dataset-datasource

Model/bin/jbrowseOrganismList

@@ -29,9 +29,9 @@ and ts.taxon_id = o.taxon_id
 ";
 
 my $historySql = "select h.build_number, o.public_abbrev, h.genome_source, h.genome_version, h.annotation_source, h.annotation_version
-        from apidbtuning.datasethistory h, apidbtuning.datasetnametaxon nt, apidb.organism o
-        where h.dataset_presenter_id = nt.dataset_presenter_id
-        and nt.name like '%primary_genome_RSRC'
+        from apidbtuning.datasethistory h, apidbtuning.datasetdatasource dd, apidb.organism o
+        where h.dataset_presenter_id = dd.dataset_presenter_id
+        and dd.name like '%primary_genome_RSRC'
         and h.annotation_version is not null
         and o.taxon_id = nt.taxon_id";
 

Model/config/datasetLinks.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <links>
-    <link type="genome" subtype="null">
+    <link category="Genomes">
       <text>View the DEFAULT_PROJECT Genomic Sequence Page for an Example Sequence</text>
       <description><![CDATA[
       The Genomic Sequence Page is a view of a chromosome, contig, or scaffold.  We provide summary information, a link to the Genome Browser, and a form for sequence retrieval.  All Genomic Sequence Searches return this type of record.
@@ -9,7 +9,7 @@
       <url><![CDATA[/a/app/record/genomic-sequence/DEFAULT_SEQUENCE]]></url>
     </link>
 
-    <link type="genome" subtype="null">
+    <link category="Genomes">
       <text>View a partial region of an Example Sequence in the DEFAULT_PROJECT Genome Browser</text>
       <description><![CDATA[
       Each Sequence for this dataset can be browsed using the Genome Browser.  Here we provide a sample region with tracks which are available for all sequences.
@@ -19,7 +19,7 @@
     </link>
 
     <!-- TODO: replace this link with a link to the dataset record for this organism -->
-    <link type="genome" subtype="null">
+    <link category="Genomes">
       <text>View the DEFAULT_PROJECT Organism Record Page</text>
       <description><![CDATA[
       The Organism Record page contains a summary of the different types of data associated with this organism.  How many genes?  Does this organism have RNA Sequence Data? ...
@@ -28,7 +28,7 @@
       <url><![CDATA[/a/app/record/organism/DEFAULT_ORGANISM_PK]]></url>
     </link>
 
-    <link type="genome" subtype="null">
+    <link category="Genomes">
       <text>Download Genome Data from DEFAULT_PROJECT</text>
       <description><![CDATA[
 Go to download directory for Current Relase of this particular organism.
@@ -37,7 +37,7 @@ Go to download directory for Current Relase of this particular organism.
       <url><![CDATA[/a/app/downloads/Current_Release/ORGANISM_FILE_NAME]]></url>
     </link>
 
-    <link type="genome" subtype="null">
+    <link category="Genomes">
       <text>Run BLAST on sequences in DEFAULT_PROJECT</text>
       <description><![CDATA[
       BLAST finds regions of similarity between sequences. The program compares nucleotide or protein sequences to sequence databases and calculates the statistical significance of matches. VEuPathDB BLAST accommodates inputs such as a single sequence or several FASTA-formatted sequences at once, i.e., is multi-query capable.
@@ -48,7 +48,7 @@ Go to download directory for Current Relase of this particular organism.
 
 
 
-    <link type="est" subtype="null">
+    <link category="EST">
       <text>Run BLAST on sequences in DEFAULT_PROJECT</text>
       <description><![CDATA[
       BLAST finds regions of similarity between sequences. The program compares nucleotide or protein sequences to sequence databases and calculates the statistical significance of matches. VEuPathDB BLAST accommodates inputs such as a single sequence or several FASTA-formatted sequences at once, i.e., is multi-query capable.
@@ -62,7 +62,7 @@ Go to download directory for Current Relase of this particular organism.
 
 
 
-    <link type="protein_expression" subtype="null">
+    <link category="Protein expression">
       <text>View peptides aligned to an Example Protein in the DEFAULT_PROJECT Genome Browser</text>
       <description><![CDATA[
 
@@ -73,7 +73,7 @@ Go to download directory for Current Relase of this particular organism.
 
