Merge pull request #320 from qbicsoftware/development

Prepare version 2.19.0

Author: wow-such-code

doc/figures/MaxQuant_Data_Structure.png

@@ -7,7 +7,7 @@
 
   <groupId>life.qbic</groupId>
   <artifactId>data-model-lib</artifactId>
-  <version>2.18.0</version>
+  <version>2.19.0-SNAPSHOT</version>
   <name>data-model-lib</name>
   <url>http://github.com/qbicsoftware/data-model-lib</url>
   <description>Data models. A collection of QBiC's central data models and DTOs. </description>

pom.xml

@@ -29,19 +29,18 @@ final class MaxQuantRunResult {
     private final static Set maxQuantFileTypes = [
             FQDN_FILES + ".AllPeptides",
             FQDN_FILES + ".Evidence",
-            FQDN_FILES + ".ExperimentalDesignTemplate",
             FQDN_FILES + ".Parameters",
             FQDN_FILES + ".Peptides",
             FQDN_FILES + ".ProteinGroups",
             FQDN_FILES + ".RunParameters",
             GENERAL_FILES + ".SampleIds",
-            FQDN_FILES + ".Summary"
     ]
 
     private final AllPeptides allPeptides
 
     private final Evidence evidence
 
+    @Deprecated
     private final ExperimentalDesignTemplate experimentalDesignTemplate
 
     private final Parameters parameters
@@ -54,8 +53,10 @@ final class MaxQuantRunResult {
 
     private final SampleIds sampleIds
 
+    @Deprecated
     private final Summary summary
 
+    @Deprecated
     MaxQuantRunResult(AllPeptides allPeptides, Evidence evidence, ExperimentalDesignTemplate experimentalDesignTemplate, Parameters parameters, Peptides peptides, ProteinGroups proteinGroups, RunParameters runParameters, SampleIds sampleIds, Summary summary) {
         this.allPeptides = Objects.requireNonNull(allPeptides, "allPeptides must not be null.")
         this.evidence = Objects.requireNonNull(evidence, "evidence must not be null.")
@@ -68,9 +69,19 @@ final class MaxQuantRunResult {
         this.summary = Objects.requireNonNull(summary, "summary must not be null.")
     }
 
+    MaxQuantRunResult(AllPeptides allPeptides, Evidence evidence, Parameters parameters, Peptides peptides, ProteinGroups proteinGroups, RunParameters runParameters, SampleIds sampleIds) {
+        this.allPeptides = Objects.requireNonNull(allPeptides, "allPeptides must not be null.")
+        this.evidence = Objects.requireNonNull(evidence, "evidence must not be null.")
+        this.parameters = Objects.requireNonNull(parameters, "parameters must not be null.")
+        this.peptides = Objects.requireNonNull(peptides, "peptides must not be null.")
+        this.proteinGroups = Objects.requireNonNull(proteinGroups, "proteinGroups must not be null.")
+        this.runParameters = Objects.requireNonNull(runParameters, "runParameters must not be null.")
+        this.sampleIds = Objects.requireNonNull(sampleIds, "sampleIds must not be null.")
+    }
+
     /**
-     * Static factory method that creates a new maxQuantRunResult instance from the bioinformatic pipeline output.
-     * See this @{link <a href="https://github.com/qbicsoftware/data-model-lib/blob/master/src/test/resources/examples/resultset/maxquant/valid-resultset-example.json">example</a>}
+     * Static factory method that creates a new maxQuantRunResult instance from the MaxQuant output.
+     * See this @{link <a href="https://github.com/qbicsoftware/data-model-lib/blob/master/src/test/resources/examples/resultset/maxquant/valid-resultset-example_latest.json">example</a>}
      * for a JSON representation of a valid map structure
      *
      * @param Map maxQuantRunOutput
@@ -82,27 +93,23 @@ final class MaxQuantRunResult {
         //Check if the required folders are in the root directory
         Objects.requireNonNull(maxQuantRunOutput.get("allPeptides"), "The provided directory must contain a allPeptides.txt file.")
         Objects.requireNonNull(maxQuantRunOutput.get("evidence"), "The provided directory must contain a evidence.txt file.")
-        Objects.requireNonNull(maxQuantRunOutput.get("experimentalDesignTemplate"), "The provided directory must contain a experimentalDesignTemplate.txt file.")
         Objects.requireNonNull(maxQuantRunOutput.get("parameters"), "The provided directory must contain a parameters.txt file.")
         Objects.requireNonNull(maxQuantRunOutput.get("peptides"), "The provided directory must contain a peptides.txt file.")
         Objects.requireNonNull(maxQuantRunOutput.get("proteinGroups"), "The provided directory must contain a proteinGroups.txt file.")
         Objects.requireNonNull(maxQuantRunOutput.get("runParameters"), "The provided director must contain a runParameters.xml file.")
         Objects.requireNonNull(maxQuantRunOutput.get("sampleIds"), "The provided directory must contain a sampleIds.txt file.")
-        Objects.requireNonNull(maxQuantRunOutput.get("summary"), "The provided directory must contain a summary.pdf file.")
 
