Mercurial > repos > devteam > lastz
diff lastz.xml @ 11:37b497aa133f draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/lastz commit 1075d38f2a8eaffb824771a5c4fe70c36aa15f2c
author | iuc |
---|---|
date | Sun, 02 Jul 2023 12:10:46 +0000 |
parents | 3e1ea2facca6 |
children |
line wrap: on
line diff
--- a/lastz.xml Sat Nov 27 10:41:24 2021 +0000 +++ b/lastz.xml Sun Jul 02 12:10:46 2023 +0000 @@ -297,15 +297,15 @@ <inputs> <expand macro="target_input"/> <param name="query" format="fasta,fastq,fasta.gz,fastq.gz,fastq.bz2" type="data" label="Select QUERY sequence(s)" help="These are the sequences that you are aligning against TARGET"/> - <param name="lastz_32" type="boolean" checked="false" label="Use lastz_32" help="It is highly recommended to use lastz_32 instead of lastz if the refernece genome size is greater than 2G"/> + <param name="lastz_32" type="boolean" checked="false" label="Use lastz_32" help="It is highly recommended to use lastz_32 instead of lastz if the reference genome size is greater than 2G"/> <section name="where_to_look" expanded="False" title="Where to look"> - <param name="strand" type="select" display="radio" label="which strand to search" argument="--strand" help="Search both strands or choose plus or minus"> + <param type="select" display="radio" label="which strand to search" argument="--strand" help="Search both strands or choose plus or minus"> <option value="--strand=both" selected="True">Both</option> <option value="--strand=plus">Plus</option> <option value="--strand=minus">Minus</option> </param> - <param name="self" type="boolean" display="radio" truevalue="--self" falsevalue="" checked="False" argument="--self" label="Perform a self-alignment: the target sequence is also the query." help="Computation is more efficient than it would be without this option, since only one of each mirror-image pair of alignment blocks is processed (the other, redundant one is skipped during processing, but re-created in the output). Also, the trivial self-alignment block along the main diagonal is omitted from the output. THIS OPTION CANNOT BE USED IF THE TARGET IS COMPRIZED OF MULTIPLE SEQUENCES"/> - <param name="nomirror" type="boolean" display="radio" truevalue="--nomirror" falsevalue="" checked="False" label="Inhibit the re-creation of mirror-image alignments." argument="--nomirror" help="Output consists of only one copy of each meaningful alignment block in a self-alignment. This option is only applicable when the ‑‑self option is used."/> + <param type="boolean" display="radio" truevalue="--self" falsevalue="" checked="False" argument="--self" label="Perform a self-alignment: the target sequence is also the query." help="Computation is more efficient than it would be without this option, since only one of each mirror-image pair of alignment blocks is processed (the other, redundant one is skipped during processing, but re-created in the output). Also, the trivial self-alignment block along the main diagonal is omitted from the output. THIS OPTION CANNOT BE USED IF THE TARGET IS COMPRIZED OF MULTIPLE SEQUENCES"/> + <param type="boolean" display="radio" truevalue="--nomirror" falsevalue="" checked="False" label="Inhibit the re-creation of mirror-image alignments." argument="--nomirror" help="Output consists of only one copy of each meaningful alignment block in a self-alignment. This option is only applicable when the ‑‑self option is used."/> <conditional name="qhsplimit"> <param name="qhsplimit_selector" type="select" display="radio" label="Set HSP limit" argument="--queryhsplimit"> <option value="yes">Yes</option> @@ -415,8 +415,8 @@ </conditional> </section> <section name="hsp" expanded="false" title="HSPs (Gap-free extension)"> - <param name="gfextend" type="boolean" truevalue="--gfextend" checked="false" argument="--gfextend" label="Perform gap-free extension of seeds to HSPs" help="This will take into account other papermeters in this section"/> - <param name="nogfextend" type="boolean" truevalue="--nogfextend" argument="--nogfextend" label="Skip the gap-free extension stage" help="Instead, pass the seeds along to the next specified stage.It is not recommended to use --nogfextend without also using --nogapped."/> + <param type="boolean" truevalue="--gfextend" checked="false" argument="--gfextend" label="Perform gap-free extension of seeds to HSPs" help="This will take into account other papermeters in this section"/> + <param type="boolean" truevalue="--nogfextend" argument="--nogfextend" label="Skip the gap-free extension stage" help="Instead, pass the seeds along to the next specified stage.It is not recommended to use --nogfextend without also using --nogapped."