Skip to content

Commit

Permalink
Pre-select samples to reduce JOIN size
Browse files Browse the repository at this point in the history
  • Loading branch information
@fuzhaoyuan
fuzhaoyuan committed Oct 24, 2024
1 parent b2ce990 commit 9e1e2b2
Showing 1 changed file with 35 additions and 39 deletions.
74 changes: 35 additions & 39 deletions src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -337,7 +337,7 @@
<!-- if 'NA' is selected, prepare NA samples -->
<if test="userSelectsNA">
SELECT DISTINCT ${unique_id}
FROM sample_derived sd
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sd
LEFT JOIN (<include refid="selectAllClinicalDataByAttribute"/>) AS categorical_clinical_data
ON
<choose>
Expand Down Expand Up @@ -428,7 +428,7 @@
<sql id="categoricalClinicalDataCountFilter">
(
SELECT ${unique_id}
FROM sample_derived sd
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sd
LEFT JOIN (<include refid="selectAllClinicalDataByAttribute"/>) AS categorical_clinical_data
ON
<choose>
Expand Down Expand Up @@ -462,6 +462,23 @@
)
</sql>

<sql id="categoricalGenomicDataFilterForCNA">
<!-- filter on study to reduce query size in preparation of the following LEFT JOIN -->
SELECT DISTINCT sample_query.sample_unique_id
<!-- join with sample table to get all 'NA' samples -->
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sample_query
LEFT JOIN (<include refid="selectAllGeneticAlterations"/>) AS cna_query ON sample_query.sample_unique_id = cna_query.sample_unique_id
WHERE
<foreach item="dataFilterValue" collection="genomicDataFilter.values" open="(" separator=" OR " close=")">
<choose>
<!-- NA value samples -->
<when test="dataFilterValue.value == 'NA'">alteration_value IS null</when>
<!-- non-NA value samples -->
<otherwise>alteration_value == #{dataFilterValue.value}</otherwise>
</choose>
</foreach>
</sql>

<sql id="numericalGenomicDataFilter">
<!-- check if 'NA' is selected -->
<bind name="userSelectsNA" value="false" />
Expand All @@ -478,9 +495,9 @@
</foreach>
<!-- if 'NA' is selected, prepare NA samples -->
<if test="userSelectsNA">
SELECT DISTINCT sd.sample_unique_id
FROM sample_derived sd
LEFT JOIN (<include refid="selectAllNumericalGeneticAlterations"/>) AS genomic_numerical_query ON sd.sample_unique_id = genomic_numerical_query.sample_unique_id
SELECT DISTINCT sample_query.sample_unique_id
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sample_query
LEFT JOIN (<include refid="selectAllGeneticAlterations"/>) AS genomic_numerical_query ON sample_query.sample_unique_id = genomic_numerical_query.sample_unique_id
WHERE alteration_value IS null
</if>
<!-- if both 'NA' and non-NA are selected, union them together -->
Expand All @@ -490,7 +507,7 @@
<!-- if non-NA is selected, prepare non-NA samples -->
<if test="userSelectsNumericalValue">
SELECT DISTINCT sample_unique_id
FROM (<include refid="selectAllNumericalGeneticAlterations"/>) AS genomic_numerical_query
FROM (<include refid="selectAllGeneticAlterations"/>) AS genomic_numerical_query
WHERE
<foreach item="dataFilterValue" collection="genomicDataFilter.values" open="((" separator=") OR (" close="))">
<trim prefix="" prefixOverrides="AND">
Expand Down Expand Up @@ -536,7 +553,7 @@
</if>
</sql>

<sql id="selectAllNumericalGeneticAlterations">
<sql id="selectAllGeneticAlterations">
SELECT sample_unique_id, alteration_value
FROM genetic_alteration_derived
WHERE profile_type = #{genomicDataFilter.profileType}
Expand All @@ -546,6 +563,15 @@
#{studyId}
</foreach>
</sql>

<sql id="selectAllSamplesInSelectedStudies">
SELECT sample_unique_id
FROM sample_derived
WHERE cancer_study_identifier IN
<foreach item="studyId" collection="studyViewFilterHelper.studyViewFilter.studyIds" open="(" separator="," close=")">
#{studyId}
</foreach>
</sql>

<sql id="selectAllGenericAssays">
SELECT sample_unique_id, value, datatype
Expand All @@ -572,7 +598,7 @@
<!-- if 'NA' is selected, prepare NA samples -->
<if test="userSelectsNA">
SELECT DISTINCT sd.sample_unique_id
FROM sample_derived sd
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sd
LEFT JOIN (<include refid="selectAllGenericAssays"/>) AS generic_numerical_query ON sd.sample_unique_id = generic_numerical_query.sample_unique_id
WHERE datatype = 'LIMIT-VALUE'
AND value IS null OR
Expand Down Expand Up @@ -646,7 +672,7 @@

<sql id="categoricalGenericAssayDataCountFilter">
SELECT ${unique_id}
FROM sample_derived sd
FROM (<include refid="selectAllSamplesInSelectedStudies"/>) AS sd
LEFT JOIN (<include refid="selectAllGenericAssays"/>) AS generic_assay_query
ON sd.sample_unique_id = generic_assay_query.sample_unique_id
<where>
Expand Down Expand Up @@ -735,34 +761,4 @@
</foreach>
</if>
</sql>

<sql id="categoricalGenomicDataFilterForCNA">
<!-- filter on study to reduce query size in preparation of the following LEFT JOIN -->
WITH cna_query AS (
SELECT sample_unique_id, alteration_value
FROM genetic_alteration_derived
WHERE profile_type = #{genomicDataFilter.profileType}
AND hugo_gene_symbol = #{genomicDataFilter.hugoGeneSymbol}
AND cancer_study_identifier IN
<foreach item="studyId" collection="studyViewFilterHelper.studyViewFilter.studyIds" open="(" separator="," close=")">
#{studyId}
</foreach>
)
SELECT DISTINCT sd.sample_unique_id
<!-- join with sample table to get all 'NA' samples -->
FROM sample_derived sd
LEFT JOIN cna_query ON sd.sample_unique_id = cna_query.sample_unique_id
WHERE cancer_study_identifier IN
<foreach item="studyId" collection="studyViewFilterHelper.studyViewFilter.studyIds" open="(" separator="," close=")">
#{studyId}
</foreach>
<foreach item="dataFilterValue" collection="genomicDataFilter.values" open="AND (" separator=" OR " close=")">
<choose>
<!-- NA value samples -->
<when test="dataFilterValue.value == 'NA'">alteration_value IS null</when>
<!-- non-NA value samples -->
<otherwise>alteration_value == #{dataFilterValue.value}</otherwise>
</choose>
</foreach>
</sql>
</mapper>

0 comments on commit 9e1e2b2

Please sign in to comment.