         //Get Files from Root Directory
         AllPeptides allPeptides = parseFile(maxQuantRunOutput.get("allPeptides") as Map) as AllPeptides
         Evidence evidence  = parseFile(maxQuantRunOutput.get("evidence") as Map) as Evidence
-        ExperimentalDesignTemplate experimentalDesignTemplate = parseFile(maxQuantRunOutput.get("experimentalDesignTemplate") as Map) as ExperimentalDesignTemplate
         Parameters parameters = parseFile(maxQuantRunOutput.get("parameters") as Map) as Parameters
         Peptides peptides = parseFile(maxQuantRunOutput.get("peptides") as Map) as Peptides
         ProteinGroups proteinGroups = parseFile(maxQuantRunOutput.get("proteinGroups") as Map) as ProteinGroups
         RunParameters runParameters = parseFile(maxQuantRunOutput.get("runParameters") as Map) as RunParameters
         SampleIds sampleIds = parseFile(maxQuantRunOutput.get("sampleIds") as Map) as SampleIds
-        Summary summary = parseFile(maxQuantRunOutput.get("summary") as Map) as Summary
 
         //Create new MaxQuantRunResult object with parsed information
-        return new MaxQuantRunResult(allPeptides, evidence, experimentalDesignTemplate, parameters, peptides, proteinGroups, runParameters, sampleIds, summary)
+        return new MaxQuantRunResult(allPeptides, evidence, parameters, peptides, proteinGroups, runParameters, sampleIds)
     }
 
     /**
@@ -128,6 +135,7 @@ final class MaxQuantRunResult {
      * @return an ExperimentalDesignTemplate file generated by MaxQuant
      * @since 2.10.0
      */
+    @Deprecated
     ExperimentalDesignTemplate getExperimentalDesignTemplate() {
         return experimentalDesignTemplate
     }
@@ -182,6 +190,7 @@ final class MaxQuantRunResult {
      * @return a Summary file generated by MaxQuant
      * @since 2.10.0
      */
+    @Deprecated
     Summary getSummary() {
         return summary
     }

src/main/groovy/life/qbic/datamodel/datasets/MaxQuantRunResult.groovy

@@ -115,7 +115,7 @@
         {
           "properties": {
             "name": {
-              "pattern": "sample_ids"
+              "pattern": "Q\\w{4}_sample_ids"
             },
             "fileType": {
               "pattern": "txt"
@@ -143,23 +143,19 @@
   "properties": {
     "allPeptides": {"$ref": "#/definitions/allPeptides"},
     "evidence": {"$ref":  "#/definitions/evidence"},
-    "experimentalDesignTemplate": {"$ref":  "#/definitions/experimentalDesignTemplate"},
     "parameters": {"$ref":  "#/definitions/parameters"},
     "peptides": {"$ref":  "#/definitions/peptides"},
     "proteinGroups": {"$ref":  "#/definitions/proteinGroups"},
     "runParameters": {"$ref":  "#/definitions/runParameters"},
     "sampleIds": {"$ref":  "#/definitions/sampleIds"},
-    "summary": {"$ref":  "#/definitions/summary"}
   },
   "required": [
     "allPeptides",
     "evidence",
-    "experimentalDesignTemplate",
     "parameters",
     "peptides",
     "proteinGroups",
     "runParameters",
-    "sampleIds",
-    "summary"
+    "sampleIds"
   ]
 }