/> <conditional name="hsp_method"> <param name="hsp_method_selector" type="select" display="radio" label="Select HSP finding method"> <option value="none" selected="true">None</option> @@ -428,15 +428,15 @@ <!-- Do nothing --> </when> <when value="match"> - <param name="exact" type="integer" optional="true" argument="--exact" label="Find HSPs using the exact match extension method with the given length threshold" help="This is instead of using the x-drop method"/> + <param type="integer" optional="true" argument="--exact" label="Find HSPs using the exact match extension method with the given length threshold" help="This is instead of using the x-drop method"/> </when> <when value="mismatch"> <param name="mismatch_count" type="integer" optional="true" label="Specify number of mismatches"/> <param name="mismatch_length" type="integer" min="1" max="50" optional="true" label="Specify length threshold" help="Find HSPs using the mismatch extension method with the given length threshold and allowing specified number of mismatches" argument="--mismatch"/> </when> <when value="x"> - <param name="xdrop" type="integer" optional="true" argument="--xdrop" label="Find HSPs using the x-drop extension method with this threshold" help="The dropoff setting determines the endpoints of each gap-free segment: the extension of each seed is stopped when its cumulative score drops off by more than the given threshold from the maximum seen so far."/> - <param name="hspthresh" type="integer" optional="true" argument="--hspthresh" label="Set the score threshold for the x-drop extension method" help="HSPs scoring lower are discarded"/> + <param type="integer" optional="true" argument="--xdrop" label="Find HSPs using the x-drop extension method with this threshold" help="The dropoff setting determines the endpoints of each gap-free segment: the extension of each seed is stopped when its cumulative score drops off by more than the given threshold from the maximum seen so far."/> + <param type="integer" optional="true" argument="--hspthresh" label="Set the score threshold for the x-drop extension method" help="HSPs scoring lower are discarded"/> <param name="hspthresh_top" type="integer" optional="true" argument="--hspthresh=top" label="Set an adaptive score threshold for the x-drop extension method" help="HSPs scoring lower are discarded. The score threshold is chosen to limit the number of target sequence bases in HSPs to about this value (or possibly a little higher in case of ties, etc.)."/> <param name="hspthresh_top_percent" type="integer" optional="true" argument="--hspthresh=top%" label="Set an adaptive score threshold for the x-drop extension method" help="HSPs scoring lower are discarded. The score threshold is chosen to limit the number of target sequence bases in HSPs to about this perentage value (or possibly a little higher in case of ties, etc.)."/> </when> @@ -446,7 +446,7 @@ <param name="noentropy" type="boolean" truevalue="--noentropy" checked="false" label="Don't adjust for entropy when qualifying HSPs"/> </section> <section name="chaining" expanded="false" title="Chaining"> - <param name="chain" type="boolean" truevalue="--chain" checked="false" argument="--chain" label="Perform chaining of HSPs with no penalties"/> + <param type="boolean" truevalue="--chain" checked="false" argument="--chain" label="Perform chaining of HSPs with no penalties"/> <conditional name="chaning_penalties"> <param name="chaning_penalties_selector" type="select" display="radio" argument="--chain=" label="Perform chaining with penalties"> <option value="yes">Yes</option> @@ -462,12 +462,12 @@ </conditional> </section> <section name="gap_ext" expanded="false" title="Gapped extension"> - <param name="gapped" type="boolean" truevalue="--gapped" argument="--gapped" label="Perform gapped extension of HSPs" help="Extension of HSPs (or seeds, if gap-free extension is not performed), is performed after first reducing them to anchor points."/> - <param name="nogapped" type="boolean" truevalue="--nogapped" argument="--nogapped" label="Skip the gapped extension stage" help="This means that interpolation must also be skipped, since it is not allowed without gapped extension"/> - <param name="ydrop" type="integer" optional="true" argument="--ydrop" label="Set the threshold for terminating gapped extension" help="This restricts the endpoints of each local alignment by limiting the local region around each anchor in which extension is performed. The boundary of this region in the dynamic programming matrix is formed by the points where the cumulative score has dropped off by more than the given threshold from the maximum seen so far."