feat: add Sentieon path argument to config (#1461)

#### Added

- Sentieon install directory path and Sentieon license to case config arguments

BALSAMIC/commands/config/case.py

@@ -33,6 +33,8 @@
     OPTION_PANEL_BED,
     OPTION_PON_CNN,
     OPTION_QUALITY_TRIM,
+    OPTION_SENTIEON_INSTALL_DIR,
+    OPTION_SENTIEON_LICENSE,
     OPTION_SWEGEN_SNV,
     OPTION_SWEGEN_SV,
     OPTION_TUMOR_SAMPLE_NAME,
@@ -43,7 +45,11 @@
 from BALSAMIC.constants.analysis import BIOINFO_TOOL_ENV, AnalysisWorkflow, Gender
 from BALSAMIC.constants.cache import GenomeVersion
 from BALSAMIC.constants.constants import FileType
-from BALSAMIC.constants.paths import CONTAINERS_DIR
+from BALSAMIC.constants.paths import (
+    CONTAINERS_DIR,
+    SENTIEON_DNASCOPE_MODEL,
+    SENTIEON_TNSCOPE_MODEL,
+)
 from BALSAMIC.constants.workflow_params import VCF_DICT
 from BALSAMIC.models.config import ConfigModel
 from BALSAMIC.utils.cli import (
@@ -84,6 +90,8 @@
 @OPTION_PANEL_BED
 @OPTION_PON_CNN
 @OPTION_QUALITY_TRIM
+@OPTION_SENTIEON_INSTALL_DIR
+@OPTION_SENTIEON_LICENSE
 @OPTION_SWEGEN_SNV
 @OPTION_SWEGEN_SV
 @OPTION_TUMOR_SAMPLE_NAME
@@ -117,6 +125,8 @@ def case_config(
     panel_bed: Path,
     pon_cnn: Path,
     quality_trim: bool,
+    sentieon_install_dir: Path,
+    sentieon_license: str,
     swegen_snv: Path,
     swegen_sv: Path,
     tumor_sample_name: str,
@@ -188,6 +198,13 @@ def case_config(
         directory.mkdir(exist_ok=True)
 
     config_collection_dict = ConfigModel(
+        sentieon={
+            "sentieon_install_dir": sentieon_install_dir,
+            "sentieon_license": sentieon_license,
+            "sentieon_exec": Path(sentieon_install_dir, "bin", "sentieon").as_posix(),
+            "dnascope_model": SENTIEON_DNASCOPE_MODEL.as_posix(),
+            "tnscope_model": SENTIEON_TNSCOPE_MODEL.as_posix(),
+        },
         QC={
             "quality_trim": quality_trim,
             "adapter_trim": adapter_trim,

BALSAMIC/commands/config/pon.py

@@ -16,6 +16,8 @@
     OPTION_FASTQ_PATH,
     OPTION_GENOME_INTERVAL,
     OPTION_GENOME_VERSION,
+    OPTION_SENTIEON_INSTALL_DIR,
+    OPTION_SENTIEON_LICENSE,
     OPTION_PANEL_BED,
     OPTION_PON_VERSION,
     OPTION_PON_WORKFLOW,
@@ -26,7 +28,11 @@
 from BALSAMIC.constants.analysis import BIOINFO_TOOL_ENV, PONWorkflow
 from BALSAMIC.constants.cache import GenomeVersion
 from BALSAMIC.constants.constants import FileType
-from BALSAMIC.constants.paths import CONTAINERS_DIR
+from BALSAMIC.constants.paths import (
+    CONTAINERS_DIR,
+    SENTIEON_DNASCOPE_MODEL,
+    SENTIEON_TNSCOPE_MODEL,
+)
 from BALSAMIC.models.config import ConfigModel
 from BALSAMIC.utils.cli import (
     generate_graph,
@@ -49,6 +55,8 @@
 @OPTION_FASTQ_PATH
 @OPTION_GENOME_VERSION
 @OPTION_GENOME_INTERVAL
+@OPTION_SENTIEON_INSTALL_DIR
+@OPTION_SENTIEON_LICENSE
 @OPTION_PANEL_BED
 @OPTION_PON_WORKFLOW
 @OPTION_PON_VERSION
@@ -66,6 +74,8 @@ def pon_config(
     fastq_path: Path,
     genome_version: GenomeVersion,
     genome_interval: Path,
+    sentieon_install_dir: Path,
+    sentieon_license: str,
     panel_bed: Path,
     pon_workflow: PONWorkflow,
     quality_trim: bool,
@@ -105,6 +115,13 @@ def pon_config(
         directory.mkdir(exist_ok=True)
 
