Merge branch 'main' of github.com:Clinical-Genomics/hermes into add-gens

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.14.1
+current_version = 1.14.3
 commit = True
 tag = True
 tag_name = {new_version}

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
     - repo: https://github.com/psf/black
-      rev: 23.9.1
+      rev: 23.12.0
       hooks:
           - id: black
             args: ["--line-length", "100"]

cg_hermes/config/rnafusion.py

@@ -14,7 +14,7 @@
         "used_by": ["deliver"],
     },
     frozenset({"arriba-visualisation", "arriba"}): {
-        "is_mandatory": True,
+        "is_mandatory": False,
         "bundle_id": True,
         "tags": ["arriba-visualisation", "visualization", "arriba", "research"],
         "used_by": ["deliver", "scout"],
@@ -40,12 +40,12 @@
         "used_by": ["deliver", "scout"],
     },
     frozenset({"fusioninspector", "report"}): {
-        "is_mandatory": True,
+        "is_mandatory": False,
         "tags": ["fusioninspector"],
         "used_by": ["deliver"],
     },
     frozenset({"fusioninspector-html", "report"}): {
-        "is_mandatory": True,
+        "is_mandatory": False,
         "tags": ["fusioninspector-html", "research"],
         "used_by": ["deliver", "scout"],
     },
@@ -57,6 +57,16 @@
     frozenset({"star-fusion-cram", "star-fusion"}): {
         "is_mandatory": True,
         "tags": ["cram"],
+        "used_by": ["deliver", "scout"],
+    },
+    frozenset({"star-fusion-cram-index", "star-fusion"}): {
+        "is_mandatory": True,
+        "tags": ["cram-index"],
+        "used_by": ["deliver", "scout"],
+    },
+    frozenset({"star-align-gene-counts", "star-align"}): {
+        "is_mandatory": True,
+        "tags": ["gene-counts"],
         "used_by": ["deliver"],
     },
     frozenset({"multiqc-json"}): {
@@ -69,9 +79,11 @@
         "tags": ["qc-metrics"],
         "used_by": ["cg"],
     },
+    frozenset({"vcf-fusion", "vcf-collect"}): {
+        "is_mandatory": False,
+        "tags": ["vcf-fusion"],
+        "used_by": ["deliver", "scout"],
+    },
 }
 
 NXF_RNAFUSION_COMMON_TAGS = {**RNAFUSION_COMMON_TAGS, **NEXTFLOW_COMMON_TAGS}
-
-
-#

cg_hermes/config/tags.py

@@ -100,6 +100,7 @@
     "vcf-report": {"description": "Results and QC from variant calling"},
     "cnv-report": {"description": "CNV variant calling report"},
     "software-versions": {"description": "Versions of software used in analysis"},
+    "gene-counts": {"description": "STAR read counts output per gene"},
 }
 
 VALIDATIONS_COMMON = {
@@ -138,6 +139,7 @@
     "umi-cram-index": {"description": "Index for the UMI consensus filtered cram file"},
     "qc-cram": {"description": "QC alignment file in CRAM format"},
     "qc-cram-index": {"description": "QC index file for alignment file in CRAM format"},
+    "vcf-fusion": {"description": "Converted RNA fusion file to SV VCF"},
 }
 
 TOOLS = {

cg_hermes/deliverables.py

@@ -1,7 +1,7 @@
 """Class to represent deliverables file"""
 import copy
 import logging
-from typing import Dict, FrozenSet, List, Optional, Set
+from typing import FrozenSet, Optional
 
 from cg_hermes.config.balsamic import (
     BALSAMIC_TAGS,
@@ -12,21 +12,21 @@
 )
 from cg_hermes.config.balsamic_qc import (
     BALSAMIC_QC_TAGS,
-    QC_TUMOR_NORMAL_WGS_TAGS,
     QC_TUMOR_NORMAL_PANEL_TAGS,
+    QC_TUMOR_NORMAL_WGS_TAGS,
 )
 from cg_hermes.config.balsamic_umi import (
     BALSAMIC_UMI_TAGS,
-    UMI_TUMOR_ONLY_PANEL_TAGS,
     UMI_TUMOR_NORMAL_PANEL_TAGS,
+    UMI_TUMOR_ONLY_PANEL_TAGS,
 )
 from cg_hermes.config.fluffy import FLUFFY_COMMON_TAGS
 from cg_hermes.config.microsalt import MICROSALT_COMMON_TAGS
 from cg_hermes.config.mip_dna import MIP_DNA_TAGS
 from cg_hermes.config.mip_rna import MIP_RNA_TAGS
 from cg_hermes.config.mutant import MUTANT_COMMON_TAGS
-from cg_hermes.config.rnafusion import NXF_RNAFUSION_COMMON_TAGS
 from cg_hermes.config.pipelines import AnalysisType, Pipeline
+from cg_hermes.config.rnafusion import NXF_RNAFUSION_COMMON_TAGS
 from cg_hermes.exceptions import MissingFileError
 from cg_hermes.models import pipeline_deliverables
 from cg_hermes.models.pipeline_deliverables import (
@@ -36,8 +36,8 @@
     MicrosaltDeliverables,
     MipDeliverables,
     MutantDeliverables,
-    RnafusionDeliverables,
     PipelineDeliverables,
+    RnafusionDeliverables,
     TagBase,
 )
 from cg_hermes.models.tags import CGTag, TagMap
@@ -50,17 +50,17 @@ class Deliverables:
 
