Mercurial > repos > iuc > hmmer_hmmsearch
changeset 11:405dd85a9408 draft default tip
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hmmer3 commit e0d4688a59e6eeba33adcfe803ac43d0bc2863e7"
| author | iuc |
|---|---|
| date | Tue, 31 Aug 2021 08:43:59 +0000 |
| parents | ffeedf9b8dce |
| children | |
| files | hmmbuild.xml.orig hmmscan.xml.orig hmmsearch.xml hmmsearch.xml.orig jackhmmer.xml.orig macros.xml macros.xml.orig nhmmer.xml.orig nhmmscan.xml.orig phmmer.xml.orig |
| diffstat | 10 files changed, 1892 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/hmmbuild.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,114 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_hmmbuild" name="hmmbuild" version="@TOOL_VERSION@+galaxy1"> + <description>Build a profile HMM from an input multiple alignment</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_hmmbuild" name="hmmbuild" version="@TOOL_VERSION@"> + <description>Build a profile HMM from an input multiple alignment</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +hmmbuild + +#if $hmmname: + -n '$hmmname' +#end if + +@FORMAT_SELECTOR@ +@MCSS@ +@ARSWS@ +@AEEWS@ +@PRIOR@ +@HSSI@ +@EVAL_CALIB@ + +@CPU@ +@SEED@ + +@LENGTHS@ +#if str($maxinsertlen): + --maxinsertlen $maxinsertlen +#end if + +'$hmmout' +'$msafile' + ]]></command> + <inputs> + <expand macro="input_msa" /> + <param name="hmmname" argument="-n" type="text" optional="true" label="Name for the HMM" /> + <expand macro="format_selector"/> + <expand macro="mcss"/> + <expand macro="arsws"/> + <expand macro="aeews"/> + <expand macro="prior"/> + <expand macro="hssi"/> + <expand macro="eval_calib_xml"/> + <expand macro="seed"/> + + <expand macro="lengths" /> + <param argument="--maxinsertlen" type="integer" optional="true" label="Pretend all inserts are length <= n" /> + </inputs> + <outputs> + <data name="hmmout" format="hmm3" label="HMM profile from $msafile.name"/> + </outputs> + <tests> + <test> + <param name="msafile" value="globins4.sto"/> + <expand macro="seed_test" /> + <output name="hmmout" file="globins4.hmm" compare="sim_size"> + <assert_contents> + <has_line_matching expression="HMMER3/f.*"/> + <has_line_matching expression="ALPH amino"/> + <has_line_matching expression="NSEQ 4"/> + <has_line_matching expression="//"/> + </assert_contents> + </output> + </test> + <test> + <param name="msafile" value="MADE1.sto"/> + <param name="input_format_select" value="--dna"/> + <expand macro="seed_test" /> + <output name="hmmout" file="MADE1.hmm" compare="sim_size"> + <assert_contents> + <has_line_matching expression="HMMER3/f.*"/> + <has_line_matching expression="ALPH DNA"/> + <has_line_matching expression="NSEQ 1997"/> + <has_line_matching expression="//"/> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +For each multiple sequence alignment in <msafile> build a profile HMM and save +it to a new file <hmmfile out>. + +@HELP_PRE_OTH@ + +@FORMAT_SELECTOR_HELP@ +@MCSS_HELP@ +@ARSWS_HELP@ +@AEEWS_HELP@ +@PRIOR_HELP@ +@HSSI_HELP@ +@EVAL_CALIB_HELP@ +@SEED_HELP@ +@LENGTHS_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/hmmscan.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,93 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_hmmscan" name="hmmscan" version="@TOOL_VERSION@+galaxy1"> + <description>search protein sequence(s) against a protein profile database</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_hmmscan" name="hmmscan" version="@TOOL_VERSION@"> + <description>search protein sequence(s) against a protein profile database</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +@INPUTHMMCHOICE@ +hmmscan + +@OFORMAT_WITH_OPTS@ +@THRESHOLDS@ +@CUT@ +@ACCEL_HEUR@ +@ADV_OPTS@ +@CPU@ +@SEED@ + +'$input_hmm_filename' +'$seqfile' +> '$output' + ]]></command> + <inputs> + <expand macro="input_hmm_choice" /> + <!-- todo use Galaxy features like data libraries/data tables/??? --> + <param name="seqfile" type="data" format="fasta" label="Sequence file"/> + <expand macro="oformat_with_opts_dom_pfam"/> + <expand macro="thresholds_xml"/> + <expand macro="cut"/> + <expand macro="accel_heur_xml"/> + <expand macro="adv_opts"/> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dom_pfam" tool="HMMSCAN"/> + </outputs> + <tests> + <test expect_num_outputs="4"> + <param name="input_hmm_conditional|input_hmm_source" value="history"/> + <param name="input_hmm_conditional|hmmfile" value="MADE1.hmm"/> + <param name="seqfile" value="dna_target.fa"/> + <expand macro="oformat_test" /> + <expand macro="seed_test" /> + <output name="output" file="MADE1.out" lines_diff="24"> + <expand macro="assert_out" tool="hmmscan"/> + </output> + <output name="tblout" file="MADE1.out.tblout" lines_diff="14"> + <expand macro="assert_tblout" tool="hmmscan"/> + </output> + <output name="domtblout" file="MADE1.out.domtblout" lines_diff="10"> + <expand macro="assert_tblout" tool="hmmscan"/> + </output> + <output name="pfamtblout" file="MADE1.out.pfamtblout" lines_diff="10"> + <expand macro="assert_tblout" tool="hmmscan"/> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +hmmscan is used to search protein sequences against collections of protein +profiles. For each sequence in <seqfile>, use that query sequence to search the +target database of profiles in <hmmfile>, and output ranked lists of the profiles +with the most significant matches to the sequence. + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_HELP@ +@THRESHOLDS_HELP@ +@CUT_HELP@ +@ACCEL_HEUR_HELP@ +@ADV_OPTS_HELP@ +@SEED_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>
--- a/hmmsearch.xml Wed Jul 21 14:06:36 2021 +0000 +++ b/hmmsearch.xml Tue Aug 31 08:43:59 2021 +0000 @@ -1,6 +1,7 @@ <?xml version="1.0"?> <tool id="hmmer_hmmsearch" name="hmmsearch" version="@TOOL_VERSION@+galaxy0"> <description>search profile(s) against a sequence database</description> + <expand macro="bio_tools"/> <macros> <import>macros.xml</import> </macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/hmmsearch.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,102 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_hmmsearch" name="hmmsearch" version="@TOOL_VERSION@+galaxy1"> + <description>search profile(s) against a sequence database</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_hmmsearch" name="hmmsearch" version="@TOOL_VERSION@"> + <description>search profile(s) against a sequence database</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +hmmsearch + +@OFORMAT_WITH_OPTS@ +@THRESHOLDS@ +@CUT@ +@ACCEL_HEUR@ +@ADV_OPTS@ +@CPU@ +@SEED@ + +'$hmmfile' +'$seqdb' +> '$output' + ]]></command> + <inputs> + <expand macro="input_hmm" /> + <!-- todo use Galaxy features like data libraries/data tables/??? --> + <param name="seqdb" type="data" format="fasta" label="Sequence database to search against"/> + <expand macro="oformat_with_opts_dom_pfam"/> + <expand macro="thresholds_xml"/> + <expand macro="cut"/> + <expand macro="accel_heur_xml"/> + <expand macro="adv_opts"/> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dom_pfam" tool="PHMMER"/> + </outputs> + <tests> + <test expect_num_outputs="4"> + <param name="hmmfile" value="globins4.hmm"/> + <param name="seqdb" value="uniprot_matches.fasta"/> + <expand macro="oformat_test" /> + <expand macro="seed_test" /> + <output name="output" file="uniprot_globins_match.out" lines_diff="20"> + <expand macro="assert_out" tool="hmmsearch"/> + </output> + <output name="domtblout" file="globins.domtblout" lines_diff="16"> + <expand macro="assert_tblout" tool="hmmsearch"/> + </output> + <output name="pfamtblout" file="globins.pfamtblout" lines_diff="12"> + <expand macro="assert_tblout" tool="hmmsearch"/> + </output> + <output name="tblout" file="globins.tblout" lines_diff="16"> + <expand macro="assert_tblout" tool="hmmsearch"/> + </output> + </test> + <test expect_num_outputs="1"> + <param name="hmmfile" value="globins4.hmm"/> + <param name="seqdb" value="uniprot_matches.fasta"/> + <expand macro="oformat_test" /> + <param name="oformat" value=""/> + <expand macro="seed_test" /> + <output name="output" file="uniprot_globins_match.out" lines_diff="20"> + <expand macro="assert_out" tool="hmmsearch"/> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +hmmsearch is used to search one or more profiles against a sequence database. +For each profile in <hmmfile>, use that query profile to search the target +database of sequences in <seqdb>, and output ranked lists of the sequences with +the most significant matches to the profile. To build profiles from multiple +alignments, see hmmbuild. + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_HELP@ +@THRESHOLDS_HELP@ +@CUT_HELP@ +@ACCEL_HEUR_HELP@ +@ADV_OPTS_HELP@ +@SEED_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/jackhmmer.