     config_collection_dict = ConfigModel(
+        sentieon={
+            "sentieon_install_dir": sentieon_install_dir,
+            "sentieon_license": sentieon_license,
+            "sentieon_exec": Path(sentieon_install_dir, "bin", "sentieon").as_posix(),
+            "dnascope_model": SENTIEON_DNASCOPE_MODEL.as_posix(),
+            "tnscope_model": SENTIEON_TNSCOPE_MODEL.as_posix(),
+        },
         QC={
             "adapter_trim": adapter_trim,
             "quality_trim": quality_trim,

BALSAMIC/commands/options.py

@@ -370,6 +370,20 @@
     help="Sample configuration file",
 )
 
+OPTION_SENTIEON_INSTALL_DIR = click.option(
+    "--sentieon-install-dir",
+    type=click.Path(exists=True, resolve_path=True),
+    required=True,
+    help="Path to Sentieon install directory",
+)
+
+OPTION_SENTIEON_LICENSE = click.option(
+    "--sentieon-license",
+    required=True,
+    type=click.STRING,
+    help="Sentieon license in format IP:Port",
+)
+
 OPTION_SHOW_ONLY_MISSING_FILES = click.option(
     "-m",
     "--show-only-missing",

BALSAMIC/constants/paths.py

@@ -13,10 +13,10 @@
 
 # Sentieon specific constants
 SENTIEON_MODELS_DIR: Path = Path(BALSAMIC_DIR, "assets", "sentieon_models")
-SENTIEON_DNASCOPE_DIR: Path = Path(
+SENTIEON_DNASCOPE_MODEL: Path = Path(
     SENTIEON_MODELS_DIR, "SentieonDNAscopeModelBeta0.4a-201808.05.model"
 )
-SENTIEON_TNSCOPE_DIR: Path = Path(
+SENTIEON_TNSCOPE_MODEL: Path = Path(
     SENTIEON_MODELS_DIR, "SentieonTNscopeModel_GiAB_HighAF_LowFP-201711.05.model"
 )
 

BALSAMIC/models/config.py

@@ -178,6 +178,23 @@ class CustomFilters(BaseModel):
     umi_min_reads: str | None = None
 
 
+class Sentieon(BaseModel):
+    """
+    Class providing common functions and variables for different balsamic workflows.
+
+    Attributes:
+        sentieon_install_dir: Field(required); path to Sentieon installation directory
+        sentieon_exec:  Field(required); path to Sentieon executeable
+        sentieon_license: Field(required); Sentieon license string
+    """
+
+    sentieon_install_dir: Annotated[str, AfterValidator(is_dir)]
+    sentieon_exec: Annotated[str, AfterValidator(is_file)]
+    sentieon_license: str
+    dnascope_model: Annotated[str, AfterValidator(is_file)]
+    tnscope_model: Annotated[str, AfterValidator(is_file)]
+
+
 class ConfigModel(BaseModel):
     """
     Class providing common functions and variables for different balsamic workflows.
@@ -194,6 +211,7 @@ class ConfigModel(BaseModel):
         background_variants: Field(Path(optional)); path to BACKGROUND VARIANTS for UMI
         analysis: Field(AnalysisModel); Pydantic model containing workflow variables
         custom_filters: Field(CustomFilters); custom parameters for variant filtering
+        sentieon: Field(required); Sentieon model attributes
 
