| Previous changeset 4:f3cc64057b4e (2018-12-14) Next changeset 6:496124e09f82 (2020-01-24) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 62ed732cba355e695181924a8ed4cce49ca21c59 |
|
modified:
gemini_db_info.xml gemini_macros.xml repository_dependencies.xml test-data/gemini_amend_input.db test-data/gemini_annotate_result.db test-data/gemini_auto_dom_input.db test-data/gemini_auto_rec_input.db test-data/gemini_comphets_input.db test-data/gemini_de_novo_input.db test-data/gemini_is_somatic_result.db test-data/gemini_load_result1.db test-data/gemini_load_result2.db test-data/gemini_versioned_databases.loc test-data/test-cache/gemini-config.yaml |
|
added:
test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz.tbi test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz.tbi test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz.tbi |
|
removed:
test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 gemini_db_info.xml --- a/gemini_db_info.xml Fri Dec 14 12:41:01 2018 -0500 +++ b/gemini_db_info.xml Fri Jan 11 17:37:04 2019 -0500 |
| [ |
| b'@@ -1,21 +1,47 @@\n-<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.1">\n- <description>List the gemini database tables and columns</description>\n+<tool id="gemini_db_info" name="GEMINI database info" version="@VERSION@">\n+ <description>Retrieve information about tables, columns and annotation data stored in a GEMINI database</description>\n <macros>\n <import>gemini_macros.xml</import>\n- <token name="@BINARY@">db_info</token>\n </macros>\n <expand macro="requirements" />\n <expand macro="stdio" />\n <expand macro="version_command" />\n <command>\n <![CDATA[\n- gemini @BINARY@\n- "${ infile }" | tr -s \' \' \'\\t\'\n- > "${ outfile }"\n+ #if str($select.info_type) == \'scheme\':\n+ gemini db_info \'$infile\' | tr -s \' \' \'\\t\'\n+ #elif str($select.info_type) == \'resources\':\n+ gemini query --header -q "SELECT name as data_source, resource as resource_file from resources" \'$infile\'\n+ #elif str($select.info_type) == \'gene_detailed\':\n+ gemini query --header -q "SELECT gene, synonym as synonyms, transcript FROM gene_detailed WHERE gene is not NULL GROUP BY transcript ORDER BY gene" \'$infile\'\n+ #else:\n+ gemini query --header -q "SELECT * FROM samples" "$infile" | cut -f 2-${select.format}\n+ #end if\n+\n+ > \'$outfile\'\n ]]>\n </command>\n <inputs>\n <expand macro="infile" />\n+ <conditional name="select">\n+ <param name="info_type" type="select"\n+ label="Information to retrieve from the database">\n+ <option value="scheme">Names of database tables and their columns</option>\n+ <option value="resources">List of annotation data sources</option>\n+ <option value="gene_detailed">List of genes and their transcripts</option>\n+ <option value="samples">Write out sample information in PED format</option>\n+ </param>\n+ <when value="scheme" />\n+ <when value="resources" />\n+ <when value="gene_detailed" />\n+ <when value="samples">\n+ <param name="format" type="select" display="radio"\n+ label="Format of the pedigree file">\n+ <option value="">Allow extra columns to accomodate custom sample info</option>\n+ <option value="7">Restrict to 6 PED standard columns and drop additional info</option>\n+ </param>\n+ </when>\n+ </conditional>\n </inputs>\n <outputs>\n <data name="outfile" format="tabular" />\n@@ -23,67 +49,71 @@\n <tests>\n <test>\n <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />\n+ <conditional name="select">\n+ <param name="info_type" value="scheme" />\n+ </conditional>\n <output name="outfile">\n <assert_contents>\n <has_line_matching expression="table_name	column_name	type.