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,116 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_jackhmmer" name="jackhmmer" version="@TOOL_VERSION@+galaxy1"> + <description>iteratively search a protein sequence against a protein database (PSIBLAST-like)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_jackhmmer" name="jackhmmer" version="@TOOL_VERSION@"> + <description>iteratively search a protein sequence against a protein database (PSIBLAST-like)</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +jackhmmer +-N $N +@OFORMAT_WITH_OPTS@ +@HSSI@ +@THRESHOLDS@ +@ACCEL_HEUR@ +@ARSWS@ +@AEEWS@ +@PRIOR@ + +@EVAL_CALIB@ +@ADV_OPTS@ +@CPU@ +@SEED@ + +'$seqfile' +'$seqdb' +> '$output' + ]]></command> + <inputs> + <param name="seqfile" type="data" format="fasta" label="Protein sequence to search with"/> + <!-- todo use Galaxy features like data libraries/data tables/??? --> + <param name="N" type="integer" value="5" min="1" label="Maximum number of iterations" help="(-N)"/> + <param name="seqdb" type="data" format="fasta" label="Sequence Database"/> + <expand macro="oformat_with_opts_dom"/> + <expand macro="hssi"/> + <expand macro="thresholds_xml"/> + <expand macro="accel_heur_xml"/> + <expand macro="arsws"/> + <expand macro="aeews"/> + <expand macro="prior"/> + <expand macro="eval_calib_xml"/> + <expand macro="adv_opts"/> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dom_pfam" tool="JACKHMMER"/> + </outputs> + <tests> + <test expect_num_outputs="3"> + <param name="seqfile" value="uniprot_matches.fasta"/> + <param name="seqdb" value="globins45.fa"/> + <expand macro="oformat_test" /> + <expand macro="seed_test" /> + <output name="output" file="jackhmmer.out" lines_diff="180"> + <expand macro="assert_out" tool="jackhmmer"/> + </output> + <output name="domtblout" file="jackhmmer.domtblout" lines_diff="10"> + <expand macro="assert_tblout" tool="jackhmmer"/> + </output> + <output name="tblout" file="jackhmmer.tblout" lines_diff="10"> + <expand macro="assert_tblout" tool="jackhmmer"/> + </output> + </test> + <test expect_num_outputs="1"> + <param name="seqfile" value="uniprot_matches.fasta"/> + <param name="seqdb" value="globins45.fa"/> + <expand macro="oformat_test" /> + <param name="oformat" value=""/> + <expand macro="seed_test" /> + <output name="output" file="jackhmmer.out" lines_diff="180"> + <expand macro="assert_out" tool="jackhmmer"/> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +jackhmmer iteratively searches each query sequence in <seqfile> against the +target sequence(s) in <seqdb>. The first iteration is identical to a phmmer +search. For the next iteration, a multiple alignment of the query together +with all target sequences satisfying inclusion thresholds is assembled, a +profile is constructed from this alignment (identical to using hmmbuild on the +alignment), and profile search of the <seqdb> is done (identical to an +hmmsearch with the profile). + + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_HELP_NOPFAM@ +@HSSI_HELP@ +@THRESHOLDS_HELP@ +@ACCEL_HEUR_HELP@ +@ARSWS_HELP@ +@AEEWS_HELP@ +@PRIOR_HELP@ +@EVAL_CALIB_HELP@ +@ADV_OPTS_HELP@ +@SEED_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>
--- a/macros.xml Wed Jul 21 14:06:36 2021 +0000 +++ b/macros.xml Tue Aug 31 08:43:59 2021 +0000 @@ -6,6 +6,11 @@ <yield/> </requirements> </xml> + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">hmmer3</xref> + </xrefs> + </xml> <token name="@TOOL_VERSION@">3.3.2</token> <xml name="stdio"> <stdio>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,1126 @@ +<?xml version="1.0"?> +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">hmmer</requirement> + <yield/> + </requirements> + </xml> +<<<<<<< HEAD + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">gemini</xref> + </xrefs> + </xml> +======= + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">hmmer3</xref> + </xrefs> + </xml> +>>>>>>> 5f65381bd (fix id of hmmer3) + <token name="@TOOL_VERSION@">3.3.2</token> + <xml name="stdio"> + <stdio> + <!-- Anything other than zero is an error --> + <exit_code range="1:"/> + <exit_code range=":-1"/> + <!-- In case the return code has not been set propery check stderr too --> + <regex match="Error:"/> + <regex match="Exception:"/> + </stdio> + </xml> + <token name="@THRESHOLDS@"> +-E $E +--domE $domE + +#if str($T): + -T $T +#end if + +#if str($domT): + --domT $domT +#end if + +#if str($incE): + --incE $incE +#end if + +#if str($incdomE): + --incdomE $incdomE +#end if + +#if str($incT): + --incT $incT +#end if + +#if str($incdomT): + --incdomT $incdomT +#end if + </token> + <xml name="thresholds_xml"> + <!-- Options controlling reporting thresholds --> + <param argument="-E" type="float" min="0" value="10.0" label="report sequences <= this E-Value threshold in output" /> + <param argument="--domE" type="float" min="0" value="10.0" label="report domains <= this E-Value threshold in output" /> + <param argument="-T" type="float" optional="true" label="report sequences >= this score threshold in output" /> + <param argument="--domT" type="float" optional="true" label="report domains >= this score threshold in output" /> + <!-- Options controlling inclusion (significance) thresholds --> + <param argument="--incE" type="float" optional="true" label="consider sequences <= this E-Value threshold as significant" /> + <param argument="--incdomE" type="float" optional="true" label="consider domains <= this E-Value threshold as significant" /> + <param argument="--incT" type="float" optional="true" label="consider sequences >= this score threshold as significant" /> + <param argument="--incdomT" type="float" optional="true" label="consider domains >= this score threshold as significant" /> + </xml> + <token name="@THRESHOLDS_NODOM@"> +-E $E + +#if str($T): + -T $T +#end if + +#if str($incE): + --incE $incE +#end if + +#if str($incT): + --incT $incT +#end if + </token> + <xml name="thresholds_nodom"> + <!-- Options controlling reporting thresholds --> + <param argument="-E" type="float" min="0" value="10.0" label="report sequences <= this E-Value threshold in output" /> + <param argument="-T" type="float" optional="true" label="report sequences >= this score threshold in output" /> + <!-- Options controlling inclusion (significance) thresholds --> + <param argument="--incE" type="float" optional="true" label="consider sequences <= this E-Value threshold as significant" /> + <param argument="--incT" type="float" optional="true" label="consider sequences >= this score threshold as significant" /> + </xml> + <token name="@ACCEL_HEUR@"> +$max +--F1 $F1 +--F2 $F2 +--F3 $F3 +$nobias + </token> + <xml name="accel_heur_xml"> + <!-- Options controlling acceleration heuristics --> + <param argument="--max" type="boolean" truevalue="--max" falsevalue="" label="Turn all heuristic filters off (less speed, more power)" /> + <param argument="--F1" type="float" value="0.02" label="Stage 1 (MSV) threshold: promote hits w/ P <= F1" /> + <param argument="--F2" type="float" value="1e-3" label="Stage 2 (Vit) threshold: promote hits w/ P <= F2" /> + <param argument="--F3" type="float" value="1e-5" label="Stage 3 (Fwd) threshold: promote hits w/ P <= F3" /> + <param argument="--nobias" type="boolean" truevalue="--nobias" falsevalue="" label="Turn off composition bias filter" /> + </xml> + <token name="@EVAL_CALIB@"> +--EmL $EmL +--EmN $EmN +--EvL $EvL +--EvN $EvN +--EfL $EfL +--EfN $EfN +--Eft $Eft + </token> + <xml name="eval_calib_xml"> + <!