Add new sample map column defaults, update sg meta on RNA ingest

metamist/parser/generic_metadata_parser.py

@@ -95,6 +95,7 @@ def __init__(
         seq_platform_column: Optional[str] = None,
         seq_facility_column: Optional[str] = None,
         library_type_column: Optional[str] = None,
+        end_type_column: Optional[str] = None,
         read_length_column: Optional[str] = None,
         gvcf_column: Optional[str] = None,
         meta_column: Optional[str] = None,
@@ -136,6 +137,7 @@ def __init__(
         self.seq_platform_column = seq_platform_column
         self.seq_facility_column = seq_facility_column
         self.library_type_column = library_type_column
+        self.end_type_column = end_type_column
         self.read_length_column = read_length_column
         self.reference_assembly_location_column = reference_assembly_location_column
         self.default_reference_assembly_location = default_reference_assembly_location
@@ -230,7 +232,12 @@ def get_library_type(self, row: SingleRow) -> str:
         value = row.get(self.library_type_column, None)
         return str(value)
 
-    def get_read_length(self, row: SingleRow) -> str:
+    def get_assay_end_type(self, row: SingleRow) -> str:
+        """Get assay end type from row"""
+        value = row.get(self.end_type_column, None)
+        return str(value)
+
+    def get_assay_read_length(self, row: SingleRow) -> str:
         """Get read length from row"""
         value = row.get(self.read_length_column, None)
         return str(value)
@@ -672,6 +679,12 @@ async def get_assays_from_group(
 
         if self.batch_number is not None:
             collapsed_assay_meta['batch'] = self.batch_number
+
+        if sequencing_group.sequencing_type in ['polyarna', 'totalrna', 'singlecellrna']:
+            rows=sequencing_group.rows
+            collapsed_assay_meta['library_type'] = self.get_library_type(rows[0])
+            collapsed_assay_meta['end_type'] = self.get_assay_end_type(rows[0])
+            collapsed_assay_meta['read_length'] = self.get_assay_read_length(rows[0])
 
         for read in reads[reads_type]:
             assays.append(

metamist/parser/generic_parser.py

@@ -410,6 +410,9 @@ def __init__(  # pylint: disable=too-many-arguments
         default_sequencing_type='genome',
         default_sequencing_technology='short-read',
         default_sequencing_platform: str | None = None,
+        default_library_type: str | None=None,
+        default_assay_end_type: str | None=None,
+        default_assay_read_length: str | None=None,
         default_sample_type=None,
         default_analysis_type='qc',
         default_analysis_status='completed',
@@ -435,6 +438,9 @@ def __init__(  # pylint: disable=too-many-arguments
         self.default_sequencing_type: str = default_sequencing_type
         self.default_sequencing_technology: str = default_sequencing_technology
         self.default_sequencing_platform: Optional[str] = default_sequencing_platform
+        self.default_library_type: Optional[str] = default_library_type
+        self.default_assay_end_type: Optional[str] = default_assay_end_type
+        self.default_assay_read_length: Optional[str] = default_assay_read_length
         self.default_sample_type: Optional[str] = default_sample_type
         self.default_analysis_type: str = default_analysis_type
         self.default_analysis_status: str = default_analysis_status
@@ -1007,13 +1013,17 @@ def get_sequencing_group_meta_from_assays(self, assays: list[ParsedAssay]) -> di
         """
         meta = {}
         for assay in assays:
-            if assay['type'] not in RNA_SEQ_TYPES:
+            if assay['meta'].get('type') not in RNA_SEQ_TYPES:
                 continue
+            if assay['meta'].get('library_type'):
+                meta['library_type'] = assay['meta']['library_type']
             if assay['meta'].get('reads', []) and len(assay['meta'].get('reads', [])) % 2 == 0:
                 meta['end_type'] = 'paired'
             else:
                 meta['end_type'] = 'single'
-
+            if assay['meta'].get('read_length'):
+                meta['read_length'] = assay['meta']['read_length']
+        return meta
 
     def get_sample_type(self, row: GroupedRow) -> str:
         """Get sample type from row"""

metamist/parser/sample_file_map_parser.py

@@ -18,6 +18,7 @@
 CHECKSUM_COL_NAME = 'checksum'
 SEQ_FACILITY_COL_NAME = 'sequencing_facility'
 LIBRARY_TYPE_COL_NAME = 'library_type'
+ASSAY_END_TYPE_COL_NAME = 'end_type'
 READ_LENGTH_COL_NAME = 'read_length'
 
 KeyMap = {
@@ -88,6 +89,9 @@ def __init__(
         default_sample_type='blood',
         default_sequencing_technology='short-read',
         default_sequencing_platform='illumina',
+        default_library_type: str | None=None,
+        default_assay_end_type: str | None=None,
+        default_assay_read_length: str | None=None,
         allow_extra_files_in_search_path=False,
         default_reference_assembly_location: str | None = None,
     ):
@@ -101,10 +105,14 @@ def __init__(
             seq_type_column=SEQ_TYPE_COL_NAME,
             seq_facility_column=SEQ_FACILITY_COL_NAME,
             library_type_column=LIBRARY_TYPE_COL_NAME,
+            end_type_column=ASSAY_END_TYPE_COL_NAME,
             read_length_column=READ_LENGTH_COL_NAME,
             default_sequencing_type=default_sequencing_type,
             default_sample_type=default_sample_type,
             default_sequencing_technology=default_sequencing_technology,
+            default_library_type=default_library_type, 
+            default_assay_end_type=default_assay_end_type,
+            default_assay_read_length=default_assay_read_length,
             default_reference_assembly_location=default_reference_assembly_location,
             participant_meta_map={},
             sample_meta_map={},