src/main/resources/schemas/maxquant-result-set.schema.json

@@ -31,11 +31,11 @@ class MaxQuantRunResultSpec extends Specification {
     Map invalidDataStructure
 
     def setupSpec() {
-        InputStream validStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("examples/resultset/maxquant/valid-resultset-example.json")
+        InputStream validStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("examples/resultset/maxquant/valid-resultset-example_latest.json")
         validDataStructure = (Map) new JsonSlurper().parse(validStream)
         validStream.close()
 
-        InputStream invalidStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("examples/resultset/maxquant/invalid-resultset-example.json")
+        InputStream invalidStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("examples/resultset/maxquant/no-sampleid-resultset-example.json")
         invalidDataStructure = (Map) new JsonSlurper().parse(invalidStream)
         invalidStream.close()
     }
@@ -48,24 +48,20 @@ class MaxQuantRunResultSpec extends Specification {
         final MaxQuantRunResult maxQuantRunResult = MaxQuantRunResult.createFrom(validExample)
         AllPeptides allPeptides = maxQuantRunResult.allPeptides
         Evidence evidence = maxQuantRunResult.evidence
-        ExperimentalDesignTemplate experimentalDesignTemplate = maxQuantRunResult.experimentalDesignTemplate
         Parameters parameters = maxQuantRunResult.parameters
         Peptides peptides = maxQuantRunResult.peptides
         ProteinGroups proteinGroups = maxQuantRunResult.proteinGroups
         RunParameters runParameters = maxQuantRunResult.runParameters
         SampleIds sampleIds = maxQuantRunResult.sampleIds
-        Summary summary = maxQuantRunResult.summary
         then:
 
         allPeptides.name == "allPeptides.txt"
         evidence.name == "evidence.txt"
-        experimentalDesignTemplate.name == "experimentalDesignTemplate.txt"
         parameters.name == "parameters.txt"
         peptides.name == "peptides.txt"
         proteinGroups.name == "proteinGroups.txt"
         runParameters.name == "mqpar.xml"
-        sampleIds.name == "sample_ids.txt"
-        summary.name == "summary_1234.pdf"
+        sampleIds.name == "Q0010_sample_ids.txt"
     }
 
     def "Invalid fileTree will return a NullPointerException"() {

src/test/groovy/life/qbic/datamodel/datasets/datastructure/MaxQuantRunResultSpec.groovy

@@ -1,5 +1,6 @@
 package life.qbic.datamodel.maxquant
 
+import groovy.json.JsonSlurper
 import org.everit.json.schema.Schema
 import org.everit.json.schema.ValidationException
 import org.everit.json.schema.loader.SchemaClient
@@ -35,7 +36,7 @@ class MaxQuantOutputSpec extends Specification {
 
         and:
         String validMaxQuantOutput = this.class.getClassLoader()
-                .getResourceAsStream("examples/resultset/maxquant/valid-resultset-example.json")
+                .getResourceAsStream("examples/resultset/maxquant/valid-resultset-example_latest.json")
                 .text
 
