Mercurial > repos > iuc > gemini_windower
changeset 5:3b5b1ebc8423 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 62ed732cba355e695181924a8ed4cce49ca21c59
line wrap: on
line diff
--- a/gemini_macros.xml Fri Dec 14 12:41:48 2018 -0500 +++ b/gemini_macros.xml Fri Jan 11 17:38:04 2019 -0500 @@ -1,15 +1,12 @@ <macros> <!-- gemini version to be used --> - <token name="@VERSION@">0.18.1</token> + <token name="@VERSION@">0.20.1</token> <!-- minimal annotation files version required by this version of gemini --> - <token name="@DB_VERSION@">181</token> + <token name="@DB_VERSION@">200</token> <xml name="requirements"> <requirements> <requirement type="package" version="@VERSION@">gemini</requirement> - <requirement type="package" version="0.2.6">tabix</requirement> - <!-- for conda useage --> - <!--requirement type="package" version="1.3.1">htslib</requirement--> <yield /> </requirements> </xml> @@ -24,9 +21,17 @@ <exit_code range=":-1" /> <regex match="Error:" /> <regex match="Exception:" /> + <yield /> </stdio> </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1003153</citation> + <yield /> + </citations> + </xml> + <xml name="annotation_dir"> <param name="annotation_databases" type="select" label="Choose a gemini annotation source"> <options from_data_table="gemini_versioned_databases"> @@ -36,31 +41,36 @@ </param> </xml> - <xml name="add_header_column"> - <param name="header" type="boolean" truevalue="--header" falsevalue="" checked="False" - label="Add a header of column names to the output" help="(--header)"/> - </xml> - - <xml name="radius"> - <param name="radius" type="integer" value="3" label="Set filter for Breadth-first search (BFS) in the Protein-Protein Interaction network" help="(-r)" > - <validator type="in_range" min="0"/> + <xml name="infile"> + <param name="infile" type="data" format="gemini.sqlite" label="GEMINI database" help="Only files with version @VERSION@ are accepted." > + <options options_filter_attribute="metadata.gemini_version" > + <filter type="add_value" value="@VERSION@" /> + </options> </param> </xml> - <xml name="variant_mode"> - <param name="variant_mode" type="boolean" truevalue="--var" falsevalue="" checked="False" - label="Returns variant info (e.g. impact, biotype) for interacting genes" help="(--var)"/> + + <xml name="add_header_column"> + <param argument="--header" name="header" type="boolean" truevalue="--header" falsevalue="" checked="True" + label="Add a header of column names to the output" /> </xml> - <xml name="column_filter"> + <xml name="column_filter" token_help="" token_minimalset="variant_id, gene"> <conditional name="report"> - <param name="report_selector" type="select" label="Columns to include in the report" - help="By default, this tool reports all columns in the variants table. One may choose to report only a subset of the columns."> - <option value="all" selected="True">all</option> - <option value="column_filter">User given columns</option> + <param name="report_selector" type="select" + label="Set of columns to include in the variant report table" + help="@HELP@"> + <option value="minimal">Minimal (report only a preconfigured minimal set of columns)</option> + <option value="full">Full (report all columns defined in the GEMINI database variants table)</option> + <option value="custom">Custom (report user-specified columns)</option> </param> - <when value="all"/> - <when value="column_filter"> - <param name="columns" type="select" display="checkboxes" multiple="True" label="Choose columns to include in the report" help="(--columns)"> + <when value="full" /> + <when value="minimal"> + <param name="columns" type="hidden" value="@MINIMALSET@" /> + <param name="extra_cols" type="hidden" value="" /> + </when> + <when value="custom"> + <param name="columns" type="select" display="checkboxes" multiple="true" optional="true" + label="Choose columns to include in the report" help="(--columns)"> <option value="gene">gene</option> <option value="chrom">chrom</option> <option value="start">start</option> @@ -69,27 +79,23 @@ <option value="alt">alt</option> <option