init single-cell core

.editorconfig

@@ -0,0 +1,9 @@
+root = true
+
+[*]
+end_of_line = lf
+insert_final_newline = true
+
+[*.{java,py}]
+indent_style = space
+indent_size = 4

scripts/importer/cbioportal_common.py

@@ -66,6 +66,7 @@ class MetaFileTypes(object):
     CNA_CONTINUOUS = 'meta_contCNA'
     SEG = 'meta_segment'
     EXPRESSION = 'meta_expression'
+    SINGLE_CELL_EXPRESSION = 'meta_single_cell_expression'
     MUTATION = 'meta_mutations_extended'
     MUTATION_UNCALLED = 'meta_mutations_uncalled'
     METHYLATION = 'meta_methylation'
@@ -214,6 +215,18 @@ class MetaFileTypes(object):
         'data_filename': True,
         'gene_panel': False
     },
+    MetaFileTypes.SINGLE_CELL_EXPRESSION: {
+        'cancer_study_identifier': True,
+        'genetic_alteration_type': True,
+        'datatype': True,
+        'stable_id': True,
+        'source_stable_id': False,
+        'show_profile_in_analysis_tab': True,
+        'profile_name': True,
+        'profile_description': True,
+        'data_filename': True,
+        'gene_panel': False
+    },
     MetaFileTypes.METHYLATION: {
         'cancer_study_identifier': True,
         'genetic_alteration_type': True,
@@ -399,6 +412,7 @@ class MetaFileTypes(object):
     MetaFileTypes.CNA_CONTINUOUS: "org.mskcc.cbio.portal.scripts.ImportProfileData",
     MetaFileTypes.SEG: "org.mskcc.cbio.portal.scripts.ImportCopyNumberSegmentData",
     MetaFileTypes.EXPRESSION: "org.mskcc.cbio.portal.scripts.ImportProfileData",
+    MetaFileTypes.SINGLE_CELL_EXPRESSION: "org.mskcc.cbio.portal.scripts.ImportProfileData",
     MetaFileTypes.MUTATION: "org.mskcc.cbio.portal.scripts.ImportProfileData",
     MetaFileTypes.MUTATION_UNCALLED: "org.mskcc.cbio.portal.scripts.ImportProfileData",
     MetaFileTypes.METHYLATION: "org.mskcc.cbio.portal.scripts.ImportProfileData",

src/main/java/org/mskcc/cbio/portal/dao/DaoSingleCellExpression.java

@@ -0,0 +1,74 @@
+/*
+ * Copyright (c) 2024 The Hyve B.V.
+ * This code is licensed under the GNU Affero General Public License (AGPL),
+ * version 3, or (at your option) any later version.
+ */
+
+/*
+ * This file is part of cBioPortal.
+ *
+ * cBioPortal is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+/*
+ * @author Matthijs Pon
+*/
+
+package org.mskcc.cbio.portal.dao;
+
+import java.sql.*;
+import org.mskcc.cbio.portal.model.*;
+
+public class DaoSingleCellExpression {
+
+	private DaoSingleCellExpression() {
+	}
+
+	/**
+     * Set genetic profile link in `genetic_profile_link` table in database.
+     * @throws DaoException
+     **/
+    public static void addSingleCellExpression(int geneticProfileId, int entrezGeneId, String tissue, String cellType, String[] sampleIds, String[] values) throws DaoException {
+        Connection connection = null;
+        PreparedStatement preparedStatement = null;
+        ResultSet resultSet = null;
+
+        try {
+        	// Open connection to database
+            connection = JdbcUtil.getDbConnection(DaoGeneticProfileLink.class);
+
+	        // Prepare SQL statement
+            preparedStatement = connection.prepareStatement("INSERT INTO single_cell_expression "
+                + "(GENETIC_PROFILE_ID, SAMPLE_ID, TISSUE, CELL_TYPE, ENTREZ_GENE_ID, EXPRESSION_VALUE) VALUES (?,?,?,?,?,?)");
+            for (int i = 0; i < sampleIds.length; i++) {
+            // for (String expressionValue: values) {
+            // Fill in statement
+                preparedStatement.setInt(1, geneticProfileId);
+                preparedStatement.setInt(2, sampleIds[i]);
+                preparedStatement.setString(3, tissue);
+                preparedStatement.setString(4, cellType);
+                preparedStatement.setInt(5, entrezGeneId);
+                preparedStatement.setFloat(6, Float.valueOf(values[i]));
+                preparedStatement.addBatch();
+            }
+
+            // Execute statement
+            preparedStatement.executeBatch();
+        } catch (SQLException e) {
+            throw new DaoException(e);
+        } finally {
+            JdbcUtil.closeAll(DaoGeneticProfileLink.class, connection, preparedStatement, resultSet);
+        }
+    }
+}

src/main/java/org/mskcc/cbio/portal/model/GeneticAlterationType.java

@@ -52,5 +52,6 @@ public enum GeneticAlterationType {
     PROTEIN_ARRAY_PROTEIN_LEVEL,
     PROTEIN_ARRAY_PHOSPHORYLATION,
     GENESET_SCORE,
-    GENERIC_ASSAY
+    GENERIC_ASSAY,
+    SINGLE_CELL_EXPRESSION
 };