-- Control of E-value calibration --> + <param argument="--EmL" type="integer" min="1" value="200" label="Length of sequences for MSV Gumbel mu fit" /> + <param argument="--EmN" type="integer" min="1" value="200" label="Number of sequences for MSV Gumbel mu fit" /> + <param argument="--EvL" type="integer" min="1" value="200" label="Length of sequences for Viterbi Gumbel mu fit" /> + <param argument="--EvN" type="integer" min="1" value="200" label="Number of sequences for Viterbi Gumbel mu fit" /> + <param argument="--EfL" type="integer" min="1" value="100" label="Length of sequences for Forward exp tail tau fit" /> + <param argument="--EfN" type="integer" min="1" value="200" label="Number of sequences for Forward exp tail tau fit" /> + <param argument="--Eft" type="float" min="0" max="1" value="0.04" label="tail mass for Forward exponential tail tau fit" /> + </xml> + <token name="@OFORMAT_WITH_OPTS@"> +#if $oformat: + #for o in str($oformat).split(','): + --$o '$getVar($o, 'MISSING_OUTPUT'+$o)' + #end for +#end if +$acc $noali $notextw + </token> + <xml name="oformat_with_opts"> + <!-- Options directing output --> + <param name="oformat" type="select" multiple="true" display="checkboxes" label="Output Formats"> + <option value="tblout" selected="true">Table of per-sequence hits (--tblout)</option> + <yield/> + </param> + <param argument="--acc" type="boolean" truevalue="--acc" falsevalue="" label="Prefer accessions over names in output" /> + <param argument="--noali" type="boolean" truevalue="--noali" falsevalue="" label="Don't output alignments, so output is smaller" /> + <param argument="--notextw" type="boolean" truevalue="--notextw" falsevalue="" label="Unlimited ASCII text output line width" /> + </xml> + + <xml name="oformat_with_opts_dom"> + <expand macro="oformat_with_opts"> + <option value="domtblout" selected="true">Table of per-domain hits (--domtblout)</option> + <yield/> + </expand> + </xml> + + <xml name="oformat_with_opts_dom_pfam"> + <expand macro="oformat_with_opts_dom"> + <option value="pfamtblout" selected="true">Table of hits and domains in Pfam format (--pfamtblout)</option> + </expand> + </xml> + + <xml name="oformat_with_opts_dfam_alisc"> + <!-- Options directing output --> + <expand macro="oformat_with_opts"> + <option value="dfamtblout" selected="true">Table of hits in Dfam format (--dfamtblout)</option> + <option value="aliscoresout">Scores for each position in each alignment to file (--aliscoresout)</option> + </expand> + </xml> + + <xml name="output" token_tool=""> + <data name="output" format="txt" label="@TOOL@ on ${on_string}"/> + <data name="tblout" format="txt" label="@TOOL@ on ${on_string}: per-sequence hits from HMM matches"> + <filter>oformat and 'tblout' in oformat</filter> + </data> + <yield/> + </xml> + <xml name="output_dom" token_tool=""> + <expand macro="output" tool="@TOOL@"> + <data name="domtblout" format="txt" label="@TOOL@ on ${on_string}: per-domain hits from HMM matches"> + <filter>oformat and 'domtblout' in oformat</filter> + </data> + </expand> + <yield/> + </xml> + <xml name="output_dom_pfam" token_tool=""> + <expand macro="output_dom" tool="@TOOL@"> + <data name="pfamtblout" format="txt" label="@TOOL@ on ${on_string}: per-sequence/per-domain hits from HMM matches"> + <filter>oformat and 'pfamtblout' in oformat</filter> + </data> + </expand> + </xml> + <xml name="output_dfam_alisc" token_tool="" token_ofvar="seqfile" token_invar="seqdb"> + <expand macro="output" tool="@TOOL@"> + <data name="dfamtblout" format="txt" label="@TOOL@ on ${on_string}: per-sequence/per-domain hits from HMM matches"> + <filter>oformat and 'dfamtblout' in oformat</filter> + </data> + <data name="aliscoresout" format="txt" label="@TOOL@ on ${on_string}: scores for positional matches"> + <filter>oformat and 'aliscoresout' in oformat</filter> + </data> + </expand> + </xml> + + <xml name="assert_out" token_tool=""> + <assert_contents> + <has_line_matching expression="# @TOOL@.*"/> + <has_line_matching expression="\[ok\]"/> + </assert_contents> + </xml> + + <xml name="assert_tblout" token_tool=""> + <assert_contents> + <has_line_matching expression="# Program: @TOOL@"/> + <has_line_matching expression="# \[ok\]"/> + </assert_contents> + </xml> + + <xml name="oformat_test"> + <param name="notextw" value="true" /> + </xml> + <token name="@HSSI@"> +#if $hssi.hssi_select == "singlemx": + --popen $hssi.popen + --pextend $hssi.pextend +#end if + </token> + <xml name="hssi"> + <!-- Handling single sequence inputs --> + <conditional name="hssi"> + <param name="hssi_select" type="select" label="Options for handling single sequence inputs"> + <option value="false" selected="true">Disable</option> + <option value="singlemx">Use substitution score matrix for single-sequence inputs</option> + </param> + <when value="false" /> + <when value="singlemx"> + <param argument="--popen" type="float" min="0.0" max="0.5" value="0.02" label="Gap open probability" /> + <param argument="--pextend" type="float" min="0.0" max="1.0" value="0.4" label="Gap extend probability" /> + </when> + <!-- -mx <s> : substitution score matrix (built-in matrices, with -singlemx)--> + <!-- -mxfile <f> : read substitution score matrix from file <f> (with -singlemx)--> + </conditional> + </xml> + <token name="@ADDTHREADS@"><![CDATA[ + ##compute the number of ADDITIONAL threads to be used (--cpu) + addthreads=\${GALAXY_SLOTS:-1} && (( addthreads-- )) && + ]]></token> + <token name="@CPU@"> + --cpu \$addthreads + </token> + <token name="@SEED@"> + --seed $seed + </token> + <xml name="seed"> + <param argument="--seed" type="integer" min="0" value="42" label="RNG seed, 0 generates a random seed" /> + </xml> + <xml name="seed_test"> + <param name="seed" value="4" /> + </xml> + <token name="@ADV_OPTS@"> +$nonull2 + +#if str($Z): + -Z $Z +#end if + +#if str($domZ): + --domZ $domZ +#end if + </token> + <xml name="adv_opts"> + <!-- Other options --> + <param argument="--nonull2" type="boolean" truevalue="--nonull2" falsevalue="" label="Turn off biased composition score corrections" /> + <param argument="-Z" type="integer" optional="true" label="# of comparisons done for E-value calculation" /> + <param argument="--domZ" type="integer" optional="true" label="# of significant sequences, for domain E-value calculation" /> + </xml> + <token name="@FORMAT_SELECTOR@"> + $input_format_select + </token> + <xml name="format_selector"> + <param name="input_format_select" type="select" label="Format of sequence and model"> + <option value="--amino">Protein</option> + <option value="--dna">DNA</option> + <option value="--rna">RNA</option> + </param> + </xml> + <xml name="format_selector_noprot"> + <param name="input_format_select" type="select" label="Format of sequence and model"> + <option value="--dna">DNA</option> + <option value="--rna">RNA</option> + </param> + </xml> + <token name="@ARSWS@"> +$arsws.arsws_select + +#if $arsws.arsws_select == "--wblosum": + --wid $arsws.wid +#end if + </token> + <xml name="arsws"> + <!-- Alternative relative sequence weighting strategies --> + <conditional name="arsws"> + <param name="arsws_select" type="select" label="Alternative relative sequence weighting strategies"> + <option value="--wpb" selected="true">Henikoff position-based weights (--wpb)</option> + <option value="--wgsc">Gerstein/Sonnhammer/Chothia tree weights (--wgsc)</option> + <option value="--wblosum">Henikoff simple filter weights (--wblosum)</option> + <option value="--wnone">don't do any relative weighting; set all to 1 (--wnnoe)</option> + <option value="--wgiven">use weights as given in MSA file (--wgiven)</option> + </param> + <when value="--wpb"> + </when> + <when value="--wgsc"> + </when> + <when value="--wblosum"> + <param argument="--wid" type="float" value="0.62" label="Set identity cutoff" /> + </when> + <when value="--wnone"> + </when> + <when value="--wgiven"> + </when> + </conditional> + </xml> + <token name="@AEEWS@"> +#if $aeews.aeews_select != "": +--$aeews.aeews_select + #if $aeews.aeews_select == "eent": + --eset $aeews.eset + --ere $aeews.ere + --esigma $aeews.esigma + #elif $aeews.aeews_select == "eclust": + --eset $aeews.eset + --eid $aeews.eid + #end if +#end if + </token> + <xml name="aeews"> + <!