Mercurial > repos > iuc > gemini_db_info
diff gemini_db_info.xml @ 5:bc8b01d1b496 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gemini commit 62ed732cba355e695181924a8ed4cce49ca21c59
| author | iuc |
|---|---|
| date | Fri, 11 Jan 2019 17:37:04 -0500 |
| parents | f3cc64057b4e |
| children | c2a413e47fe9 |
line wrap: on
line diff
--- 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 @@ -1,21 +1,47 @@ -<tool id="gemini_@BINARY@" name="GEMINI @BINARY@" version="@VERSION@.1"> - <description>List the gemini database tables and columns</description> +<tool id="gemini_db_info" name="GEMINI database info" version="@VERSION@"> + <description>Retrieve information about tables, columns and annotation data stored in a GEMINI database</description> <macros> <import>gemini_macros.xml</import> - <token name="@BINARY@">db_info</token> </macros> <expand macro="requirements" /> <expand macro="stdio" /> <expand macro="version_command" /> <command> <![CDATA[ - gemini @BINARY@ - "${ infile }" | tr -s ' ' '\t' - > "${ outfile }" + #if str($select.info_type) == 'scheme': + gemini db_info '$infile' | tr -s ' ' '\t' + #elif str($select.info_type) == 'resources': + gemini query --header -q "SELECT name as data_source, resource as resource_file from resources" '$infile' + #elif str($select.info_type) == 'gene_detailed': + gemini query --header -q "SELECT gene, synonym as synonyms, transcript FROM gene_detailed WHERE gene is not NULL GROUP BY transcript ORDER BY gene" '$infile' + #else: + gemini query --header -q "SELECT * FROM samples" "$infile" | cut -f 2-${select.format} + #end if + + > '$outfile' ]]> </command> <inputs> <expand macro="infile" /> + <conditional name="select"> + <param name="info_type" type="select" + label="Information to retrieve from the database"> + <option value="scheme">Names of database tables and their columns</option> + <option value="resources">List of annotation data sources</option> + <option value="gene_detailed">List of genes and their transcripts</option> + <option value="samples">Write out sample information in PED format</option> + </param> + <when value="scheme" /> + <when value="resources" /> + <when value="gene_detailed" /> + <when value="samples"> + <param name="format" type="select" display="radio" + label="Format of the pedigree file"> + <option value="">Allow extra columns to accomodate custom sample info</option> + <option value="7">Restrict to 6 PED standard columns and drop additional info</option> + </param> + </when> + </conditional> </inputs> <outputs> <data name="outfile" format="tabular" /> @@ -23,67 +49,71 @@ <tests> <test> <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" /> + <conditional name="select"> + <param name="info_type" value="scheme" /> + </conditional> <output name="outfile"> <assert_contents> <has_line_matching expression="table_name	column_name	type.*" /> </assert_contents> </output> </test> + <test> + <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" /> + <conditional name="select"> + <param name="info_type" value="resources" /> + </conditional> + <output name="outfile"> + <assert_contents> + <has_line line="data_source	resource_file" /> + <has_n_columns n="2" /> + </assert_contents> + </output> + </test> + <test> + <param name="infile" value="gemini_load_result1.db" ftype="gemini.sqlite" /> + <conditional name="select"> + <param name="info_type" value="gene_detailed" /> + </conditional> + <output name="outfile"> + <assert_contents> + <has_line line="gene	synonyms	transcript" /> + <has_n_columns n="3" /> + </assert_contents> + </output> + </test> + <test> + <param name="infile" value="gemini_comphets_input.db" ftype="gemini.sqlite" /> + <conditional name="select"> + <param name="info_type" value="samples" /> + </conditional> + <output name="outfile"> + <assert_contents> + <has_line_matching expression="family_id	name	paternal_id	maternal_id	sex	phenotype	.+" /> + </assert_contents> + </output> + </test> + <test> + <param name="infile" value="gemini_comphets_input.db" ftype="gemini.sqlite" /> + <conditional name="select"> + <param name="info_type" value="samples" /> + <param name="format" value="7" /> + </conditional> + <output name="outfile"> + <assert_contents> + <has_line line="family_id	name	paternal_id	maternal_id	sex	phenotype" /> + <has_n_columns n="6" /> + </assert_contents> + </output> + </test> </tests> <help><![CDATA[ **What it does** -Because of the sheer number of annotations that are stored in gemini, there are admittedly too many columns to remember by rote. -If you can’t recall the name of particular column, just use the db_info tool. -It will report all of the tables and all of the columns / types in each table:: +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. - table_name column_name type - variants chrom text - variants start integer - variants end integer - variants variant_id integer - variants anno_id integer - variants ref text - variants alt text - variants qual float - variants filter text - variants type text - variants sub_type text - variants gts blob - variants gt_types blob - variants gt_phases blob - variants gt_depths blob - variants call_rate float - variants in_dbsnp bool - variants rs_ids text - variants in_omim bool - variants clin_sigs text - variants cyto_band text - variants rmsk text - variants in_cpg_island bool - variants in_segdup bool - variants is_conserved bool - variants num_hom_ref integer - variants num_het integer - variants num_hom_alt integer - variants num_unknown integer - variants aaf float - variants hwe float - variants inbreeding_coeff float - variants pi float - variants recomb_rate float - variants gene text - variants transcript text - variants is_exonic bool - variants is_coding bool - variants is_lof bool - variants exon text - variants codon_change text - variants aa_change text - ... ... ... - -For more columns see https://gemini.readthedocs.org/en/latest/content/tools.html#db-info-list-the-gemini-database-tables-and-columns - +This tool offers a simple way to inspect the structure, the origin of the +annotations and some of the actual annotation content quickly. ]]></help> <expand macro="citations"/> </tool>