Skip to content
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.

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

Add tests for case list sample counts endpoint #10935

Merged
merged 3 commits into from
Aug 19, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ public interface StudyViewRepository {

Map<String, ClinicalDataType> getClinicalAttributeDatatypeMap();

List<CaseListDataCount> getCaseListDataCounts(StudyViewFilter studyViewFilter);
List<CaseListDataCount> getCaseListDataCountsPerStudy(StudyViewFilter studyViewFilter);

Map<String, Integer> getTotalProfiledCounts(StudyViewFilter studyViewFilter, String alterationType);

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ List<AlterationCountByGene> getStructuralVariantGenes(StudyViewFilter studyViewF
List<ClinicalDataCount> getClinicalDataCounts(StudyViewFilter studyViewFilter, CategorizedClinicalDataCountFilter categorizedClinicalDataCountFilter,
boolean applyPatientIdFilters, List<String> attributeIds, List<String> filteredAttributeValues);

List<CaseListDataCount> getCaseListDataCounts(StudyViewFilter studyViewFilter, CategorizedClinicalDataCountFilter categorizedClinicalDataCountFilter, boolean applyPatientIdFilters);
List<CaseListDataCount> getCaseListDataCountsPerStudy(StudyViewFilter studyViewFilter, CategorizedClinicalDataCountFilter categorizedClinicalDataCountFilter, boolean applyPatientIdFilters);

List<ClinicalAttribute> getClinicalAttributes();

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -134,11 +134,11 @@ public Map<String, ClinicalDataType> getClinicalAttributeDatatypeMap() {

return attributeDatatypeMap;
}

@Override
public List<CaseListDataCount> getCaseListDataCounts(StudyViewFilter studyViewFilter) {
public List<CaseListDataCount> getCaseListDataCountsPerStudy(StudyViewFilter studyViewFilter) {
CategorizedClinicalDataCountFilter categorizedClinicalDataCountFilter = extractClinicalDataCountFilters(studyViewFilter);
return mapper.getCaseListDataCounts(studyViewFilter, categorizedClinicalDataCountFilter, shouldApplyPatientIdFilters(studyViewFilter,categorizedClinicalDataCountFilter));
return mapper.getCaseListDataCountsPerStudy(studyViewFilter, categorizedClinicalDataCountFilter, shouldApplyPatientIdFilters(studyViewFilter,categorizedClinicalDataCountFilter));
}


Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,10 @@ public List<ClinicalDataCountItem> getClinicalDataCounts(StudyViewFilter studyVi

@Override
public List<CaseListDataCount> getCaseListDataCounts(StudyViewFilter studyViewFilter) {
return studyViewRepository.getCaseListDataCounts(studyViewFilter);
// the study view merges case lists by type across studies
// type is determined by the suffix of case list name (after study name)
var caseListDataCountsPerStudy = studyViewRepository.getCaseListDataCountsPerStudy(studyViewFilter);
return mergeCaseListCounts(caseListDataCountsPerStudy);
}


Expand Down Expand Up @@ -146,4 +149,31 @@ public List<GenomicDataCountItem> getMutationTypeCountsByGeneSpecific(StudyViewF
return studyViewRepository.getMutationCountsByType(studyViewFilter, genomicDataFilters);
}



public static List<CaseListDataCount> mergeCaseListCounts(List<CaseListDataCount> counts) {
Map<String, List<CaseListDataCount>> countsPerListType = counts.stream()
.collect((Collectors.groupingBy(CaseListDataCount::getValue)));

// different cancer studies combined into one cohort will have separate case lists
// of a given type (e.g. rppa). We need to merge the counts for these
// different lists based on the type and choose a label
// this code just picks the first label, which assumes that the labels will match for a give type
List<CaseListDataCount> mergedCounts = new ArrayList<>();
for (Map.Entry<String,List<CaseListDataCount>> entry : countsPerListType.entrySet()) {
var dc = new CaseListDataCount();
dc.setValue(entry.getKey());
// here just snatch the label of the first profile
dc.setLabel(entry.getValue().get(0).getLabel());
Integer sum = entry.getValue().stream()
.map(x -> x.getCount())
.collect(Collectors.summingInt(Integer::intValue));
dc.setCount(sum);
mergedCounts.add(dc);
}
return mergedCounts;
}