/> - <param name="noytrim" type="boolean" truevalue="--noytrim" argument="--noytrim" label="If y-drop extension encounters the end of the sequence, extend the alignment to the end of the sequence rather than trimming it back to the location giving the maximum score" help="This is highly recommended when either the target or query sequences are short reads (say, less than 100 bases), to prevent y-drop mismatch shadow."/> - <param name="gappedthresh" type="integer" optional="true" argument="--gappedthresh" label="Set the threshold for gapped extension" help="Alignments scoring lower than that value are discarded. When used along with the x-drop method for gap-free extension, this value is generally set at least as high as the HSP threshold. Setting it lower has no effect, since at worst the HSP itself would always qualify (both extension stages use the same scoring matrix)."/> - <param name="allgappedbounds" type="boolean" truevalue="--allgappedbounds" argument="--allgappedbounds" label="Revert to handling bounding alignments the way they were handled in BLASTZ."/> + <param type="boolean" truevalue="--gapped" argument="--gapped" label="Perform gapped extension of HSPs" help="Extension of HSPs (or seeds, if gap-free extension is not performed), is performed after first reducing them to anchor points."/> + <param type="boolean" truevalue="--nogapped" argument="--nogapped" label="Skip the gapped extension stage" help="This means that interpolation must also be skipped, since it is not allowed without gapped extension"/> + <param type="integer" optional="true" argument="--ydrop" label="Set the threshold for terminating gapped extension" help="This restricts the endpoints of each local alignment by limiting the local region around each anchor in which extension is performed. The boundary of this region in the dynamic programming matrix is formed by the points where the cumulative score has dropped off by more than the given threshold from the maximum seen so far."/> + <param type="boolean" truevalue="--noytrim" argument="--noytrim" label="If y-drop extension encounters the end of the sequence, extend the alignment to the end of the sequence rather than trimming it back to the location giving the maximum score" help="This is highly recommended when either the target or query sequences are short reads (say, less than 100 bases), to prevent y-drop mismatch shadow."/> + <param type="integer" optional="true" argument="--gappedthresh" label="Set the threshold for gapped extension" help="Alignments scoring lower than that value are discarded. When used along with the x-drop method for gap-free extension, this value is generally set at least as high as the HSP threshold. Setting it lower has no effect, since at worst the HSP itself would always qualify (both extension stages use the same scoring matrix)."/> + <param type="boolean" truevalue="--allgappedbounds" argument="--allgappedbounds" label="Revert to handling bounding alignments the way they were handled in BLASTZ."/> </section> <section name="filters" expanded="false" title="Filtering"> <section name="identity" expanded="true" title="Filter alignments by percent identity"> @@ -487,17 +487,17 @@ <param name="filter_nmismatch" type="integer" min="0" optional="true" argument="--filter=nmismatch:0.." label="Filter alignments by the number of mismatches" help="Allow no more than this number of mismatched bases. Mismatch count, or nmismatch, is the number of aligned bases in the alignment that are mismatches (substitutions)."/> <param name="filter_ngap" type="integer" min="0" optional="true" argument="--filter=ngap:0.." label="Filter alignments by the number of gaps" help="Allow no more than this number of gaps. Gap count, or ngap, is the number of runs of gapped columns in the alignment (each run is counted as one gap)."/> <param name="filter_cgap" type="integer" min="0" optional="true" argument="--filter=cgap:0.." label="Filter alignments by the number of gap columns" help="Allow no more than this number of gaps. Gap column count, or cgap, is the number of gapped columns in the alignment (each column is counted as one gap)."/> - <param name="notrivial" type="boolean" truevalue="--notrivial" argument="--notrivial" label="Do not output a trivial self-alignment block if the target and query sequences are identical" help="Note that using ‑‑self automatically enables this option."/> + <param type="boolean" truevalue="--notrivial" argument="--notrivial" label="Do not output a trivial self-alignment block if the target and query sequences are identical" help="Note that using ‑‑self automatically enables this option."