Mercurial > repos > jjohnson > eggnog_mapper
diff eggnog_mapper.xml @ 2:a74d61dbd155 draft
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/eggnog_mapper commit f431329cd1c7f8a6014207a4ebfd9ffaa67e5497-dirty
| author | jjohnson |
|---|---|
| date | Mon, 04 Nov 2019 16:38:44 -0500 |
| parents | 7de7487a7e8d |
| children | a093b9061498 |
line wrap: on
line diff
--- a/eggnog_mapper.xml Tue Aug 08 12:40:56 2017 -0400 +++ b/eggnog_mapper.xml Mon Nov 04 16:38:44 2019 -0500 @@ -1,24 +1,23 @@ -<tool id="eggnog_mapper" name="eggNOG Mapper" version="0.1.0"> +<tool id="eggnog_mapper" name="eggNOG Mapper" version="@VERSION@.1"> <description>functional sequence annotation by orthology</description> + <macros> + <token name="@VERSION@">1.0.3</token> + </macros> <requirements> - <requirement type="package" version="0.99.2">eggnog-mapper</requirement> + <requirement type="package" version="@VERSION@">eggnog-mapper</requirement> </requirements> - <stdio> - <exit_code range="1:" /> - </stdio> - <version_command>python emapper.py --version</version_command> - <command><![CDATA[ - ### Load on demand - with changes to download_eggnog_data.py - ## #if $db.mode == 'hmmer': - ## download_eggnog_data.py -y -q --data_dir ~/src/eggnog-mapper/data $db.database && - ## #else - ## download_eggnog_data.py -y -q --data_dir ~/src/eggnog-mapper/data $db.database && - ## #end if - emapper.py - --data_dir '$eggnog_data.fields.data_dir' - -m $db.mode $translate - #if $db.mode == 'hmmer': - --database=$db.database + <version_command>emapper.py --version</version_command> + <command detect_errors="aggressive"><![CDATA[ + emapper.py + --data_dir '$eggnog_data.fields.path' + -m $db.mode + $translate + #if ($db.mode == 'hmmer'): + #if $db.database.fields.path: + --database=$db.database.fields.path + #else + --database=$db.database + #end if #if $db.hmm_options.hmm_settings == 'specified': --hmm_maxhits=$db.hmm_options.hmm_maxhits --hmm_evalue=$db.hmm_options.hmm_evalue @@ -29,13 +28,9 @@ #end if --Z=$db.hmm_options.Z #end if - #elif $db.mode == 'diamond': - ## $db.sensitive - ## $db.more_sensitive - --matrix '$db.matrix' - --gapopen '$db.gapopen' - --gapextend '$db.gapextend' - ## --seg '$db.seg' + #elif ($db.mode == 'diamond'): + --matrix '$db.matrix_gapcosts.matrix' + $db.matrix_gapcosts.gap_costs #end if #if $annotation_options.tax_scope: --tax_scope=$annotation_options.tax_scope @@ -49,75 +44,186 @@ #if $seed_ortholog_options.seed_ortholog_evalue: --seed_ortholog_evalue=$seed_ortholog_options.seed_ortholog_evalue #end if - #if $seed_ortholog_options.seed_ortholog_score: + #if str($seed_ortholog_options.seed_ortholog_score): --seed_ortholog_score=$seed_ortholog_options.seed_ortholog_score #end if - $output_options.file_comments + $output_options.no_file_comments $output_options.no_annot $output_options.report_orthologs --output='results' -i '${input}' + --cpu "\${GALAXY_SLOTS:-4}" ]]></command> - <inputs> - <param name="input" type="data" format="fasta" label="Fasta sequences to annotate"/> - <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" - label="Are these CDS sequences that need to be translated"/> - <param name="eggnog_data" type="select" label="Eggnog Data"> - <options from_data_table="eggnog_mapper" > - <filter type="static_value" name="type" value="data" column="2"/> - <validator type="no_options" message="No cached eggnog data is available" /> - </options> - </param> - <conditional name="db"> - <param name="mode" type="select" label="Annotation Type"> - <option value="hmmer">HMM</option> - <option value="diamond">DIAMOND</option> + <inputs> + <param name="input" type="data" format="fasta" label="Fasta sequences to annotate"/> + <param name="eggnog_data" type="select" label="Version of eggNOG Database"> + <options from_data_table="eggnog_mapper_db"/> </param> - <when value="hmmer"> - <param name="database" type="select" multiple="true" min="1" label="HMM target database"> - <options from_data_table="eggnog_mapper" > - <!