cg 83.18.1__tar.gz → 83.19.0__tar.gz

{cg-83.18.1 → cg-83.19.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cg
-Version: 83.18.1
+Version: 83.19.0
 Summary: Clinical Genomics command center
 Requires-Python: >=3.11,<3.13
 Classifier: Programming Language :: Python

cg-83.19.0/cg/__init__.py

@@ -0,0 +1,2 @@
+__title__ = "cg"
+__version__ = "83.19.0"

{cg-83.18.1 → cg-83.19.0}/cg/apps/crunchy/crunchy.py

@@ -1,8 +1,8 @@
 """
-    Module for interacting with crunchy to perform:
-        1. Compressing: FASTQ to SPRING
-        2. Decompressing: SPRING to FASTQ
-    along with the helper methods.
+Module for interacting with crunchy to perform:
+    1. Compressing: FASTQ to SPRING
+    2. Decompressing: SPRING to FASTQ
+along with the helper methods.
 """
 
 import logging

{cg-83.18.1 → cg-83.19.0}/cg/apps/demultiplex/sample_sheet/sample_sheet_creator.py

@@ -1,4 +1,4 @@
-""" Create a sample sheet for NovaSeq flow cells."""
+"""Create a sample sheet for NovaSeq flow cells."""
 
 import logging
 

{cg-83.18.1 → cg-83.19.0}/cg/apps/environ.py

@@ -1,4 +1,4 @@
-""" Ask questions to the shell """
+"""Ask questions to the shell"""
 
 import getpass
 import os

{cg-83.18.1 → cg-83.19.0}/cg/apps/housekeeper/hk.py

@@ -1,4 +1,4 @@
-""" Module to decouple cg code from Housekeeper code """
+"""Module to decouple cg code from Housekeeper code"""
 
 import logging
 import os

cg-83.19.0/cg/apps/mip/__init__.py

@@ -0,0 +1 @@
+"""Export MIP API"""

{cg-83.18.1 → cg-83.19.0}/cg/apps/mutacc_auto.py

@@ -1,5 +1,5 @@
 """
-    Module for mutacc-auto API
+Module for mutacc-auto API
 """
 
 import copy

{cg-83.18.1 → cg-83.19.0}/cg/cli/delete/base.py

@@ -1,4 +1,4 @@
-"""CLI for deleting records in statusDB """
+"""CLI for deleting records in statusDB"""
 
 import logging
 
@@ -7,10 +7,7 @@ import rich_click as click
 from cg.cli.delete.case import delete_case
 from cg.cli.delete.cases import delete_cases
 from cg.cli.delete.illumina_sequencing_run import delete_illumina_run
-from cg.cli.delete.observations import (
-    delete_available_observations,
-    delete_observations,
-)
+from cg.cli.delete.observations import delete_available_observations, delete_observations
 from cg.cli.utils import CLICK_CONTEXT_SETTINGS
 
 LOG = logging.getLogger(__name__)

{cg-83.18.1 → cg-83.19.0}/cg/cli/upload/nipt/base.py

@@ -1,4 +1,4 @@
-""" Upload NIPT results via the CLI"""
+"""Upload NIPT results via the CLI"""
 
 import logging
 import traceback

{cg-83.18.1 → cg-83.19.0}/cg/cli/workflow/balsamic/umi.py

@@ -1,4 +1,4 @@
-"""CLI support to create config and/or start BALSAMIC """
+"""CLI support to create config and/or start BALSAMIC"""
 
 import logging
 import traceback

{cg-83.18.1 → cg-83.19.0}/cg/constants/pacbio.py

@@ -14,6 +14,7 @@ class PacBioDirsAndFiles:
     STATISTICS_DIR: str = "statistics"
     UNZIPPED_REPORTS_DIR: str = "unzipped_reports"
     METADATA_DIR: str = "metadata"
+    METADATA_FILE_SUFFIX: str = "metadata.xml"
     RUN_IS_VALID: str = "is_valid"
 
