Skip to content

restore non-gene profile unions lost in Oracle->Postgres migration #172

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

Open
jbrestel wants to merge 1 commit into
base: master
Choose a base branch
from
Open

restore non-gene profile unions lost in Oracle->Postgres migration #172

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
150 changes: 148 additions & 2 deletions Model/lib/xml/tuningManager/apiTuningManager.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2225,20 +2225,26 @@ create index Organism_projectId_idx&1 ON OrganismAttributes&1 (project_id, sourc
<tuningTable name="Profile">
<comment> One profile per gene per dataset. Used for graphs.</comment>
<externalDependency name="apidb.Datasource"/>
<externalDependency name="apidb.OntologyTermResult"/>
<externalDependency name="apidb.SubjectResult"/>
<externalDependency name="results.CompoundMassSpec"/>
<externalDependency name="apidb.CompoundMassSpecResult"/>
<externalDependency name="apidb.CompoundPeaks"/>
<externalDependency name="apidb.CompoundPeaksChebi"/>
<!--
NOTE: if we revive these datasets, hard code 'no_org_abbrev' for their org_abbrev value. for dataplotter.
<externalDependency name="apidb.OntologyTermResult"/>
<externalDependency name="apidb.NaFeatureMetacycle"/>
<externalDependency name="apidb.LopitResults"/>
<externalDependency name="apidb.EigenGeneWgcnaResults"/>
<externalDependency name="results.CompoundMassSpec"/>
<externalDependency name="results.NaFeatureHostResponse"/>
-->
<externalDependency name="results.NaFeatureExpression"/>
<externalDependency name="sres.ExternalDatabase"/>
<externalDependency name="sres.ExternalDatabaseRelease"/>
<externalDependency name="study.ProtocolAppNode"/>
<externalDependency name="study.NodeSet"/>
<externalDependency name="sres.OntologyTerm"/>
<externalDependency name="webready.CompoundAttributes"/>
<internalDependency name="NodeSetOutputNode"/>
<internalDependency name="GeneAttributes"/>
<intermediateTable name="profile_nafeatureexp_summary"/>
Expand Down Expand Up @@ -2464,6 +2470,146 @@ create index Organism_projectId_idx&1 ON OrganismAttributes&1 (project_id, sourc
AND d.external_database_id = r.external_database_id
AND profile.node_set_id = ps.node_set_id
AND ps.external_database_release_id = r.external_database_release_id
UNION ALL
-- SubjectResult profiles
SELECT
ds.name as dataset_name, ds.type as dataset_type, coalesce(o.abbrev, 'no_org_abbrev') as org_abbrev,
ds.subtype as dataset_subtype, 'values' AS profile_type, ps.node_type,
sr.subject as source_id, sr.node_set_id as profile_study_id,
ps.name as profile_set_name,
null as profile_set_suffix,
CASE WHEN replace(sr.profile_as_string, 'NA' || CHR(9), '') = 'NA' THEN null ELSE sr.profile_as_string END as profile_as_string,
'-1' as max_value, '1' as min_value, '-1' as max_timepoint, '-1' as min_timepoint
FROM apidb.DataSource ds
JOIN sres.ExternalDatabase d ON ds.name = d.name
JOIN sres.ExternalDatabaseRelease r ON ds.version = r.version
AND d.external_database_id = r.external_database_id
LEFT JOIN apidb.organism o ON ds.taxon_id = o.taxon_id
JOIN study.NodeSet ps ON ps.external_database_release_id = r.external_database_release_id
JOIN (SELECT sl.node_set_id, result.subject,
string_agg(coalesce(round(result.value::numeric, 2)::varchar, 'NA'), chr(9) order by pan.node_order_num) as profile_as_string
FROM study.ProtocolAppNode pan, NodeSetOutputNode sl, apidb.SubjectResult result
WHERE result.protocol_app_node_id = sl.protocol_app_node_id
