Feature/cov1 to cov2 projections

orthopairs/cov1_cov2_mapping.tsv

@@ -0,0 +1,59 @@
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6U8	P0DTC1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P0C6X7	P0DTD1
+P59594	P0DTC2
+P59632	P0DTC3
+P59596	P0DTC5
+P59637	P0DTC4
+P59634	P0DTC6
+P59635	P0DTC7
+Q7TFA1	P0DTD8
+Q7TFA0	P0DTC8
+P59595	P0DTC9
+P59636	P0DTD2
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3
+NC_004718.3	MN908947.3

orthopairs/cov2_coordinate_mapping.tsv

@@ -0,0 +1,59 @@
+full genome	NC_004718.3	1	29751	MN908947.3	1	29903
+mRNA1	NC_004718.3	1	21485	MN908947.3	1	21555
+mRNA2	NC_004718.3	21492	29751	MN908947.3	21563	29903
+mRNA3	NC_004718.3	25268	29751	MN908947.3	25393	29903
+mRNA4	NC_004718.3	26117	29751	MN908947.3	26245	29903
+mRNA5	NC_004718.3	26398	29751	MN908947.3	26523	29903
+mRNA6	NC_004718.3	26913	29751	MN908947.3	27202	29903
+mRNA7	NC_004718.3	27273	29751	MN908947.3	27394	29903
+mRNA8	NC_004718.3	27779	29751	MN908947.3	27894	29903
+mRNA9	NC_004718.3	28120	29751	MN908947.3	28274	29903
+full minus strand	NC_004718.3	-29751	-1	MN908947.3	-29903	-1
+minus mRNA2	NC_004718.3	-29751	-21492	MN908947.3	-29903	-21563
+minus mRNA3	NC_004718.3	-29751	-25268	MN908947.3	-29903	-25393
+minus mRNA4	NC_004718.3	-29751	-26117	MN908947.3	-29903	-26245
+minus mRNA5	NC_004718.3	-29751	-26398	MN908947.3	-29903	-26523
+minus mRNA6	NC_004718.3	-29751	-26913	MN908947.3	-29903	-27202
+minus mRNA7	NC_004718.3	-29751	-27273	MN908947.3	-29903	-27394
+minus mRNA8	NC_004718.3	-29751	-27779	MN908947.3	-29903	-27894
+minus mRNA9	NC_004718.3	-29751	-28120	MN908947.3	-29903	-28274
+pp1a	P0C6U8			P0DTC1		
+pp1a-nsp1	P0C6U8	1	180	P0DTC1	1	180
+pp1a-nsp2	P0C6U8	181	818	P0DTC1	181	818
+pp1a-nsp3	P0C6U8	819	2740	P0DTC1	819	2763
+pp1a-nsp4	P0C6U8	2741	3240	P0DTC1	2764	3263
+pp1a-nsp5	P0C6U8	3241	3546	P0DTC1	3264	3569
+pp1a-nsp6	P0C6U8	3547	3836	P0DTC1	3570	3859
+pp1a-nsp7	P0C6U8	3837	3919	P0DTC1	3860	3942
+pp1a-nsp8	P0C6U8	3920	4117	P0DTC1	3943	4140
+pp1a-nsp9	P0C6U8	4118	4230	P0DTC1	4141	4253
+pp1a-nsp10	P0C6U8	4231	4369	P0DTC1	4254	4392
+pp1a-nsp11	P0C6U8	4370	4382	P0DTC1	4393	4405
+pp1a-nsp3-4	P0C6U8	819	3240	P0DTC1	819	3263
+pp1a-nsp6-11	P0C6U8	3547	4382	P0DTC1	3570	4382
+rep	P0C6X7			P0DTD1		
+pp1ab-nsp1	P0C6X7	1	180	P0DTD1	1	180
+pp1ab-nsp2	P0C6X7	181	818	P0DTD1	181	818
+pp1ab-nsp3	P0C6X7	819	2740	P0DTD1	819	2763
+pp1ab-nsp4	P0C6X7	2741	3240	P0DTD1	2764	3263
+pp1ab-nsp5	P0C6X7	3241	3546	P0DTD1	3264	3569
+pp1ab-nsp6	P0C6X7	3547	3836	P0DTD1	3570	3859
+pp1ab-nsp7	P0C6X7	3837	3919	P0DTD1	3860	3942
+pp1ab-nsp8	P0C6X7	3920	4117	P0DTD1	3943	4140
+pp1ab-nsp9	P0C6X7	4118	4230	P0DTD1	4141	4253
+pp1ab-nsp10	P0C6X7	4231	4369	P0DTD1	4254	4392
+pp1ab-nsp12	P0C6X7	4370	5301	P0DTD1	4393	5324
+pp1ab-nsp13	P0C6X7	5302	5902	P0DTD1	5325	5925
+pp1ab-nsp14	P0C6X7	5903	6429	P0DTD1	5926	6452
+pp1ab-nsp15	P0C6X7	6430	6775	P0DTD1	6453	6798
+pp1ab-nsp15	P0C6X7	6776	7073	P0DTD1	6799	7096
+S	P59594			P0DTC2		
+3a	P59632			P0DTC3		
+M	P59596			P0DTC5		
+E	P59637			P0DTC4		
+6	P59634			P0DTC6		
+7a	P59635			P0DTC7		
+7b	Q7TFA1			P0DTD8		
+8a	Q7TFA0			P0DTC8		
+N	P59595			P0DTC9		
+9b	P59636			P0DTD2		

