From 2f1b0b8067ee2bebb635e3421b1b47b78605ad09 Mon Sep 17 00:00:00 2001
From: steve-fischer-200 <sfischer@upenn.edu>
Date: Thu, 2 Nov 2023 19:59:06 -0400
Subject: [PATCH 1/3] add new search for UD UI

---
 .../wdk/model/questions/genomicQuestions.xml  | 10 ++++++++
 .../model/questions/params/genomicParams.xml  |  2 ++
 .../questions/queries/genomicQueries.xml      | 25 +++++++++++++++++++
 3 files changed, 37 insertions(+)

diff --git a/Model/lib/wdk/model/questions/genomicQuestions.xml b/Model/lib/wdk/model/questions/genomicQuestions.xml
index 61ac3a77de..4660386986 100644
--- a/Model/lib/wdk/model/questions/genomicQuestions.xml
+++ b/Model/lib/wdk/model/questions/genomicQuestions.xml
@@ -359,6 +359,16 @@
         <description>Find all primary sequences to by organisms</description>
     </question>
 
+  <!--===========================================================================-->
+  <!-- retrieve sequence record which is the longest sequence in a provided organism -->
+  <!-- used internally by the User Dataset UI to form browser track URLs -->
+  <!--===========================================================================-->
+    <question name="LongestSeqForAnOrganism" excludeProjects="EuPathDB"
+         displayName="Longest seq for an organism"
+              queryRef="SequenceIds.ByOrganismNameForFiles"
+              recordClassRef="SequenceRecordClasses.SequenceRecordClass">
+        <description>Find longest seq for an organism</description>
+    </question>
 
 
 
diff --git a/Model/lib/wdk/model/questions/params/genomicParams.xml b/Model/lib/wdk/model/questions/params/genomicParams.xml
index 8d4d43c881..2ae9e59c8e 100644
--- a/Model/lib/wdk/model/questions/params/genomicParams.xml
+++ b/Model/lib/wdk/model/questions/params/genomicParams.xml
@@ -190,6 +190,8 @@
         <suggest includeProjects="UniDB,PlasmoDB,ToxoDB,CryptoDB" default="1"/>
     </stringParam>
 
+    <stringParam name="organismNameForFiles" excludeProjects="EuPathDB" prompt="Org name for files"/>
+
     <enumParam name="medianOrIndividual" includeProjects="AmoebaDB,TriTrypDB,PlasmoDB,ToxoDB,CryptoDB,FungiDB,UniDB"
             prompt="Median Or By Strain/Sample?"
             multiPick="false">
diff --git a/Model/lib/wdk/model/questions/queries/genomicQueries.xml b/Model/lib/wdk/model/questions/queries/genomicQueries.xml
index f6bd2e8884..fc75c343ac 100644
--- a/Model/lib/wdk/model/questions/queries/genomicQueries.xml
+++ b/Model/lib/wdk/model/questions/queries/genomicQueries.xml
@@ -416,4 +416,29 @@ from apidbtuning.GenomicSeqAttributes s
 
   </querySet>
 
+  <!--++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-->
+  <!-- Retrieves genomic sequence ID of longest sequence in an organism -->
+  <!-- Used by user datasets UI to build genome browser track URLs  -->
+  <!--++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-->
+
+    <sqlQuery name="ByOrganismNameForFiles"  excludeProjects="EuPathDB">
+        <paramRef ref="genomicsParams.organismNameForFiles"/>
+        <column name="project_id"/>
+        <column name="source_id"/>
+        <sql>
+            <![CDATA[
+      SELECT gsa.project_id, gsa.source_id
+      FROM apidbtuning.genomicseqattributes gsa, apidb.organism o,
+        (SELECT MAX(length) AS ML, taxon_id 
+         FROM apidbtuning.genomicseqattributes 
+         GROUP BY taxon_id ) info
+      WHERE info.taxon_id = gsa.taxon_id
+      AND info.ml = gsa.length
+      AND gsa.taxon_id = o.taxon_id
+      AND $$organismNameForFiles$$ = o.name_for_filenames
+
+            ]]>
+        </sql>
+    </sqlQuery>
+
 </wdkModel>

From 0f38adeffd1d64432136a233a9b9fd252d3b2202 Mon Sep 17 00:00:00 2001
From: steve-fischer-200 <sfischer@upenn.edu>
Date: Sat, 4 Nov 2023 10:52:15 -0400
Subject: [PATCH 2/3] debug

---
 Model/lib/wdk/model/questions/params/genomicParams.xml   | 2 +-
 Model/lib/wdk/model/questions/queries/genomicQueries.xml | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Model/lib/wdk/model/questions/params/genomicParams.xml b/Model/lib/wdk/model/questions/params/genomicParams.xml
index 2ae9e59c8e..19d0537626 100644
--- a/Model/lib/wdk/model/questions/params/genomicParams.xml
+++ b/Model/lib/wdk/model/questions/params/genomicParams.xml
@@ -190,7 +190,7 @@
         <suggest includeProjects="UniDB,PlasmoDB,ToxoDB,CryptoDB" default="1"/>
     </stringParam>
 