AND result.protocol_app_node_id = pan.protocol_app_node_id
GROUP BY sl.node_set_id, result.subject
) sr ON sr.node_set_id = ps.node_set_id
UNION ALL
-- OntologyTermResult profiles
SELECT
ds.name as dataset_name, ds.type as dataset_type, coalesce(o.abbrev, 'no_org_abbrev') as org_abbrev,
ds.subtype as dataset_subtype, 'value' AS profile_type, ps.node_type,
otr.term_name as source_id, otr.node_set_id as profile_study_id,
ps.name as profile_set_name,
null as profile_set_suffix,
CASE WHEN replace(otr.profile_as_string, 'NA' || CHR(9), '') = 'NA' THEN null ELSE otr.profile_as_string END as profile_as_string,
'-1' as max_value, '1' as min_value, '-1' as max_timepoint, '-1' as min_timepoint
FROM apidb.DataSource ds
JOIN sres.ExternalDatabase d ON ds.name = d.name
JOIN sres.ExternalDatabaseRelease r ON ds.version = r.version
AND d.external_database_id = r.external_database_id
LEFT JOIN apidb.organism o ON ds.taxon_id = o.taxon_id
JOIN study.NodeSet ps ON ps.external_database_release_id = r.external_database_release_id
JOIN (SELECT sl.node_set_id, ot.name as term_name,
string_agg(coalesce(round(result.value::numeric, 2)::varchar, 'NA'), chr(9) order by pan.node_order_num) as profile_as_string
FROM study.ProtocolAppNode pan, NodeSetOutputNode sl,
apidb.OntologyTermResult result, sres.OntologyTerm ot
WHERE ot.ontology_term_id = result.ontology_term_id
AND result.protocol_app_node_id = sl.protocol_app_node_id
AND result.protocol_app_node_id = pan.protocol_app_node_id
GROUP BY sl.node_set_id, ot.name
) otr ON otr.node_set_id = ps.node_set_id
UNION ALL
-- Compound profiles from results.CompoundMassSpec (values with isotopomers)
SELECT
ds.name as dataset_name, ds.type as dataset_type, coalesce(o.abbrev, 'no_org_abbrev') as org_abbrev,
ds.subtype as dataset_subtype, 'values' AS profile_type, ps.node_type,
CASE WHEN cp.isotopomer IS NOT NULL THEN ca.source_id || '|' || cp.isotopomer
ELSE ca.source_id
END as source_id,
cp.node_set_id as profile_study_id,
ps.name as profile_set_name,
null as profile_set_suffix,
CASE WHEN replace(cp.profile_as_string, 'NA' || CHR(9), '') = 'NA' THEN null ELSE cp.profile_as_string END as profile_as_string,
'-1' as max_value, '1' as min_value, '-1' as max_timepoint, '-1' as min_timepoint
FROM apidb.DataSource ds
JOIN sres.ExternalDatabase d ON ds.name = d.name
JOIN sres.ExternalDatabaseRelease r ON ds.version = r.version
AND d.external_database_id = r.external_database_id
LEFT JOIN apidb.organism o ON ds.taxon_id = o.taxon_id
JOIN study.NodeSet ps ON ps.external_database_release_id = r.external_database_release_id
JOIN (SELECT sl.node_set_id, result.compound_id, result.isotopomer,
string_agg(coalesce(round(result.value::numeric, 2)::varchar, 'NA'), chr(9) order by pan.node_order_num) as profile_as_string
FROM study.ProtocolAppNode pan, NodeSetOutputNode sl,
(SELECT max(value) as value, compound_id, protocol_app_node_id, isotopomer
FROM results.CompoundMassSpec
GROUP BY compound_id, protocol_app_node_id, isotopomer) result
WHERE result.protocol_app_node_id = sl.protocol_app_node_id
AND result.protocol_app_node_id = pan.protocol_app_node_id
GROUP BY sl.node_set_id, result.compound_id, result.isotopomer
) cp ON cp.node_set_id = ps.node_set_id
JOIN webready.CompoundAttributes ca ON ca.id = cp.compound_id
UNION ALL
-- Compound profiles from apidb.CompoundMassSpecResult (values)
SELECT
ds.name as dataset_name, ds.type as dataset_type, coalesce(o.abbrev, 'no_org_abbrev') as org_abbrev,
ds.subtype as dataset_subtype, 'values' AS profile_type, ps.node_type,