 
@@ -77,7 +78,7 @@ class BarcodeMetricsAliases:
     BARCODED_HIFI_READS_PERCENTAGE: str = "barcode.percent_barcoded_reads"
     BARCODED_HIFI_YIELD: str = "barcode.barcoded_bases"
     BARCODED_HIFI_YIELD_PERCENTAGE: str = "barcode.percent_barcoded_bases"
-    BARCODED_MEAN_READ_LENGTH: str = "barcode.n_barcoded_readlength_mean"
+    BARCODED_MEAN_READ_LENGTH: str = "barcode.mean_read_length"
     UNBARCODED_HIFI_READS: str = "barcode.n_unbarcoded_reads"
     UNBARCODED_HIFI_YIELD: str = "barcode.unbarcoded_bases"
     UNBARCODED_HIFI_MEAN_READ_LENGTH: str = "barcode.mean_unbarcoded_read_length"
@@ -100,6 +101,7 @@ class PacBioHousekeeperTags:
     LOADING_REPORT: str = "loading-report"
     RAWDATA_REPORT: str = "raw-data-report"
     DATASETS_REPORT: str = "datasets-report"
+    METADATA: str = "smrt-link-metadata"
 
 
 class PacBioBundleTypes:
@@ -115,6 +117,7 @@ file_pattern_to_bundle_type: dict[str, str] = {
     PacBioDirsAndFiles.RAW_DATA_REPORT: PacBioBundleTypes.SMRT_CELL,
     PacBioDirsAndFiles.SMRTLINK_DATASETS_REPORT: PacBioBundleTypes.SMRT_CELL,
     f"{PacBioDirsAndFiles.HIFI_READS}.*{FileExtensions.BAM}$": PacBioBundleTypes.SAMPLE,
+    f".*{PacBioDirsAndFiles.METADATA_FILE_SUFFIX}$": PacBioBundleTypes.SMRT_CELL,
 }
 
 ZIPPED_REPORTS_PATTERN: str = "*reports.zip"

{cg-83.18.1 → cg-83.19.0}/cg/meta/backup/backup.py

@@ -1,4 +1,4 @@
-""" Module for retrieving flow cells from backup."""
+"""Module for retrieving flow cells from backup."""
 
 import logging
 import subprocess

{cg-83.18.1 → cg-83.19.0}/cg/meta/upload/mutacc.py

@@ -1,5 +1,5 @@
 """
-    Module to upload cases to mutacc
+Module to upload cases to mutacc
 """
 
 import logging

{cg-83.18.1 → cg-83.19.0}/cg/meta/workflow/microsalt/constants.py

@@ -1,4 +1,3 @@
 from cg.constants.constants import FileExtensions
 
-
 QUALITY_REPORT_FILE_NAME: str = f"QC_done{FileExtensions.JSON}"

{cg-83.18.1 → cg-83.19.0}/cg/services/analysis_starter/configurator/file_creators/nextflow/params_file/tomte_params_file_creator.py

@@ -37,7 +37,7 @@ class TomteParamsFileCreator(ParamsFileCreator):
             input=sample_sheet_path,
             outdir=case_run_directory,
             gene_panel_clinical_filter=Path(case_run_directory, ScoutExportFileName.PANELS),
-            tissue=self._get_case_source_type(case_id),  # type:ignore
+            tissue=self._get_case_source_type(case_id),  # type: ignore
             genome=GenomeVersion.HG38,
         ).model_dump()
 

{cg-83.18.1 → cg-83.19.0}/cg/services/deliver_files/file_formatter/files/concatenation_service.py

@@ -1,24 +1,21 @@
 import logging
-from pathlib import Path
 import re
+from pathlib import Path
 
-from cg.constants.constants import ReadDirection, FileFormat, FileExtensions
+from cg.constants.constants import FileExtensions, ReadDirection
+from cg.services.deliver_files.file_fetcher.models import SampleFile
+from cg.services.deliver_files.file_formatter.destination.models import FormattedFile
 from cg.services.deliver_files.file_formatter.files.abstract import FileFormatter
 from cg.services.deliver_files.file_formatter.files.models import FastqFile
+from cg.services.deliver_files.file_formatter.files.sample_service import FileManager
 from cg.services.deliver_files.file_formatter.path_name.abstract import PathNameFormatter
-
+from cg.services.deliver_files.file_formatter.path_name.nested_structure import (
+    NestedStructurePathFormatter,
+)
 from cg.services.fastq_concatenation_service.fastq_concatenation_service import (
     FastqConcatenationService,
 )
 from cg.services.fastq_concatenation_service.utils import generate_concatenated_fastq_delivery_path
-from cg.services.deliver_files.file_fetcher.models import SampleFile
-from cg.services.deliver_files.file_formatter.destination.models import FormattedFile
-from cg.services.deliver_files.file_formatter.files.sample_service import (
-    FileManager,
-)
-from cg.services.deliver_files.file_formatter.path_name.nested_structure import (
-    NestedStructurePathFormatter,
-)
 from cg.utils.files import get_all_files_in_directory_tree
 
 LOG = logging.getLogger(__name__)
@@ -279,7 +276,7 @@ class SampleFileConcatenationFormatter(FileFormatter):
 
     @staticmethod
     def _validate_sample_fastq_file_share_same_directory(
-        sample_fastq_files: dict[str, list[FastqFile]]
+        sample_fastq_files: dict[str, list[FastqFile]],
     ) -> None:
         """
         Assert that all fastq files for a sample share the same directory.