src/main/java/org/reactome/orthoinference/EventsInferrer.java

@@ -51,9 +51,10 @@ public class EventsInferrer
 	private static List<GKInstance> manualHumanEvents = new ArrayList<>();
 	private static StableIdentifierGenerator stableIdentifierGenerator;
 	private static OrthologousPathwayDiagramGenerator orthologousPathwayDiagramGenerator;
+	private static Long sarsCOV1InfectionsPathwayDbId = 9678108L;
 
 	@SuppressWarnings("unchecked")
-	public static void inferEvents(Properties props, String species) throws Exception
+	public static void inferEvents(Properties props, String referenceSpecies, String targetSpecies) throws Exception
 	{
 		logger.info("Preparing DB Adaptor and setting project variables");
 		// Set up DB adaptor using config.properties file
@@ -65,6 +66,7 @@ public static void inferEvents(Properties props, String species) throws Exceptio
 		int port = Integer.valueOf(props.getProperty("release.database.port"));
 
 		dbAdaptor = new MySQLAdaptor(host, database, username, password, port);
+		System.out.println(dbAdaptor.fetchMaxDbId());
 		dbAdaptorPrev = new MySQLAdaptor(host, prevDatabase, username, password, port);
 		if (dbAdaptor == null || dbAdaptorPrev == null) {
 			logger.fatal("Null MySQLAdaptor, terminating orthoinference");
@@ -91,82 +93,102 @@ public static void inferEvents(Properties props, String species) throws Exceptio
 		JSONObject jsonObject = (JSONObject) obj;
 
 		// Parse Species information (found in Species.json config file)
-		JSONObject speciesObject = (JSONObject) jsonObject.get(species);
-		JSONArray speciesNames = (JSONArray) speciesObject.get("name");
-		String speciesName = (String) speciesNames.get(0);
-		logger.info("Beginning orthoinference of " + speciesName);
+		JSONObject targetSpeciesObject = (JSONObject) jsonObject.get(targetSpecies);
+		JSONArray targetSpeciesNames = (JSONArray) targetSpeciesObject.get("name");
+		String targetSpeciesName = (String) targetSpeciesNames.get(0);
 
-		JSONObject refDb = (JSONObject) speciesObject.get("refdb");
-		String refDbUrl = (String) refDb.get("url");
-		String refDbProteinUrl = (String) refDb.get("access");
-		String refDbGeneUrl = (String) refDb.get("ensg_access");
+		JSONObject referenceSpeciesObject = (JSONObject) jsonObject.get(referenceSpecies);
+		JSONArray referenceSpeciesNames = (JSONArray) referenceSpeciesObject.get("name");
+		String referenceSpeciesName = (String) referenceSpeciesNames.get(0);
+
+		logger.info("Beginning orthoinference of " + targetSpeciesName);
+		JSONObject targetSpeciesRefDb = (JSONObject) targetSpeciesObject.get("refdb");
+//		String refDbUrl = (String) refDb.get("url");
+//		String refDbProteinUrl = (String) refDb.get("access");
+//		String refDbGeneUrl = (String) refDb.get("ensg_access");
 