-- Alternative effective sequence weighting strategies --> + <conditional name="aeews"> + <param name="aeews_select" type="select" label="Alternative effective sequence weighting strategies"> + <option value="">Disabled</option> + <option value="eent">Adjust eff seq # to achieve relative entropy target (--eent)</option> + <option value="eclust">Eff seq # is the # of single linkage clusters (--eclust)</option> + <option value="enone">No effective seq # weighting: just use nseq (--enone)</option> + </param> + <when value=""> + </when> + <when value="eent"> + <param argument="--eset" type="float" value="0" label="set eff seq # for all models" /> + <param argument="--ere" type="float" value="0" label="set minimum rel entropy/position" /> + <param argument="--esigma" type="float" value="45" label="set sigma param" /> + </when> + <when value="eclust"> + <param argument="--eset" type="float" value="0" label="set eff seq # for all models" /> + <param argument="--eid" type="float" min="0" max="1" value="0.62" label="set fractional identity cutoff" /> + </when> + <when value="enone"> + </when> + </conditional> + </xml> + <token name="@CUT@"> +$cut_ga +$cut_nc +$cut_tc + </token> + <xml name="cut"> + <param argument="--cut_ga" type="boolean" truevalue="--cut_ga" falsevalue="" label="use profile's GA gathering cutoffs to set all thresholding" /> + <param argument="--cut_nc" type="boolean" truevalue="--cut_nc" falsevalue="" label="use profile's NC gathering cutoffs to set all thresholding" /> + <param argument="--cut_tc" type="boolean" truevalue="--cut_tc" falsevalue="" label="use profile's TC gathering cutoffs to set all thresholding" /> + </xml> + <token name="@MCSS@"> +--$mcs.model_construction_strategy_select + +#if $mcs.model_construction_strategy_select == "fast": + --symfrac $mcs.symfrac +#end if +#if str($fragthresh) + --fragthresh $fragthresh +#end if + </token> + <xml name="mcss"> + <!-- Alternative model construction strategies --> + <conditional name="mcs"> + <param name="model_construction_strategy_select" type="select" label="Model Construction Strategy"> + <option value="fast" selected="true">Assign columns with >= symfrac residues as consensus (--fast)</option> + <option value="hand">Manual construction (requires reference annotation) (--hand)</option> + </param> + <when value="fast"> + <param argument="--symfrac" value="0.5" type="float" label="Sets sym fraction controlling --fast construction"/> + </when> + <when value="hand"></when> + </conditional> + <param argument="--fragthresh" type="float" value="0.5" optional="true" label="Fraction of alignment length, under which sequences are excluded" help="HMMER infers fragments if the sequence length L is less than or equal to a fraction x times the alignment length in columns" /> + </xml> + <token name="@PRIOR@"> +$aps_select + </token> + <xml name="prior"> + <param name="aps_select" type="select" label="Alternative Prior Strategies"> + <option value="" selected="true">Unspecified</option> + <option value="--pnone">Don't use any prior; parameters are frequencies (--pnone)</option> + <option value="--plaplace">Use a Laplace +1 prior (--plaplace)</option> + </param> + </xml> + <xml name="citation"> + <citations> + <citation type="doi">10.1093/nar/gkr367</citation> + </citations> + </xml> + <token name="@LENGTHS@"> +#if str($w_beta): + --w_beta $w_beta +#end if + +#if str($w_length): + --w_length $w_length +#end if + </token> + <xml name="lengths"> + <param argument="--w_beta" type="float" optional="true" label="Tail mass at which window length is determined" /> + <param argument="--w_length" type="integer" optional="true" label="Window Length" /> + </xml> + <token name="@INPUTHMMCHOICE@"><![CDATA[ +#if $input_hmm_conditional.input_hmm_source == "history": + #set $input_hmm_filename = "localref.hmm" + ln -s '${input_hmm_conditional.hmmfile}' '${input_hmm_filename}' && + ## "Press" database + hmmpress '${input_hmm_filename}' && +#else: + #set $input_hmm_filename = str($input_hmm_conditional.index.fields.db_path) +#end if + ]]></token> + <xml name="input_hmm_choice"> + <conditional name="input_hmm_conditional"> + <param name="input_hmm_source" type="select" label="Use a built-in HMM model database or own from your history" > + <option value="indexed" selected="true">Use a built-in HMM model database</option> + <option value="history">Use a HMM database from history</option> + </param> + <when value="indexed"> + <param name="index" type="select" label="Select a HMM model database" help="If your database of interest is not listed, contact the Galaxy administrator"> + <options from_data_table="hmm_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="hmmfile" type="data" format="hmm2,hmm3" label="HMM model" /> + </when> <!-- history --> + </conditional> <!-- input_hmm_conditional --> + </xml> + <xml name="input_hmm"> + <param name="hmmfile" type="data" format="hmm2,hmm3" label="HMM model" /> + </xml> + <xml name="input_msa"> + <param name="msafile" type="data" label="Multiple Sequence Alignment" format="stockholm,clustal,fasta" + help="in Stockholm, Clustal, or Fasta format. While this tool accepts fasta, please ensure that the sequences are not unaligned"/> + </xml> + + + <token name="@ACCEL_HEUR_HELP@"><![CDATA[ +Acceleration Heuristicts (--F1, --F2, --F3) +------------------------------------------- + +**MSV filter** + +The sequence is aligned to the profile using a specialized model that +allows multiple high-scoring local ungapped segments to match. The +optimal alignment score (Viterbi score) is calculated under this multi- +segment model, hence the term MSV, for “multi-segment Viterbi”. This is +HMMER’s main speed heuristic. The MSV score is comparable to BLAST’s sum +score (optimal sum of ungapped alignment segments). Roughly speaking, +MSV is comparable to skipping the heuristic word hit and hit extension +steps of the BLAST acceleration algorithm. + +The MSV filter is very, very fast. In addition to avoiding indel +calculations in the dynamic programming table, it uses reduced precision +scores scaled to 8-bit integers, enabling acceleration via 16-way +parallel SIMD vector instructions. + +The MSV score is a true log-odds likelihood ratio, so it obeys +conjectures about the expected score distribution (Eddy, 2008) that +allow immediate and accurate calculation of the statistical significance +(P- value) of the MSV bit score. + +By default, comparisons with a P-value of ≤ 0.02 pass this filter, +meaning that about 2% of nonhomol- ogous sequences are expected to pass. +You can use the --F1 option to change this threshold. For example, --F1 +<0.05> would pass 5% of the comparisons, making a search more sensitive +but slower. Setting the threshold to ≥ 1.0 (--F1 99 for example) assures +that all comparisons will pass. Shutting off the MSV filter may be +worthwhile if you want to make sure you don’t miss comparisons that have +a lot of scattered insertions and deletions. Alternatively, the --max +option causes the MSV filter step (and all other filter steps) to be +bypassed. + +The MSV bit score is calculated as a log-odds score using the null model +for comparison. No correction for a biased composition or repetitive +sequence is done at this stage. For comparisons involving biased +sequences and/or profiles, more than 2% of comparisons will pass the MSV +filter. At the end of search output, there is a line like: + + Passed MSV filter: 107917 (0.020272); expected 106468.8 (0.02) + +which tells you how many and what fraction of comparisons passed the MSV +filter, versus how many (and what fraction) were expected. + +**Viterbi filter** + +The sequence is now aligned to the profile using a fast Viterbi algorithm for +optimal gapped alignment. + +This Viterbi implementation is specialized for speed. It is implemented in +8-way parallel SIMD vector instructions, using reduced precision scores that +have been scaled to 16-bit integers. Only one row of the dynamic programming +matrix is stored, so the routine only recovers the score, not the optimal +alignment itself. The reduced representation has limited range; local alignment +scores will not underflow, but high scoring comparisons can overflow and return +infinity, in which case they automatically pass the filter. + +The final Viterbi filter bit score is then computed using the appropriate null +model log likelihood (by default the biased composition filter model score, or +if the biased filter is off, just the null model score). If the P-value of this +score passes the Viterbi filter threshold, the sequence passes on to the next +step of the pipeline. + +The --F2 <x> option controls the P-value threshold for passing the Viterbi +filter score. The default is 0.001. The --max option bypasses all filters in +the pipeline. At the end of a search output, you will see a line like: + + Passed Vit filter: 2207 (0.00443803); expected 497.3 (0.001) + +which tells you how many and what fraction of comparisons passed the Viterbi +filter, versus how many were expected. + +**Forward filter/parser** + +The