Mercurial > repos > iuc > hmmer3
view macros.xml @ 0:62479bdcc059 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hmmer3 commit 4164b44c651bcbdac6637eccce61b2a802c9b569
| author | iuc |
|---|---|
| date | Tue, 12 May 2015 15:04:26 -0400 |
| parents | |
| children | b5066aa77fea |
line wrap: on
line source
<?xml version="1.0"?> <macros> <xml name="requirements"> <requirements> <requirement type="package" version="3.1b1">hmmer3_1b1</requirement> <yield/> </requirements> </xml> <token name="@WRAPPER_VERSION@">0.1</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 $T: -T $T #end if #if $domT: --domT $domT #end if #if $incE: --incE $incE #end if #if $incT: --incT $incT #end if #if $incdomE: --incdomE $incdomE #end if #if $incdomT: --incdomT $incdomT #end if </token> <xml name="thresholds_xml"> <!-- Options controlling reporting thresholds --> <param name="E" label="report sequences <= this E-Value threshold in output" help="(-E)" value="10.0" type="float" min="0"/> <param name="domE" label="report domains <= this E-Value threshold in output" help="(--domE)" value="10.0" type="float" min="0"/> <param name="T" label="report sequences >= this score threshold in output" help="(-T)" type="float" optional="True"/> <param name="domT" label="report domains >= this score threshold in output" help="(--domT)" type="float" optional="True"/> <!-- Options controlling inclusion (significance) thresholds --> <param name="incE" label="consider sequences <= this E-Value threshold as significant" help="(--incE)" type="float" optional="True"/> <param name="incdomE" label="consider domains <= this E-Value threshold as significant" help="(--incdomE)" type="float" optional="True"/> <param name="incT" label="consider sequences >= this score threshold as significant" help="(--incT)" type="float" optional="True"/> <param name="incdomT" label="consider domains >= this score threshold as significant" help="(--incdomT)" type="float" optional="True"/> </xml> <token name="@THRESHOLDS_NODOM@"> -E $E #if $T: -T $T #end if #if $incE: --incE $incE #end if #if $incT: --incT $incT #end if </token> <xml name="thresholds_nodom"> <!-- Options controlling reporting thresholds --> <param name="E" label="report sequences <= this E-Value threshold in output" help="(-E)" value="10.0" type="float" min="0"/> <param name="T" label="report sequences >= this score threshold in output" help="(-T)" type="float" optional="True"/> <!-- Options controlling inclusion (significance) thresholds --> <param name="incE" label="consider sequences <= this E-Value threshold as significant" help="(--incE)" type="float" optional="True"/> <param name="incT" label="consider sequences >= this score threshold as significant" help="(--incT)" type="float" optional="True"/> </xml> <token name="@ACCEL_HEUR@"> $max --F1 $F1 --F2 $F2 --F3 $F3 $nobias </token> <xml name="accel_heur_xml"> <!-- Options controlling acceleration heuristics --> <param name="max" type="boolean" truevalue="--max" label="Turn all heuristic filters off (less speed, more power)" help="(--max)" falsevalue=""/> <param name="F1" type="float" label="Stage 1 (MSV) threshold: promote hits w/ P <= F1" help="(--F1)" value="0.02"/> <param name="F2" type="float" label="Stage 2 (Vit) threshold: promote hits w/ P <= F2" help="(--F2)" value="1e-3"/> <param name="F3" type="float" label="Stage 3 (Fwd) threshold: promote hits w/ P <= F3" help="(--F3)" value="1e-5"/> <param name="nobias" type="boolean" truevalue="--nobias" label="Turn off composition bias filter" help="(--nobias)" falsevalue=""/> </xml> <token name="@EVAL_CALIB@"> --EmL $EmL --EmN $EmN --EvL $EvL --EvN $EvN --EfL $EfL --EfN $EfN --Eft $Eft </token> <xml name="eval_calib_xml"> <!