-- - --> - <filter type="param_value" ref="eggnog_data" column="3" /> - <filter type="static_value" name="type" value="hmmer" column="2"/> - <validator type="no_options" message="No HMM DBs are available, request from your galaxy admin" /> - </options> + <param name="translate" type="boolean" truevalue="--translate" falsevalue="" checked="false" + label="Are these coding DNA sequences that need to be translated?"/> + <conditional name="db"> + <param name="mode" type="select" label="Annotation Type"> + <option value="hmmer">HMM</option> + <option value="diamond">DIAMOND</option> </param> - <conditional name="hmm_options"> - <param name="hmm_settings" type="select" label="HMM Search Options"> - <option value="default">Use defaults</option> - <option value="specified">Set HMM Search Options</option> + <when value="hmmer"> + <param name="database" type="select" label="HMM target database" help="Choose either the full eggNOG database or a subset of it. Contact your Galaxy admin to have additional HMM databases installed."> + <options from_data_table="eggnog_mapper_hmm_dbs"> + <!-- + <filter type="param_value" ref="eggnog_data" column="1" /> + <filter type="unique_value" column="3" /> + <validator type="no_options" message="No HMM databases are available; request installation from your Galaxy admin." /> + --> + </options> </param> - <when value="default"/> - <when value="specified"> - <param name="hmm_maxhits" type="integer" value="1" label="Max number of hits to report. Default=1" /> - <param name="hmm_evalue" type="float" value="0.001" label="E-value threshold. Default=0.001" /> - <param name="hmm_score" type="integer" value="20" label="Bit score threshold. Default=20" /> - <param name="hmm_maxseqlen" type="integer" value="5000" label="Ignore query sequences larger than `maxseqlen`. Default=5000" /> - <param name="hmm_qcov" type="float" value="" min="0." max="1." optional="true" label="min query coverage (from 0 to 1). Default=(disabled)" /> - <param name="Z" type="integer" value="" label="Fixed database size used in phmmer/hmmscan (allows comparing e-values among databases). Default=40,000,000" /> - </when> - </conditional> - </when> - <when value="diamond"> - <param name="database" type="hidden" value="diamond"/> - <param argument="--sensitive" type="boolean" truevalue="--sensitive" falsevalue="" checked="false" label="Trigger the sensitive alignment mode with a 16x9 seed shape configuration?" help=""/> - <param name="more_sensitive" argument="--more-sensitive" type="boolean" truevalue="--more-sensitive" falsevalue="" checked="false" label="Trigger the more sensitive mode?" help="This mode provides some additional sensitivity compared to the sensitive mode."/> - <param argument="--seg" type="boolean" truevalue="yes" falsevalue="no" checked="true" label="Enable SEG masking of low complexity segments in the query?" help=""/> - <param argument="--matrix" type="select" label="Scoring matrix" help="In brackets are the supported values for (gap open)/(gap extend)"> - <option value="BLOSUM45">BLOSUM45 ((10-13)/3; (12-16)/2; (16-19)/1)</option> - <option value="BLOSUM50">BLOSUM50 ((9-13)/3; (12-16)/2; (15-19)/1)</option> - <option value="BLOSUM62" selected="True">BLOSUM62 ((6-11)/2; (9-13)/1)</option> - <option value="BLOSUM80">BLOSUM80 ((6-9)/2; 13/2; 25/2; (9-11)/1)</option> - <option value="BLOSUM90">BLOSUM90 ((6-9)/2; (9-11)/1)</option> - <option value="PAM250">PAM250 ((11-15)/3; (13-17)/2; (17-21)/1)</option> - <option value="PAM70">PAM70 ((6-8)/2; (9-11)/1)</option> - <option value="PAM30">PAM30 ((5-7)/2; (8-10)/1)</option> - </param> - <param argument="--gapopen" type="integer" value="11" label="Gap open penalty" help="" /> - <param argument="--gapextend" type="integer" value="1" label="Gap extension penalty" help="" /> - </when> - </conditional> + <conditional name="hmm_options"> + <param name="hmm_settings" type="select" label="HMM Search Options"> + <option value="default">Use defaults</option> + <option value="specified">Set HMM Search Options</option> + </param> + <when value="default"/> + <when value="specified"> + <param name="hmm_maxhits" type="integer" value="1" label="Max number of hits to report per query sequence"/> + <param