Skip to content

Community counts attribute query #207

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mvnural merged 3 commits into from
Aug 4, 2026
Merged

Community counts attribute query #207

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
643ddb4
exclude usercomments_userdb_betan.mappedComment and so not have commu…
bgajria Jul 27, 2026
e224f87
Move communitycount and community_flag to their own attribute query
bgajria Jul 30, 2026
9f22c4e
Remove dead CommunityCount tuning code
bgajria Jul 30, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 29 additions & 4 deletions Model/lib/wdk/model/records/organismAttributeQueries.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,6 @@
<column name="tfbscount"/>
<column name="gocount"/>
<column name="proteomicscount"/>
<column name="communitycount"/>
<column name="organism_name"/>
<column name="organism_full"/>
<column name="isOrganellar_flag"/>
Expand All @@ -113,7 +112,6 @@
<column name="go_flag"/>
<column name="ec_flag"/>
<column name="rtpcr_flag"/>
<column name="community_flag"/>
<column name="tfbs_flag"/>
<column name="hasHTSIsolate_flag"/>
<!-- <column name="hasPopset_flag"/> -->
Expand Down Expand Up @@ -158,7 +156,6 @@
nullif(oa.gocount,0) as gocount,
nullif(oa.tfbscount,0) as tfbscount,
nullif(oa.proteomicscount,0) as proteomicscount,
nullif(oa.communitycount,0) as communitycount,
CASE oa.isOrganellar WHEN 0 THEN 'no' ELSE 'yes' END as isOrganellar_flag,
CASE oa.arraygenecount WHEN 0 THEN 'none' ELSE 'yes' END as array_flag,
CASE oa.chipchipgenecount WHEN 0 THEN 'none' ELSE 'yes' END as chipchip_flag,
Expand All @@ -168,7 +165,6 @@
CASE oa.ecnumbercount WHEN 0 THEN 'none' ELSE 'yes' END as ec_flag,
CASE oa.gocount WHEN 0 THEN 'none' ELSE 'yes' END as go_flag,
CASE oa.rtpcrcount WHEN 0 THEN 'none' ELSE 'yes' END as rtpcr_flag,
CASE oa.communitycount WHEN 0 THEN 'none' ELSE 'yes' END as community_flag,
CASE oa.tfbscount WHEN 0 THEN 'none' ELSE 'yes' END as tfbs_flag,
CASE oa.hasHTSIsolate WHEN 0 THEN 'none' ELSE 'yes' END as hasHTSIsolate_flag,
--CASE oa.hasPopset WHEN 0 THEN 'none' ELSE 'yes' END as hasPopset_flag,
Expand Down Expand Up @@ -241,6 +237,35 @@
</sql>
</sqlQuery>


<sqlQuery name="CommunityCounts">
<column name="source_id"/>
<column name="project_id"/>
<column name="communitycount"/>
<column name="community_flag"/>
<sql>
<![CDATA[
SELECT o.source_id, o.project_id,
nullif(count(comm.stable_id), 0) as communitycount,
CASE WHEN count(comm.stable_id) = 0 THEN 'none' ELSE 'yes' END as community_flag
FROM apidbtuning.organismAttributes o
LEFT JOIN apidbtuning.GeneAttributes ga
ON ga.taxon_id = o.component_taxon_id
AND ga.project_id = o.project_id
LEFT JOIN (
SELECT distinct stable_id, project_name
FROM @REMOTE_COMMENT_SCHEMA@MappedComment
WHERE is_visible = true
AND comment_target_id = 'gene'
) comm ON comm.stable_id = ga.source_id
AND comm.project_name = ga.project_id
where o.project_id = '@PROJECT_ID@' or '@PROJECT_ID@' = 'UniDB'
GROUP BY o.source_id, o.project_id
]]>
</sql>
</sqlQuery>


<sqlQuery name="BuscoGenomeCounts">
<column name="source_id"/>
<column name="project_id"/>
Expand Down
23 changes: 12 additions & 11 deletions Model/lib/wdk/model/records/organismRecords.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,8 +180,6 @@
help="Number of genes that have evidence of protein expression based on Mass Spectrometry studies" align="right"/>
<columnAttribute name="tfbscount" type="number" displayName="TFBS" attributeCategory="genemetrics"
help="Total number of genes having evidence of expression based on transcription factor binding site identification experiments" align="right" />
<columnAttribute name="communitycount" type="number" displayName="User comments" attributeCategory="genemetrics"
help="Number of genes with comments/notes from the research community" align="right"/>