         and:
@@ -101,4 +102,52 @@ class MaxQuantOutputSpec extends Specification {
         then:
         thrown(ValidationException)
     }
+
+    def "Validating the outdated schema v2 shall raise a validation exception"() {
+        given:
+        def stream = MaxQuantOutput.getSchemaAsStream()
+
+        and:
+        String wrongMaxQuantOutput = this.class.getClassLoader()
+                .getResourceAsStream("examples/resultset/maxquant/old_valid-resultset-example.json")
+                .text
+
+        and:
+        SchemaLoader schemaLoader = SchemaLoader.builder()
+                .schemaClient(SchemaClient.classPathAwareClient())
+                .schemaJson(new JSONObject(new JSONTokener(stream)))
+                .resolutionScope("classpath://schemas/")
+                .build()
+        Schema schema = schemaLoader.load().build()
+
+        when:
+        schema.validate(new JSONObject(wrongMaxQuantOutput))
+
+        then:
+        thrown(ValidationException)
+    }
+
+    def "An invalid project code in the sample ids file shall raise a validation exception"() {
+        given:
+        def stream = MaxQuantOutput.getSchemaAsStream()
+
+        and:
+        String missingMaxQuantOutput = this.class.getClassLoader()
+                .getResourceAsStream("examples/resultset/maxquant/invalid-project-resultset-example.json")
+                .text
+
+        and:
+        SchemaLoader schemaLoader = SchemaLoader.builder()
+                .schemaClient(SchemaClient.classPathAwareClient())
+                .schemaJson(new JSONObject(new JSONTokener(stream)))
+                .resolutionScope("classpath://schemas/")
+                .build()
+        Schema schema = schemaLoader.load().build()
+
+        when:
+        schema.validate(new JSONObject(missingMaxQuantOutput))
+
+        then:
+        thrown(ValidationException)
+    }
 }

src/test/groovy/life/qbic/datamodel/maxquant/MaxQuantOutputSpec.groovy

@@ -0,0 +1,37 @@
+{
+  "allPeptides": {
+    "name": "allPeptides.txt",
+    "fileType": "txt",
+    "path": "./txt/allPeptides.txt"
+  },
+  "evidence": {
+    "name": "evidence.txt",
+    "fileType": "txt",
+    "path": "./txt/evidence.txt"
+  },
+    "parameters": {
+      "name": "parameters.txt",
+      "fileType": "txt",
+      "path": "./txt/parameters.txt"
+    },
+    "peptides": {
+      "name": "peptides.txt",
+      "fileType": "txt",
+      "path": "./txt/peptides.txt"
+    },
+    "proteinGroups": {
+      "name": "proteinGroups.txt",
+      "fileType": "txt",
+      "path": "./txt/proteinGroups.txt"
+    },
+    "runParameters": {
+      "name": "mqpar.xml",
+      "fileType": "xml",
+      "path": "./mqpar.xml"
+    },
+    "sampleIds": {
+      "name": "0010_sample_ids.txt",
+      "fileType": "txt",
+      "path": "./0010_sample_ids.txt"
+  }
+}

src/test/resources/examples/resultset/maxquant/invalid-project-resultset-example.json

@@ -0,0 +1,37 @@
+{
+  "allPeptides": {
+    "name": "allPeptides.txt",
+    "fileType": "txt",
+    "path": "./txt/allPeptides.txt"
+  },
+  "evidence": {
+    "name": "evidence.txt",
+    "fileType": "txt",
+    "path": "./txt/evidence.txt"
+  },
+    "parameters": {
+      "name": "parameters.txt",
+      "fileType": "txt",
+      "path": "./txt/parameters.txt"
+    },
+    "peptides": {
+      "name": "peptides.txt",
+      "fileType": "txt",
+      "path": "./txt/peptides.txt"
+    },
+    "proteinGroups": {
+      "name": "proteinGroups.txt",
+      "fileType": "txt",
+      "path": "./txt/proteinGroups.txt"
+    },
+    "runParameters": {
+      "name": "mqpar.xml",
+      "fileType": "xml",
+      "path": "./mqpar.xml"
+    },
+    "sampleIds": {
+      "name": "Q0010_sample_ids.txt",
+      "fileType": "txt",
+      "path": "./Q0010_sample_ids.txt"
+  }
+}