-- Control of E-value calibration --> <param name="EmL" type="integer" value="200" min="1" help="(--EmL)" label="Length of sequences for MSV Gumbel mu fit"/> <param name="EmN" type="integer" value="200" min="1" help="(--EmN)" label="Number of sequences for MSV Gumbel mu fit"/> <param name="EvL" type="integer" value="200" min="1" help="(--EvL)" label="Length of sequences for Viterbi Gumbel mu fit"/> <param name="EvN" type="integer" value="200" min="1" help="(--EvN)" label="Number of sequences for Viterbi Gumbel mu fit"/> <param name="EfL" type="integer" value="100" min="1" help="(--EfL)" label="Length of sequences for Forward exp tail tau fit"/> <param name="EfN" type="integer" value="200" min="1" help="(--EfN)" label="Number of sequences for Forward exp tail tau fit"/> <param name="Eft" type="float" value="0.04" min="0" max="1" help="(--Eft)" label="tail mass for Forward exponential tail tau fit"/> </xml> <token name="@OFORMAT_WITH_OPTS_NOPFAM@"> #if 'tblout' in str($oformat): --tblout $tblout #end if #if 'domtblout' in str($oformat): --domtblout $domtblout #end if $acc $noali $notextw </token> <xml name="oformat_with_opts_nopfam"> <!-- Options directing output --> <param name="oformat" multiple="True" display="checkboxes" label="Output Formats" type="select"> <option value="tblout" selected="true">Table of per-sequence hits (--tblout)</option> <option value="domtblout" selected="true">Table of per-domain hits (--domtblout)</option> </param> <param name="acc" type="boolean" truevalue="--acc" falsevalue="" label="Prefer accessions over names in output" help="(--acc)"/> <param name="noali" type="boolean" truevalue="--noali" falsevalue="" label="Don't output alignments, so output is smaller" help="(--noali)"/> <param name="notextw" type="boolean" truevalue="--notextw" falsevalue="" label="Unlimited ASCII text output line width" help="(--notextw)"/> </xml> <token name="@OFORMAT_WITH_OPTS@"> #if 'tblout' in str($oformat): --tblout $tblout #end if #if 'domtblout' in str($oformat): --domtblout $domtblout #end if #if 'pfamtblout' in str($oformat): --pfamtblout $pfamtblout #end if $acc $noali $notextw </token> <xml name="oformat_with_opts"> <!-- Options directing output --> <param name="oformat" multiple="True" display="checkboxes" label="Output Formats" type="select"> <option value="tblout" selected="true">Table of per-sequence hits (--tblout)</option> <option value="domtblout" selected="true">Table of per-domain hits (--domtblout)</option> <option value="pfamtblout" selected="true">Table of hits and domains in Pfam format (--pfamtblout)</option> </param> <param name="acc" type="boolean" truevalue="--acc" falsevalue="" label="Prefer accessions over names in output" help="(--acc)"/> <param name="noali" type="boolean" truevalue="--noali" falsevalue="" label="Don't output alignments, so output is smaller" help="(--noali)"/> <param name="notextw" type="boolean" truevalue="--notextw" falsevalue="" label="Unlimited ASCII text output line width" help="(--notextw)"/> </xml> <xml name="oformat_test"> <param name="notextw" value="True" /> </xml> <!-- TODO: tblout will match 'pfamtblout,dfamtblout' --> <token name="@OFORMAT_WITH_OPTS_N@"> #if 'tblout' in str($oformat): --tblout $tblout #end if #if 'dfamtblout' in str($oformat): --dfamtblout $dfamtblout #end if #if 'aliscoresout' in str($oformat): --aliscoresout $aliscoresout #end if $acc $noali $notextw </token> <xml name="oformat_with_opts_n"> <!-- Options directing output --> <param name="oformat" multiple="True" display="checkboxes" label="Output Formats" type="select"> <option value="tblout" selected="true">Table of hits (--tblout)</option> <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> </param> <param name="acc" type="boolean" truevalue="--acc" falsevalue="" label="Prefer accessions over names in output" help="(--acc)"/> <param name="noali" type="boolean" truevalue="--noali" falsevalue="" label="Don't output alignments, so output is smaller" help="(--noali)"/> <param name="notextw" type="boolean" truevalue="--notextw" falsevalue="" label="Unlimited ASCII text output line width" help="(--notextw)"/> </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="singlemx"> <param name="popen" type="float" value="0.02" label="Gap open probability" help="(--popen)" min="0.0" max="0.5"/> <param name="pextend" type="float" value="0.4" label="Gap extend probability" help="(--pextend)" min="0.0" max="1.0"/> </when> <when value="false"> </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="@CPU@"> --cpu \${GALAXY_SLOTS:-2} </token> <token name="@SEED@"> --seed $seed </token> <xml name="seed"> <param name="seed" label="RNG seed, 0 generates a random seed" value="42" type="integer" help="(--seed)" min="0"/> </xml> <xml name="seed_test"> <param name="seed" value="4" /> </xml> <token name="@ADV_OPTS@"> $nonull2 #if $Z: -Z $Z #end if #if $domZ: --domZ $domZ #end if </token> <xml name="adv_opts"> <!