sequence is now aligned to the profile using the full Forward algorithm, +which calculates the likelihood of the target sequence given the profile, +summed over the ensemble of all possible alignments. + +This is a specialized time- and memory-efficient Forward implementation called +the “Forward parser”. It is implemented in 4-way parallel SIMD vector +instructions, in full precision (32-bit floating point). It stores just enough +information that, in combination with the results of the Backward parser +(below), posterior probabilities of start and stop points of alignments +(domains) can be calculated in the domain definition step (below), although the +detailed alignments themselves cannot be. + +The Forward filter bit score is calculated by correcting this score using the +appropriate null model log likelihood (by default the biased composition filter +model score, or if the biased filter is off, just the null model score). If the +P-value of this bit score passes the Forward filter threshold, the sequence +passes on to the next step of the pipeline. + +The bias filter score has no further effect in the pipeline. It is only used in +filter stages. It has no effect on final reported bit scores or P-values. +Biased composition compensation for final bit scores is done by a more complex +domain-specific algorithm, described below. + +The --F3 <x> option controls the P-value threshold for passing the Forward +filter score. The default is 1e-5. The --max option bypasses all filters in the +pipeline. At the end of a search output, you will see a line like: + + Passed Fwd filter: 1076 (0.00216371); expected 5.0 (1e-05) + +which tells you how many and what fraction of comparisons passed the Forward +filter, versus how many were expected. + +**Bias Filter Options** + +The --max option bypasses all filters in the pipeline, including the bias +filter. + +The --nobias option turns off (bypasses) the biased composition filter. The +simple null model is used as a null hypothesis for MSV and in subsequent filter +steps. The biased composition filter step compromises a small amount of +sensitivity. Though it is good to have it on by default, you may want to shut +it off if you know you will have no problem with biased composition hits. + + +**Advanced Documentation** + +A more detailed look at the internals of the various filter pipelines was +posted on the `developer's blog <http://cryptogenomicon.org/hmmer3-is-stubborn.html>`__. +The information posted there may be useful to those who are struggling with +poor-scoring sequences. +]]></token> + <token name="@ADV_OPTS_HELP@"><![CDATA[ +Advanced Options +---------------- + +**nonull2** + +can be too aggressive sometimes, causing you to miss homologs. You can turn the +biased-composition score correction off with the --nonull2 option (and if +you’re doing that, you may also want to set --nobias, to turn off another +biased composition step called the bias filter, which affects which sequences +get scored at all). + +**domZ** + +Assert that the total number of targets in your searches is <x>, for the +purposes of per-domain conditional E-value calculations, rather than the number +of targets that passed the reporting thresholds. + +**Z** + +Assert that the total number of targets in your searches is <x>, for the +purposes of per-sequence E-value calculations, rather than the actual number of +targets seen. +]]></token> + <token name="@AEEWS_HELP@"><![CDATA[ +Effective Sequence Number +------------------------- + +After relative weights are determined, they are normalized to sum to a total +effective sequence number, eff nseq. This number may be the actual number of +sequences in the alignment, but it is almost always smaller than that. The +default entropy weighting method (--eent) reduces the effective sequence num- +ber to reduce the information content (relative entropy, or average expected +score on true homologs) per consensus position. The target relative entropy is +controlled by a two-parameter function, where the two parameters are settable +with --ere and --esigma. + +**--eent** + +Adjust effective sequence number to achieve a specific relative entropy per +position (see --ere). This is the default. + +**--eclust** + +Set effective sequence number to the number of single-linkage clusters at a +specific identity threshold (see --eid). This option is not recommended; it’s +for experiments evaluating how much better --eent is. + +**--enone** + +Turn off effective sequence number determination and just use the actual number +of sequences. One reason you might want to do this is to try to maximize the +relative entropy/position of your model, which may be useful for short models. + +**--eset** + +Explicitly set the effective sequence number for all models to <x>. + +**--ere** + +Set the minimum relative entropy/position target to <x>. Requires --eent. Default +depends on the sequence alphabet. For protein sequences, it is 0.59 bits/position; +for nucleotide sequences, it is 0.45 bits/position. + +**--esigma** + +Sets the minimum relative entropy contributed by an entire model alignment, over +its whole length. This has the effect of making short models have higher relative +entropy per position than --ere alone would give. The default is 45.0 bits. + +**--eid** + +Sets the fractional pairwise identity cutoff used by single linkage clustering +with the --eclust option. The default is 0.62. +]]></token> + <token name="@ARSWS_HELP@"><![CDATA[ +Options Controlling Relative Weights +------------------------------------ + +HMMER uses an ad hoc sequence weighting algorithm to downweight closely related +sequences and up-weight distantly related ones. This has the effect of making +models less biased by uneven phylogenetic representation. For example, two +identical sequences would typically each receive half the weight that one +sequence would. These options control which algorithm gets used. + + +**--wpb** + +Use the Henikoff position-based sequence weighting scheme [Henikoff and +Henikoff, J. Mol. Biol. 243:574, 1994]. This is the default. + +**--wgsc** + +Use the Gerstein/Sonnhammer/Chothia weighting algorithm [Gerstein et al, J. +Mol. Biol. 235:1067, 1994]. + +**--wblosum** + +Use the same clustering scheme that was used to weight data in calculating +BLOSUM subsitution matrices [Henikoff and Henikoff, Proc. Natl. Acad. Sci +89:10915, 1992]. Sequences are single-linkage clustered at an identity +threshold (default 0.62; see --wid) and within each cluster of c sequences, +each sequence gets rela- tive weight 1/c. + +**--wnone** + +No relative weights. All sequences are assigned uniform weight. + +**--wid** + +Sets the identity threshold used by single-linkage clustering when using +--wblosum. Invalid with any other weighting scheme. Default is 0.62. +]]></token> + <token name="@BIAS_COMP_HELP@"><![CDATA[ +Bias Composition +---------------- + +The next number, the bias, is a correction term for biased sequence composition +that has been applied to the sequence bit score.1 For instance, for the top hit +MYG PHYCA that scored 222.7 bits, the bias of 3.2 bits means that this sequence +originally scored 225.9 bits, which was adjusted by the slight 3.2 bit biased- +composition correction. The only time you really need to pay attention to the +bias value is when it’s large, on the same order of magnitude as the sequence +bit score. Sometimes (rarely) the bias correction isn’t aggressive enough, and +allows a non-homolog to retain too much score. Conversely, the bias correction +can be too aggressive sometimes, causing you to miss homologs. You can turn the +biased-composition score correction off with the --nonull2 option (and if +you’re doing that, you may also want to set --nobias, to turn off another +biased composition step called the bias filter, which affects which sequences +get scored at all). + +]]></token> + <token name="@CUT_HELP@"><![CDATA[ +Options for Model-specific Score Thresholding +--------------------------------------------- + +Curated profile databases may define specific bit score thresholds for each +profile, superseding any thresholding based on statistical significance alone. +To use these options, the profile must contain the appropriate (GA, TC, and/or +NC) optional score threshold annotation; this is picked up by hmmbuild from +Stockholm format alignment files. Each thresholding