| Previous changeset 18:2fa9d4f1b48f (2022-02-14) Next changeset 20:14ae456b8cc5 (2022-05-03) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/pangolin commit 98c0d716cbd1237ae735ce83e0153ee246abd5d8" |
|
modified:
pangolin.xml |
| b |
| diff -r 2fa9d4f1b48f -r abf6dbe8c9d7 pangolin.xml --- a/pangolin.xml Mon Feb 14 07:17:26 2022 +0000 +++ b/pangolin.xml Thu Apr 21 11:40:56 2022 +0000 |
| [ |
| b'@@ -1,55 +1,65 @@\n <tool id="pangolin" name="Pangolin" version="@TOOL_VERSION@+galaxy0" profile="20.01">\n <description>Phylogenetic Assignment of Outbreak Lineages</description>\n <macros>\n- <token name="@TOOL_VERSION@">3.1.20</token>\n+ <token name="@TOOL_VERSION@">4.0.5</token>\n </macros>\n <requirements>\n <requirement type="package" version="@TOOL_VERSION@">pangolin</requirement>\n <requirement type="package" version="0.3.16">scorpio</requirement>\n <requirement type="package" version="0.23.0">csvtk</requirement>\n </requirements>\n+ <version_command><![CDATA[pangolin --version]]></version_command>\n <command detect_errors="exit_code"><![CDATA[\n #if str($db.source) == "download"\n+ ## Pangolin version 4 tries to update from an existing directory\n+ mkdir datadir &&\n pangolin --update-data --datadir datadir &&\n #else if str($db.source) == "builtin"\n ln -s $db.db_release.fields.path datadir &&\n #end if\n pangolin\n --threads \\${GALAXY_SLOTS:-1}\n+ --tempdir "\\${TMPDIR:-.}"\n #if str($db.source) == "download" or str($db.source) == "builtin"\n- --datadir \'datadir\'\n+ --datadir datadir\n #end if\n- $usher\n- $alignment\n+ --analysis-mode $engine.analysis_mode\n+ #if str($engine.analysis_mode) == \'usher\':\n+ $engine.use_assignment_cache\n+ #end if\n+ #if $alignment:\n+ $alignment --alignment-file \'$align1\'\n+ #end if\n --outfile report.csv \n --max-ambig $max_ambig\n --min-length $min_length\n+ $expanded_lineage\n \'$input1\'\n && csvtk csv2tab report.csv\n #if not $include_header:\n | tail -n+2 \n #end if\n > \'$output1\'\n- #if $alignment\n- && mv sequences.aln.fasta \'$align1\'\n- #end if \n ]]></command>\n <inputs>\n- <param type="data" name="input1" format="fasta" label="Input FASTA File(s)" /> \n- <param argument="--usher" type="boolean" label="Use UShER model" truevalue="--usher" falsevalue="" help="Use UShER model instead of default pangoLEARN model" />\n- <param argument="--alignment" type="boolean" label="Generate output alignment" \n- truevalue="--alignment" falsevalue="" /> \n- <param argument="--max-ambig" type="float" label="Maximum proportion of Ns allowed" \n- value="0.5" min="0" max="1" help="Maximum proportion of Ns allowed for pangolin to attempt assignment" />\n- <param argument="--min-length" type="integer" label="Minimum query length allowed" \n- value="10000" min="0" help="Minimum query length allowed for pangolin to attempt assignment"/>\n- <param name="include_header" type="boolean" label="Include header line in output file" \n- truevalue="true" falsevalue="false" />\n+ <param type="data" name="input1" format="fasta" label="Input FASTA File(s)" />\n+ <conditional name="engine">\n+ <param argument="--analysis-mode" type="select" label="Analysis mode"\n+ help="The analysis engine to use for lineage assignment. UShER is considered more accurate, but pangoLEARN is faster">\n+ <option value="usher">UShER</option>\n+ <option value="pangolearn">pangoLEARN</option>\n+ </param>\n+ <when value="usher">\n+ <param argument="--use-assignment-cache" type="boolean" truevalue="--add-assignment-cache --use-assignment-cache" falsevalue="" label="Use latest UShER assignment cache"\n+ help="Get the latest UShER assignment cache from the pangolin-assignment online repository and use it to speed up UShER lineage assignment. Note: Downloading the cached assignments will only pay off for large numbers of input samples. Also note that using the latest assignment cache in combination with the built-in or a cached pangol'..b'and the SARS-CoV-2 diversity designated.