 
 
-    <link type="protein_expression" subtype="null">
+    <link category="Protein expression">
       <text>View peptides aligned to an Example Protein in the DEFAULT_PROJECT Protein Browser</text>
       <description><![CDATA[
 
@@ -83,7 +83,7 @@ Go to download directory for Current Relase of this particular organism.
     </link>
 
 
-    <link type="protein_expression" subtype="null">
+    <link category="Protein expression">
       <text>View the DEFAULT_PROJECT Proteomics Section on an Example Gene Page</text>
       <description><![CDATA[
 
@@ -93,15 +93,15 @@ Go to download directory for Current Relase of this particular organism.
     </link>
 
 
-    <link type="protein_expression" subtype="quantitative">
+    <link category="Protein expression">
       <text>View All Quantitative Proteomics Searches at DEFAULT_PROJECT</text>
       <description><![CDATA[
       ]]>
       </description>
       <url><![CDATA[/a/app/search/transcript/GenesByQuantitativeProteomics]]></url>
     </link>
 
-    <link type="transcript_expression" subtype="array">
+    <link category="DNA Microarray Assay">
       <text>View All Microarray Searches at DEFAULT_PROJECT</text>
       <description><![CDATA[
 
@@ -111,7 +111,7 @@ Go to download directory for Current Relase of this particular organism.
     </link>
 
 
-    <link type="transcript_expression" subtype="rnaseq">
+    <link category="RNASeq">
       <text>View All RNA-Seq Searches at DEFAULT_PROJECT</text>
       <description><![CDATA[
 
@@ -120,7 +120,7 @@ Go to download directory for Current Relase of this particular organism.
       <url><![CDATA[/a/app/search/transcript/GenesByRNASeqEvidence]]></url>
     </link>
 
-    <link type="transcript_expression" subtype="rnaseq">
+    <link category="RNASeq">
       <text>View/Download this Data Set in the DEFAULT_PROJECT Genome Browser</text>
       <description><![CDATA[
       View JBrowse tracks associated with this dataset.
@@ -130,7 +130,7 @@ Go to download directory for Current Relase of this particular organism.
     </link>
 
 
-    <link type="transcript_expression" subtype="chipseq">
+    <link category="CHIP Seq">
       <text>View/Download this Data Set in the DEFAULT_PROJECT Genome Browser</text>
       <description><![CDATA[
       View JBrowse tracks associated with this dataset.

Model/lib/dst/profileGraphs.dst

@@ -224,16 +224,16 @@ prop=includeProjectsExcludeEuPathDB
                     , APIDBTUNING.DATASETPROPERTY dp 
                     , APIDBTUNING.DATASETPROPERTY dp2
                     , APIDBTUNING.DATASETPROPERTY dp3
-                    , APIDBTUNING.datasetnametaxon dnt
+                    , APIDBTUNING.datasetdatasource dd
                      where ps.DATASET_NAME = '${datasetName}'
                       and ps.profile_type = 'values'
                       and ps.dataset_name = ct.dataset_name
-                      and ps.dataset_name = dnt.name
-                      and dnt.dataset_presenter_id = dp.dataset_presenter_id
+                      and ps.dataset_name = dd.name
+                      and dd.name = dp.datasource_name
                       and dp.property = 'profileSamplesHelp'
-                      and dnt.dataset_presenter_id = dp2.dataset_presenter_id
+                      and dd.dataset_presenter_id = dp2.dataset_presenter_id
                       and dp2.property = 'datasetShortDisplayName'
-                      and dnt.dataset_presenter_id = dp3.dataset_presenter_id
+                      and dd.dataset_presenter_id = dp3.dataset_presenter_id
                       and dp3.property = 'datasetDisplayName'
                       ORDER BY ps.study_id, ps.NODE_ORDER_NUM
             ]]>
@@ -324,15 +324,15 @@ FROM apidbtuning.profilesamples ps
  , APIDBTUNING.DATASETPROPERTY dp 
  , APIDBTUNING.DATASETPROPERTY dp2
  , APIDBTUNING.DATASETPROPERTY dp3
- , APIDBTUNING.datasetnametaxon dnt
+ , APIDBTUNING.datasetdatasource dd
 WHERE ps.DATASET_NAME = '${datasetName}'
 AND ps.profile_type = 'values'
-and ps.dataset_name = dnt.name
-and dnt.dataset_presenter_id = dp.dataset_presenter_id
+and ps.dataset_name = dd.name
+and dd.name = dp.datasource_name
 and dp.property = 'profileSamplesHelp'
-and dnt.dataset_presenter_id = dp2.dataset_presenter_id
+and dd.dataset_presenter_id = dp2.dataset_presenter_id
 and dp2.property = 'datasetShortDisplayName'
-and dnt.dataset_presenter_id = dp3.dataset_presenter_id
+and dd.dataset_presenter_id = dp3.dataset_presenter_id
 and dp3.property = 'datasetDisplayName'
 ORDER BY ps.study_id, ps.NODE_ORDER_NUM
             ]]>