     This class also contains functions that help retrieve sample and file information,
     facilitating BALSAMIC run operations in Snakemake.
@@ -220,6 +238,7 @@ class ConfigModel(BaseModel):
     background_variants: Optional[str] = None
     analysis: AnalysisModel
     custom_filters: CustomFilters | None = None
+    sentieon: Sentieon
 
     @field_validator("reference")
     def abspath_as_str(cls, reference: Dict[str, Path]):

BALSAMIC/snakemake_rules/align/sentieon_alignment.rule

@@ -13,8 +13,8 @@ rule sentieon_align_sort:
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         header = params.common.align_header,
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample_id = "{sample}",
         sample_type = lambda wildcards: config_model.get_sample_type_by_name(wildcards.sample, uppercase=True),
         fastq_pattern = "{fastq_pattern}"
@@ -53,8 +53,8 @@ rule sentieon_dedup:
         Path(benchmark_dir, "sentieon_dedup_{sample_type}.{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample_id = "{sample}"
     threads:
         get_threads(cluster_config, 'sentieon_dedup')
@@ -98,8 +98,8 @@ rule sentieon_realign:
         Path(benchmark_dir, "sentieon_realign_{sample_type}.{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample_id = "{sample}"
     threads:
         get_threads(cluster_config, 'sentieon_realign')

BALSAMIC/snakemake_rules/quality_control/sentieon_qc_metrics.rule

@@ -24,8 +24,8 @@ rule sentieon_wgs_metrics:
         min_base_qual = '10',
         gene_list = config["reference"]["refgene_txt"],
         cov_threshold = repeat("--cov_thresh", [50, 100, 150, 200, 250]),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample = '{sample}'
     threads:
         get_threads(cluster_config, 'sentieon_wgs_metrics')

BALSAMIC/snakemake_rules/umi/sentieon_consensuscall.rule

@@ -13,9 +13,9 @@ rule sentieon_consensuscall_umi:
         Path(benchmark_dir, "sentieon_consensuscall_umi_{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_install_dir = config["SENTIEON_INSTALL_DIR"],
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_install_dir = config_model.sentieon.sentieon_install_dir,
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         tag = params.umiconsensuscall.tag,
         ip_format = params.umiconsensuscall.align_format,
         sample_id = '{sample}'
@@ -54,9 +54,9 @@ rule sentieon_bwa_umiconsensus:
         Path(benchmark_dir, "sentieon_bwa_umiconsensus_{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_install_dir = config["SENTIEON_INSTALL_DIR"],
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_install_dir = config_model.sentieon.sentieon_install_dir,
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sheader = params.umicommon.align_header,
         ip_bases = params.umicommon.align_intbases,
         sample_id = "{sample}"

BALSAMIC/snakemake_rules/umi/sentieon_umiextract.rule

@@ -14,9 +14,9 @@ rule sentieon_umiextract:
         Path(benchmark_dir, "sentieon_umiextract_{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_install_dir = config["SENTIEON_INSTALL_DIR"],
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_install_dir = config_model.sentieon.sentieon_install_dir,
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         ds_params = params.umiextract.read_structure,
         sample = "{sample}"
     threads:
@@ -50,9 +50,9 @@ rule sentieon_bwa_umiextract:
         Path(benchmark_dir, "sentieon_bwa_umiextract_{sample}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_install_dir = config["SENTIEON_INSTALL_DIR"],
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_install_dir = config_model.sentieon.sentieon_install_dir,
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample_id = '{sample}',
         sheader = params.umicommon.align_header,
         ip_bases = params.umicommon.align_intbases

BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope.rule

@@ -19,8 +19,8 @@ rule sentieon_tnscope_umi:
     params:
         housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         tumor_af = params.umicommon.filter_tumor_af,
         algo = params.tnscope_umi.algo,
         disable_detect = params.tnscope_umi.disable_detect,

BALSAMIC/snakemake_rules/umi/sentieon_varcall_tnscope_tn.rule

@@ -19,8 +19,8 @@ rule sentieon_tnscope_umi_tn:
     params:
         housekeeper_id = {"id": config["analysis"]["case_id"], "tags": "research"},
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         tumor_af = params.umicommon.filter_tumor_af,
         algo = params.tnscope_umi.algo,
         disable_detect = params.tnscope_umi.disable_detect,