option has two scores: the +per-sequence threshold <x1> and the per-domain threshold <x2> These act as if +-T<x1> --incT<x1> --domT<x2> --incdomT<x2> has been applied specifically using +each model’s curated thresholds. + +**--cut_ga** + +Use the GA (gathering) bit scores in the model to set per-sequence (GA1) and +per-domain (GA2) reporting and inclusion thresholds. GA thresholds are +generally considered to be the reliable curated thresholds defining family +membership; for example, in Pfam, these thresholds define what gets included in +Pfam Full alignments based on searches with Pfam Seed models. + +**--cut_nc** + +Use the NC (noise cutoff) bit score thresholds in the model to set +per-sequence (NC1) and per-domain (NC2) reporting and inclusion thresholds. NC +thresholds are generally considered to be the score of the highest-scoring +known false positive. + +**--cut_tc** + +Use the NC (trusted cutoff) bit score thresholds in the model to set +per-sequence (TC1) and per-domain (TC2) reporting and inclusion thresholds. TC +thresholds are generally considered to be the score of the lowest-scoring known +true positive that is above all known false positives. +]]></token> + <token name="@EVAL_CALIB_HELP@"><![CDATA[ +Options Controlling H3 Parameter Estimation Methods +--------------------------------------------------- + +H3 uses three short random sequence simulations to estimating the location +parameters for the expected score distributions for MSV scores, Viterbi scores, +and Forward scores. These options allow these simulations to be modified. + +**--EmL** + +Sets the sequence length in simulation that estimates the location parameter mu +for MSV E-values. Default is 200. + +**--EmN** + +Sets the number of sequences in simulation that estimates the location parameter +mu for MSV E-values. Default is 200. + +**--EvL** + +Sets the sequence length in simulation that estimates the location parameter mu +for Viterbi E-values. Default is 200. + +**--EvN** + +Sets the number of sequences in simulation that estimates the location parameter +mu for Viterbi E-values. Default is 200. + + +**--EfL** + +Sets the sequence length in simulation that estimates the location parameter tau +for Forward E-values. Default is 100. + +**--EfN** + +Sets the number of sequences in simulation that estimates the location parameter +tau for Forward E-values. Default is 200. + +**--Eft** + +Sets the tail mass fraction to fit in the simulation that estimates the location param- +eter tau for Forward evalues. Default is 0.04. +]]></token> + <token name="@FORMAT_SELECTOR_HELP@"><![CDATA[ +Options for Specifying the Alphabet +----------------------------------- + +The alphabet type (amino, DNA, or RNA) is autodetected by default, by looking +at the composition of the msafile. Autodetection is normally quite reliable, +but occasionally alphabet type may be ambiguous and autodetection can fail (for +instance, on tiny toy alignments of just a few residues). To avoid this, or to +increase robustness in automated analysis pipelines, you may specify the +alphabet type of msafile with these options. +]]></token> + <token name="@HSSI_HELP@"><![CDATA[ +Options Controlling Single Sequence Scoring (first Iteration) +------------------------------------------------------------- + +By default, the first iteration uses a search model constructed from a single +query sequence. This model is constructed using a standard 20x20 substitution +matrix for residue probabilities, and two additional pa- rameters for +position-independent gap open and gap extend probabilities. These options allow +the default single-sequence scoring parameters to be changed. + +**Gap Open (--popen)** + +Set the gap open probability for a single sequence query model to <x> + +**Gap Extend (--pextend)** + +Set the gap extend probability for a single sequence query model to <x>. + + +**--mx/--mxfile** + +These options are not currently supported +]]></token> + <token name="@LENGTHS_HELP@"><![CDATA[ +Tail Mass Options +----------------- + +**Window length tail mass (--w_beta)** + +The upper bound, W, on the length at which nhmmer expects to find an instance +of the model is set such that the fraction of all sequences generated by the +model with length >= W is less than <x>. The default is 1e-7. + + +**Model instance length upper bound (--w length)** + +Override the model instance length upper bound, W, which is otherwise +controlled by --w beta. It should be larger than the model length. The value of +W is used deep in the acceleration pipeline, and modest changes are not +expected to impact results (though larger values of W do lead to longer run +time). + +]]></token> + <token name="@MCSS_HELP@"><![CDATA[ +**Options Controlling Profile Construction** + +These options control how consensus columns are defined in an alignment. + +**--fast** + +Define consensus columns as those that have a fraction >= symfrac of residues +as opposed to gaps. (See below for the --symfrac option.) This is the default. + +**--hand** + +Define consensus columns in next profile using reference annotation to the multiple +alignment. This allows you to define any consensus columns you like. + + +**--symfrac** + +Define the residue fraction threshold necessary to define a consensus column +when using the --fast option. The default is 0.5. The symbol fraction in each +column is calculated after taking relative sequence weighting into account, and +ignoring gap characters corresponding to ends of sequence fragments (as opposed +to internal insertions/deletions). Setting this to 0.0 means that every +alignment column will be assigned as consensus, which may be useful in some +cases. Setting it to 1.0 means that only columns that include 0 gaps (internal +insertions/deletions) will be assigned as consensus. + +**--fragthresh** + +We only want to count terminal gaps as deletions if the aligned sequence is +known to be full-length, not if it is a fragment (for instance, because only +part of it was sequenced). HMMER uses a simple rule to infer fragments: if the +sequence length L is less than or equal to a fraction <x> times the alignment +length in columns, then the sequence is handled as a fragment. The default is +0.5. Setting --fragthresh0 will define no (nonempty) sequence as a fragment; +you might want to do this if you know you’ve got a carefully curated alignment +of full-length sequences. Setting --fragthresh1 will define all sequences as +fragments; you might want to do this if you know your alignment is entirely +composed of fragments, such as translated short reads in metagenomic shotgun +data. + +]]></token> + <token name="@OFORMAT_WITH_OPTS_HELP@"><![CDATA[ +Options for Controlling Output +------------------------------ + +**Table of hits** + +Save a simple tabular (space-delimited) file summarizing the per-target output, with +one data line per homologous target model found. + +**Table of per-domain hits** + +Save a simple tabular (space-delimited) file summarizing the per-domain output, +with one data line per homologous domain detected in a query sequence for each +homologous model. + +**Table of hits and domains in Pfam Format** + +Save an especially succinct tabular (space-delimited) file summarizing the +per-target output, with one data line per homologous target model found. +]]></token> + <token name="@OFORMAT_WITH_OPTS_NOPFAM_HELP@"><![CDATA[ +Options for Controlling Output +------------------------------ + +**Table of hits** + +Save a simple tabular (space-delimited) file summarizing the per-target output, with +one data line per homologous target model found. + +**Table of per-domain hits** + +Save a simple tabular (space-delimited) file summarizing the per-domain output, +with one data line per homologous domain detected in a query sequence for each +homologous model. +]]></token> + <token name="@OFORMAT_WITH_OPTS_N_HELP@"><![CDATA[ +Options for Controlling Output +------------------------------ + +**Table of hits** + +Save a simple tabular (space-delimited) file summarizing the per-target output, with +one data line per homologous target model found. + +**Table of hits (dfam)** + +Save a tabular (space-delimited) file summarizing the per-hit output, similar +to --tblout but more succinct. + + +**List of per-position scores for each hit (--aliscoreout)** + +Save to file a list of per-position scores