Patch that fixes several bugs in metadata validation and submission

bin/submission_new.py

@@ -132,7 +132,8 @@ def submission_main():
 		report_fetched = False  # Flag to indicate if a report has been fetched
 
 		while time.time() - start_time < timeout:
-			if sample.ftp_upload:
+			# if user is submitting to genbank via ftp and provided the necessary files
+			if parameters['genbank'] and 'genbank' not in databases_to_skip and sample.ftp_upload:
 				submission_objects = {'biosample': biosample_submission, 'sra': sra_submission, 'genbank': genbank_submission}
 			else:
 				submission_objects = {'biosample': biosample_submission, 'sra': sra_submission}
@@ -605,11 +606,13 @@ def add_action_block(self, submission):
 		spuid = ET.SubElement(sample_id, 'SPUID', {'spuid_namespace': f"{spuid_namespace_value}_BS"})
 		spuid.text = self.safe_text(self.top_metadata['ncbi-spuid'])
 		descriptor = ET.SubElement(biosample, 'Descriptor')
-		title = ET.SubElement(descriptor, 'Title')
-		title.text = self.safe_text(self.top_metadata['title'])
-		# BioSample XSD will not accept a description here, even though the example submission.xml has one
-		#description = ET.SubElement(descriptor, 'Description')
-		#description.text = self.safe_text(self.top_metadata['description'])
+		if 'title' in self.top_metadata and self.top_metadata['title']:
+			title = ET.SubElement(descriptor, 'Title')
+			title.text = self.safe_text(self.top_metadata['title'])
+		# BioSample XSD will not accept a description here, although the example submission.xml has one ("white space not allowed, attribute is element-only")
+		#if 'description' in self.top_metadata and self.top_metadata['description']:
+		#	description = ET.SubElement(descriptor, 'Description')
+		#	description.text = self.safe_text(self.top_metadata['description'])
 		organism = ET.SubElement(biosample, 'Organism')
 		organismName = ET.SubElement(organism, 'OrganismName')
 		organismName.text = self.safe_text(self.biosample_metadata['organism'])

bin/validate_metadata.py

@@ -213,13 +213,11 @@ def populate_fields(self):
 			)
 		# Validate populated fields
 		try:
-			 # Ensure no null values in specified columns
-			assert not any(final_df[field].isnull().any() for field in existing_terms)
-			# Ensure all values are either empty or "Not Provided"
+			# Ensure all values, if absent, are either empty or "Not Provided"
 			for field in existing_terms:
 				final_df[field] = final_df[field].apply(
-				lambda x: "Not Provided" if str(x).strip().lower() == "not provided" else x)
-				assert all(value == "" or value == "Not Provided" for value in final_df[field].values)
+					lambda x: "Not Provided" if str(x).strip().lower() == "not provided" else x)
+				assert all(isinstance(value, str) for value in final_df[field].values)
 		except AssertionError:
 			raise AssertionError(
 				f'Populating certain fields in the metadata df with "" or "Not Provided" was unsuccessful'
@@ -271,9 +269,21 @@ def __init__(self, filled_df, parameters):
 		# get the main utility class 
 		self.main_util = main_util()
 
+		# normalize authors column
+		self.normalize_author_columns()
+
+	def normalize_author_columns(self):
+		""" Normalize author/authors column to always be 'authors' """
+		# Rename 'author' to 'authors' if 'authors' doesn't already exist
+		if 'author' in self.metadata_df.columns and 'authors' not in self.metadata_df.columns:
+			self.metadata_df.rename(columns={'author': 'authors'}, inplace=True)
+		elif 'authors' in self.metadata_df.columns and 'author' in self.metadata_df.columns:
+			# Merge both columns if they exist, prioritizing 'authors'
+			self.metadata_df['authors'] = self.metadata_df['authors'].fillna(self.metadata_df['author'])
+			self.metadata_df.drop(columns=['author'], inplace=True)
+
 	def validate_main(self):
-		""" Main validation function for the metadata
-		"""
+		""" Main validation function for the metadata """
 		# check if user would like to validate custom fields
 		metadata_samp_names = self.metadata_df['sample_name'].tolist()
 

modules/local/update_submission/main.nf

@@ -32,7 +32,7 @@ process UPDATE_SUBMISSION {
         --metadata_file $validated_meta_path \
         --species $params.species \
         --output_dir  . \
-        --fasta_file $fasta_path \
+        ${fasta_path ? "--fasta_file $fasta_path" : ""} \
         ${annotations_path ? "--annotation_file $annotations_path" : ""} \
         ${fastq_1 ? "--fastq1 $fastq_1" : ""} \
         ${fastq_2 ? "--fastq2 $fastq_2" : ""} \

nextflow.config

@@ -75,7 +75,7 @@ params {
     vadr_output_dir          = "vadr_outputs"
     final_liftoff_output_dir = "liftoff_outputs"
     val_output_dir           = "validation_outputs"
-    vadr_models_dir          = " "
+    vadr_models_dir          = "${projectDir}/vadr_files/rsv-models"
 
     // environment params
     env_yml                = "${projectDir}/environment.yml"

nextflow_schema.json

@@ -87,7 +87,7 @@
       "description": "Map only if its child features align with sequence identity > this value",
       "default": 0.5
     },
-    "lift_unmapped_feature_file_name": {
+    "lift_unmapped_features_file_name": {
       "type": "string",
       "description": "Name of unmapped features file name",
       "default": "output.unmapped_features.txt"