 		// Creates two files that a) list reactions that are eligible for inference and b) those that are successfully inferred
-		String eligibleFilename = "eligible_" + species	+ "_75.txt";
-		String inferredFilename = "inferred_" + species + "_75.txt";
+		String eligibleFilename = "eligible_" + targetSpecies	+ "_75.txt";
+		String inferredFilename = "inferred_" + targetSpecies + "_75.txt";
 		createNewFile(eligibleFilename);
 		createNewFile(inferredFilename);
 		ReactionInferrer.setEligibleFilename(eligibleFilename);
 		ReactionInferrer.setInferredFilename(inferredFilename);
 
-		stableIdentifierGenerator = new StableIdentifierGenerator(dbAdaptor, (String) speciesObject.get("abbreviation"));
+		stableIdentifierGenerator = new StableIdentifierGenerator(dbAdaptor, (String) targetSpeciesObject.get("abbreviation"));
 		// Set static variables (DB/Species Instances, mapping files) that will be repeatedly used
 		setInstanceEdits(personId);
 		try {
-			readAndSetHomologueMappingFile(species, "hsap", pathToOrthopairs);
-			readAndSetGeneNameMappingFile(species, pathToOrthopairs);
+			readAndSetHomologueMappingFile(targetSpecies, referenceSpecies, pathToOrthopairs);
+//			readAndSetGeneNameMappingFile(targetSpecies, pathToOrthopairs);
 		} catch (Exception e) {
-			logger.fatal("Unable to locate " + speciesName +" mapping file: hsap_" + species + "_mapping.tsv. Orthology prediction not possible.");
+			logger.fatal("Unable to locate " + targetSpeciesName +" mapping file: hsap_" + targetSpecies + "_mapping.tsv. Orthology prediction not possible.");
 			e.printStackTrace();
 			System.exit(1);
 		}
-		EWASInferrer.readENSGMappingFile(species, pathToOrthopairs);
-		EWASInferrer.fetchAndSetUniprotDbInstance();
-		EWASInferrer.createEnsemblProteinDbInstance(speciesName, refDbUrl, refDbProteinUrl);
-		EWASInferrer.createEnsemblGeneDBInstance(speciesName, refDbUrl, refDbGeneUrl);
+		try {
+			EWASInferrer.readAndSetCoordinateMappingFile(targetSpecies);
+		} catch (Exception e) {
+			logger.fatal("Unable to locate coordinate mapping file");
+			e.printStackTrace();
+			System.exit(1);
+		}
+//		EWASInferrer.readENSGMappingFile(targetSpecies, pathToOrthopairs);
+		EWASInferrer.fetchAndSetDbInstances();
+//		EWASInferrer.createEnsemblProteinDbInstance(speciesName, refDbUrl, refDbProteinUrl);
+//		EWASInferrer.createEnsemblGeneDBInstance(speciesName, refDbUrl, refDbGeneUrl);
 
-		JSONObject altRefDbJSON = (JSONObject) speciesObject.get("alt_refdb");
+		JSONObject altRefDbJSON = (JSONObject) targetSpeciesObject.get("alt_refdb");
 		if (altRefDbJSON != null)
 		{
-			logger.info("Alternate DB exists for " + speciesName);
+			logger.info("Alternate DB exists for " + targetSpeciesName);
 			EWASInferrer.createAlternateReferenceDBInstance(altRefDbJSON);
 		} else {
 			EWASInferrer.setAltRefDbToFalse();
 		}
-		createAndSetSpeciesInstance(speciesName);
-		setSummationInstance();
+		createAndSetSpeciesInstance(targetSpeciesName);
+//		setSummationInstance();
 		setEvidenceTypeInstance();
-		OrthologousEntityGenerator.setComplexSummationInstance();
+		InstanceUtilities.setDiseaseInstance(dbAdaptor.fetchInstance(9683915L));
+//		OrthologousEntityGenerator.setComplexSummationInstance();
 
