emapper.annotations_orthologs" ftype="tabular"/> </test> + <test> + <param name="input" value="Nmar_0135.fa" ftype="fasta"/> + <param name="eggnog_data" value="@EGGNOG_DB_VERSION@"/> <!-- not passed in test, but required for test to work --> + <section name="seed_ortho_options"> + <conditional name="ortho_method"> + <param name="m" value="diamond" /> + <param name="sensmode" value="fast" /> + </conditional> + </section> + <param name="report_orthologs" value="true"/> + <param name="no_file_comments" value="true"/> + <output name="seed_orthologs" file="DIA_nlim.emapper.seed_orthologs" ftype="tabular" compare="sim_size"/> + <output name="annotations" file="DIA_nlim.emapper.annotations" ftype="tabular" compare="sim_size"/> + <output name="annotations_orthologs" file="DIA_nlim.emapper.annotations_orthologs" ftype="tabular"/> + </test> + <!-- not enabled as it requires a specific .db file, hard to minimize --> + <!--test> + <param name="input" value="Nmar_0135.fa" ftype="fasta"/> + <param name="eggnog_data" value="@EGGNOG_DB_VERSION@"/> + <section name="seed_ortho_options"> + <conditional name="ortho_method"> + <param name="m" value="mmseqs" /> + <param name="start_sens" value="4" /> + </conditional> + </section> + <param name="report_orthologs" value="true"/> + <param name="no_file_comments" value="true"/> + <output name="seed_orthologs" file="DIA_nlim.emapper.seed_orthologs" ftype="tabular" compare="sim_size"/> + <output name="annotations" file="DIA_nlim.emapper.annotations" ftype="tabular" compare="sim_size"/> + <output name="annotations_orthologs" file="DIA_nlim.emapper.annotations_orthologs" ftype="tabular"/> + </test--> </tests> <help><![CDATA[
--- a/test-data/DIA_nlim.emapper.annotations Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/DIA_nlim.emapper.annotations Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,2 @@ -Nmar_0135 436308.Nmar_0135 3.8e-149 510.8 Thaumarchaeota Archaea 41T2K@651137,COG1083@1,arCOG04817@2157 NA|NA|NA M Cytidylyltransferase +#query seed_ortholog evalue score eggNOG_OGs max_annot_lvl COG_category Description Preferred_name GOs EC KEGG_ko KEGG_Pathway KEGG_Module KEGG_Reaction KEGG_rclass BRITE KEGG_TC CAZy BiGG_Reaction PFAMs +Nmar_0135 436308.Nmar_0135 7.67e-188 503.0 COG1083@1|root,arCOG04817@2157|Archaea,41T2K@651137|Thaumarchaeota 651137|Thaumarchaeota M Cytidylyltransferase - - - ko:K07257 - - - - ko00000 - - - -
--- a/test-data/DIA_nlim.emapper.annotations_orthologs Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/DIA_nlim.emapper.annotations_orthologs Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,3 @@ -Nmar_0135 +#query orth_type species orthologs +Nmar_0135 one2one Marine Group I thaumarchaeote SCGC AB-629-I23(1131266) *ARWQ01000003_gene1537 +Nmar_0135 one2one Nitrosopumilus maritimus SCM1(436308) *Nmar_0135
--- a/test-data/DIA_nlim.emapper.seed_orthologs Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/DIA_nlim.emapper.seed_orthologs Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,2 @@ -Nmar_0135 436308.Nmar_0135 3.8e-149 510.8 +#qseqid sseqid evalue bitscore qstart qend sstart send pident qcov scov +Nmar_0135 436308.Nmar_0135 7.67e-188 503.0 1 252 1 252 100.0 100.0 100.0
--- a/test-data/README Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/README Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,1 @@ -cached_locally content is a reduced database, following instructions on https://github.com/galaxyproteomics/egglet +cached_locally content is a reduced database, using the eggnog_tiny.sh and eggnog_tiny_taxa.db (inspired from instructions on https://github.com/galaxyproteomics/egglet)
--- a/test-data/cached_locally/eggnog_mapper_db_versioned.loc Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/cached_locally/eggnog_mapper_db_versioned.loc Tue Jan 25 13:51:50 2022 +0000 @@ -1,2 +1,2 @@ #value name path version -2.0 eggNOG_2.0 ${__HERE__} 2.0 +5.0.2 eggNOG_5.0.2 ${__HERE__} 5.0.2