for each hit. This is useful, for +example, in identifying regions of high score density for use in resolving +overlapping hits from different models. + +]]></token> + <token name="@PRIOR_HELP@"><![CDATA[ +Options Controlling Priors +-------------------------- + +By default, weighted counts are converted to mean posterior probability +parameter estimates using mixture Dirichlet priors. Default mixture Dirichlet +prior parameters for protein models and for nucleic acid (RNA and DNA) models +are built in. The following options allow you to override the default priors. + +**No priors (--pnone)** + +Don’t use any priors. Probability parameters will simply be the observed +frequencies, after relative sequence weighting. + +**Laplace +1 prior** + +Use a Laplace +1 prior in place of the default mixture Dirichlet prior. +]]></token> + <token name="@SEED_HELP@"><![CDATA[ +Random Seeding +-------------- + +Seed the random number generator with <n>, an integer >= 0. If <n> is nonzero, +any stochastic simulations will be reproducible; the same command will give the +same results. If <n> is 0, the random number generator is seeded arbitrarily, +and stochastic simulations will vary from run to run of the same command. + +]]></token> + <token name="@THRESHOLDS_HELP@"><![CDATA[ +Options for Reporting Thresholds +-------------------------------- + +Reporting thresholds control which hits are reported in output files (the main +output, --tblout, and --domtblout). + +**E-value (-E)** + +In the per-target output, report target profiles with an E-value of <= <x>. The +default is 10.0, meaning that on average, about 10 false positives will be +reported per query, so you can see the top of the noise and decide for yourself +if it’s really noise. + +**Bit score (-T)** + +Instead of thresholding per-profile output on E-value, instead report target profiles +with a bit score of >= <x>. + +**domain E-value (--domE)** + +In the per-domain output, for target profiles that have already satisfied the +per-profile reporting threshold, report individual domains with a conditional +E-value of <= <x>. The default is 10.0. A conditional E-value means the +expected number of additional false positive domains in the smaller search +space of those comparisons that already satisfied the per-profile reporting +threshold (and thus must have at least one homologous domain already). + +**domain Bit scores (--domT)** + +Instead of thresholding per-domain output on E-value, instead report domains +with a bit score of >= <x>. + +Options for Inclusion Thresholds +-------------------------------- + +Inclusion thresholds are stricter than reporting thresholds. Inclusion +thresholds control which hits are considered to be reliable enough to be +included in an output alignment or a subsequent search round. In hmmscan, which +does not have any alignment output (like hmmsearch or phmmer) nor any iterative +search steps (like jackhmmer), inclusion thresholds have little effect. They +only affect what domains get marked as significant (!) or questionable (?) in +domain output. + +**E-value of per target inclusion threshold** + +Use an E-value of <= <x> as the per-target inclusion threshold. The default is +0.01, meaning that on average, about 1 false positive would be expected in +every 100 searches with different query sequences. + +**Bit score of per target inclusion threshold** + +Instead of using E-values for setting the inclusion threshold, instead use a +bit score of >= <x> as the per-target inclusion threshold. It would be unusual +to use bit score thresholds with hmmscan, because you don’t expect a single +score threshold to work for different profiles; different profiles have +slightly different expected score distributions. + +**domain E-value per target inclusion treshold** + +Use a conditional E-value of <= <x> as the per-domain inclusion threshold, in +targets that have already satisfied the overall per-target inclusion threshold. + +**domain Bit score per target inclusion treshold** + +Instead of using E-values, instead use a bit score of >= <x> as the per-domain +inclusion threshold. As with --incT above, it would be unusual to use a single +bit score threshold in hmmscan. + +]]></token> + <token name="@THRESHOLDS_NODOM_HELP@"><![CDATA[ +Options for Reporting Thresholds +-------------------------------- + +Reporting thresholds control which hits are reported in output files (the main +output, --tblout, and --domtblout). + +**E-value (-E)** + +In the per-target output, report target profiles with an E-value of <= <x>. The +default is 10.0, meaning that on average, about 10 false positives will be +reported per query, so you can see the top of the noise and decide for yourself +if it’s really noise. + +**Bit score (-T)** + +Instead of thresholding per-profile output on E-value, instead report target profiles +with a bit score of >= <x>. + +Options for Inclusion Thresholds +-------------------------------- + +Inclusion thresholds are stricter than reporting thresholds. Inclusion +thresholds control which hits are considered to be reliable enough to be +included in an output alignment or a subsequent search round. In hmmscan, which +does not have any alignment output (like hmmsearch or phmmer) nor any iterative +search steps (like jackhmmer), inclusion thresholds have little effect. They +only affect what domains get marked as significant (!) or questionable (?) in +domain output. + +**E-value of per target inclusion threshold** + +Use an E-value of <= <x> as the per-target inclusion threshold. The default is +0.01, meaning that on average, about 1 false positive would be expected in +every 100 searches with different query sequences. + +**Bit score of per target inclusion threshold** + +Instead of using E-values for setting the inclusion threshold, instead use a +bit score of >= <x> as the per-target inclusion threshold. It would be unusual +to use bit score thresholds with hmmscan, because you don’t expect a single +score threshold to work for different profiles; different profiles have +slightly different expected score distributions. + +]]></token> + <token name="@ATTRIBUTION@"><![CDATA[ + +Attribution +----------- + +This Galaxy tool relies on HMMER3_ +Internally the software is cited as: + +:: + + # hmmscan :: search sequence(s) against a profile database + # HMMER 3.1 (February 2013); http://hmmer.org/ + # Copyright (C) 2011 Howard Hughes Medical Institute. + # Freely distributed under the GNU General Public License (GPLv3). + # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + +The wrappers were written by the IUC and are licensed under Apache2_. The +documentation is copied from the HMMER3 documentation. + +.. _Apache2: http://www.apache.org/licenses/LICENSE-2.0 +.. _HMMER3: http://hmmer.org/ + + + ]]></token> + <token name="@HELP_PRE@"><![CDATA[ + +What it does +============ + ]]></token> + <token name="@HELP_PRE_OTH@"><![CDATA[ +Options +======= + ]]></token> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/nhmmer.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,115 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_nhmmer" name="nhmmer" version="@TOOL_VERSION@+galaxy1"> + <description>search a DNA model or alignment against a DNA database (BLASTN-like)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_nhmmer" name="nhmmer" version="@TOOL_VERSION@"> + <description>search a DNA model or alignment against a DNA database (BLASTN-like)</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +nhmmer + +@OFORMAT_WITH_OPTS@ +@HSSI@ +@THRESHOLDS_NODOM@ +@CUT@ +@ACCEL_HEUR@ +@FORMAT_SELECTOR@ +@ADV_OPTS@ +@LENGTHS@ +@CPU@ +@SEED@ + +'$hmmfile' +'$seqfile' +> '$output' + ]]></command> + <inputs> + <expand macro="input_hmm" /> + <param name="seqfile" type="data" format="fasta" label="Target sequence file"/> + <expand macro="oformat_with_opts_dfam_alisc"/> + <expand macro="hssi"/> + <expand macro="thresholds_nodom"/> + <expand macro="cut" /> + <expand macro="accel_heur_xml"/> + <expand macro="format_selector_noprot"/> + <expand macro="adv_opts"/> + <expand macro="lengths"/> + <!