*" />\n </assert_contents>\n </output>\n </test>\n+ <test>\n+ <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />\n+ <conditional name="select">\n+ <param name="info_type" value="resources" />\n+ </conditional>\n+ <output name="outfile">\n+ <assert_contents>\n+ <has_line line="data_source	resource_file" />\n+ <has_n_columns n="2" />\n+ </assert_contents>\n+ </output>\n+ </test>\n+ <test>\n+ <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" />\n+ <conditional name="select">\n+ <param name="info_type" value="gene_detailed" />\n+ </conditional>\n+ <output name="outfile">\n+ <assert_contents>\n+ <has_line line="gene	'..b'+ </test>\n+ <test>\n+ <param name="infile" value="gemini_comphets_input.db" ftype="gemini.sqlite" />\n+ <conditional name="select">\n+ <param name="info_type" value="samples" />\n+ <param name="format" value="7" />\n+ </conditional>\n+ <output name="outfile">\n+ <assert_contents>\n+ <has_line line="family_id	name	paternal_id	maternal_id	sex	phenotype" />\n+ <has_n_columns n="6" />\n+ </assert_contents>\n+ </output>\n+ </test>\n </tests>\n <help><![CDATA[\n **What it does**\n \n-Because of the sheer number of annotations that are stored in gemini, there are admittedly too many columns to remember by rote.\n-If you can\xe2\x80\x99t recall the name of particular column, just use the db_info tool.\n-It will report all of the tables and all of the columns / types in each table::\n+Because of the sheer number of annotations that are stored in gemini, it is easy to lose the overview of what is actually available through database queries.\n \n- table_name column_name type\n- variants chrom text\n- variants start integer\n- variants end integer\n- variants variant_id integer\n- variants anno_id integer\n- variants ref text\n- variants alt text\n- variants qual float\n- variants filter text\n- variants type text\n- variants sub_type text\n- variants gts blob\n- variants gt_types blob\n- variants gt_phases blob\n- variants gt_depths blob\n- variants call_rate float\n- variants in_dbsnp bool\n- variants rs_ids text\n- variants in_omim bool\n- variants clin_sigs text\n- variants cyto_band text\n- variants rmsk text\n- variants in_cpg_island bool\n- variants in_segdup bool\n- variants is_conserved bool\n- variants num_hom_ref integer\n- variants num_het integer\n- variants num_hom_alt integer\n- variants num_unknown integer\n- variants aaf float\n- variants hwe float\n- variants inbreeding_coeff float\n- variants pi float\n- variants recomb_rate float\n- variants gene text\n- variants transcript text\n- variants is_exonic bool\n- variants is_coding bool\n- variants is_lof bool\n- variants exon text\n- variants codon_change text\n- variants aa_change text\n- ... ... ... \n-\n-For more columns see https://gemini.readthedocs.org/en/latest/content/tools.html#db-info-list-the-gemini-database-tables-and-columns\n-\n+This tool offers a simple way to inspect the structure, the origin of the\n+annotations and some of the actual annotation content quickly.\n ]]></help>\n <expand macro="citations"/>\n </tool>\n' |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 gemini_macros.xml --- a/gemini_macros.xml Fri Dec 14 12:41:01 2018 -0500 +++ b/gemini_macros.xml Fri Jan 11 17:37:04 2019 -0500 |
| [ |
| b'@@ -1,15 +1,12 @@\n <macros>\n <!-- gemini version to be used -->\n- <token name="@VERSION@">0.18.1</token>\n+ <token name="@VERSION@">0.20.1</token>\n <!-- minimal annotation files version required by this version of gemini -->\n- <token name="@DB_VERSION@">181</token>\n+ <token name="@DB_VERSION@">200</token>\n \n <xml name="requirements">\n <requirements>\n <requirement type="package" version="@VERSION@">gemini</requirement>\n- <requirement type="package" version="0.2.6">tabix</requirement>\n- <!-- for conda useage -->\n- <!--requirement type="package" version="1.3.1">htslib</requirement-->\n <yield />\n </requirements>\n </xml>\n@@ -24,9 +21,17 @@\n <exit_code range=":-1" />\n <regex match="Error:" />\n <regex match="Exception:" />\n+ <yield />\n </stdio>\n </xml>\n \n+ <xml name="citations">\n+ <citations>\n+ <citation type="doi">10.1371/journal.pcbi.1003153</citation>\n+ <yield />\n+ </citations>\n+ </xml>\n+\n <xml name="annotation_dir">\n <param name="annotation_databases" type="select" label="Choose a gemini annotation source">\n <options from_data_table="gemini_versioned_databases">\n@@ -36,31 +41,36 @@\n </param>\n </xml>\n \n- <xml name="add_header_column">\n- <param name="header" type="boolean" truevalue="--header" falsevalue="" checked="False" \n- label="Add a header of column names to the output" help="(--header)"/>\n- </xml>\n-\n- <xml