}
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@
</select>

<!-- for /sample-lists-counts/fetch (returns CaseListDataCount) -->
<select id="getCaseListDataCounts" resultType="org.cbioportal.model.CaseListDataCount">
<select id="getCaseListDataCountsPerStudy" resultType="org.cbioportal.model.CaseListDataCount">
SELECT
name AS label,
REPLACE(stable_id, CONCAT(cancer_study_identifier, '_'), '') AS value,
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,124 @@
package org.cbioportal.persistence.mybatisclickhouse;

import org.cbioportal.persistence.mybatisclickhouse.config.MyBatisConfig;

import org.cbioportal.service.impl.StudyViewColumnarServiceImpl;
import org.cbioportal.web.parameter.CategorizedClinicalDataCountFilter;
import org.cbioportal.web.parameter.StudyViewFilter;
import org.junit.Test;
import org.junit.runner.RunWith;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.autoconfigure.jdbc.AutoConfigureTestDatabase;
import org.springframework.boot.test.autoconfigure.orm.jpa.DataJpaTest;
import org.springframework.context.annotation.Import;
import org.springframework.test.annotation.DirtiesContext;
import org.springframework.test.context.ContextConfiguration;
import org.springframework.test.context.junit4.SpringRunner;

import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

import static org.junit.Assert.assertEquals;

@RunWith(SpringRunner.class)
@Import(MyBatisConfig.class)
@DataJpaTest
@DirtiesContext
@AutoConfigureTestDatabase(replace= AutoConfigureTestDatabase.Replace.NONE)
@ContextConfiguration(initializers = AbstractTestcontainers.Initializer.class)
public class StudyViewCaseListSamplesCountsTest extends AbstractTestcontainers {

private static final String STUDY_TCGA_PUB = "study_tcga_pub";
private static final String STUDY_ACC_TCGA = "acc_tcga";

@Autowired
private StudyViewMapper studyViewMapper;

@Test
public void getMolecularProfileCounts() {
StudyViewFilter studyViewFilter = new StudyViewFilter();
studyViewFilter.setStudyIds(List.of(STUDY_TCGA_PUB));

var caseList = new ArrayList<String>(Arrays.asList("pub_cna"));
var caseListGroups = new ArrayList(Arrays.asList(caseList));

studyViewFilter.setCaseLists(caseListGroups);

var sampleListCounts = studyViewMapper.getCaseListDataCountsPerStudy(studyViewFilter,
CategorizedClinicalDataCountFilter.getBuilder().build(), false );

var size = sampleListCounts.stream().filter(gc->gc.getValue().equals("mrna"))
.findFirst().get().getCount().intValue();
assertEquals(7, size);

}

@Test
public void getMolecularProfileCountsMultipleListsOr() {
StudyViewFilter studyViewFilter = new StudyViewFilter();
studyViewFilter.setStudyIds(List.of(STUDY_TCGA_PUB));

var caseList = new ArrayList<String>(Arrays.asList("mrna","pub_cna"));
var caseListGroups = new ArrayList(Arrays.asList(caseList));

studyViewFilter.setCaseLists(caseListGroups);

var sampleListCounts = studyViewMapper.getCaseListDataCountsPerStudy(studyViewFilter,
CategorizedClinicalDataCountFilter.getBuilder().build(), false );

var size = sampleListCounts.stream().filter(gc->gc.getValue().equals("mrna"))
.findFirst().get().getCount().intValue();
assertEquals(8, size);

}

@Test
public void getMolecularProfileCountsMultipleListsAnd() {
StudyViewFilter studyViewFilter = new StudyViewFilter();
studyViewFilter.setStudyIds(List.of(STUDY_TCGA_PUB));

var caseList1 = new ArrayList<String>(Arrays.asList("mrna"));
var caseList2 = new ArrayList<String>(Arrays.asList("pub_cna"));
var caseListGroups = new ArrayList(Arrays.asList(caseList1, caseList2));

studyViewFilter.setCaseLists(caseListGroups);

var sampleListCounts = studyViewMapper.getCaseListDataCountsPerStudy(studyViewFilter,
CategorizedClinicalDataCountFilter.getBuilder().build(), false );

var size = sampleListCounts.stream().filter(gc->gc.getValue().equals("mrna"))
.findFirst().get().getCount().intValue();
assertEquals(7, size);

}

@Test
public void getMolecularProfileCountsAcrossStudies() {
StudyViewFilter studyViewFilter = new StudyViewFilter();
studyViewFilter.setStudyIds(List.of(STUDY_TCGA_PUB, STUDY_ACC_TCGA));

var caseList1 = new ArrayList<String>(Arrays.asList("all"));
var caseListGroups = new ArrayList(Arrays.asList(caseList1));

studyViewFilter.setCaseLists(caseListGroups);

var unMergedCounts = studyViewMapper.getCaseListDataCountsPerStudy(studyViewFilter,
CategorizedClinicalDataCountFilter.getBuilder().build(), false );

var caseListCountsMerged = StudyViewColumnarServiceImpl.mergeCaseListCounts(
unMergedCounts
);

var sizeUnmerged = unMergedCounts.stream().filter(gc->gc.getValue().equals("all"))
.findFirst().get().getCount().intValue();
assertEquals(14, sizeUnmerged);

// now we've combined the "all" from the two studies
var sizeMerged = caseListCountsMerged.stream().filter(gc->gc.getValue().equals("all"))
.findFirst().get().getCount().intValue();
assertEquals(15, sizeMerged);

}

}
Loading