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.

Sign up for GitHub

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

Jump to bottom

TASK-5877 - Accept non-normalized variant ID filtering by variant #2418

Merged
merged 2 commits into from
Apr 24, 2024
Merged

TASK-5877 - Accept non-normalized variant ID filtering by variant #2418

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a37f1b4
storage: Accept non-normalized variants when filtering by ID or XREF.…
j-coll Mar 19, 2024
92492ec
Merge branch 'release-2.12.x' into TASK-5877
j-coll Apr 24, 2024
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
2 changes: 1 addition & 1 deletion ...rage-core/src/main/java/org/opencb/opencga/storage/core/variant/VariantStorageEngine.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1200,7 +1200,7 @@ public DataResult<Variant> getSampleData(String variantStr, String study, QueryO
public Variant getVariant(String variantStr) {
final Variant variant;
if (VariantQueryUtils.isVariantId(variantStr)) {
variant = new Variant(variantStr);
variant = VariantQueryUtils.toVariant(variantStr, true);
} else if (VariantQueryUtils.isVariantAccession(variantStr)) {
VariantQueryResult<Variant> result = get(new Query(VariantQueryParam.ANNOT_XREF.key(), variantStr),
new QueryOptions(QueryOptions.INCLUDE, VariantField.ID).append(QueryOptions.LIMIT, 1).append(QueryOptions.COUNT, true));
Expand Down
26 changes: 26 additions & 0 deletions ...-core/src/main/java/org/opencb/opencga/storage/core/variant/query/VariantQueryParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,9 @@
import org.opencb.biodata.models.variant.Variant;
import org.opencb.biodata.models.variant.avro.ClinicalSignificance;
import org.opencb.biodata.models.variant.avro.VariantType;
import org.opencb.biodata.models.variant.exceptions.NonStandardCompliantSampleField;
import org.opencb.biodata.models.variant.metadata.VariantFileHeaderComplexLine;
import org.opencb.biodata.tools.variant.VariantNormalizer;
import org.opencb.commons.datastore.core.Query;
import org.opencb.commons.datastore.core.QueryOptions;
import org.opencb.commons.datastore.core.QueryParam;
Expand Down Expand Up @@ -862,8 +864,17 @@ public static ParsedVariantQuery.VariantQueryXref parseXrefs(Query query) {
}
}
}
}

if (!xrefs.getVariants().isEmpty()) {
List<Variant> normalizedVariants = normalizeVariants(xrefs.getVariants());
for (Variant normalizedVariant : normalizedVariants) {
if (!xrefs.getVariants().contains(normalizedVariant)) {
xrefs.getVariants().add(normalizedVariant);
}
}
}

if (isValidParam(query, ANNOT_GENE_ROLE_IN_CANER_GENES)) {
List<String> thisGenes = query.getAsStringList(ANNOT_GENE_ROLE_IN_CANER_GENES.key());
if (thisGenes.size() != 1 || !thisGenes.get(0).equals(NONE)) {
Expand All @@ -890,6 +901,21 @@ public static ParsedVariantQuery.VariantQueryXref parseXrefs(Query query) {
return xrefs;
}

public static Variant normalizeVariant(Variant variant) {
return normalizeVariants(Collections.singletonList(variant)).get(0);
}

public static List<Variant> normalizeVariants(List<Variant> variants) {
VariantNormalizer variantNormalizer = new VariantNormalizer();
List<Variant> normalizedVariants;
try {
normalizedVariants = variantNormalizer.normalize(variants, false);
} catch (NonStandardCompliantSampleField e) {
throw VariantQueryException.internalException(e);
}
return normalizedVariants;
}

public static ParsedQuery<KeyOpValue<String, Float>> parseFreqFilter(Query query, QueryParam queryParam) {
return VariantQueryUtils.splitValue(query, queryParam)
.map(VariantQueryUtils::parseKeyOpValue)
Expand Down
8 changes: 8 additions & 0 deletions ...e-core/src/main/java/org/opencb/opencga/storage/core/variant/query/VariantQueryUtils.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -578,6 +578,14 @@ public static Variant toVariant(String value) {
return variant;
}

public static Variant toVariant(String variantStr, boolean normalize) {
Variant variant = toVariant(variantStr);
if (normalize && variant != null) {
return VariantQueryParser.normalizeVariant(variant);
}
return variant;
}

public static String[] splitStudyResource(String value) {
int idx = value.lastIndexOf(STUDY_RESOURCE_SEPARATOR);
if (idx <= 0 || idx == value.length() - 1) {
Expand Down
10 changes: 10 additions & 0 deletions .../java/org/opencb/opencga/storage/core/variant/adaptors/VariantDBAdaptorMultiFileTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1333,6 +1333,16 @@ public void testSampleData() throws Exception {
assertEquals(0, variant.getStudies().get(0).getFiles().size());
}

@Test
public void testSampleDataUnnormalized() throws Exception {
// Check unnormalized queries
Variant variant = variantStorageEngine.getSampleData("1:10352:T:TA", study1, new QueryOptions()).first();
assertEquals("1:10353:-:A", variant.toString());
System.out.println("variant = " + variant.toJson());
assertNotNull(variant.getStudies().get(0).getStats(DEFAULT_COHORT));
assertEquals(4, variant.getStudies().get(0).getSamples().size());
assertEquals(4, variant.getStudies().get(0).getFiles().size());
}

@Test
public void testCount() throws StorageEngineException {
Expand Down
23 changes: 19 additions & 4 deletions .../src/test/java/org/opencb/opencga/storage/core/variant/adaptors/VariantDBAdaptorTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -529,11 +529,14 @@ public long filterPopulation(DataResult<Variant> queryResult, Predicate<Variant>
public void testGetAllVariants_variantId() {
int i = 0;
List<Variant> variants = new ArrayList<>();
Map<String, String> normalizedVariants = new HashMap<>();
for (Variant variant : allVariants.getResults()) {
if (i++ % 10 == 0) {
if (!variant.isSymbolic()) {
variants.add(variant);
}
if ((i++ % 10) == 0) {
variants.add(variant);
}
OriginalCall call = variant.getStudies().get(0).getFiles().get(0).getCall();
if (call != null) {
normalizedVariants.put(variant.toString(), call.getVariantId());
}
}
List<Variant> result = query(new Query(ID.key(), variants), new QueryOptions()).getResults();
Expand All @@ -552,6 +555,18 @@ public void testGetAllVariants_variantId() {
}
}
assertEquals(expectedList, actualList);

normalizedVariants.forEach((key, value) -> {
System.out.println(key + " = " + value);
});
List<Variant> resultNormalized = query(new Query(ID.key(), normalizedVariants.values()).append(INCLUDE_FILE.key(), ALL), new QueryOptions()).getResults();
assertEquals(normalizedVariants.size(), resultNormalized.size());
assertTrue(!resultNormalized.isEmpty());
for (Variant variant : resultNormalized) {
String expected = normalizedVariants.get(variant.toString());
String actual = variant.getStudies().get(0).getFiles().get(0).getCall().getVariantId();
assertEquals(expected, actual);
}
}

@Test
Expand Down
Loading