CASE WHEN cpc.isotopomer IS NOT NULL THEN ca.source_id || '|' || cpc.isotopomer
WHEN cph.mass IS NOT NULL THEN ca.source_id || '|' || cph.mass || '|' || cph.retention_time
ELSE ca.source_id
END as source_id,
cmsr_agg.node_set_id as profile_study_id,
ps.name as profile_set_name,
null as profile_set_suffix,
CASE WHEN replace(cmsr_agg.profile_as_string, 'NA' || CHR(9), '') = 'NA' THEN null ELSE cmsr_agg.profile_as_string END as profile_as_string,
'-1' as max_value, '1' as min_value, '-1' as max_timepoint, '-1' as min_timepoint
FROM apidb.DataSource ds
JOIN sres.ExternalDatabase d ON ds.name = d.name
JOIN sres.ExternalDatabaseRelease r ON ds.version = r.version
AND d.external_database_id = r.external_database_id
LEFT JOIN apidb.organism o ON ds.taxon_id = o.taxon_id
JOIN study.NodeSet ps ON ps.external_database_release_id = r.external_database_release_id
JOIN (SELECT sl.node_set_id, cmsr.compound_peaks_id,
string_agg(coalesce(round(cmsr.value::numeric, 2)::varchar, 'NA'), chr(9) order by pan.node_order_num) as profile_as_string
FROM study.ProtocolAppNode pan, NodeSetOutputNode sl, apidb.CompoundMassSpecResult cmsr
WHERE cmsr.protocol_app_node_id = sl.protocol_app_node_id
AND cmsr.protocol_app_node_id = pan.protocol_app_node_id
AND pan.name like '%mean%'
GROUP BY sl.node_set_id, cmsr.compound_peaks_id
) cmsr_agg ON cmsr_agg.node_set_id = ps.node_set_id
JOIN apidb.CompoundPeaksChebi cpc ON cpc.compound_peaks_id = cmsr_agg.compound_peaks_id
JOIN apidb.CompoundPeaks cph ON cph.compound_peaks_id = cpc.compound_peaks_id
JOIN webready.CompoundAttributes ca ON ca.id = cpc.compound_id
UNION ALL
-- Compound profiles from apidb.CompoundMassSpecResult (percentiles)
SELECT
ds.name as dataset_name, ds.type as dataset_type, coalesce(o.abbrev, 'no_org_abbrev') as org_abbrev,
ds.subtype as dataset_subtype, 'percentiles' AS profile_type, ps.node_type,
CASE WHEN cpc.isotopomer IS NOT NULL THEN ca.source_id || '|' || cpc.isotopomer
WHEN cph.mass IS NOT NULL THEN ca.source_id || '|' || cph.mass || '|' || cph.retention_time
ELSE ca.source_id
END as source_id,
cmsr_agg.node_set_id as profile_study_id,
ps.name as profile_set_name,
null as profile_set_suffix,
CASE WHEN replace(cmsr_agg.profile_as_string, 'NA' || CHR(9), '') = 'NA' THEN null ELSE cmsr_agg.profile_as_string END as profile_as_string,
'-1' as max_value, '1' as min_value, '-1' as max_timepoint, '-1' as min_timepoint
FROM apidb.DataSource ds
JOIN sres.ExternalDatabase d ON ds.name = d.name
JOIN sres.ExternalDatabaseRelease r ON ds.version = r.version
AND d.external_database_id = r.external_database_id
LEFT JOIN apidb.organism o ON ds.taxon_id = o.taxon_id
JOIN study.NodeSet ps ON ps.external_database_release_id = r.external_database_release_id
JOIN (SELECT sl.node_set_id, cmsr.compound_peaks_id,
string_agg(coalesce(round(cmsr.percentile::numeric, 2)::varchar, 'NA'), chr(9) order by pan.node_order_num) as profile_as_string
FROM study.ProtocolAppNode pan, NodeSetOutputNode sl, apidb.CompoundMassSpecResult cmsr
WHERE cmsr.protocol_app_node_id = sl.protocol_app_node_id
AND cmsr.protocol_app_node_id = pan.protocol_app_node_id
AND pan.name like '%mean%'
GROUP BY sl.node_set_id, cmsr.compound_peaks_id
) cmsr_agg ON cmsr_agg.node_set_id = ps.node_set_id
JOIN apidb.CompoundPeaksChebi cpc ON cpc.compound_peaks_id = cmsr_agg.compound_peaks_id
JOIN apidb.CompoundPeaks cph ON cph.compound_peaks_id = cpc.compound_peaks_id
JOIN webready.CompoundAttributes ca ON ca.id = cpc.compound_id

]]>
</sql>
Expand Down