Submission fasta reroute ick4

bin/submission_create.py

@@ -471,6 +471,17 @@ def create_genbank_zip(submission_name, submission_files_dir):
 	while not os.path.isfile(os.path.join(submission_files_dir, submission_name + ".zip")):
 		time.sleep(10)
 
+# Detect multiple contig fasta
+def is_multicontig_fasta(fasta):
+	headers = set()
+	with open(fasta, 'r') as file:
+		for line in file:
+			if line.startswith('>'):
+				headers.add(line.strip())
+				if len(headers) > 1:
+					return True
+	return False
+
 # Run Table2asn to generate sqn file for submission
 def create_genbank_table2asn(submission_dir, submission_name, submission_files_dir, gff_file=None):
 	submission_status = "processed-ok"
@@ -481,16 +492,22 @@ def create_genbank_table2asn(submission_dir, submission_name, submission_files_d
 	print("Downloading Table2asn.", file=sys.stdout)
 	download_table2asn(table2asn_dir=table2asn_dir)
 	# Command to generate table2asn submission file
-	command = [table2asn_dir, "-t", os.path.join(submission_files_dir, "authorset.sbt"), "-i", os.path.join(submission_files_dir, "sequence.fsa"), \
-							  "-src-file", os.path.join(submission_files_dir, "source.src"), "-locus-tag-prefix", get_gff_locus_tag(gff_file), \
-							  "-o", os.path.join(submission_files_dir, submission_name + ".sqn")]
+	fasta = os.path.join(submission_files_dir, "sequence.fsa")
+	command = [table2asn_dir, "-t", os.path.join(submission_files_dir, "authorset.sbt"), "-i", fasta, \
+			"-src-file", os.path.join(submission_files_dir, "source.src"), "-locus-tag-prefix", get_gff_locus_tag(gff_file), \
+			"-o", os.path.join(submission_files_dir, submission_name + ".sqn")]
+	if is_multicontig_fasta(fasta):
+		command.append("-M")
+		command.append("n")
+		command.append("-Z")
 	if os.path.isfile(os.path.join(submission_files_dir, "comment.cmt")):
 		command.append("-w")
 		command.append( os.path.join(submission_files_dir, "comment.cmt"))
 	if gff_file is not None:
 		command.append("-f")
 		command.append(os.path.join(submission_dir, gff_file))
 	print("Running Table2asn.", file=sys.stdout)
+	print(command)
 	proc = subprocess.run(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd = os.path.join(os.path.dirname(os.path.abspath(__file__))))
 	if proc.returncode != 0:
 		print("Table2asn-Error", file=sys.stderr)

bin/validate_metadata.py

@@ -360,7 +360,7 @@ def validate_main(self):
 						  'meta_core_grade': self.meta_core_grade},
 				errors = {'sample_error_msg': self.sample_error_msg, 'sra_msg': self.sra_msg,
 						  'illumina_error_msg': self.illumina_error_msg, 'nanopore_error_msg': self.nanopore_error_msg,
-					      'list_of_sample_errors': self.list_of_sample_errors,},
+						  'list_of_sample_errors': self.list_of_sample_errors,},
 				valid_sample_num = self.valid_sample_num,
 				sample_info = sample_info,
 				sample_flag = True,
@@ -688,6 +688,7 @@ def check_instruments(self, instrument_type):
 				self.meta_illumina_grade = False
 
 		# check if the SRA file exists for the first file path
+		path_failed = False
 		if instrument_type == 'illumina':
 			if self.sample_info["illumina_library_layout"].tolist()[0] == 'paired':
 				paths = [file_path1, file_path2]
@@ -1008,8 +1009,8 @@ def read_custom_fields_file(self):
 		# save contents to dictionary
 		for field_name, field_data in data.items():
 			self.custom_fields_dict[field_name] = {
-        		'type': field_data['type'],
-        		'samples': field_data['samples'],
+				'type': field_data['type'],
+				'samples': field_data['samples'],
 				'replace_empty_with': field_data['replace_empty_with'], 
 				'new_field_name': field_data['new_field_name']
 			}

conf/modules.config

@@ -20,23 +20,23 @@ process {
 
     withName: METADATA_VALIDATION {
         publishDir = [
-            path: { "${params.output_dir}/${params.validation_outputs}" },
+            path: { "${params.output_dir}/${params.val_output_dir}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
     withName: BAKTA {
         publishDir = [
-            path: { "${params.output_dir}/${params.bakta_outputs}" },
+            path: { "${params.output_dir}/${params.bakta_output_dir}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
 
     withName: VADR_POST_CLEANUP {
         publishDir = [
-            path: { "${params.output_dir}/${params.vadr_outputs}" },
+            path: { "${params.output_dir}/${params.vadr_output_dir}" },
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]

modules/local/metadata_validation/main.nf

@@ -14,8 +14,6 @@ process METADATA_VALIDATION {
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'staphb/tostadas:latest' : 'staphb/tostadas:latest' }"
 