-- Other options --> <param name="nonull2" type="boolean" truevalue="--nonull2" label="Turn off biased composition score corrections" help="(--nonull2)" falsevalue=""/> <param name="Z" type="integer" label="# of comparisons done for E-value calculation" help="(-Z)" optional="True"/> <param name="domZ" type="integer" label="# of significant sequences, for domain E-value calculation" help="(--domZ)" optional="True"/> </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 name="wid" label="Set identity cutoff" value="0.62" type="float" help="(--wid)"/> </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 name="eset" type="float" value="0" label="set eff seq # for all models" help="(--eset)"/> <param name="ere" type="float" value="0" label="set minimum rel entropy/position" help="(--ere)"/> <param name="esigma" type="float" value="45" label="set sigma param" help="(--esigma)"/> </when> <when value="eclust"> <param name="eset" type="float" value="0" label="set eff seq # for all models" help="(--eset)"/> <param name="eid" type="float" value="0.62" label="set fractional identity cutoff" min="0" max="1" help="(--eid)"/> </when> <when value="enone"> </when> </conditional> </xml> <token name="@CUT@"> $cut_ga $cut_nc $cut_tc </token> <xml name="cut"> <param name="cut_ga" type="boolean" truevalue="--cut_ga" label="use profile's GA gathering cutoffs to set all thresholding" help="(--cut_ga)" falsevalue=""/> <param name="cut_nc" type="boolean" truevalue="--cut_nc" label="use profile's NC gathering cutoffs to set all thresholding" help="(--cut_nc)" falsevalue=""/> <param name="cut_tc" type="boolean" truevalue="--cut_tc" label="use profile's TC gathering cutoffs to set all thresholding" help="(--cut_tc)" falsevalue=""/> </xml> <token name="@MCSS@"> --$mcs.model_construction_strategy_select #if $mcs.model_construction_strategy_select == "fast": --symfrac $mcs.symfrac #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 name="symfrac" value="0.5" type="float" label="Sets sym fraction controlling --fast construction"/> </when> <when value="hand"></when> </conditional> <param name="fragthresh" 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 (--fragthresh)" value="0.5" optional="True" type="float" /> </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 $w_beta: --w_beta $w_beta #end if #if $w_length: --w_length $w_length #end if </token> <xml name="lengths"> <param name="w_beta" label="Tail mass at which window length is determined" help="(--w_beta)" optional="True" type="float"/> <param name="w_length" label="Window Length" help="(--w_length)" optional="True" type="integer" /> </xml> <xml name="input_hmm"> <param name="hmmfile" type="data" label="HMM model" format="hmmer2,hmmer3"/> </xml> <xml name="input_msa"> <param name="msafile" type="data" label="MSA File" format="stockholm"/> </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://selab.janelia.org/people/eddys/blog/?p=508>`__. 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_ from http://hmmer.janelia.org/ 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 Eric Rasche and is licensed under Apache2_. The documentation is copied from the HMMER3 documentation. .. _Apache2: http://www.apache.org/licenses/LICENSE-2.0 .. _HMMER3: http://hmmer.janelia.org/ ]]></token> <token name="@HELP_PRE@"><![CDATA[ What it does ============ ]]></token> <token name="@HELP_PRE_OTH@"><![CDATA[ Options ======= ]]></token> </macros>