{cg-83.18.1 → cg-83.19.0}/cg/services/pdc_service/pdc_service.py

@@ -1,4 +1,4 @@
-""" Module to group PDC related commands."""
+"""Module to group PDC related commands."""
 
 import logging
 from subprocess import CalledProcessError

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/data_transfer_service/dto.py

@@ -65,6 +65,8 @@ class PacBioSampleSequencingMetricsDTO(BaseModel):
 class PacBioSequencingRunDTO(BaseModel):
     instrument_name: RevioNames
     run_id: str
+    run_name: str
+    unique_id: str
 
 
 class PacBioDTOs(PostProcessingDTOs):

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/data_transfer_service/utils.py

@@ -82,4 +82,6 @@ def get_sequencing_run_dto(
     return PacBioSequencingRunDTO(
         instrument_name=metrics.dataset_metrics.instrument_name,  # type: ignore - pydantic will convert to correct type
         run_id=run_data.run_id,
+        run_name=metrics.metadata.run_name,
+        unique_id=metrics.metadata.unique_id,
     )

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/housekeeper_service/pacbio_houskeeper_service.py

@@ -86,6 +86,7 @@ class PacBioHousekeeperService(PostProcessingHKService):
             PacBioDirsAndFiles.RAW_DATA_REPORT: [PacBioHousekeeperTags.RAWDATA_REPORT],
             PacBioDirsAndFiles.SMRTLINK_DATASETS_REPORT: [PacBioHousekeeperTags.DATASETS_REPORT],
             f"{PacBioDirsAndFiles.HIFI_READS}.*{FileExtensions.BAM}$": [AlignmentFileTag.BAM],
+            f".*{PacBioDirsAndFiles.METADATA_FILE_SUFFIX}$": [PacBioHousekeeperTags.METADATA],
         }
         return get_item_by_pattern_in_source(source=file_path.name, pattern_map=file_pattern_to_tag)
 

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/metrics_parser/metrics_parser.py

@@ -15,6 +15,7 @@ from cg.services.run_devices.exc import (
 from cg.services.run_devices.pacbio.metrics_parser.models import (
     BarcodeMetrics,
     ControlMetrics,
+    MetadataMetrics,
     PacBioMetrics,
     PolymeraseMetrics,
     ProductivityMetrics,
@@ -23,6 +24,7 @@ from cg.services.run_devices.pacbio.metrics_parser.models import (
     SmrtlinkDatasetsMetrics,
 )
 from cg.services.run_devices.pacbio.metrics_parser.utils import (
+    get_parsed_metadata_file,
     get_parsed_metrics_from_file_name,
     get_parsed_sample_metrics,
 )
@@ -63,6 +65,7 @@ class PacBioMetricsParser(PostProcessingMetricsParser):
         barcodes_metrics: BarcodeMetrics = get_parsed_metrics_from_file_name(
             metrics_files=metrics_files, file_name=PacBioDirsAndFiles.BARCODES_REPORT
         )
+        metadata_metrics: MetadataMetrics = get_parsed_metadata_file(metrics_files)
         sample_metrics: list[SampleMetrics] = get_parsed_sample_metrics(metrics_files)
         LOG.debug(f"All metrics parsed for run {run_data.run_id}")
         return PacBioMetrics(
@@ -72,5 +75,6 @@ class PacBioMetricsParser(PostProcessingMetricsParser):
             polymerase=polymerase_metrics,
             dataset_metrics=dataset_metrics,
             barcodes=barcodes_metrics,
+            metadata=metadata_metrics,
             samples=sample_metrics,
         )

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/metrics_parser/models.py

@@ -135,7 +135,7 @@ class BarcodeMetrics(RunMetrics):
         ..., alias=BarcodeMetricsAliases.BARCODED_HIFI_YIELD_PERCENTAGE
     )
     barcoded_hifi_mean_read_length: int = Field(
-        ..., alias=BarcodeMetricsAliases.UNBARCODED_HIFI_MEAN_READ_LENGTH
+        ..., alias=BarcodeMetricsAliases.BARCODED_MEAN_READ_LENGTH
     )
     unbarcoded_hifi_reads: int = Field(..., alias=BarcodeMetricsAliases.UNBARCODED_HIFI_READS)
     unbarcoded_hifi_yield: int = Field(..., alias=BarcodeMetricsAliases.UNBARCODED_HIFI_YIELD)
@@ -156,6 +156,13 @@ class SampleMetrics(RunMetrics):
     sample_internal_id: str = Field(..., alias=SampleMetricsAliases.SAMPLE_INTERNAL_ID)
 