BALSAMIC/snakemake_rules/variant_calling/gens_preprocessing.rule

@@ -11,9 +11,9 @@ rule sentieon_DNAscope_gnomad:
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         pcr_model = params.common.pcr_model,
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
-        sentieon_ml_dnascope = config["SENTIEON_DNASCOPE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic =  config_model.sentieon.sentieon_license,
+        sentieon_ml_dnascope = config_model.sentieon.dnascope_model,
         sample = "{sample}"
     benchmark:
         Path(benchmark_dir, "sentieon_DNAscope_gnomad_{sample}.tsv").as_posix()

BALSAMIC/snakemake_rules/variant_calling/germline.rule

@@ -13,8 +13,8 @@ rule sentieon_DNAscope:
         Path(benchmark_dir, "sentieon_dnascope_{sample_type}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample = '{sample_type}'
     threads:
         get_threads(cluster_config, 'sentieon_DNAscope')

BALSAMIC/snakemake_rules/variant_calling/sentieon_germline.rule

@@ -13,9 +13,9 @@ rule sentieon_DNAscope:
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
         pcr_model = params.common.pcr_model,
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
-        sentieon_ml_dnascope = config["SENTIEON_DNASCOPE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
+        sentieon_ml_dnascope = config_model.sentieon.dnascope_model,
         sample = "{sample_type}"
     benchmark:
         Path(benchmark_dir, 'sentieon_DNAscope_' + "{sample_type}.tsv").as_posix()

BALSAMIC/snakemake_rules/variant_calling/sentieon_t_varcall.rule

@@ -25,8 +25,8 @@ rule sentieon_base_calibration:
         Path(benchmark_dir, "sentieon_base_calibration_{sample_type}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample = "sample_type"
     threads:
         get_threads(cluster_config, 'sentieon_base_calibration')
@@ -92,8 +92,8 @@ rule sentieon_TNscope_tumor_only:
         tumor_options = VARCALL_PARAMS["tnscope"]["tumor"],
         pon = " " if get_pon(config) is None else " ".join(["--pon", get_pon(config)]),
         pcr_model = params.common.pcr_model,
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         case_name =  config["analysis"]["case_id"]
     threads:
         get_threads(cluster_config, 'sentieon_TNscope_tumor_only')

BALSAMIC/snakemake_rules/variant_calling/sentieon_tn_varcall.rule

@@ -18,8 +18,8 @@ rule sentieon_base_calibration:
         Path(benchmark_dir, "sentieon_base_calibration_{sample_type}.tsv").as_posix()
     params:
         tmpdir = tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         sample = "{sample_type}"
     threads:
         get_threads(cluster_config, 'sentieon_base_calibration')
@@ -85,9 +85,9 @@ rule sentieon_TNscope:
         pcr_model = params.common.pcr_model,
         tumor_options = VARCALL_PARAMS["tnscope"]["tumor"],
         normal_options = VARCALL_PARAMS["tnscope"]["normal"],
-        sentieon_ml_tnscope = config["SENTIEON_TNSCOPE"],
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_ml_tnscope = config_model.sentieon.tnscope_model,
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         case_name = config["analysis"]["case_id"]
     threads:
         get_threads(cluster_config, 'sentieon_TNscope')

BALSAMIC/snakemake_rules/variant_calling/somatic_tumor_only.rule

@@ -97,8 +97,8 @@ rule sentieon_TNhaplotyper_tumor_only:
     params:
         tumor = "TUMOR",
         tmpdir= tempfile.mkdtemp(prefix=tmp_dir),
-        sentieon_exec = config["SENTIEON_EXEC"],
-        sentieon_lic = config["SENTIEON_LICENSE"],
+        sentieon_exec = config_model.sentieon.sentieon_exec,
+        sentieon_lic = config_model.sentieon.sentieon_license,
         case_name = config["analysis"]["case_id"]
     threads:
         get_threads(cluster_config, 'sentieon_TNhaplotyper_tumor_only')