name="hmm_evalue" type="float" min="0" value="0.001" label="E-value threshold" /> + <param name="hmm_score" type="integer" min="0" value="20" label="Bit score threshold" /> + <param name="hmm_maxseqlen" type="integer" value="5000" label="Ignore query sequences larger than `maxseqlen`. Default=5000" /> + <param name="hmm_qcov" type="float" value="" min="0." max="1." optional="true" label="min query coverage (from 0 to 1). Default=(disabled)" /> + <param name="Z" type="integer" value="40000000" min="0" label="Fixed database size used in phmmer/hmmscan (allows comparing e-values among databases). Default=40,000,000" /> + </when> + </conditional> + </when> + <when value="diamond"> + <!-- db.database is used in diamond mode only to name outputs --> + <param name="database" type="hidden" 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> + </when> + </conditional> <section name="annotation_options" expanded="false" title="Annotation Options"> <param name="tax_scope" type="select" optional="true" label="Set taxonomic scope"> <option value="NOG">All organisms (NOG)</option> @@ -228,38 +334,39 @@ <option value="verrNOG">Verrucomicrobiae (verrNOG)</option> <option value="virNOG">Viridiplantae (virNOG)</option> </param> - <param name="target_orthologs" type="select" optional="true" label="target orthologs for functional transfer"> + <param name="target_orthologs" type="select" label="target orthologs for functional transfer"> <option value="one2one">one2one</option> <option value="many2one">many2one</option> <option value="one2many">one2many</option> <option value="many2many">many2many</option> - <option value="all">all</option> + <option value="all" selected="true">all</option> </param> - <param name="go_evidence" type="select" optional="true" label="Type of GO terms should be used for annotation"> + <param name="go_evidence" type="select" + 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">non-electronic = Use only non-electronically curated terms</option> + <option value="non-electronic" selected="true">non-electronic = Use only non-electronically curated terms</option> </param> </section> <section name="seed_ortholog_options" expanded="false" title="Seed Ortholog Search Options"> - <param name="seed_ortholog_evalue" type="float" value="0.001" optional="true" label="Min E-value threshold. Default=0.001"> + <param name="seed_ortholog_evalue" type="float" value="0.001" min="0" label="Min E-value threshold"> <help> Min E-value expected when searching for seed eggNOG ortholog. Applies to phmmer/diamond searches. - Queries not having a significant seed orthologs will not be annotated. + 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" optional="true" label="Bit score threshold. Default=60"> + <param name="seed_ortholog_score" type="integer" value="60" min="0" label="Minimum bit score threshold"> <help> - Min bit score expected when searching for seed eggNOG ortholog. Applies to phmmer/diamond searches. - Queries not having a significant seed orthologs will not be annotated. Default=60 + Min bit score expected when searching for seed eggNOG ortholog. + Queries not having a significant seed orthologs will not be annotated. </help> </param> </section> <section name="output_options" expanded="false" title="Output Options"> - <param name="file_comments" type="boolean" truevalue="--no_file_comments" falsevalue="" checked="false" + <param name="no_file_comments" type="boolean" truevalue="--no_file_comments" falsevalue="" checked="true" label="Exclude header lines and stats from output files"/> - <param name="no_annot" type="boolean" truevalue="--no_annot" falsevalue="" checked="false" + <param name="no_annot" type="boolean" truevalue="--no_annot" falsevalue="" checked="false" label="Skip functional annotation, reporting only hits"/> - <param name="report_orthologs" type="boolean" truevalue="--report_orthologs" falsevalue="" checked="false" + <param name="report_orthologs" type="boolean" truevalue="--report_orthologs" falsevalue="" checked="false" label="Output a file with the list of orthologs for each hits"/> </section> </inputs> @@ -272,7 +379,7 @@ <data