Add initial pipelne job to cleanup extraneous MHC typing results

Author: bbimber

SequenceAnalysis/resources/queries/sequenceanalysis/alignment_summary_by_lineage.query.xml

@@ -38,6 +38,10 @@
                             </conditionalFormat>
                         </conditionalFormats>
                     </column>
+                    <column columnName="rowids">
+                        <columnTitle>RowIds</columnTitle>
+                        <isHidden>true</isHidden>
+                    </column>
                 </columns>
             </table>
         </tables>

SequenceAnalysis/resources/queries/sequenceanalysis/alignment_summary_by_lineage.sql

@@ -34,6 +34,7 @@ select
       SELECT distinct asj.alignment_id from sequenceanalysis.alignment_summary_junction asj WHERE asj.ref_nt_id.locus = a.loci and asj.status = true
     )
   ) as float)), 2) as percent_from_locus,
+  group_concat(distinct a.rowid, ',') as rowids
 
 FROM (
 

SequenceAnalysis/resources/queries/sequenceanalysis/alignment_summary_grouped.query.xml

@@ -50,6 +50,18 @@
                             </conditionalFormat>
                         </conditionalFormats>
                     </column>
+                    <column columnName="rowids">
+                        <columnTitle>RowIds</columnTitle>
+                        <isHidden>true</isHidden>
+                    </column>
+                    <column columnName="nAlignments">
+                        <columnTitle># Alignments</columnTitle>
+                        <isHidden>true</isHidden>
+                    </column>
+                    <column columnName="nLoci">
+                        <columnTitle># Loci</columnTitle>
+                        <isHidden>true</isHidden>
+                    </column>
                 </columns>
             </table>
         </tables>

SequenceAnalysis/resources/queries/sequenceanalysis/alignment_summary_grouped.sql

@@ -45,7 +45,10 @@ select
       SELECT distinct asj.alignment_id from sequenceanalysis.alignment_summary_junction asj WHERE asj.ref_nt_id.locus = a.loci and asj.status = true
     )
   ) as float) END), 2) as percent_from_locus,
-  max(lastModified) as lastModified
+  max(lastModified) as lastModified,
+  group_concat(distinct a.rowid, ',') as rowids,
+  count(distinct a.rowid) as nAlignments,
+  max(a.nloci) as nLoci
 
 FROM (
 
@@ -58,6 +61,7 @@ FROM (
     group_concat(distinct j.ref_nt_id.lineage, chr(10)) as lineages,
     count(distinct j.ref_nt_id.lineage) as totalLineages,
     group_concat(distinct j.ref_nt_id.locus, chr(10)) as loci,
+    count(distinct j.ref_nt_id.locus) as nloci,
     group_concat(distinct hs.haplotype, chr(10)) as haplotypesWithAllele,
 
     total,