name="radius">\n- <param name="radius" type="integer" value="3" label="Set filter for Breadth-first search (BFS) in the Protein-Protein Interaction network" help="(-r)" >\n- <validator type="in_range" min="0"/>\n+ <xml name="infile">\n+ <param name="infile" type="data" format="gemini.sqlite" label="GEMINI database" help="Only files with version @VERSION@ are accepted." >\n+ <options options_filter_attribute="metadata.gemini_version" >\n+ <filter type="add_value" value="@VERSION@" />\n+ </options>\n </param>\n </xml>\n- <xml name="variant_mode">\n- <param name="variant_mode" type="boolean" truevalue="--var" falsevalue="" checked="False" \n- label="Returns variant info (e.g. impact, biotype) for interacting genes" help="(--var)"/>\n+\n+ <xml name="add_header_column">\n+ <param argument="--header" name="header" type="boolean" truevalue="--header" falsevalue="" checked="True" \n+ label="Add a header of column names to the output" />\n </xml>\n \n- <xml name="column_filter">\n+ <xml name="column_filter" token_help="" token_minimalset="variant_id, gene">\n <conditional name="report">\n- <param name="report_selector" type="select" label="Columns to include in the report"\n- help="By default, this tool reports all columns in the variants table. One may choose to report only a subset of the columns.">\n- <option value="all" selected="True">all</option>\n- <option value="column_filter">User given columns</option>\n+ <param name="report_selector" type="select"\n+ label="Set of columns to include in the variant report table"\n+ help="@HELP@">\n+ <option value="minimal">Minimal (report only a preconfigured minimal set of columns)</option>\n+ <option value="full">Full (report all columns defined in the GEMINI database variants table)</option>\n+ <option value="custom">Custom (report user-specified columns)</option>\n </param>\n- <when value="all"/>\n- <when value="column_filter">\n- <param name="columns" type="select" display="checkboxes" multiple="True" label="Choose columns to include in the report" help="(--columns)">\n+ <when value="full" />\n+ <when value="minimal">\n+ '..b'r($report.extra_cols).strip():\n+ #if $cols:\n+ #set $cols = $cols + \', \' + str($report.extra_cols)\n+ #else:\n+ #set $cols = str($report.extra_cols)\n+ #end if\n+ #end if\n+ #if not $cols:\n+ #set $cols = "variant_id, gene"\n+ #end if\n #end if\n </token>\n \n <token name="@COLUMN_SELECT@">\n- #if $report.report_selector != \'all\':\n- --columns "${report.columns}\n- #if str($report.extra_cols).strip()\n- #echo \',\'+\',\'.join(str($report.extra_cols).split()) \n- #end if\n- "\n+ @SET_COLS@\n+ #if $cols != "*"\n+ --columns \'$cols\'\n #end if\n </token>\n \n- <xml name="family">\n- <param name="families" type="text" value="" label="Comma seperated list of families to restrict the analysis to." help="e.g. Family1,Family3 (--families)"/>\n- </xml>\n-\n- <xml name="lenient">\n- <param name="lenient" type="boolean" truevalue="--lenient" falsevalue="" checked="False" label="Loosen the restrictions on family structure"/>\n- </xml>\n-\n- <xml name="unaffected">\n- <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)"/>\n- </xml>\n-\n- <xml name="min_kindreds">\n- <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)" />\n- </xml>\n-\n- <xml name="min_sequence_depth">\n- <param name="d" type="integer" value="0" min="0" label="The minimum aligned sequence depth (genotype DP) required for each sample"\n- help="default: 0 (-d)" />\n- </xml>\n-\n- <xml name="min_gq">\n- <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)">\n- <validator type="in_range" min="0"/>\n- </param>\n- </xml>\n-\n- <xml name="gt_pl_max">\n- <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)" />\n- </xml>\n-\n- <xml name="citations">\n- <citations>\n- <citation type="doi">10.1371/journal.pcbi.1003153</citation>\n- <yield />\n- </citations>\n- </xml>\n-\n- <xml name="infile">\n- <param name="infile" type="data" format="gemini.sqlite" label="GEMINI database" help="Only files with version @VERSION@ are accepted." >\n- <options options_filter_attribute="metadata.gemini_version" >\n- <filter type="add_value" value="@VERSION@" />\n- </options>\n- <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>\n- </param>\n- </xml>\n-\n+ <token name="@PARSE_REGION_ELEMENTS@"><![CDATA[\n+ #set $region_elements = []\n+ #for $r in $regions:\n+ ## The actual chromosome name needs to be single-quoted\n+ ## in SQL, so we need to quote the single quotes like the\n+ ## sanitize_query macro would if the whole was a parameter.