-    <stringParam name="organismNameForFiles" excludeProjects="EuPathDB" prompt="Org name for files"/>
+    <stringParam name="organismNameForFiles" excludeProjects="EuPathDB" prompt="Org name for files" number="false"/>
 
     <enumParam name="medianOrIndividual" includeProjects="AmoebaDB,TriTrypDB,PlasmoDB,ToxoDB,CryptoDB,FungiDB,UniDB"
             prompt="Median Or By Strain/Sample?"
diff --git a/Model/lib/wdk/model/questions/queries/genomicQueries.xml b/Model/lib/wdk/model/questions/queries/genomicQueries.xml
index fc75c343ac..ee569c6290 100644
--- a/Model/lib/wdk/model/questions/queries/genomicQueries.xml
+++ b/Model/lib/wdk/model/questions/queries/genomicQueries.xml
@@ -414,15 +414,13 @@ from apidbtuning.GenomicSeqAttributes s
         </sql>
     </sqlQuery>
 
-  </querySet>
-
   <!--++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-->
   <!-- Retrieves genomic sequence ID of longest sequence in an organism -->
   <!-- Used by user datasets UI to build genome browser track URLs  -->
   <!--++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-->
 
     <sqlQuery name="ByOrganismNameForFiles"  excludeProjects="EuPathDB">
-        <paramRef ref="genomicsParams.organismNameForFiles"/>
+        <paramRef ref="genomicParams.organismNameForFiles"/>
         <column name="project_id"/>
         <column name="source_id"/>
         <sql>
@@ -441,4 +439,6 @@ from apidbtuning.GenomicSeqAttributes s
         </sql>
     </sqlQuery>
 
+  </querySet>
+
 </wdkModel>

From 319c5e48b933fe780d457f1b542d86bc33e9c59b Mon Sep 17 00:00:00 2001
From: steve-fischer-200 <sfischer@upenn.edu>
Date: Mon, 6 Nov 2023 16:00:47 -0500
Subject: [PATCH 3/3] improve perf of GO Term query

---
 .../wdk/model/questions/params/geneParams.xml    | 16 ++++------------
 .../wdk/model/questions/queries/geneQueries.xml  | 12 ++++++++----
 2 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/Model/lib/wdk/model/questions/params/geneParams.xml b/Model/lib/wdk/model/questions/params/geneParams.xml
index 598d90653f..a96092abec 100644
--- a/Model/lib/wdk/model/questions/params/geneParams.xml
+++ b/Model/lib/wdk/model/questions/params/geneParams.xml
@@ -2020,21 +2020,13 @@ products of your selected type (or types).<br><br>
     <!--++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-->
 
         <stringParam name="go_term"
-                     prompt="GO Term or GO ID wildcard search" number="false" length="1000"
+                     prompt="GO Term wildcard search" number="false" length="1000"
                      sanityDefault="catalytic activity">
             <suggest default="N/A"/>
             <help><![CDATA[
-                  
-                  
-                  Use this parameter to indicate the GO Term (e.g. "catalytic activity") or ID (e.g. "GO:0003824") that you wish to query for. Genes returned by this search 
-            are annotated with the GO Term or ID you indicate here.<br><br>
-            To find genes with any GO association, you may use "*" or "any"<br><br>
-            Type the text term you wish to find, including an asterisk wildcard for ambiguous portions of your text term. (*ase, kin*, *kinase*) 
-            The search will query for all GO Terms and IDs that contain your text.
-            
-            
-            
-            
+                  Use this parameter to include wildcards in your GO Term.
+            Type the GO term you wish to find, including an asterisk for ambiguous portions, eg *ase, kin*, *kinase*.
+            To find genes with any GO association, use "*"<br><br>
             ]]>
             </help>
         </stringParam>
diff --git a/Model/lib/wdk/model/questions/queries/geneQueries.xml b/Model/lib/wdk/model/questions/queries/geneQueries.xml
index 990e6418e3..6d2a297112 100644
--- a/Model/lib/wdk/model/questions/queries/geneQueries.xml
+++ b/Model/lib/wdk/model/questions/queries/geneQueries.xml
@@ -1877,10 +1877,14 @@ AND 1=0
 --                       when ($$go_term_slim$$ = 'No' and (gs.is_go_slim = '1' or gs.is_go_slim = '0')) then 1 
 --                       else 0
  --                 end = 1 
-                AND (gs.go_id IN ($$go_typeahead$$)
-                     OR (lower(gs.go_term_name) like lower(REPLACE($$go_term$$, '*', '%'))
-                     OR lower( gs.go_id) like lower(REPLACE($$go_term$$, '*', '%'))
-                     OR lower(gs.go_id || ' : ' || gs.go_term_name) like lower(REPLACE($$go_term$$, '*', '%'))) )
+                AND (
+                  gs.go_id IN ($$go_typeahead$$) OR (
+                    $$go_term$$ != 'N/A' AND (               
+                      lower(gs.go_term_name) like lower(REPLACE($$go_term$$, '*', '%')) OR
+                      gs.go_id = upper($$go_term$$)
+                    )
+                  )
+                )
               GROUP BY gs.transcript_source_id, gs.gene_source_id, ta.project_id
               ORDER BY gs.transcript_source_id
            ]]>