     def __init__(
         self,
-        deliverables: Dict[str, List[Dict[str, str]]],
+        deliverables: dict[str, list[dict[str, str]]],
         pipeline: Pipeline,
         analysis_type: Optional[AnalysisType] = None,
     ):
         self.raw_deliverables = deliverables
         self.pipeline = pipeline
         self.analysis_type = analysis_type
         self.bundle_id: Optional[str] = None
-        self.configs: Dict[FrozenSet[str], TagMap]
-        self.files: List[TagBase]
-        self.file_identifiers: Set[FrozenSet[str]]
+        self.configs: dict[FrozenSet[str], TagMap]
+        self.files: list[TagBase]
+        self.file_identifiers: set[FrozenSet[str]]
         self.model: PipelineDeliverables
         self.set_pipeline_specific_variables()
         self.file_identifiers = {file_obj.tags for file_obj in self.files}
@@ -105,18 +105,18 @@ def set_pipeline_specific_variables(self):
             )
 
     @staticmethod
-    def build_internal_tag_map(tag_map: Dict[FrozenSet[str], dict]) -> Dict[FrozenSet[str], TagMap]:
+    def build_internal_tag_map(tag_map: dict[FrozenSet[str], dict]) -> dict[FrozenSet[str], TagMap]:
         """Convert and validate a tag map to TagMap objects"""
         LOG.debug("Build internal tag map")
-        internal_tag_map: Dict[FrozenSet[str], TagMap] = dict()
+        internal_tag_map: dict[FrozenSet[str], TagMap] = dict()
         for pipeline_tags in tag_map:
             internal_tag_map[pipeline_tags] = TagMap.parse_obj(tag_map[pipeline_tags])
         return internal_tag_map
 
     @staticmethod
     def convert_to_cg_tag(conversion_info: TagMap, subject_id: str, path: str) -> CGTag:
         """Convert tags from pipeline specific tags to CG tags"""
-        cg_tags: List[str] = copy.deepcopy(conversion_info.tags)
+        cg_tags: list[str] = copy.deepcopy(conversion_info.tags)
         cg_tags.append(subject_id)
         cg_tags.extend(
             [tool for tool in conversion_info.used_by if tool not in ["cg", "audit", "store"]]
@@ -125,7 +125,7 @@ def convert_to_cg_tag(conversion_info: TagMap, subject_id: str, path: str) -> CG
 
     def convert_to_cg_deliverables(self) -> CGDeliverables:
         """Convert pipeline specific information from deliverables file to CG formatted information"""
-        cg_files: List[CGTag] = []
+        cg_files: list[CGTag] = []
         file_object: TagBase
         for file_object in self.files:
             pipeline_tags = file_object.tags
@@ -155,7 +155,7 @@ def convert_to_cg_deliverables(self) -> CGDeliverables:
             pipeline=self.pipeline.value, files=cg_files, bundle_id=self.bundle_id
         )
 
-    def get_balsamic_analysis_configs(self) -> Dict[FrozenSet[str], dict]:
+    def get_balsamic_analysis_configs(self) -> dict[FrozenSet[str], dict]:
         """Extracts all the BALSAMIC mandatory files depending on the analysis workflow and type executed"""
 
         BALSAMIC_COMMON_TAGS = []
@@ -203,9 +203,9 @@ def validate_mandatory_files(self) -> None:
                 files=missing_mandatory_files, message="Deliverables is missing mandatory files"
             )
 
-    def get_mip_files(self) -> List[TagBase]:
+    def get_mip_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.MipFile
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             identifier = [file_obj.step]
             if file_obj.tag:
@@ -220,9 +220,9 @@ def get_mip_files(self) -> List[TagBase]:
             )
         return files
 
-    def get_microsalt_files(self) -> List[TagBase]:
+    def get_microsalt_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.MicrosaltFile
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             identifier = [file_obj.step]
             if file_obj.tag:
@@ -236,9 +236,9 @@ def get_microsalt_files(self) -> List[TagBase]:
             )
         return files
 