Model/lib/perl/JbrowseRnaSeqJunctionTracks.pm

@@ -50,7 +50,7 @@ sub processOrganism {
 
   my $sql = "select count(*)
 from apidbtuning.datasetproperty p
-   , apidbtuning.datasetnametaxon d
+   , apidbtuning.datasetdatasource d
    , apidb.organism o
 where d.DATASET_PRESENTER_ID = p.DATASET_PRESENTER_ID
 and o.taxon_id = d.taxon_id

Model/lib/wdk/model/questions/params/datasetParams.xml

@@ -117,8 +117,8 @@
          <![CDATA[
 select distinct organism_name as term, oa.COMPONENT_TAXON_ID as internal
 from apidbtuning.organismattributes oa
-, apidbtuning.datasetnametaxon dnt
-where dnt.taxon_id = oa.COMPONENT_TAXON_ID
+, apidbtuning.datasetdatasource dd
+where dd.taxon_id = oa.COMPONENT_TAXON_ID
 union
 select 'any', -1
          ]]>
@@ -145,7 +145,7 @@ select 'any', -1
              <column name="term"/>
             <sql>
          <![CDATA[
-                  select distinct dataset_presenter_id as term, dataset_presenter_id as internal from APIDBTUNING.datasetnametaxon
+                  select distinct dataset_presenter_id as term, dataset_presenter_id as internal from APIDBTUNING.datasetdatasource
          ]]>
             </sql>
    </sqlQuery>

Model/lib/wdk/model/questions/params/geneParams.xml

@@ -6422,10 +6422,10 @@ products of your selected type (or types).<br><br>
             select distinct 'long_transcript_novelty' as ontology_term_name, cast(null as varchar(1)) as parent_ontology_term_name,
             'Support From Long Read Evidence' as display_name, 'Find genes based on overlapping models from long read RNA sequencing, for example from Oxford Nanopore or PacBio sequencing platforms. To be considered in this query, a model must have at least 5 supporting reads and be at least 20 bases long. Categories as follows: Novel in Collection (NIC): Prediction uses known splice donors and acceptors but reveals new connections (e.g., skipped exon isoforms); Incomplete Splice Match (ISM): Prediction matches subsection of a known transcript model, but has a novel putative start or end point; Novel Not In Collection (NNC): Prediction has at least one novel splice donor or acceptor; Genomic: Prediction has no overlapping splice junctions compared to known transcripts; Genomic: Prediction has no overlapping splice junctions compared to known transcripts; Known: Prediction exactly matches a known model.  NOTE: The percentage add up to more than 100% because one existing gene model can have more than associated TALON model.' as description, cast(null as varchar(1)) as units,
             'string' as type, 0 as is_range, cast(null as varchar(1)) as precision, 7 as display_order
-            from apidbtuning.datasetnametaxon dnt
+            from apidbtuning.datasetdatasource dd
             where '$$gene_or_transcript$$' = 'gene_source_id'
-              and dnt.name like '%nanopore_longReadRnaSeq_RSRC'
-              and dnt.taxon_id in ($$organism_select_all$$)
+              and dd.name like '%nanopore_longReadRnaSeq_RSRC'
+              and dd.taxon_id in ($$organism_select_all$$)
               and '@PROJECT_ID@' != 'EuPathDB'
             UNION
             select 'intron_junction' as ontology_term_name, cast(null as varchar(1)) as parent_ontology_term_name,
@@ -6608,8 +6608,8 @@ products of your selected type (or types).<br><br>
           FROM sres.externaldatabaserelease edr
             , sres.externaldatabase ed
             , apidbtuning.datasetpresenter dsp
-            , apidbtuning.datasetnametaxon dnt
-          WHERE dnt.taxon_id = $$organismsWithSingleCell$$
+            , apidbtuning.datasetdatasource dd
+          WHERE dd.taxon_id = $$organismsWithSingleCell$$
             AND dsp.name like '%cellxgene%'
             AND dsp.name = dnt.name
             AND ed.name = dnt.name
@@ -8869,19 +8869,19 @@ end as term
                 sdi.sort_order
             FROM apidbTuning.sampledisplayinfo sdi,
                   apidbTuning.datasetPresenter dsp,
-                  apidbTuning.datasetNameTaxon dsnt,
+                  apidbTuning.datasetdatasource dd,
                   apidbTuning.datasetContact dsc,
                   (SELECT DISTINCT ta.organism,ta.taxon_id,ta.project_id
                     FROM apidbtuning.transcriptattributes ta, apidb.massspecpeptide msf
                     WHERE msf.protein_source_id = ta.protein_source_id
                    and (ta.project_id = '@PROJECT_ID@' OR 'UniDB' = '@PROJECT_ID@')
                   ) org
             WHERE sdi.dataset_name like '%_massSpec_%'
-              AND sdi.dataset_name = dsnt.name
-              AND dsc.dataset_presenter_id = dsnt.dataset_presenter_id
-              AND dsp.dataset_presenter_id = dsnt.dataset_presenter_id
+              AND sdi.dataset_name = dd.name
+              AND dsc.dataset_presenter_id = dd.dataset_presenter_id
+              AND dsp.dataset_presenter_id = dd.dataset_presenter_id
               AND Dsc.Is_Primary_Contact = true
-              AND dsnt.taxon_id = org.taxon_id
+              AND dd.taxon_id = org.taxon_id
           )
           SELECT replace(replace(term,',',''),(''''), '') as term,
               replace(replace(parentTerm,',', ''),(''''), '') as parentTerm,
@@ -10164,16 +10164,16 @@ end as term
       <column name="internal"/>
       <sql>
         <![CDATA[
-          SELECT dsnt.name AS term
-            , dsnt.name as internal
+          SELECT dd.name AS term
+            , dd.name as internal
             , dsp.display_name AS display
           FROM
               apidbtuning.datasetpresenter dsp
-            , apidbtuning.datasetnametaxon dsnt
+            , apidbtuning.datasetdatasource dd
           WHERE
-            dsp.dataset_presenter_id = dsnt.dataset_presenter_id
+            dsp.dataset_presenter_id = dd.dataset_presenter_id
             AND dsp.subtype in ('Broad_3k_array', 'Broad_75K_array', 'Broad_barcode', 'NIH_10k')
-          ORDER BY dsnt.name DESC
+          ORDER BY dd.name DESC
         ]]>
       </sql>
     </sqlQuery>

