Skip to content

Commit

Permalink
Filtering with NA for generic-assay-data-bin-counts
Browse files Browse the repository at this point in the history
  • Loading branch information
@fuzhaoyuan
fuzhaoyuan committed Oct 2, 2024
1 parent a213c6b commit 626f27c
Show file tree
Hide file tree
Showing 2 changed files with 95 additions and 52 deletions.
143 changes: 92 additions & 51 deletions src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewFilterMapper.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -152,7 +152,7 @@
<!-- Apply Generic Assay Data Filter -->
<if test="studyViewFilterHelper.categorizedGenericAssayDataCountFilter.getSampleNumericalGenericAssayDataFilters() != null and !studyViewFilterHelper.categorizedGenericAssayDataCountFilter.getSampleNumericalGenericAssayDataFilters().isEmpty()">
<foreach item="genericAssayDataFilter" collection="studyViewFilterHelper.categorizedGenericAssayDataCountFilter.getSampleNumericalGenericAssayDataFilters()" open="INTERSECT" separator="INTERSECT">
<include refid="numericalGenericAssayDataCountFilter">
<include refid="numericalGenericAssayDataFilter">
<property name="unique_id" value="sample_unique_id"/>
<property name="table_name" value="generic_assay_data_derived"/>
</include>
Expand Down Expand Up @@ -469,59 +469,100 @@
</foreach>
</sql>

<sql id="selectAllNumericalGenericAssays">
SELECT sample_unique_id, value
FROM generic_assay_data_derived
WHERE profile_type = #{genericAssayDataFilter.profileType}
AND entity_stable_id = #{genericAssayDataFilter.stableId}
<!-- It needs to include all numerical data types. Currently it's only LIMIT-VALUE -->
AND datatype = 'LIMIT-VALUE'
</sql>

<!-- TODO: update the database scheme to include the data_type column -->
<sql id="numericalGenericAssayDataCountFilter">
SELECT ${unique_id}
FROM ${table_name}
WHERE entity_stable_id = '${genericAssayDataFilter.stableId}' AND
profile_type='${genericAssayDataFilter.profileType}'
<foreach item="dataFilterValue" collection="genericAssayDataFilter.values" open=" AND ((" separator=") OR (" close="))">
<trim prefix="" prefixOverrides="AND">
<if test="dataFilterValue.value eq 'NA'">
AND
<include refid="isAttributeValueNA">
<property name="attribute_value" value="value"/>
</include>
</if>
<if test="dataFilterValue.start != null and dataFilterValue.end == null">
AND match(value, '^>?=?[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start == null and dataFilterValue.end != null">
AND match(value, '^&lt;?=?[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start != null and dataFilterValue.end != null">
AND match(value, '^[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start != null or dataFilterValue.end != null">
<choose>
<when test="dataFilterValue.start == dataFilterValue.end">
AND abs(
minus(
<include refid="castStringValueToFloat">
<property name="attribute_value" value="value"/>
</include>,
${dataFilterValue.start}
)
) &lt; exp(-11)
</when>
<otherwise>
<if test="dataFilterValue.start != null">
AND
<include refid="castStringValueToFloat">
<property name="attribute_value" value="value"/>
</include> &gt; ${dataFilterValue.start}
</if>
<if test="dataFilterValue.end != null">
AND
<sql id="numericalGenericAssayDataFilter">
<!-- check if 'NA' is selected -->
<bind name="userSelectsNA" value="false" />
<bind name="userSelectsNumericalValue" value="false" />
<foreach item="dataFilterValue" collection="genericAssayDataFilter.values">
<choose>
<when test="dataFilterValue.value == 'NA'">
<bind name="userSelectsNA" value="true" />
</when>
<otherwise>
<bind name="userSelectsNumericalValue" value="true" />
</otherwise>
</choose>
</foreach>
<!-- if 'NA' is selected, prepare NA samples -->
<if test="userSelectsNA">
SELECT DISTINCT sd.sample_unique_id
FROM sample_derived sd
LEFT JOIN (<include refid="selectAllNumericalGenericAssays"/>) AS generic_numerical_query ON sd.sample_unique_id = generic_numerical_query.sample_unique_id
WHERE value IS null OR
<include refid="normalizeAttributeValue">
<property name="attribute_value" value="value"/>
</include> = 'NA'
</if>
<!-- if both 'NA' and non-NA are selected, union them together -->
<if test="userSelectsNA and userSelectsNumericalValue">
UNION ALL
</if>
<!-- if non-NA is selected, prepare non-NA samples -->
<if test="userSelectsNumericalValue">
SELECT DISTINCT sample_unique_id
FROM (<include refid="selectAllNumericalGenericAssays"/>) AS generic_numerical_query
WHERE
<include refid="normalizeAttributeValue">
<property name="attribute_value" value="value"/>
</include> != 'NA'
<foreach item="dataFilterValue" collection="genericAssayDataFilter.values" open=" AND ((" separator=") OR (" close="))">
<trim prefix="" prefixOverrides="AND">
<if test="dataFilterValue.value eq 'NA'">
AND
<include refid="isAttributeValueNA">
<property name="attribute_value" value="value"/>
</include>
</if>
<if test="dataFilterValue.start != null and dataFilterValue.end == null">
AND match(value, '^>?=?[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start == null and dataFilterValue.end != null">
AND match(value, '^&lt;?=?[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start != null and dataFilterValue.end != null">
AND match(value, '^[-+]?[0-9]*[.,]?[0-9]+$')
</if>
<if test="dataFilterValue.start != null or dataFilterValue.end != null">
<choose>
<when test="dataFilterValue.start == dataFilterValue.end">
AND abs(
minus(
<include refid="castStringValueToFloat">
<property name="attribute_value" value="value"/>
</include> &lt;= ${dataFilterValue.end}
</if>
</otherwise>
</choose>
</if>
</trim>
</foreach>
</include>,
${dataFilterValue.start}
)
) &lt; exp(-11)
</when>
<otherwise>
<if test="dataFilterValue.start != null">
AND
<include refid="castStringValueToFloat">
<property name="attribute_value" value="value"/>
</include> &gt; ${dataFilterValue.start}
</if>
<if test="dataFilterValue.end != null">
AND
<include refid="castStringValueToFloat">
<property name="attribute_value" value="value"/>
</include> &lt;= ${dataFilterValue.end}
</if>
</otherwise>
</choose>
</if>
</trim>
</foreach>
</if>
</sql>

<sql id="categoricalGenericAssayDataCountFilter">
Expand Down
4 changes: 3 additions & 1 deletion src/main/resources/org/cbioportal/persistence/mybatisclickhouse/StudyViewMapper.xml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -623,15 +623,17 @@

<select id="getGenericAssayDataBinCounts" resultType="org.cbioportal.model.ClinicalDataCount">
<bind name="profileType" value="genericAssayDataBinFilters[0].profileType" />
<!-- get all non-NA value samples. A caveat here is that if user select only 'NA', this query will return empty (null) thus we need the 2 coalesce() below to handle this case -->
WITH generic_assay_query AS (
SELECT
concat(entity_stable_id, profile_type) AS attributeId,
<include refid="normalizeAttributeValue">
<property name="attribute_value" value="value"/>
</include> AS value,
count(value) AS count
cast(count(value) as INTEGER) AS count
FROM generic_assay_data_derived
<where>
<!-- Need to ensure no NA values -->
<include refid="normalizeAttributeValue">
<property name="attribute_value" value="value"/>
</include> != 'NA' AND
Expand Down

0 comments on commit 626f27c

Please sign in to comment.