-    def get_mutant_files(self) -> List[TagBase]:
+    def get_mutant_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.MutantFile
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             identifier = [file_obj.step]
             if file_obj.tag:
@@ -252,22 +252,22 @@ def get_mutant_files(self) -> List[TagBase]:
             )
         return files
 
-    def get_fluffy_files(self) -> List[TagBase]:
+    def get_fluffy_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.FileBase
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             identifier = frozenset([file_obj.tag.lower()])
             files.append(TagBase(tags=identifier, subject_id=file_obj.id, path=file_obj.path))
         return files
 
-    def get_balsamic_files(self) -> List[TagBase]:
+    def get_balsamic_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.BalsamicFile
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             sample_id: str = file_obj.id
             tag_sample_id: str = sample_id.replace("_", "-")
             # This is due to older balsamic format
-            split_id: List[str] = sample_id.split("_")
+            split_id: list[str] = sample_id.split("_")
             if len(split_id) > 2:
                 sample_id = split_id[1]
                 tag_sample_id: str = "-".join(split_id)
@@ -277,9 +277,9 @@ def get_balsamic_files(self) -> List[TagBase]:
             files.append(TagBase(tags=identifier, subject_id=sample_id, path=file_obj.path))
         return files
 
-    def get_rnafusion_files(self) -> List[TagBase]:
+    def get_rnafusion_files(self) -> list[TagBase]:
         file_obj: pipeline_deliverables.RnafusionFile
-        files: List[TagBase] = []
+        files: list[TagBase] = []
         for file_obj in self.model.files:
             identifier = [file_obj.step]
             if file_obj.tag:

cg_hermes/exceptions.py

@@ -1,6 +1,3 @@
-from typing import List
-
-
 class Error(Exception):
     """Base class for exceptions in this module."""
 
@@ -10,7 +7,7 @@ class Error(Exception):
 class MissingFileError(Error):
     """Exception when mandatory file is missing."""
 
-    def __init__(self, files: List[str], message: str):
+    def __init__(self, files: list[str], message: str):
         self.files = files
         self.message = message
 

cg_hermes/models/pipeline_deliverables.py

@@ -1,4 +1,4 @@
-from typing import FrozenSet, List, Optional
+from typing import FrozenSet, Optional
 
 from pydantic import BaseModel, validator
 
@@ -49,7 +49,7 @@ class BalsamicFile(FileBase):
     """Definition of elements in balsamic deliverables"""
 
     format: Optional[str]
-    tag: List[str]
+    tag: list[str]
 
     @validator("tag", pre=True)
     def split_str(cls, v):
@@ -64,51 +64,51 @@ def split_str(cls, v):
 class PipelineDeliverables(BaseModel):
     """Specification for a general deliverables file"""
 
-    files: List[FileBase]
+    files: list[FileBase]
 
 
 class MipDeliverables(PipelineDeliverables):
     """Specification for a MIP specific deliverables file"""
 
-    files: List[MipFile]
+    files: list[MipFile]
 
 
 class MicrosaltDeliverables(PipelineDeliverables):
     """Specification for a MIP specific deliverables file"""
 
-    files: List[MicrosaltFile]
+    files: list[MicrosaltFile]
 
 
 class BalsamicDeliverables(PipelineDeliverables):
     """Specification for a BALSAMIC specific deliverables file"""
 
-    files: List[BalsamicFile]
+    files: list[BalsamicFile]
 
 
 class FluffyDeliverables(PipelineDeliverables):
     """Specification for a FLUFFY specific deliverables file"""
 
-    files: List[FileBase]
+    files: list[FileBase]
 
 
 class MutantDeliverables(PipelineDeliverables):
     """Specification for a MUTANT specific deliverables file"""
 
-    files: List[MutantFile]
+    files: list[MutantFile]
 
 
 class RnafusionDeliverables(PipelineDeliverables):
     """Specification for a RNAFUSION specific deliverables file"""
 
-    files: List[RnafusionFile]
+    files: list[RnafusionFile]
 
 
 class CGDeliverables(PipelineDeliverables):
     """Class that specifies the output to CG"""
 
     pipeline: str
     bundle_id: str
-    files: List[CGTag]
+    files: list[CGTag]
 
 
 class TagBase(BaseModel):

cg_hermes/models/tags.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import Optional
 
 from pydantic import validator
 from pydantic.main import BaseModel
@@ -7,9 +7,9 @@
 
 
 class TagMap(BaseModel):
-    tags: List[str]
+    tags: list[str]
     is_mandatory: bool
-    used_by: List[str]
+    used_by: list[str]
     bundle_id: Optional[bool] = False
 
     @validator("tags", each_item=True)
@@ -25,5 +25,5 @@ def check_usage(cls, usage):
 
 class CGTag(BaseModel):
     path: str
-    tags: List[str]
+    tags: list[str]
     mandatory: bool