src/main/java/org/mskcc/cbio/portal/scripts/ImportProfileData.java

@@ -151,6 +151,7 @@ public void run() {
                 );
                 importer.importData();
             } else {
+                // All other files go through this
                 ImportTabDelimData importer = new ImportTabDelimData(
                     dataFile, 
                     geneticProfile.getTargetLine(), 

src/main/java/org/mskcc/cbio/portal/scripts/ImportTabDelimData.java

@@ -141,7 +141,7 @@ public ImportTabDelimData(
      * @param geneticProfileId GeneticProfile ID.
      * @param isIncrementalUpdateMode if true, update/append data to the existing one
      *
-     * @deprecated : TODO shall we deprecate this feature (i.e. the targetLine)?
+     * //@deprecated : TODO shall we deprecate this feature (i.e. the targetLine)?
      */
     public ImportTabDelimData(
         File dataFile,
@@ -197,6 +197,7 @@ public void importData() {
             return null;
         });
     }
+    // TODO: update this function
     private void doImportData() throws IOException, DaoException {
         try {
             this.numLines = FileUtil.getNumLines(dataFile);
@@ -222,6 +223,8 @@ private void doImportData() throws IOException, DaoException {
         boolean isGenericAssayProfile = geneticProfile != null
             && geneticProfile.getGeneticAlterationType() == GeneticAlterationType.GENERIC_ASSAY
             && headerParts[0].equalsIgnoreCase("ENTITY_STABLE_ID");
+        boolean isSingleCellExpressionProfile = geneticProfile != null
+            && geneticProfile.getGeneticAlterationType() == GeneticAlterationType.SINGLE_CELL_EXPRESSION;
 
         long typesDetected = List.of(isDiscretizedCnaProfile, isRppaProfile, isGsvaProfile, isGenericAssayProfile).stream().filter(Boolean::booleanValue).count();
         if (typesDetected > 1) {
@@ -231,11 +234,15 @@ private void doImportData() throws IOException, DaoException {
         int numRecordsToAdd = 0;
         int samplesSkipped = 0;
         try {
+            // TODO: also add profile somewhere?
             int hugoSymbolIndex = getHugoSymbolIndex(headerParts);
             int entrezGeneIdIndex = getEntrezGeneIdIndex(headerParts);
             int rppaGeneRefIndex = getRppaGeneRefIndex(headerParts);
             int genesetIdIndex = getGenesetIdIndex(headerParts);
-            int sampleStartIndex = getStartIndex(headerParts, hugoSymbolIndex, entrezGeneIdIndex, rppaGeneRefIndex, genesetIdIndex);
+            List<Integer> singleCellExpressionIndices = getSingleCellExpressionIndices(headerParts);
+            // TODO: add indices to here
+            int sampleStartIndex = getStartIndex(headerParts, hugoSymbolIndex, entrezGeneIdIndex, rppaGeneRefIndex, genesetIdIndex,
+                singleCellExpressionIndices.get(0), singleCellExpressionIndices.get(1));
             int genericAssayIdIndex = getGenericAssayIdIndex(headerParts);
             if (isRppaProfile) {
                 if (rppaGeneRefIndex == -1) {
@@ -250,7 +257,12 @@ private void doImportData() throws IOException, DaoException {
                     throw new RuntimeException("Error: the following column should be present for this type of data: ENTITY_STABLE_ID");
                 }
             } else if (hugoSymbolIndex == -1 && entrezGeneIdIndex == -1) {
+                if (isSingleCellExpressionProfile) {
+                    if (singleCellExpressionIndices.stream().anyMatch(n -> (n == -1))) {
+                        throw new RuntimeException("Error the following columns should be present for single cell data: "); // TODO: ad columns
+                    }
                 throw new RuntimeException("Error: at least one of the following columns should be present: Hugo_Symbol or Entrez_Gene_Id");
+                }
             }
 
             String sampleIds[];
@@ -366,6 +378,11 @@ private void doImportData() throws IOException, DaoException {
                         }
                         if (entrez != null && !DataValidator.isValidNumericSequence(entrez)) {
                             ProgressMonitor.logWarning("Ignoring line with invalid Entrez_Id " + entrez);
+                        } else if (isSingleCellExpressionProfile) {
+                            String sCExpTissue = rowParts[singleCellExpressionIndices.get(0)];
+                            String sCExpCellType = rowParts[singleCellExpressionIndices.get(1)];
+                            recordAdded = saveSingleCellExpressionLine(sampleValues, entrez, geneSymbol,
+                                sCExpTissue, sCExpCellType);
                         } else {
                             String firstCellValue = rowParts[0];
                             if (targetLine == null || firstCellValue.equals(targetLine)) {
@@ -894,6 +911,13 @@ private int getRppaGeneRefIndex(String[] headers) {
         return getColIndexByName(headers, "Composite.Element.Ref");
     }
 
+    private List<Integer> getSingleCellExpressionIndices(String[] headers) {
+        return List.of(
+            getColIndexByName(headers, "Tissue"),
+            getColIndexByName(headers, "Cell_Type")
+        );
+    }
+
     // helper function for finding the index of a column by name
     private int getColIndexByName(String[] headers, String colName) {
         for (int i = 0; i < headers.length; i++) {