value="impact">impact</option> <option value="impact_severity">impact_severity</option> - <option value="max_aaf_all">alternative allele frequency</option> + <option value="max_aaf_all">alternative allele frequency (max_aaf_all)</option> </param> - <param name="extra_cols" type="text" label="Additional columns." help="Separate by whitespace"/> + <param name="extra_cols" type="text" + label="Additional columns (comma-separated)" + help="Column must be specified by the exact name they have in the GEMINI database, e.g., is_exonic or num_hom_alt, but, for genotype columns, GEMINI wildcard syntax is supported. The order of columns in the list is maintained in the output."> + <expand macro="sanitize_query" /> + </param> </when> </conditional> </xml> - <xml name="filter"> - <conditional name="filter"> - <param name="filter_selector" type="select" label="Apply additional constraints" - help="By default, this tool will report all variants regardless of their putative functional impact. In order to apply additional constraints on the variants returned, you can this optional filter."> - <option value="no">No additional constraints</option> - <option value="yes">Apply additional constraints</option> - </param> - <when value="no"/> - <when value="yes"> - <param name="filter" type="text" label="Contraints in SQL syntax" help="Conditions applied here will become WHERE clauses in the query issued to the GEMINI database. E.g. alt='G' or impact_severity = 'HIGH'. (--filter)"> - <expand macro="sanitize_query" /> - </param> - </when> - </conditional> + <xml name="filter" token_argument="--filter"> + <param argument="@ARGUMENT@" name="filter" type="text" + label="Additional constraints expressed in SQL syntax" + help="Constraints defined here will become the WHERE clause of the SQL query issued to the GEMINI database. E.g. alt='G' or impact_severity = 'HIGH'."> + <expand macro="sanitize_query" /> + </param> </xml> <xml name="sanitize_query"> @@ -103,10 +109,90 @@ </sanitizer> </xml> + <xml name="lenient" token_argument="--lenient" token_truevalue="--lenient" token_help="The exact consequence of this setting depends on the type of inheritance pattern you are looking for (see the tool help below)."> + <param argument="@ARGUMENT@" name="lenient" type="boolean" truevalue="@TRUEVALUE@" falsevalue="" checked="False" + label="Include hits with less convincing inheritance patterns" + help= "@HELP@" /> + </xml> + + <xml name="unaffected"> + <param argument="--allow-unaffected" name="allow_unaffected" type="boolean" truevalue="--allow-unaffected" falsevalue="" checked="False" + label="Report candidates shared by unaffected samples" + help="Activating this option will enable the reporting of variants as candidate causative even if they are shared by unaffected samples in the family tree. The default will only report variants that are unique to affected samples."/> + </xml> + + <xml name="min_kindreds" token_label="Minimum number of families with a candidate variant for a gene to be reported" token_help="This is the number of families required to have a variant fitting the inheritance model in the same gene in order for the gene and its variants to be reported. For example, we may only be interested in candidates where at least 4 families have a variant (with a fitting inheritance pattern) in that gene."> + <param argument="--min-kindreds" name="min_kindreds" type="integer" value="1" min="1" + label="@LABEL@" + help="@HELP@" /> + </xml> + + <xml name="insert_constraint" token_max_repeat="1"> + <repeat name="constraint" title="Additional constraints on variants" default="0" max="@MAX_REPEAT@"> + <expand macro="filter" /> + <yield /> + </repeat> + </xml> + + <xml name="overwritable_where_default" token_default_where=""> + <param name="overwrite_default_filter" type="boolean" checked="false" + label="Overwrite the default constraint of this tool" + help="By default, this tool restricts its analysis to @DEFAULT_WHERE@ and this constraint is applied on top of any constraint expressed above. With this option here selected, your