<columnAttribute name="organism_name" displayName="Organism (text)" inReportMaker="false"/>
<columnAttribute name="organism_full" displayName="Organism" inReportMaker="false"/>
Expand Down Expand Up @@ -302,15 +300,6 @@
</text>
</textAttribute>

<columnAttribute name="community_flag" inReportMaker="false"/>
<textAttribute name="hasCommunity" displayName="Community" align="center" inReportMaker="false" >
<text>
<![CDATA[
<img width="8" border="0" alt="$$community_flag$$" src="/a/images/reddot.gif" style="display:$$community_flag$$"/>
]]>
</text>
</textAttribute>

<columnAttribute name="ec_flag" inReportMaker="false"/>
<textAttribute name="hasEC" displayName="EC#" align="center" inReportMaker="false" >
<text>
Expand Down Expand Up @@ -434,6 +423,18 @@
help ="VectorBase genomes initial annotation source (version 1.0) is either from NCBI RefSeq or from the genome authors own pipeline. Subsequent annotations are provided by VectorBase, either by the community (currently via Apollo) or by the EBI pipeline (via predictions and alignments to external databases)." />
</attributeQueryRef>

<attributeQueryRef ref="OrganismAttributes.CommunityCounts">
<columnAttribute name="communitycount" type="number" displayName="User comments" attributeCategory="genemetrics"
help="Number of genes with comments/notes from the research community" align="right"/>
<columnAttribute name="community_flag" inReportMaker="false"/>
<textAttribute name="hasCommunity" displayName="Community" align="center" inReportMaker="false" >
<text>
<![CDATA[
<img width="8" border="0" alt="$$community_flag$$" src="/a/images/reddot.gif" style="display:$$community_flag$$"/>
]]>
</text>
</textAttribute>
</attributeQueryRef>

<attributeQueryRef ref="OrganismAttributes.BuscoProteinCounts" excludeProjects="HostDB,EuPathDB">
<columnAttribute name="busco_protein" displayName="BUSCO Protein"
Expand Down
18 changes: 0 additions & 18 deletions Model/lib/xml/tuningManager/apiTuningManager.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1318,7 +1318,6 @@
<intermediateTable name="DataSourceCount"/>
<intermediateTable name="OrganismCentromere"/>
<intermediateTable name="SequenceCount"/>
<intermediateTable name="CommunityCount"/>
<intermediateTable name="ProfileCount"/>
<!-- <intermediateTable name="PopsetCount"/> -->
<intermediateTable name="GeneCount"/>
Expand Down Expand Up @@ -1396,21 +1395,6 @@
]]>
</sql>

<sql>
<![CDATA[
CREATE UNLOGGED TABLE CommunityCount AS
SELECT taxon_id, count(*) as communityCount
FROM Geneattributes
WHERE (source_id, project_id) IN (
SELECT distinct stable_id, project_name
FROM usercomments_userdb_betan.mappedComment
WHERE is_visible = '1'
AND comment_target_id = 'gene'
)
GROUP BY taxon_id
]]>
</sql>

<sql>
<![CDATA[
CREATE UNLOGGED TABLE ProfileCount AS
Expand Down Expand Up @@ -1659,7 +1643,6 @@
coalesce(sc.contig_num, 0) as contigCount,
coalesce(sc.supercont_num, 0) as supercontigCount,
coalesce(sc.chrom_num, 0) as chromosomeCount,
coalesce(cc.communityCount, 0) as communityCount,
--coalesce(psc.popsetCount, 0) as popsetCount,
coalesce(pc.geneArrayCount, 0) as arrayGeneCount,
coalesce(pc.rnaSeqCount, 0) as rnaSeqCount,
Expand All @@ -1671,7 +1654,6 @@
LEFT JOIN DataSourceCount dsc ON o.taxon_id = dsc.taxon_id
LEFT JOIN OrganismCentromere oc ON o.taxon_id = oc.taxon_id
LEFT JOIN SequenceCount sc ON o.taxon_id = sc.taxon_id
LEFT JOIN CommunityCount cc ON o.taxon_id = cc.taxon_id
LEFT JOIN GeneCount gc ON o.taxon_id = gc.taxon_id
--LEFT JOIN popsetCount psc ON o.taxon_id = psc.taxon_id
LEFT JOIN profileCount pc ON o.taxon_id = pc.taxon_id
Expand Down