 
+class MetadataMetrics(BaseModel):
+    """Model that holds metadata for a specific run."""
+
+    run_name: str
+    unique_id: str
+
+
 class PacBioMetrics(RunMetrics):
     """Model that holds all relevant PacBio metrics."""
 
@@ -165,4 +172,5 @@ class PacBioMetrics(RunMetrics):
     polymerase: PolymeraseMetrics
     dataset_metrics: SmrtlinkDatasetsMetrics
     barcodes: BarcodeMetrics
+    metadata: MetadataMetrics
     samples: list[SampleMetrics]

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/metrics_parser/utils.py

@@ -1,13 +1,17 @@
 from pathlib import Path
 from typing import Any, Type
+from xml.etree import ElementTree
+from xml.etree.ElementTree import Element
 
 from cg.constants.constants import FileFormat
 from cg.constants.pacbio import MetricsFileFields, PacBioDirsAndFiles
+from cg.exc import XMLError
 from cg.io.controller import ReadFile
 from cg.services.run_devices.pacbio.metrics_parser.models import (
     BarcodeMetrics,
     BaseMetrics,
     ControlMetrics,
+    MetadataMetrics,
     PolymeraseMetrics,
     ProductivityMetrics,
     ReadMetrics,
@@ -78,3 +82,24 @@ def get_parsed_sample_metrics(metrics_files: list[Path]) -> list[SampleMetrics]:
         MetricsFileFields.COLUMNS
     )
     return _parse_sample_data(sample_data)
+
+
+def get_parsed_metadata_file(metrics_files: list[Path]) -> MetadataMetrics:
+    namespaces: dict[str, str] = {
+        "pb": "http://pacificbiosciences.com/PacBioDataModel.xsd"  # NOSONAR
+    }
+    metadata_file: Path = get_file_with_pattern_from_list(
+        files=metrics_files, pattern=PacBioDirsAndFiles.METADATA_FILE_SUFFIX
+    )
+    root: Element = ElementTree.parse(metadata_file).getroot()
+    run: Element | None = root.find(".//pb:Run", namespaces=namespaces)
+    if run is not None:
+        run_name, unique_id = run.get("Name"), run.get("UniqueId")
+        if run_name and unique_id:
+            return MetadataMetrics(run_name=run_name, unique_id=unique_id)
+        else:
+            raise XMLError(
+                f"'Run' element is missing either 'Name' or 'UniqueId' in {metadata_file}"
+            )
+    else:
+        raise XMLError(f"No 'Run' element found in {metadata_file}")

{cg-83.18.1 → cg-83.19.0}/cg/services/run_devices/pacbio/run_file_manager/run_file_manager.py

@@ -20,7 +20,18 @@ class PacBioRunFileManager(RunFileManager):
         """Get the file paths required by the PacBioMetricsParser."""
         run_path: Path = run_data.full_path
         validate_files_or_directories_exist([run_path])
-        return self._get_report_files(run_path)
+        unzipped_dir: Path = self._get_unzipped_reports_dir(run_path)
+        files_to_parse: list[Path] = [
+            Path(unzipped_dir, PacBioDirsAndFiles.BARCODES_REPORT),
+            Path(unzipped_dir, PacBioDirsAndFiles.CONTROL_REPORT),
+            Path(unzipped_dir, PacBioDirsAndFiles.LOADING_REPORT),
+            Path(unzipped_dir, PacBioDirsAndFiles.RAW_DATA_REPORT),
+            Path(unzipped_dir, PacBioDirsAndFiles.SMRTLINK_DATASETS_REPORT),
+            self._get_ccs_report_file(run_path),
+            self._get_metadata_file(run_path),
+        ]
+        validate_files_or_directories_exist(files_to_parse)
+        return files_to_parse
 
     @handle_post_processing_errors(
         to_except=(FileNotFoundError,), to_raise=PostProcessingRunFileManagerError
@@ -53,19 +64,16 @@ class PacBioRunFileManager(RunFileManager):
             raise FileNotFoundError(f"No CCS report file found in {statistics_dir}")
         return files[0]
 