 /**
- *  Start of ReactionlikeEvent inference. Retrieves all human ReactionlikeEvents, and attempts to infer each for the species.
+ *  Start of ReactionlikeEvent inference. Retrieves all human ReactionlikeEvents, and attempts to infer each for the targetSpecies.
  */
-		// Gets DB instance of source species (human)
-		Collection<GKInstance> sourceSpeciesInst = (Collection<GKInstance>) dbAdaptor.fetchInstanceByAttribute("Species", "name", "=", "Homo sapiens");
-		if (sourceSpeciesInst.isEmpty())
+		// Gets DB instance of source targetSpecies (human)
+		Collection<GKInstance> referenceSpeciesInst = (Collection<GKInstance>) dbAdaptor.fetchInstanceByAttribute("Species", "name", "=", referenceSpeciesName);
+		if (referenceSpeciesInst.isEmpty())
 		{
-			logger.fatal("Could not find Species instance for Homo sapiens");
+			logger.fatal("Could not find Species instance for " + referenceSpeciesName);
 			System.exit(1);
 		}
-		long humanInstanceDbId = sourceSpeciesInst.iterator().next().getDBID();
-		orthologousPathwayDiagramGenerator = new OrthologousPathwayDiagramGenerator(dbAdaptor, dbAdaptorPrev, speciesInst, personId, humanInstanceDbId);
-		// Gets Reaction instances of source species (human)
-		Collection<GKInstance> reactionInstances = (Collection<GKInstance>) dbAdaptor.fetchInstanceByAttribute("ReactionlikeEvent", "species", "=", humanInstanceDbId);
-
+		long referenceSpeciesInstanceDbId = referenceSpeciesInst.iterator().next().getDBID();
+		orthologousPathwayDiagramGenerator = new OrthologousPathwayDiagramGenerator(dbAdaptor, dbAdaptorPrev, speciesInst, personId, referenceSpeciesInstanceDbId);
+		// Gets Reaction instances of source targetSpecies (human)
+		Collection<GKInstance> reactionInstances = new ArrayList<>(); //
+		if (referenceSpeciesName.equals("Human SARS coronavirus")) {
+			GKInstance covPathwayInst = dbAdaptor.fetchInstance(sarsCOV1InfectionsPathwayDbId);
+			Set<GKInstance> uniqueReactionInstances = new HashSet<>();
+			for (GKInstance hasEventInst : (Collection<GKInstance>) covPathwayInst.getAttributeValuesList(hasEvent)) {
+				uniqueReactionInstances.addAll(getReactionsInEventHierarchy(hasEventInst));
+			}
+			reactionInstances.addAll(uniqueReactionInstances);
+		} else {
+			reactionInstances = (Collection<GKInstance>) dbAdaptor.fetchInstanceByAttribute(ReactionlikeEvent, species, "=", referenceSpeciesInstanceDbId);
+		}
 		List<Long> dbids = new ArrayList<>();
 		Map<Long, GKInstance> reactionMap = new HashMap<>();
 		for (GKInstance reactionInst : reactionInstances) {
 			dbids.add(reactionInst.getDBID());
 			reactionMap.put(reactionInst.getDBID(), reactionInst);
 		}
 		Collections.sort(dbids);
-
-		logger.info(sourceSpeciesInst.iterator().next().getDisplayName() + " ReactionlikeEvent instances: " + dbids.size());
+		logger.info(referenceSpeciesInst.iterator().next().getDisplayName() + " ReactionlikeEvent instances: " + dbids.size());
 		for (Long dbid : dbids)
 		{
 			GKInstance reactionInst = reactionMap.get(dbid);
 			logger.info("Attempting RlE inference: " + reactionInst);
-			// Check if the current Reaction already exists for this species, that it is a valid instance (passes some filters), and that it doesn't have a Disease attribute.
+			// Check if the current Reaction already exists for this targetSpecies, that it is a valid instance (passes some filters), and that it doesn't have a Disease attribute.
 			// Adds to manualHumanEvents array if it passes conditions. This code block allows you to re-run the code without re-inferring instances.
 			List<GKInstance> previouslyInferredInstances = new ArrayList<GKInstance>();
 			previouslyInferredInstances = checkIfPreviouslyInferred(reactionInst, orthologousEvent, previouslyInferredInstances);
@@ -185,7 +207,7 @@ public static void inferEvents(Properties props, String species) throws Exceptio
 				continue;
 			}
 
