Release 2.24.0

Merge pull request #345 from qbicsoftware/development

README.md

@@ -107,6 +107,10 @@ A more recent model, which places two of the configuration files into a subfolde
 
 ![Nanopore Data Structure Model v2](./doc/figures/Nanopore_Data_Structure_Model_v2.svg)
 
+V4 outlines a model in which a second higher-accuracy basecalling was performed after the initial basecalling
+
+![Nanopore Data Structure Model v4](./doc/figures/Nanopore_Data_Structure_Model_v4.svg)
+
 #### Nanopore usage example
 
 For usage examples, see the [usage documentation](./doc/examples.md).

pom.xml

@@ -7,7 +7,7 @@
 
   <groupId>life.qbic</groupId>
   <artifactId>data-model-lib</artifactId>
-  <version>2.23.0</version>
+  <version>2.24.0-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>

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

@@ -40,7 +40,9 @@ final class OxfordNanoporeExperiment implements ExperimentFolder {
             FQDN_FILES + ".BarcodeAlignmentLog",
             FQDN_FILES + ".PoreActivityLog",
             FQDN_FILES + ".SampleSheetLog",
-            FQDN_FILES + ".PoreScanDataLog"
+            FQDN_FILES + ".PoreScanDataLog",
+            FQDN_FILES + ".SequencingTelemetryLog",
+            FQDN_FILES + ".GuppyBasecallLog"
     ]
 
     private final static Set nanoporeFolderTypes = [
@@ -52,7 +54,8 @@ final class OxfordNanoporeExperiment implements ExperimentFolder {
             FQDN_FOLDERS + ".FastQFailFolder",
             FQDN_FOLDERS + ".UnclassifiedFast5Folder",
             FQDN_FOLDERS + ".UnclassifiedFastQFolder",
-            FQDN_FOLDERS + ".OtherReportsFolder"
+            FQDN_FOLDERS + ".OtherReportsFolder",
+            FQDN_FOLDERS + ".BasecallingFolder"
     ]
 
     private OxfordNanoporeExperiment(String sampleId, List<OxfordNanoporeMeasurement> measurements) {

src/main/groovy/life/qbic/datamodel/datasets/datastructure/files/nanopore/GuppyBasecallLog.groovy

@@ -0,0 +1,30 @@
+package life.qbic.datamodel.datasets.datastructure.files.nanopore
+
+import life.qbic.datamodel.datasets.datastructure.files.DataFile
+
+/**
+ * A specialisation of a DataFile, represents an Oxford Nanopore guppy basecalling client log file
+ */
+class GuppyBasecallLog extends DataFile {
+
+    final private static String FILE_TYPE = "log"
+
+    final private static String NAME_SCHEMA = $/guppy_basecall_client_log-.*/$
+
+    protected GuppyBasecallLog() {}
+
+    protected GuppyBasecallLog(String name, String relativePath) {
+        super(name, relativePath, FILE_TYPE)
+        validateName()
+    }
+
+    static GuppyBasecallLog create(String name, String relativePath) {
+        return new GuppyBasecallLog(name, relativePath)
+    }
+
+    private void validateName() {
+        if (!(this.name =~ NAME_SCHEMA)) {
+            throw new IllegalArgumentException("Name must match the Nanopore guppy basecall client log schema!")
+        }
+    }
+}

src/main/groovy/life/qbic/datamodel/datasets/datastructure/files/nanopore/SequencingTelemetryLog.groovy

@@ -0,0 +1,32 @@
+package life.qbic.datamodel.datasets.datastructure.files.nanopore
+
+import life.qbic.datamodel.datasets.datastructure.files.DataFile
+
+/**
+ *  A specialisation of a DataFile, represents an Oxford Nanopore sequencing telemetry log file
+ *
+ */
+class SequencingTelemetryLog extends DataFile {
+
+    final private static String FILE_TYPE = "js"
+
+    final private static String NAME_SCHEMA = $/sequencing_telemetry_.*/$
+
+    protected SequencingTelemetryLog() {}
+
+    protected SequencingTelemetryLog(String name, String relativePath) {
+        super(name, relativePath, FILE_TYPE)
+        validateName()
+    }
+
+    static SequencingTelemetryLog create(String name, String relativePath) {
+        return new SequencingTelemetryLog(name, relativePath)
+    }
+
+    private void validateName() {
+        if (!(this.name =~ NAME_SCHEMA)) {
+            throw new IllegalArgumentException("Name must match the Nanopore sequencing telemetry log name schema!")
+        }
+    }
+
+}

src/main/groovy/life/qbic/datamodel/datasets/datastructure/folders/nanopore/BasecallingFolder.groovy