custom constraint, if given, will overwrite the default instead." /> + </xml> + + <xml name="gt_filter" token_default_repeat="0" token_min_repeat="0" token_max_repeat="1"> + <repeat name="filter_by_genotype" title="Genotype filter expression" default="@DEFAULT_REPEAT@" min="@MIN_REPEAT@" max="@MAX_REPEAT@"> + <param argument="--gt-filter" name="gt_filter" type="text" value="" area="True" size="5x50" + label="Restrictions to apply to genotype values" help=""> + <expand macro="sanitize_query" /> + <validator type="expression" message="Genotype filter expression cannot be empty">value.strip()</validator> + </param> + <yield /> + </repeat> + </xml> + + <xml name="sample_filter"> + <repeat name="filter_by_sample" title="Sample filter expression" default="0" max="1"> + <param argument="--sample-filter" name="sample_filter" type="text" area="True" size="5x50" + label="SQL filter to use to filter the sample table" help=""> + <expand macro="sanitize_query" /> + <validator type="expression" message="Sample filter expression cannot be empty">value.strip()</validator> + </param> + <param argument="--in" name="in" type="select" + label="A variant must be in either all, none or any samples passing the sample-query filter" + help=""> + <option value="">Return a variant if it is found in any sample passing the sample filter. (default) </option> + <option value="--in all">Return a variant if it is found in ALL samples passing the sample filter. (all)</option> + <option value="--in none">Return a variant if it is found in NO sample passing the sample filter. (none)</option> + <option value="--in only">Return a variant if it is found in any sample passing the sample filter, and in NO sample NOT passing it. (only)</option> + <option value="--in only all">Return a variant if is found in ALL samples passing the sample filter, and in NO sample NOT passing it. (only all)</option> + </param> + <expand macro="min_kindreds" + label="Minimum number of families in which a variant must pass the sample filter" help=""/> + <param argument="--family-wise" name="family_wise" type="boolean" truevalue="--family-wise" falsevalue="" checked="False" + label="Apply the sample-filter on a family-wise basis" help="If a variant passes the sample filter in at least the minimum number of families specified above it is retained." /> + </repeat> + </xml> + + <xml name="region_filter"> + <repeat name="regions" title="Region Filter" default="0" min="0" + help="Filter variant sites by their position in the genome. If multiple Region Filters are specified, all variants that fall in ONE of the regions are reported."> + <param name="chrom" type="text" label="Chromosome"> + <validator type="expression" message="A chromosome identifier is required when specifying a region filter">value.strip()</validator> + </param> + <param name="start" type="text" label="Region Start"> + <validator type="expression" message="an integer number is required">not value or value.isdigit()</validator> + </param> + <param name="stop" type="text" label="Region End"> + <validator type="expression" message="an integer number is required">not value or value.isdigit()</validator> + </param> + </repeat> + </xml> + <token name="@PROVIDE_ANNO_DATA@"><![CDATA[ mkdir gemini && - ln -s "${annotation_databases.fields.path}/gemini/data" gemini/data && - export GEMINI_CONFIG="${annotation_databases.fields.path}" && + ln -s '${annotation_databases.fields.path}/gemini/data' gemini/data && + export GEMINI_CONFIG='${annotation_databases.fields.path}' && ]]></token> <token name="@MULTILN_SQL_EXPR_TO_CMDLN@"> @@ -119,67 +205,50 @@ #end if </token> - <token name="@CMDLN_SQL_FILTER_FILTER_OPTION@"> - #if str($filter.filter_selector) == 'yes' and $filter.filter: - --filter '${ str( $filter.filter ) }' + <token name="@SET_COLS@"> + #if str($report.report_selector) == 'full': + #set cols = "*" + #else: + #if $report.columns and str($report.columns) != '': + #set $cols = str($report.columns) + #else + #set $cols = '' + #end if + #if str($report.extra_cols).strip(): + #if $cols: + #set $cols = $cols + ', ' + str($report.extra_cols) + #else: + #set $cols = str($report.extra_cols) + #end if + #end if + #if not $cols: + #set $cols = "variant_id, gene" + #end if #end if </token> <token name="@COLUMN_SELECT@"> - #if $report.report_selector != 'all': - --columns "${report.columns} - #if str($report.extra_cols).strip() - #echo ','+','.join(str($report.extra_cols).split()) - #end if - " + @SET_COLS@ + #if $cols != "*" + --columns '$cols' #end if </token> - <xml name="family"> - <param name="families" type="text" value="" label="Comma seperated list of families to restrict the analysis to." help="e.g. Family1,Family3 (--families)"/> - </xml> - - <xml name="lenient"> - <param name="lenient" type="boolean" truevalue="--lenient" falsevalue="" checked="False" label="Loosen the restrictions on family structure"/> - </xml> - - <xml name="unaffected"> - <param name="allow_unaffected" type="boolean" truevalue="--allow-unaffected" falsevalue="" checked="False" label="Report candidates that also impact samples labeled as unaffected." help="(--allow-unaffected)"/> - </xml> - - <xml name="min_kindreds"> - <param name="min_kindreds" type="integer" value="1" label="The min. number of kindreds that must have a candidate variant in a gene" help="default: 1 (--min-kindreds)" /> - </xml> - - <xml name="min_sequence_depth"> - <param name="d" type="integer" value="0" min="0" label="The minimum aligned sequence depth (genotype DP) required for each sample" - help="default: 0 (-d)" /> - </xml> - - <xml name="min_gq"> - <param name="min_gq" type="integer" value="0" label="the minimum genotype quality required for each sample in a family" help="default: 0 (--min-gq)"> - <validator type="in_range" min="0"/> - </param> - </xml> - - <xml name="gt_pl_max"> - <param name="gt_pl_max" type="integer" value="-1" min="-1" label="The maximum phred-scaled genotype likelihod (PL) allowed for each sample in a family" help="default: -1 (not set) (--gt-pl-max)" /> - </xml> - - <xml name="citations"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1003153</citation> - <yield /> - </citations> - </xml> - - <xml name="infile"> - <param name="infile" type="data" format="gemini.sqlite" label="GEMINI database" help="Only files with version @VERSION@ are accepted." > - <options options_filter_attribute="metadata.gemini_version" > - <filter type="add_value" value="@VERSION@" /> - </options> - <validator type="expression" message="This version of Gemini will only work with Gemini files that are for version @VERSION@.">value is not None and value.metadata.gemini_version == "@VERSION@"</validator> - </param> - </xml> - + <token name="@PARSE_REGION_ELEMENTS@"><![CDATA[ + #set $region_elements = [] + #for $r in $regions: + ## The actual chromosome name needs to be single-quoted + ## in SQL, so we need to quote the single quotes like the + ## sanitize_query macro would if the whole was a parameter. + #set $r_elements = ["chrom = '\"'\"'%s'\"'\"'" % str($r.chrom).strip()] + #if str($r.start).strip(): + #silent $r_elements.append("start >= %d" % int($r.start)) + #end if + #if str($r.stop).strip(): + #silent $r_elements.append("end <= %d" % int($r.stop)) + #end if + #silent $region_elements.append("(%s)" % " AND ".join($r_elements)) + #end for + ]]> + </token> </macros>
--- a/gemini_windower.xml Fri Dec 14 12:41:48 2018 -0500 +++ b/gemini_windower.xml Fri Jan 11 17:38:04 2019 -0500 @@ -1,5 +1,5 @@ -<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.1"> - <description>Conducting analyses on genome "windows"</description> +<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@"> + <description>Compute sliding window statistics from variants</description> <macros> <import>gemini_macros.xml</import> <token name="@BINARY@">windower</token> @@ -14,19 +14,21 @@ -s $s -t $window_analysis -o $operation - "${ infile }" - > "${ outfile }" + '$infile' + > '$outfile' ]]> </command> <inputs> <expand macro="infile" /> - <param name="window_analysis" type="select" label="The type of window analysis requested?" help="(-t)"> + <param argument="-t" name="window_analysis" type="select" + label="The