Model/lib/wdk/model/questions/params/sharedParams.xml

@@ -3074,19 +3074,19 @@ This parameter allows you to apply the minimum number of peptides to each select
       <column name="internal"/>
       <sql>
         <![CDATA[
-          SELECT dsnt.name AS term
-            , dsnt.name as internal
+          SELECT dd.name AS term
+            , dd.name as internal
             , dsp.display_name AS display
           FROM
             apidbtuning.datasetpresenter dsp
-            , apidbtuning.datasetnametaxon dsnt
+            , apidbtuning.datasetdatasource dd
           WHERE
             dsp.dataset_presenter_id = dsnt.dataset_presenter_id
             AND dsp.subtype in ('Broad_3k_array', 'Broad_75K_array', 'Broad_barcode', 'NIH_10k')
-            AND dsnt.name in (SELECT dataset_name
+            AND dd.name in (SELECT dataset_name
                               FROM apidbTuning.Ontology
                               WHERE organism = '$$organismSinglePick$$')
-          ORDER BY dsnt.name DESC
+          ORDER BY dd.name DESC
         ]]>
       </sql>
     </sqlQuery>

Model/lib/wdk/model/records/geneAttributeQueries.xml

@@ -604,20 +604,20 @@ GROUP BY source_id
           SELECT ga.source_id, ga.project_id, v.annotation_version as ds_annotation_version, v.dataset_presenter_id as dataset_id, v.description as attribution_partial
           FROM apidbtuning.geneattributes ga
             LEFT JOIN (
-              SELECT ga.source_id, ga.project_id,dsh.annotation_version,dsh.annotation_source, dnt.dataset_presenter_id, dsp.description
+              SELECT ga.source_id, ga.project_id,dsh.annotation_version,dsh.annotation_source, dd.dataset_presenter_id, dsp.description
               FROM (
                 SELECT max(dsh.build_number) bld, dsh.dataset_presenter_id
                 FROM apidbtuning.datasethistory dsh
                 WHERE dsh.annotation_version is not null
                 GROUP BY dsh.dataset_presenter_id
                 ) dpb
-                , apidbtuning.datasethistory dsh, apidbtuning.datasetnametaxon dnt
+                , apidbtuning.datasethistory dsh, apidbtuning.datasetdatasource dd
                 , apidbtuning.geneattributes ga, apidbtuning.datasetpresenter dsp
               WHERE dpb.bld = dsh.BUILD_NUMBER
                 AND dpb.dataset_presenter_id = dsh.DATASET_PRESENTER_ID
-                AND dnt.dataset_presenter_id = dsp.dataset_presenter_id
-                AND dsh.dataset_presenter_id = dnt.dataset_presenter_id
-                AND dnt.taxon_id = ga.taxon_id
+                AND dd.dataset_presenter_id = dsp.dataset_presenter_id
+                AND dsh.dataset_presenter_id = dd.dataset_presenter_id
+                AND dd.taxon_id = ga.taxon_id
             ) v ON  ga.source_id = v.source_id AND ga.project_id = v.project_id
         ]]>
       </sql>