/> </section> <section name="interpolation" expanded="false" title="Interpolation"> - <param name="inner" type="integer" optional="true" argument="--inner" label="Perform additional alignment between the gapped alignment blocks, using (presumably) more sensitive alignment parameters" help="This value is used as the threshold for both the gap-free and gapped extension sub-stages; see the discussion of interpolation for more details. This option is only valid if gapped extension is performed."/> + <param type="integer" optional="true" argument="--inner" label="Perform additional alignment between the gapped alignment blocks, using (presumably) more sensitive alignment parameters" help="This value is used as the threshold for both the gap-free and gapped extension sub-stages; see the discussion of interpolation for more details. This option is only valid if gapped extension is performed."/> </section> <section name="output_format" expanded="false" title="Output"> <conditional name="out"> <param name="format" type="select" display="radio" label="Specify the output format"> <option value="bam" selected="true">BAM --format=sam)</option> <option value="general_def">General default (--format=general)</option> - <option value="general_full">Customized general (‑‑format=general[:fields])</option> + <option value="general_full">Customized general (--format=general[:fields])</option> <option value="maf">MAF (--format=maf)</option> <option value="blastn">blastn (--format=BLASTN)</option> <option value="differences">Differences (--format=differences)</option> @@ -596,7 +596,7 @@ </data> </outputs> <tests> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="cached" /> <param name="target_2bit" value="phiX174" /> <param name="query" value="phiX_split.fasta" /> @@ -604,7 +604,7 @@ <param name="format" value="general_def" /> <output name="output" value="test1.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" value="phiX_split.fasta" /> <param name="query" value="phiX.fasta" /> @@ -612,7 +612,7 @@ <param name="format" value="general_def" /> <output name="output" value="test2.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" value="phiX_split.fasta" /> <param name="query" value="phiX.fasta" /> @@ -621,7 +621,7 @@ <param name="format" value="general_def" /> <output name="output" value="test3.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" value="chrM_mouse.fa.gz" /> <param name="query" value="chrM_human.fa.gz" /> @@ -629,17 +629,15 @@ <param name="format" value="blastn" /> <output name="output" value="test4.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" ftype="fasta.gz" value="chrM_human.fa.gz" /> <param name="query" ftype="fastq.bz2" value="chrM_mouse.fq.bz2" /> - <param name="traceback" value="83886080" /> - <param name="word" value="28" /> <param name="strand" value="--strand=both" /> <param name="format" value="blastn" /> <output name="output" value="test5.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" ftype="fasta.gz" value="chrM_human.fa.gz" /> <param name="query" ftype="fastq.gz" value="chrM_mouse.fq.gz" /> @@ -647,7 +645,7 @@ <param name="format" value="blastn" /> <output name="output" value="test5.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="history" /> <param name="target" ftype="fasta.gz" value="chrM_human.fa.gz" /> <param name="query" ftype="fastq" value="chrM_mouse.fq" /> @@ -656,7 +654,7 @@ <param name="format" value="blastn" /> <output name="output" value="test5.out" /> </test> - <test> + <test expect_num_outputs="1"> <param name="ref_source" value="cached" /> <param name="target_2bit" value="phiX174" /> <param name="query" value="phiX_split.fasta" /> @@ -674,11 +672,11 @@ .. class:: infomark -**Read documentation** before proceeding. LASTZ is a complex tool with many parameter options. Fortunately, there is a `great manual <https://lastz.github.io/lastz/>`_ maintained by its author. Default parameters may be sufficient to obtain the initial idea about how similar your sequences are, but to produce reliable alignments you may need to tweak the parameters. So RTFM! +**Read documentation** before proceeding. LASTZ is a complex tool with many parameter options. Fortunately, there is a `great manual <https://lastz.github.io/lastz/>`_ maintained by its author. Default parameters may be sufficient to obtain the initial idea about how similar your sequences are, but to produce reliable alignments you may need to tweak the parameters. Read the manual. .. class:: warningmark -Galaxy version of LASTZ sets **--ambiguous=iupac** as default (see **Scoring** section). This prevents LASTZ from erroring out if one of the DNA inputrs contains "non-strandard" nucleotides. +Galaxy version of LASTZ sets **--ambiguous=iupac** as default (see **Scoring** section). This prevents LASTZ from erroring out if one of the DNA inputrs contains "non-standard" nucleotides. **About LASTZ parameters**