-    publishDir "$params.output_dir", mode: 'copy', overwrite: params.overwrite_output
-
     input:
     path meta_path
 

modules/local/post_bakta_annotation/main.nf

@@ -9,8 +9,6 @@ process BAKTA_POST_CLEANUP {
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'staphb/tostadas:latest' : 'staphb/tostadas:latest' }"
 
-    // publishDir "$params.output_dir", mode: 'copy', overwrite: params.overwrite_output
-
     input:
     path bakta_results
     path meta_path

modules/local/post_vadr_annotation/main.nf

@@ -11,9 +11,6 @@ process VADR_POST_CLEANUP {
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'staphb/tostadas:latest' : 'staphb/tostadas:latest' }"
 
-
-    publishDir "$params.output_dir", mode: 'copy', overwrite: params.overwrite_output
-
     input:
     path vadr_outputs
     tuple val(meta), path meta_path

subworkflows/local/bakta.nf

@@ -32,6 +32,7 @@ workflow RUN_BAKTA {
 
         emit:
         gff3 = BAKTA.out.gff3
+        fna = BAKTA.out.fna
     }
 
 

workflows/tostadas.nf

@@ -86,12 +86,6 @@ workflow TOSTADAS {
     // Create initial submission channel
     submission_ch = metadata_ch.join(reads_ch)
 
-    // print error if they provide gff and annotation flag
-    // if ( !params.annotation && params.genbank ) {
-    //             // todo: make an error msg that follows the rest of the code protocol
-    //             throw new Exception("Cannot submit to GenBank without assembly and annotation files")
-    //     }
-
     // check if the user wants to skip annotation or not
     if ( params.annotation ) {
         if ( params.virus && !params.bacteria ) {
@@ -110,7 +104,7 @@ workflow TOSTADAS {
                 }
 
             // set up submission channels
-            submission_ch = submission_ch.join(repeatmasker_gff_ch) // meta.id, fasta, fastq1, fastq2, gff
+            submission_ch = submission_ch.join(repeatmasker_gff_ch) // meta.id, tsv, fasta, fastq1, fastq2, gff
             }
 
             // run vadr processes
@@ -126,7 +120,7 @@ workflow TOSTADAS {
                         meta['id'] = it.getSimpleName().replaceAll('_reformatted', '')
                         [ meta, it ] 
                     }
-                submission_ch = submission_ch.join(vadr_gff_ch) // meta.id, fasta, fastq1, fastq2, gff
+                submission_ch = submission_ch.join(vadr_gff_ch) // meta.id, tsv, fasta, fastq1, fastq2, gff
             }
         }
         if ( params.bacteria ) {
@@ -140,9 +134,20 @@ workflow TOSTADAS {
                     .flatten()
                     .map { 
                         meta = [id:it.getSimpleName()] 
+                        //meta = it.getSimpleName()
+                        [ meta, it ]
+                    }
+                bakta_fasta_ch = RUN_BAKTA.out.fna
+                    .flatten()
+                    .map { 
+                        meta = [id:it.getSimpleName()] 
+                        //meta = it.getSimpleName()
                         [ meta, it ]
                     }
-                submission_ch = submission_ch.join(bakta_gff_ch) // meta.id, fasta, fastq1, fastq2, gff
+                submission_ch = submission_ch.join(bakta_gff_ch) // meta.id, tsv, fasta, fastq1, fastq2, gff
+                submission_ch = submission_ch.map { meta, tsv, _, fq1, fq2, gff -> [meta, tsv, fq1, fq2, gff] } // drop original fasta
+                submission_ch = submission_ch.join(bakta_fasta_ch) // join annotated fasta
+                submission_ch = submission_ch.map { meta, tsv, fq1, fq2, gff, fasta -> [meta, tsv, fasta, fq1, fq2, gff] }  // meta.id, tsv, annotated fasta, fastq1, fastq2, gff
             }   
         }
     }