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/eggnogg_tiny.sh Tue Jan 25 13:51:50 2022 +0000 @@ -0,0 +1,28 @@ +#!/bin/bash + +# Script adapted from https://github.com/galaxyproteomics/egglet to produce a minimal eggnog 5.0.2 database + +sqlite3 $1 << "EOF" + +CREATE TEMP TABLE og +AS SELECT * FROM og +WHERE description = 'Cytidylyltransferase' +AND level LIKE "651137" +LIMIT 1; + +CREATE TEMP TABLE event +AS SELECT * FROM event +WHERE level=651137 +AND og='41T2K' +LIMIT 20; + +CREATE TEMP TABLE prots +AS SELECT * FROM prots +WHERE name = "436308.Nmar_0135"; + +CREATE TEMP TABLE version +AS SELECT * FROM version; + + +.backup temp eggnog_tiny.db +EOF
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/eggnogg_tiny_taxa.sh Tue Jan 25 13:51:50 2022 +0000 @@ -0,0 +1,23 @@ +#!/bin/bash + +# Script adapted from https://github.com/galaxyproteomics/egglet to produce a minimal eggnog 5.0.2 database + +sqlite3 $1 << "EOF" + +CREATE TEMP TABLE species +AS SELECT * FROM species +WHERE taxid in (1131266, 436308); + +CREATE TEMP TABLE synonym +AS SELECT * FROM synonym +WHERE taxid in (1131266, 436308); + +CREATE TEMP TABLE merged +AS SELECT * FROM merged +WHERE taxid_old in (1131266, 436308); + +CREATE TEMP TABLE stats +AS SELECT * FROM stats; + +.backup temp eggnog_tiny_taxa.db +EOF
--- a/test-data/scoped.emapper.annotations Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/scoped.emapper.annotations Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,2 @@ -Nmar_0135 436308.Nmar_0135 3.8e-149 510.8 Thaumarchaeota ko:K07257 ko00000 Thaumarchaeota 41T2K@651137,COG1083@1,arCOG04817@2157 NA|NA|NA M Cytidylyltransferase +#query seed_ortholog evalue score eggNOG_OGs max_annot_lvl COG_category Description Preferred_name GOs EC KEGG_ko KEGG_Pathway KEGG_Module KEGG_Reaction KEGG_rclass BRITE KEGG_TC CAZy BiGG_Reaction PFAMs +Nmar_0135 436308.Nmar_0135 7.67e-188 503.0 COG1083@1|root,arCOG04817@2157|Archaea,41T2K@651137|Thaumarchaeota 651137|Thaumarchaeota M Cytidylyltransferase - - - ko:K07257 - - - - ko00000 - - - -
--- a/test-data/scoped.emapper.annotations_orthologs Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/scoped.emapper.annotations_orthologs Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,3 @@ -Nmar_0135 1131266.ARWQ01000003_gene1537,436308.Nmar_0135 +#query orth_type species orthologs +Nmar_0135 one2one Marine Group I thaumarchaeote SCGC AB-629-I23(1131266) *ARWQ01000003_gene1537 +Nmar_0135 one2one Nitrosopumilus maritimus SCM1(436308) *Nmar_0135
--- a/test-data/scoped.emapper.seed_orthologs Fri Feb 19 18:54:25 2021 +0000 +++ b/test-data/scoped.emapper.seed_orthologs Tue Jan 25 13:51:50 2022 +0000 @@ -1,1 +1,2 @@ -Nmar_0135 436308.Nmar_0135 3.8e-149 510.8 +#qseqid sseqid evalue bitscore qstart qend sstart send pident qcov scov +Nmar_0135 436308.Nmar_0135 7.67e-188 503.0 1 252 1 252 100.0 100.0 100.0
--- a/tool-data/eggnog_mapper_db_versioned.loc.sample Fri Feb 19 18:54:25 2021 +0000 +++ b/tool-data/eggnog_mapper_db_versioned.loc.sample Tue Jan 25 13:51:50 2022 +0000 @@ -3,9 +3,9 @@ # # eggnog-mapper requires the following files to be installed in the data directory: # https://github.com/jhcepas/eggnog-mapper/blob/master/data/og2level.tsv.gz -# http://eggnog5.embl.de/download/emapperdb-5.0.0/eggnog.db.gz +# http://eggnog5.embl.de/download/emapperdb-5.0.2/eggnog.db.gz # A complete diamond database is available from: -# http://eggnog5.embl.de/download/emapperdb-5.0.0/eggnog_proteins.dmnd.gz +# http://eggnog5.embl.de/download/emapperdb-5.0.2/eggnog_proteins.dmnd.gz # # The python script download_eggnog_data.py, # included with eggnog_mapper, can be used to download the files to the correct directory