\n+ This assignment is sensitive to missing data at key sites.\n+\n+conflict:\n+ In the pangoLEARN model, a given sequence gets assigned to the most likely\n+ category based on known diversity.\n+ If a sequence can fit into more than one category, the conflict score will\n+ be greater than 0 and reflect the number of categories the sequence could\n+ fit into.\n+ If the conflict score is 0, this means that within the current decision\n+ tree there is only one category that the sequence could be assigned to.\n+\n+ambiguity_score:\n+ This score is a function of the quantity of missing data in a sequence.\n+ It represents the proportion of relevant sites in a sequnece which were\n+ imputed to the reference values.\n+ A score of 1 indicates that no sites were imputed, while a score of 0\n+ indicates that more sites were imputed than were not imputed.\n+ This score only includes sites which are used by the decision tree to\n+ classify a sequence.\n+\n+scorpio_call:\n+ If a query is assigned a constellation by scorpio this call is output in\n+ this column.\n+ The full set of constellations searched by default can be found at the\n+ constellations repository.\n+\n+scorpio_support:\n+ The support score is the proportion of defining variants which have the\n+ alternative allele in the sequence.\n+\n+scorpio_conflict:\n+ The conflict score is the proportion of defining variants which have the\n+ reference allele in the sequence. Ambiguous/other non-ref/alt bases at each\n+ of the variant positions contribute only to the denominators of these\n+ scores.\n+\n+scorpio_notes:\n+ A notes column specific to the scorpio output.\n+\n+version:\n+ A version number that represents both the inference method and the\n+ pangolin-data version number, which as of pangolin 4.0 corresponds to the\n+ pango-designation version used to prepare the inference files. For example:\n+\n+ PANGO-1.2 indicates an identical sequence has been previously designated\n+ this lineage, and has so gone through manual curation.\n+ The number 1.2 indicates the version of pango-designation that this\n+ assignment is based on. These hashes and pango-designation version are\n+ bundled with the pangoLEARN and UShER models.\n+\n+ PLEARN-1.2 indicates that this sequence is different from any previously\n+ designated and that the pangoLEARN model was used as an inference engine to\n+ predict the most likely lineage based on the given version of\n+ pango-designation upon which the pangoLEARN model was trained.\n+\n+ PUSHER-1.2 indicates that this sequence is different from any previously\n+ designated and that UShER was used as an inference engine with fast tree\n+ placement and parsimony-based lineage assignment, based on a guide tree\n+ (protobuf) file built from the data in a given pango-designation release\n+ version.\n+\n+pangolin_version:\n+ The version of pangolin software running.\n+\n+scorpio_version:\n+ The version of the scorpio software installed.\n+\n+constellation_version:\n+ The version of constellations that scorpio has used to curate the lineage\n+ assignment.\n+\n+is_designated:\n+ A boolean (True/False) column indicating whether that particular sequence\n+ has been offically designated a lineage.\n+\n+qc_status:\n+ Indicates whether the sequence passed the QC thresholds for minimum length\n+ and maximum N content.\n+\n+qc_notes:\n+ Notes specific to the QC checks run on the sequences.\n+\n+note:\n+ If any conflicts from the decision tree, this field will output the\n+ alternative assignments. If the sequence failed QC this field will describe\n+ why.\n+ If the sequence met the SNP thresholds for scorpio to call a constellation,\n+ it\xe2\x80\x99ll describe the exact SNP counts of Alt, Ref and Amb (Alternative,\n+ reference and ambiguous) alleles for that call.\n ]]></help>\n <citations>\n <citation type="doi">10.1093/ve/veab064</citation>\n' |