-			// An inferred ReactionlikeEvent doesn't already exist for this species, and an orthologous inference will be attempted.
+			// An inferred ReactionlikeEvent doesn't already exist for this targetSpecies, and an orthologous inference will be attempted.
 			try {
 				ReactionInferrer.inferReaction(reactionInst);
 				logger.info("Successfully inferred " + reactionInst);
@@ -194,11 +216,58 @@ public static void inferEvents(Properties props, String species) throws Exceptio
 				System.exit(1);
 			}
 		}
+
+		// Outputs a file that contains all EWAS' that were inferred and their contained hasModifiedResidues.
+//		Map<GKInstance, List<GKInstance>> modifiedResiduesMapping = EWASInferrer.getModifiedResiduesMapping();
+//		String header = "COV-1 EWAS\tCOV-1 ModifiedResidues\n";
+//		Files.write(Paths.get("EWAS-ModifiedResidues-Mappings.tsv"), header.getBytes(), StandardOpenOption.CREATE, StandardOpenOption.APPEND);
+//		for (GKInstance ewasInst : modifiedResiduesMapping.keySet()) {
+//			String outputLine = ewasInst + "\t";
+//			List<GKInstance> modifiedResidues = modifiedResiduesMapping.get(ewasInst);
+//			int count = 0;
+//			for (GKInstance modifiedResidueInst : modifiedResidues) {
+//				if (count != 0) {
+//					outputLine += "|" + modifiedResidueInst;
+//				} else {
+//					outputLine += modifiedResidueInst;
+//					count++;
+//				}
+//			}
+//			outputLine += "\n";
+//			Files.write(Paths.get("EWAS-ModifiedResidues-Mappings.tsv"), outputLine.getBytes(), StandardOpenOption.CREATE, StandardOpenOption.APPEND);
+//		}
+
 		PathwaysInferrer.setInferredEvent(ReactionInferrer.getInferredEvent());
 		PathwaysInferrer.inferPathways(ReactionInferrer.getInferrableHumanEvents());
 		orthologousPathwayDiagramGenerator.generateOrthologousPathwayDiagrams();
-		outputReport(species);
-		logger.info("Finished orthoinference of " + speciesName);
+		outputReport(targetSpecies);
+		logger.info("Finished orthoinference of " + targetSpeciesName);
+
+		System.out.println(dbAdaptor.fetchMaxDbId());
+
+		// Find inferred instances that are referred to by multiple curated instances
+		// Likely due to lack of distinguishing 'defining' attributes.
+//		Collection<GKInstance> inferredInstances = dbAdaptor.fetchInstancesByClass(Event);
+//		inferredInstances.addAll(dbAdaptor.fetchInstancesByClass(PhysicalEntity));
+//		for (GKInstance inferredInst : inferredInstances) {
+//			GKInstance createdInst = (GKInstance) inferredInst.getAttributeValue(created);
+//			Collection<GKInstance> inferredFromInstances = inferredInst.getAttributeValuesList(inferredFrom);
+//			if (createdInst != null && createdInst.getDisplayName().contains("Justin") && inferredFromInstances.size() > 1) {
+//				System.out.println(inferredInst);
+//			}
+//		}
+	}
+
+	private static Set<GKInstance> getReactionsInEventHierarchy(GKInstance eventInst) throws Exception {
+		Set<GKInstance> reactionInstances = new HashSet<>();
+		if (eventInst.getSchemClass().isa(ReactionlikeEvent)) {
+			reactionInstances.add(eventInst);
+		} else {
+			for (GKInstance hasEventInst : (Collection<GKInstance>) eventInst.getAttributeValuesList(hasEvent)) {
+				reactionInstances.addAll(getReactionsInEventHierarchy(hasEventInst));
+			}
+		}
+		return reactionInstances;
 	}
 
 	/**