\n+ #set $r_elements = ["chrom = \'\\"\'\\"\'%s\'\\"\'\\"\'" % str($r.chrom).strip()]\n+ #if str($r.start).strip():\n+ #silent $r_elements.append("start >= %d" % int($r.start))\n+ #end if\n+ #if str($r.stop).strip():\n+ #silent $r_elements.append("end <= %d" % int($r.stop))\n+ #end if\n+ #silent $region_elements.append("(%s)" % " AND ".join($r_elements))\n+ #end for\n+ ]]>\n+ </token>\n </macros>\n' |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 repository_dependencies.xml --- a/repository_dependencies.xml Fri Dec 14 12:41:01 2018 -0500 +++ b/repository_dependencies.xml Fri Jan 11 17:37:04 2019 -0500 |
| b |
| @@ -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 |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_amend_input.db |
| b |
| Binary file test-data/gemini_amend_input.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_annotate_result.db |
| b |
| Binary file test-data/gemini_annotate_result.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_auto_dom_input.db |
| b |
| Binary file test-data/gemini_auto_dom_input.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_auto_rec_input.db |
| b |
| Binary file test-data/gemini_auto_rec_input.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_comphets_input.db |
| b |
| Binary file test-data/gemini_comphets_input.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_de_novo_input.db |
| b |
| Binary file test-data/gemini_de_novo_input.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_is_somatic_result.db |
| b |
| Binary file test-data/gemini_is_somatic_result.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_load_result1.db |
| b |
| Binary file test-data/gemini_load_result1.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_load_result2.db |
| b |
| Binary file test-data/gemini_load_result2.db has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/gemini_versioned_databases.loc --- a/test-data/gemini_versioned_databases.loc Fri Dec 14 12:41:01 2018 -0500 +++ b/test-data/gemini_versioned_databases.loc Fri Jan 11 17:37:04 2019 -0500 |
| b |
| @@ -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 |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini-config.yaml --- a/test-data/test-cache/gemini-config.yaml Fri Dec 14 12:41:01 2018 -0500 +++ b/test-data/test-cache/gemini-config.yaml Fri Jan 11 17:37:04 2019 -0500 |
| b |
| @@ -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 |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz |
| b |
| Binary file test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi |
| b |
| Binary file test-data/test-cache/gemini/data/clinvar_20160203.tidy.vcf.gz.tbi has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz |
| b |
| Binary file test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz.tbi |
| b |
| Binary file test-data/test-cache/gemini/data/clinvar_20170130.tidy.vcf.gz.tbi has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz |
| b |
| Binary file test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi |
| b |
| Binary file test-data/test-cache/gemini/data/dbsnp.b141.20140813.hg19.tidy.vcf.gz.tbi has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz |
| b |
| Binary file test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz.tbi |
| b |
| Binary file test-data/test-cache/gemini/data/dbsnp.b147.20160601.tidy.vcf.gz.tbi has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz |
| b |
| Binary file test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz has changed |
| b |
| diff -r f3cc64057b4e -r bc8b01d1b496 test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz.tbi |
| b |
| Binary file test-data/test-cache/gemini/data/gnomad.exomes.r2.0.1.sites.no-VEP.nohist.tidy.vcf.gz.tbi has changed |