name="annotations" format="tabular" label="${tool.name} on ${on_string}: ${db.database}.annotations" from_work_dir="results.emapper.annotations"> <filter>not output_options['no_annot']</filter> <actions> - <action name="column_names" type="metadata" default="query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,predicted_gene_name,GO_terms,KEGG_pathways,Annotation_tax_scope,Matching_OGs,best_OG|evalue|score,COG,functional,categories,eggNOG_HMM_model_annotation"/> + <action name="column_names" type="metadata" default="query_name,seed_eggNOG_ortholog,seed_ortholog_evalue,seed_ortholog_score,predicted_gene_name,GO_terms,KEGG_KO,BiGG_Reactions,Annotation_tax_scope,Matching_OGs,best_OG|evalue|score,COG_functional_categories,eggNOG_HMM_model_annotation"/> </actions> </data> <data name="hmm_hits" format="tabular" label="${tool.name} on ${on_string}: ${db.database}.hmm_hits" from_work_dir="results.emapper.hmm_hits"> @@ -288,98 +395,84 @@ </actions> </data> </outputs> + <tests> + <test> + <param name="input" value="nlim_fragment.fasta" ftype="fasta"/> + <param name="database" value="ENOG411CB2I"/> + <param name="mode" value="hmmer"/> + <!-- + <param name="test" value="true"/> + --> + <param name="eggnog_data" value="4.5"/> + <param name="no_annot" value="true"/> + <param name="no_file_comments" value="true"/> + <output name="hmm_hits" file="HMM_nlim.emapper.hmm_hits" ftype="tabular"/> + </test> + <test> + <param name="input" value="nlim_fragment.fasta" ftype="fasta"/> + <param name="eggnog_data" value="4.5"/> <!-- not passed in test, but required for test to work --> + <param name="no_annot" value="true"/> + <param name="mode" value="diamond"/> + <output name="seed_orthologs" file="DIA_nlim.emapper.seed_orthologs" ftype="tabular"/> + </test> + </tests> <help><![CDATA[ eggnog-mapper - -optional arguments: - -h, --help show this help message and exit - --version +============= +Overview +-------- -Target HMM Database Options: - --guessdb guess eggnog db based on the provided taxid - --database , -d specify the target database for sequence searches. - Choose among: euk,bact,arch, host:port, or a local - hmmpressed database - --dbtype {hmmdb,seqdb} - --qtype {hmm,seq} +``eggnog-mapper`` is a tool for fast functional annotation of novel sequences (genes or proteins) using precomputed eggNOG-based orthology assignments. +Obvious examples include the annotation of novel genomes, transcriptomes or even metagenomic gene catalogs. +The use of orthology predictions for functional annotation is considered more precise than traditional homology searches, +as it avoids transferring annotations from paralogs (duplicate genes with a higher chance of being involved in functional divergence). + +EggNOG-mapper is also available as a public online resource: `<http://beta-eggnogdb.embl.de/#/app/emapper>`_. -Annotation Options: - --tax_scope Fix the taxonomic scope used for annotation, so only - orthologs from a particular clade are used for - functional transfer. By default, this is automatically - adjusted for every query sequence. - --target_orthologs {one2one,many2one,one2many,many2many,all} - defines what type of orthologs should be used for - functional transfer - --excluded_taxa (for debugging and benchmark purposes) - --go_evidence {experimental,non-electronic} - Defines what type of GO terms should be used for - annotation:experimental = Use only terms inferred from - experimental evidencenon-electronic = Use only non- - electronically curated terms +Options +------- + +``eggnog-mapper`` can use two search algorithms: `HMMER <http://hmmer.org/>`_ and `DIAMOND <https://github.com/bbuchfink/diamond>`_. +HMMER is more sensitive, while DIAMOND is faster and useful for larger sets of query sequences. -HMM search_options: - --hmm_maxhits Max number of hits to report. Default=1 - --hmm_evalue E-value threshold. Default=0.001 - --hmm_score Bit score threshold. Default=20 - --hmm_maxseqlen Ignore query sequences larger than `maxseqlen`. - Default=5000 - --hmm_qcov min query coverage (from 0 to 1). Default=(disabled) - --Z Fixed database size used in phmmer/hmmscan (allows - comparing e-values among databases). - Default=40,000,000 + +Outputs +------- + +**hmm_hits** -Seed ortholog search option: - --seed_ortholog_evalue - Min E-value expected when searching for seed eggNOG - ortholog. Applies to phmmer/diamond searches. Queries - not having a significant seed orthologs will not be - annotated. Default=0.001 - --seed_ortholog_score - Min bit score expected when searching for seed eggNOG - ortholog. Applies to phmmer/diamond searches. Queries - not having a significant seed orthologs will not be - annotated. Default=60 +For each query sequence, a list of significant +hits to eggNOG Orthologous Groups (OGs) is reported. +Each line in the file represents a hit, where evalue, bit-score, +query-coverage and the sequence coordinates of the match are reported. +If multiple hits exist for a given query, results are sorted by e-value. +Only returned when using HMMER mode. + +**seed_orthologs** + +each line in the file provides the best match of each query within the best Orthologous Group (OG) +reported in the [project].hmm_hits file, obtained running PHMMER against all sequences within the best OG. +The seed ortholog is used to fetch fine-grained orthology relationships from eggNOG. +If using the diamond search mode, seed orthologs are directly +obtained from the best matching sequences by running DIAMOND against the whole eggNOG protein space. -Output options: - --output , -o base name for output files - --resume Resumes a previous execution skipping reported hits in - the output file. - --override Overwrites output files if they exist. - --no_refine Skip hit refinement, reporting only HMM hits. - --no_annot Skip functional annotation, reporting only hits - --no_search Skip HMM search mapping. Use existing hits file - --report_orthologs The list of orthologs used for functional transferred - are dumped into a separate file - --scratch_dir Write output files in a temporary scratch dir, move - them to final the final output dir when finished. - Speed up large computations using network file - systems. - --output_dir Where output files should be written - --temp_dir Where temporary files are created. Better if this is a - local disk. - --no_file_comments No header lines nor stats are included in the output - files - --keep_mapping_files Do not delete temporary mapping files used for - annotation (i.e. HMMER and DIAMOND search outputs) +**annotations** + +This file provides final annotations of each query. Tab-delimited columns in the file are: -Execution options: - -m {hmmer,diamond} Default:hmmer - -i Computes annotations for the provided FASTA file - --translate Assume sequences are genes instead of proteins - --servermode Loads target database in memory and keeps running in - server mode, so another instance of eggnog-mapper can - connect to this sever. Auto turns on the --usemem flag - --usemem If a local hmmpressed database is provided as target - using --db, this flag will allocate the whole database - in memory using hmmpgmd. Database will be unloaded - after execution. - --cpu - --annotate_hits_table - Annotatate TSV formatted table of query->hits. 4 - fields required: query, hit, evalue, score. Implies - --no_search and --no_refine. +- ``query_name``: query sequence name +- ``seed_eggNOG_ortholog``: best protein match in eggNOG +- ``seed_ortholog_evalue``: best protein match (e-value) +- ``seed_ortholog_score``: best protein match (bit-score) +- ``predicted_gene_name``: Predicted gene name for query sequences +- ``GO_terms``: Comma delimited list of predicted Gene Ontology terms +- ``KEGG_pathways``: Comma delimited list of predicted KEGG pathways +- ``Annotation_tax_scope``: The taxonomic scope used to annotate this query sequence +- ``Matching_OGs``: Comma delimited list of matching eggNOG Orthologous Groups +- ``best_OG|evalue|score``: Best matching Orthologous Groups (only in HMM mode) +- ``COG functional categories``: COG functional category inferred from best matching OG +- ``eggNOG_HMM_model_annotation``: eggNOG functional description inferred from best matching OG ]]></help> <citations>