@@ -0,0 +1,42 @@
+package life.qbic.datamodel.datasets.datastructure.folders.nanopore
+
+import life.qbic.datamodel.datasets.datastructure.folders.DataFolder
+
+/**
+ * <class short description - One Line!>
+ *
+ * <More detailed description - When to use, what it solves, etc.>
+ *
+ * @since <version tag>
+ *
+ */
+class BasecallingFolder extends DataFolder {
+  /**
+   * The name schema of a basecalling folder contained within the nanopore dataset.
+   *
+   */
+  final private static String NAME_SCHEMA = /basecalling/
+
+  protected BasecallingFolder() {}
+
+  protected BasecallingFolder(String name, String relativePath, List children) {
+    super(name, relativePath, children)
+    validateName()
+  }
+
+  /**
+   * Creates a new instance of a BasecallingFolder object
+   * @param relativePath The relative path of the folder
+   * @param children A list with child elements of unknown type of the folder
+   * @return A new instance of a BasecallingFolder object
+   */
+  static BasecallingFolder create(String name, String relativePath, List<?> children) {
+    new BasecallingFolder(name, relativePath, children)
+  }
+
+  private void validateName() {
+    if (!(this.name =~ NAME_SCHEMA)) {
+      throw new IllegalArgumentException("Name must match the Nanopore Basecalling schema!")
+    }
+  }
+}

src/main/groovy/life/qbic/datamodel/instruments/OxfordNanoporeInstrumentOutputV4.groovy

@@ -0,0 +1,22 @@
+package life.qbic.datamodel.instruments
+
+
+/**
+ * Represents the Nanopore instrument output data structure schema.
+ *
+ * The original schema is defined in as resource and is
+ * referenced here, wrapped in a Groovy class for reference
+ * in applications that want to validate the instrument
+ * output structure against the schema.
+ *
+ * @author Steffen Greiner
+ * @since 1.9.0
+ */
+class OxfordNanoporeInstrumentOutputV4 {
+
+  private static final String SCHEMA_PATH = "/schemas/nanopore-instrument-output_v4.schema.json"
+
+  static InputStream getSchemaAsStream() {
+    return OxfordNanoporeInstrumentOutputV4.getResourceAsStream(SCHEMA_PATH)
+  }
+}

src/main/resources/schemas/nanopore-instrument-output.schema.json

@@ -2,7 +2,7 @@
   "$schema": "http://json-schema.org/draft-07/schema",
   "$id": "http://qbic.life/nanopore-instrument-output.schema.json",
   "title": "Nanopore Instrument Output",
-  "description": "Describes in which form Nanopore data is received from the lab.",
+  "description": "Describes in which form PromethION/MinION sequenced Nanopore is received from the Microbiology lab.",
   "definitions": {
     "folder": {
       "description": "Describes a folder",

src/main/resources/schemas/nanopore-instrument-output_v2.schema.json

@@ -2,7 +2,7 @@
   "$schema": "http://json-schema.org/draft-07/schema",
   "$id": "http://qbic.life/nanopore-instrument-output_v2.schema.json",
   "title": "Nanopore Instrument Output V2",
-  "description": "Describes in which form Nanopore data is received from the lab.",
+  "description": "Describes in which form PromethION/MinION sequenced Nanopore data is received from the medical genetics lab. Accounts for 'other reports' folder created by the lab",
   "definitions": {
     "folder": {
       "description": "Describes a folder",

src/main/resources/schemas/nanopore-instrument-output_v3.schema.json

@@ -2,7 +2,7 @@
   "$schema": "http://json-schema.org/draft-07/schema",
   "$id": "http://qbic.life/nanopore-instrument-output_v3.schema.json",
   "title": "Nanopore Instrument Output V3",
-  "description": "Describes in which form Nanopore data is received from the lab.",
+  "description": "Describes in which form PromethION/MinION sequenced Nanopore data is received from the medical genetics lab. Accounts for the adapted 'other_reports' folder structure provided by the lab",
   "definitions": {
     "folder": {
       "description": "Describes a folder",