-- TODO: block_length toponly bottomonly --> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dfam_alisc" tool="NHMMER"/> + </outputs> + <tests> + <test expect_num_outputs="4"> + <param name="hmmfile" value="MADE1.hmm"/> + <param name="seqfile" value="dna_target.fa"/> + <expand macro="oformat_test" /> + <param name="oformat" value="tblout,dfamtblout,aliscoresout"/> + <expand macro="seed_test" /> + <output name="output" file="nhmmer.out" lines_diff="16"> + <expand macro="assert_out" tool="nhmmer"/> + </output> + <output name="tblout" file="nhmmer.out.tblout" lines_diff="12"> + <expand macro="assert_tblout" tool="nhmmer"/> + </output> + <output name="aliscoresout" file="nhmmer.out.aliscoresout" lines_diff="10"/> + <output name="dfamtblout" file="nhmmer.out.dfamtblout" lines_diff="10"> + <assert_contents> + <has_line_matching expression="# hit scores"/> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="hmmfile" value="MADE1.hmm"/> + <param name="seqfile" value="dna_target.fa"/> + <expand macro="oformat_test" /> + <param name="oformat" value=""/> + <expand macro="seed_test" /> + <output name="output" file="nhmmer.out" lines_diff="16"> + <expand macro="assert_out" tool="nhmmer"/> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +nhmmer is used to search one or more nucleotide queries against a nucleotide +sequence database. For each query in <queryfile>, use that query to search the +target database of sequences in <seqdb>, and output a ranked list of the hits +with the most significant matches to the query. A query may be either a profile +model built using hmmbuild, a sequence alignment, or a single sequence. +Sequence based queries can be in a number of formats (see --qformat), and can +typically be autodetected. Note that only Stockholm format supports the use of +multiple sequence-based queries. + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_N_HELP@ +@HSSI_HELP@ +@THRESHOLDS_NODOM_HELP@ +@CUT_HELP@ +@ACCEL_HEUR_HELP@ +@FORMAT_SELECTOR_HELP@ +@ADV_OPTS_HELP@ +@LENGTHS_HELP@ +@SEED_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/nhmmscan.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,113 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_nhmmscan" name="nhmmscan" version="@TOOL_VERSION@+galaxy1"> + <description>search DNA sequence(s) against a DNA profile database</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_nhmmscan" name="nhmmscan" version="@TOOL_VERSION@"> + <description>search DNA sequence(s) against a DNA profile database</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +@INPUTHMMCHOICE@ +nhmmscan + +@OFORMAT_WITH_OPTS@ +@THRESHOLDS_NODOM@ +@CUT@ +@ACCEL_HEUR@ +--B1 $B1 +--B2 $B2 +--B3 $B3 + +@ADV_OPTS@ +@LENGTHS@ +@CPU@ +@SEED@ + +'$input_hmm_filename' +'$seqfile' +> '$output' + ]]></command> + <inputs> + <expand macro="input_hmm_choice" /> + <!-- todo use Galaxy features like data libraries/data tables/??? --> + <param name="seqfile" type="data" format="fasta" label="Sequence file"/> + <expand macro="oformat_with_opts_dfam_alisc"/> + <expand macro="thresholds_nodom"/> + <expand macro="cut"/> + <expand macro="accel_heur_xml"/> + + <param argument="--B1" type="integer" value="110" label="window length for biased-composition modifier (MSV)" /> + <param argument="--B2" type="integer" value="240" label="window length for biased-composition modifier (Vit)" /> + <param argument="--B3" type="integer" value="1000" label="window length for biased-composition modifier (Fwd)" /> + + <expand macro="adv_opts"/> + <expand macro="lengths"/> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dfam_alisc" tool="NHMMSCAN"/> + </outputs> + <tests> + <test expect_num_outputs="3"> + <param name="input_hmm_conditional|input_hmm_source" value="history"/> + <param name="input_hmm_conditional|hmmfile" value="MADE1.hmm"/> + <param name="seqfile" value="dna_target.fa"/> + <expand macro="oformat_test" /> + <expand macro="seed_test" /> + <output name="output" file="MADE1.nhmmscan_out" lines_diff="12"> + <expand macro="assert_out" tool="nhmmscan"/> + </output> + <output name="tblout" file="MADE1.nhmmscan_out.tblout" lines_diff="10"> + <!-- nhmmscan reports as hmmscan https://github.com/EddyRivasLab/hmmer/issues/190 --> + <expand macro="assert_tblout" tool="hmmscan"/> + </output> + <output name="dfamtblout" file="MADE1.nhmmscan_out.dfamtblout"> + <assert_contents> + <has_line_matching expression="# hit scores"/> + </assert_contents> + </output> + <!--not test because https://github.com/EddyRivasLab/hmmer/issues/190 <output name="aliscoresout" file="MADE1.nhmmscan_out.aliscoresout" lines_diff="10" />--> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +nhmmscan is used to search nucleotide sequences against collections of +nucleotide profiles. For each sequence in <seqfile>, use that query sequence to +search the target database of profiles in <hmmfile>, and output ranked lists of +the profiles with the most significant matches to the sequence. + +The <seqfile> may contain more than one query sequence. It can be in FASTA +format, or several other common sequence file formats (genbank, embl, and +uniprot, among others), or in alignment file formats (stockholm, aligned fasta, +and others). See the --qformat option for a complete list. + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_N_HELP@ +@THRESHOLDS_NODOM_HELP@ +@CUT_HELP@ +@ACCEL_HEUR_HELP@ +@BIAS_COMP_HELP@ +@ADV_OPTS_HELP@ +@LENGTHS_HELP@ +@SEED_HELP@ + + +@ATTRIBUTION@ +]]></help> + <expand macro="citation"/> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/phmmer.xml.orig Tue Aug 31 08:43:59 2021 +0000 @@ -0,0 +1,107 @@ +<?xml version="1.0"?> +<<<<<<< HEAD +<tool id="hmmer_phmmer" name="phmmer" version="@TOOL_VERSION@+galaxy1"> + <description>search a protein sequence against a protein database (BLASTP-like)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +@ADDTHREADS@ +======= +<tool id="hmmer_phmmer" name="phmmer" version="@TOOL_VERSION@"> + <description>search a protein sequence against a protein database (BLASTP-like)</description> + <expand macro="bio_tools"/> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <expand macro="stdio"/> + <command><![CDATA[ +>>>>>>> c37d72558 (add more bio.tool IDs) +phmmer + +@OFORMAT_WITH_OPTS@ +@HSSI@ +@THRESHOLDS@ +@ACCEL_HEUR@ +@EVAL_CALIB@ +@ADV_OPTS@ + +@CPU@ +@SEED@ + +'$seqfile' +'$seqdb' +> '$output' + ]]></command> + <inputs> + <param name="seqfile" type="data" format="fasta" label="Protein sequence to search with"/> + <!-- todo use Galaxy features like data libraries/data tables/??? --> + <param name="seqdb" type="data" format="fasta" label="Sequence Database"/> + <expand macro="oformat_with_opts_dom_pfam"/> + <expand macro="hssi"/> + <expand macro="thresholds_xml"/> + <expand macro="accel_heur_xml"/> + <expand macro="eval_calib_xml"/> + <expand macro="adv_opts"/> + <expand macro="seed"/> + </inputs> + <outputs> + <expand macro="output_dom_pfam" tool="PHMMER"/> + </outputs> + <tests> + <test expect_num_outputs="4"> + <param name="seqfile" value="globins45.fa"/> + <param name="seqdb" value="uniprot_matches.fasta"/> + <expand macro="oformat_test" /> + <expand macro="seed_test" /> + <output name="output" file="phmmer.out" lines_diff="200"> + <expand macro="assert_out" tool="phmmer"/> + </output> + <!-- Lines diff is high due to a line of cpu/timing information for EACH sequence --> + <output name="domtblout" file="phmmer.domtblout" lines_diff="12"> + <expand macro="assert_tblout" tool="phmmer"/> + </output> + <output name="pfamtblout" file="phmmer.pfamtblout" lines_diff="12"> + <expand macro="assert_tblout" tool="phmmer"/> + </output> + <output name="tblout" file="phmmer.tblout" lines_diff="12"> + <expand macro="assert_tblout" tool="phmmer"/> + </output> + </test> + <test expect_num_outputs="1"> + <param name="seqfile" value="globins45.fa"/> + <param name="seqdb" value="uniprot_matches.fasta"/> + <expand macro="oformat_test" /> + <param name="oformat" value=""/> + <expand macro="seed_test" /> + <output name="output" file="phmmer.out" lines_diff="200"> + <expand macro="assert_out" tool="phmmer"/> + </output> + </test> + </tests> + <help><![CDATA[ +@HELP_PRE@ + +phmmer is used to search one or more query protein sequences against a protein +sequence database. For each query sequence in <seqfile>, use that sequence to +search the target database of sequences in <seqdb>, and output ranked lists of +the sequences with the most significant matches to the query. + + +@HELP_PRE_OTH@ + +@OFORMAT_WITH_OPTS_HELP@ +@HSSI_HELP@ +@THRESHOLDS_HELP@ +@ACCEL_HEUR_HELP@ +@EVAL_CALIB_HELP@ +@ADV_OPTS_HELP@ +@SEED_HELP@ + +@ATTRIBUTION@ + ]]></help> + <expand macro="citation"/> +</tool>