-    def _get_report_files(self, run_path: Path) -> list[Path]:
-        """Return the paths to the report files."""
-        unzipped_dir: Path = self._get_unzipped_reports_dir(run_path)
-        report_files: list[Path] = [
-            Path(unzipped_dir, PacBioDirsAndFiles.BARCODES_REPORT),
-            Path(unzipped_dir, PacBioDirsAndFiles.CONTROL_REPORT),
-            Path(unzipped_dir, PacBioDirsAndFiles.LOADING_REPORT),
-            Path(unzipped_dir, PacBioDirsAndFiles.RAW_DATA_REPORT),
-            Path(unzipped_dir, PacBioDirsAndFiles.SMRTLINK_DATASETS_REPORT),
-            self._get_ccs_report_file(run_path),
-        ]
-        validate_files_or_directories_exist(report_files)
-        return report_files
+    @staticmethod
+    def _get_metadata_file(run_path: Path) -> Path:
+        """Return the path to the metadata file."""
+        metadata_dir: Path = Path(run_path, PacBioDirsAndFiles.METADATA_DIR)
+        files: list[Path] = get_files_matching_pattern(
+            directory=metadata_dir, pattern=f"*{PacBioDirsAndFiles.METADATA_FILE_SUFFIX}"
+        )
+        if not files:
+            raise FileNotFoundError(f"No metadata file found in {metadata_dir}")
+        return files[0]
 
     @staticmethod
     def _remove_unassigned_bam_file(bam_files: list[Path]) -> list[Path]:

{cg-83.18.1 → cg-83.19.0}/cg/store/crud/create.py

@@ -524,6 +524,8 @@ class CreateMixin(ReadHandler):
             sequencing_run = PacbioSequencingRun(
                 instrument_name=pacbio_sequencing_run_dto.instrument_name,
                 run_id=pacbio_sequencing_run_dto.run_id,
+                run_name=pacbio_sequencing_run_dto.run_name,
+                unique_id=pacbio_sequencing_run_dto.unique_id,
             )
             self.add_item_to_store(sequencing_run)
             return sequencing_run

{cg-83.18.1 → cg-83.19.0}/cg/store/models.py

@@ -1186,11 +1186,13 @@ class PacbioSequencingRun(Base):
 
     id: Mapped[PrimaryKeyInt]
     run_id: Mapped[Str64] = mapped_column(unique=True)
+    run_name: Mapped[Str64 | None]
     processed: Mapped[bool] = mapped_column(default=False)
     comment: Mapped[Text] = mapped_column(default="")
     instrument_name: Mapped[RevioNames] = mapped_column(
         types.Enum(*(revio_name.value for revio_name in RevioNames))
     )
+    unique_id: Mapped[Str64 | None] = mapped_column(unique=True)
 
     smrt_cell_metrics: Mapped[list[PacbioSMRTCellMetrics]] = orm.relationship(
         back_populates="sequencing_run"

{cg-83.18.1 → cg-83.19.0}/cg/utils/click/EnumChoice.py

@@ -1,4 +1,4 @@
-""" class to use when the click option is an Enum
+"""class to use when the click option is an Enum
 based on suggestion https://github.com/pallets/click/issues/605#issuecomment-277539425
 """
 

{cg-83.18.1 → cg-83.19.0}/cg/utils/enums.py

@@ -1,4 +1,4 @@
-"""Enum classes has string or list values that behaves like defined """
+"""Enum classes has string or list values that behaves like defined"""
 
 from enum import Enum
 

{cg-83.18.1 → cg-83.19.0}/cg/utils/files.py

@@ -27,7 +27,7 @@ def get_file_in_directory(directory: Path, file_name: str) -> Path:
     raise FileNotFoundError(f"File {file_name} not found in {directory}")
 
 
-def get_file_with_pattern_from_list(files: list[Path], pattern: str) -> Path | None:
+def get_file_with_pattern_from_list(files: list[Path], pattern: str) -> Path:
     """
     Return the path whose name matches a pattern from a list of paths.
     Raises:

{cg-83.18.1 → cg-83.19.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [project]
 name = "cg"
-version = "83.18.1"
+version = "83.19.0"
 description = "Clinical Genomics command center"
 readme = {file = "README.md", content-type = "text/markdown"}
 homepage = "https://github.com/Clinical-Genomics/cg"

cg-83.18.1/cg/__init__.py

@@ -1,2 +0,0 @@
-__title__ = "cg"
-__version__ = "83.18.1"

cg-83.18.1/cg/apps/mip/__init__.py

@@ -1 +0,0 @@
-""" Export MIP API """