added SampleClass for NMR and targeted

phenomecentre · Mar 7, 2024 · bdf8192 · bdf8192
1 parent 4068f23
commit bdf8192
Show file tree

Hide file tree

Showing 3 changed files with 23 additions and 1 deletion.
diff --git a/nPYc/objects/_msDataset.py b/nPYc/objects/_msDataset.py
@@ -1350,7 +1350,7 @@ def _getSampleMetadataFromFilename(self, filenameSpec):
 		fileNameParts.loc[
 			fileNameParts['groupingKind'].str.match('E?IC', na=False).astype(bool), 'SampleType'] = SampleType.StudyPool
 
-		# Standardised NPC types based on SampleType/AssayRole combinations
+		# Define `SampleClass` - standardised NPC types based on SampleType/AssayRole combinations
 		fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.StudySample) & (
 					fileNameParts['AssayRole'] == AssayRole.Assay), 'SampleClass'] = 'Study Sample'
 		fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.StudyPool) & (

diff --git a/nPYc/objects/_nmrDataset.py b/nPYc/objects/_nmrDataset.py
@@ -90,6 +90,7 @@ def __init__(self, datapath, fileType='Bruker', pulseProgram='noesygppr1d', sop=
 
 			self.sampleMetadata['AssayRole'] = None
 			self.sampleMetadata['SampleType'] = None
+			self.sampleMetadata['SampleClass'] = None
 			self.sampleMetadata['Dilution'] = 100
 			self.sampleMetadata['Batch'] = numpy.nan
 			self.sampleMetadata['Correction Batch'] = numpy.nan
@@ -184,6 +185,11 @@ def _matchDatasetToLIMS(self, pathToLIMSfile):
 		self.sampleMetadata.loc[self.sampleMetadata.loc[:, 'Status'].str.match('Study Reference', na=False).astype(bool), 'SampleType'] = SampleType.StudyPool
 		self.sampleMetadata.loc[self.sampleMetadata.loc[:, 'Status'].str.match('Long Term Reference', na=False).astype(bool), 'SampleType'] = SampleType.ExternalReference
 
+		# Define `SampleClass` - standardised NPC types based on SampleType/AssayRole combinations
+		self.sampleMetadata.loc[:,'SampleClass'] = 'Study Sample'
+		self.sampleMetadata.loc[self.sampleMetadata.loc[:, 'Status'].str.match('Study Reference', na=False).astype(bool), 'SampleClass'] = 'Study Reference'
+		self.sampleMetadata.loc[self.sampleMetadata.loc[:, 'Status'].str.match('Long Term Reference', na=False).astype(bool), 'AssayRole'] = 'Long-Term Reference'
+
 		# Update Sampling ID values using new 'SampleType', special case for Study Pool, External Reference and Procedural Blank
 		self.sampleMetadata.loc[(((self.sampleMetadata['Sample ID'] == 'Not specified') | (self.sampleMetadata['Sample ID'] == 'Present but undefined in the LIMS file')) & (self.sampleMetadata['SampleType'] == SampleType.StudyPool)).tolist(), 'Sample ID'] = 'Study Pool Sample'
 		self.sampleMetadata.loc[(((self.sampleMetadata['Sample ID'] == 'Not specified') | (self.sampleMetadata['Sample ID'] == 'Present but undefined in the LIMS file')) & (self.sampleMetadata['SampleType'] == SampleType.ExternalReference)).tolist(), 'Sample ID'] = 'External Reference Sample'

diff --git a/nPYc/objects/_targetedDataset.py b/nPYc/objects/_targetedDataset.py
@@ -3248,6 +3248,22 @@ def _getSampleMetadataFromFilename(self, filenameSpec):
         fileNameParts.loc[fileNameParts['groupingKind'].str.match('Blank', na=False).astype(bool), 'SampleType'] = SampleType.ProceduralBlank
         fileNameParts.loc[fileNameParts['groupingKind'].str.match('E?IC', na=False).astype(bool), 'SampleType'] = SampleType.StudyPool
 
+        # Define `SampleClass` - standardised NPC types based on SampleType/AssayRole combinations
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.StudySample) & (
+                fileNameParts['AssayRole'] == AssayRole.Assay), 'SampleClass'] = 'Study Sample'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.StudyPool) & (
+                fileNameParts['AssayRole'] == AssayRole.PrecisionReference), 'SampleClass'] = 'Study Reference'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.ExternalReference) & (
+                fileNameParts['AssayRole'] == AssayRole.PrecisionReference), 'SampleClass'] = 'Long-Term Reference'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.StudyPool) & (
+                fileNameParts['AssayRole'] == AssayRole.LinearityReference), 'SampleClass'] = 'Linearity Reference'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.MethodReference) & (
+                fileNameParts['AssayRole'] == AssayRole.PrecisionReference), 'SampleClass'] = 'Method Reference'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.ProceduralBlank) & (
+                fileNameParts['AssayRole'] == AssayRole.Blank), 'SampleClass'] = 'Blank'
+        fileNameParts.loc[(fileNameParts['SampleType'] == SampleType.UnknownType) & (
+                fileNameParts['AssayRole'] == AssayRole.UnknownRole), 'SampleClass'] = 'Unknown'
+
         # Skipped runs
         fileNameParts['Skipped'] = fileNameParts['exclusion'].str.match('[Xx]', na=False)