type of window analysis requested?" help=""> <option value="nucl_div">(nucl_div)</option> <option value="hwe">(hwe)</option> </param> - <param name="operation" type="select" label="The operation that should be applied to the -t values" help="(-o)"> + <param argument="-o" name="operation" type="select" + label="The operation that should be applied to the -t values" help=""> <option value="mean">mean</option> <option value="median">median</option> <option value="min">min</option> @@ -34,18 +36,11 @@ <option value="collapse">collapse</option> </param> - <param name="w" type="integer" value="10000" label="The window size in bp" - help="(-w)"> - <validator type="in_range" min="0"/> - </param> - - <param name="s" type="integer" value="1000" label="The step size for the windows in bp" - help="(-s)"> - <validator type="in_range" min="0"/> - </param> - + <param argument="-w" name="w" type="integer" value="10000" min="2" + label="Window size in bp" help="" /> + <param argument="-s" name="s" type="integer" value="1000" min="0" + label="Step size for sliding the window in bp" help="Specify 0 here for sliding by one full window size" /> </inputs> - <outputs> <data name="outfile" format="tabular" /> </outputs> @@ -62,27 +57,28 @@ <help><![CDATA[ **What it does** -It computs variation metrics across genomic windows (both fixed and sliding). +Compute variation metrics across genomic windows. **Examples** -Compute the average nucleotide diversity for all variants found in non-overlapping, 50Kb windows with following settings:: +Compute the average nucleotide diversity for all variants found in non-overlapping, 50Kb windows:: -w 50000 -s 0 -t nucl_div -o mean -Compute the average nucleotide diversity for all variants found in 50Kb windows that overlap by 10kb with following settings:: +Compute the average nucleotide diversity for all variants found in 50Kb windows that overlap by 40kb:: -w 50000 -s 10000 -t nucl_div -o mean -Compute the max value for HWE statistic for all variants in a window of size 10kb with following settings:: +Compute the max value for HWE statistics for all variants in 10kb windows every 100kb along the genome:: - -w 10000 + -w 10000 + -s 100000 -t hwe -o max
--- a/repository_dependencies.xml Fri Dec 14 12:41:48 2018 -0500 +++ b/repository_dependencies.xml Fri Jan 11 17:38:04 2019 -0500 @@ -1,4 +1,4 @@ <?xml version="1.0" ?> <repositories description="This requires the GEMINI data manager definition to install all required annotation databases."> - <repository changeset_revision="fe5a9a7d95b0" name="data_manager_gemini_database_downloader" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"/> + <repository changeset_revision="f57426daa04d" name="data_manager_gemini_database_downloader" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu"/> </repositories> \ No newline at end of file
--- a/test-data/gemini_versioned_databases.loc Fri Dec 14 12:41:48 2018 -0500 +++ b/test-data/gemini_versioned_databases.loc Fri Jan 11 17:38:04 2019 -0500 @@ -1,3 +1,3 @@ ## GEMINI versioned databases #DownloadDate dbkey DBversion Description Path -1999-01-01 hg19 181 GEMINI annotations (test snapshot) ${__HERE__}/test-cache +1999-01-01 hg19 200 GEMINI annotations (test snapshot) ${__HERE__}/test-cache
--- a/test-data/test-cache/gemini-config.yaml Fri Dec 14 12:41:48 2018 -0500 +++ b/test-data/test-cache/gemini-config.yaml Fri Jan 11 17:38:04 2019 -0500 @@ -2,12 +2,14 @@ versions: ALL.wgs.phase3_shapeit2_mvncall_integrated_v5a.20130502.sites.tidy.vcf.gz: 4 ESP6500SI.all.snps_indels.tidy.v2.vcf.gz: 2 - ExAC.r0.3.sites.vep.tidy.vcf.gz: 3 + ExAC.r0.3.sites.vep.tidy.vcf.gz: 4 GRCh37-gms-mappability.vcf.gz: 2 - clinvar_20160203.tidy.vcf.gz: 5 + clinvar_20170130.tidy.vcf.gz: 5 cosmic-v68-GRCh37.tidy.vcf.gz: 3 - dbsnp.b141.20140813.hg19.tidy.vcf.gz: 4 + dbsnp.b147.20160601.tidy.vcf.gz: 1 detailed_gene_table_v75: 2 geno2mp.variants.tidy.vcf.gz: 1 + gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz: 2 hg19.rmsk.bed.gz: 2 summary_gene_table_v75: 2 + whole_genome_SNVs.tsv.compressed.gz: 2