grz-cli 0.1.4__tar.gz → 0.2.0__tar.gz

{grz_cli-0.1.4/src/grz_cli.egg-info → grz_cli-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: grz-cli
-Version: 0.1.4
+Version: 0.2.0
 Summary: Tool for validation, encryption and upload of MV submissions to GDCs.
 Author-email: Koray Kirli <koraykirli@gmail.com>, Mathias Lesche <mathias.lesche@tu-dresden.de>, "Florian R. Hölzlwimmer" <git.ich@frhoelzlwimmer.de>, Till Hartmann <till.hartmann@bih-charite.de>, Thomas Sell <thomas.sell@bih-charite.de>
 License: MIT

{grz_cli-0.1.4 → grz_cli-0.2.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "grz-cli"
-version = "0.1.4"
+version = "0.2.0"
 description = "Tool for validation, encryption and upload of MV submissions to GDCs."
 readme = "README.md"
 license = { text = "MIT" }

{grz_cli-0.1.4 → grz_cli-0.2.0}/src/grz_cli/cli.py

@@ -2,6 +2,7 @@
 CLI module for handling command-line interface operations.
 """
 
+import importlib
 import logging
 import logging.config
 import sys
@@ -107,7 +108,7 @@ class OrderedGroup(click.Group):
     cls=OrderedGroup,
     help="Validate, encrypt, decrypt and upload submissions to a GRZ/GDC.",
 )
-@click.version_option(version="0.1", prog_name="grz-cli")
+@click.version_option(version=importlib.metadata.version("grz-cli"), prog_name="grz-cli")
 @click.option("--log-file", metavar="FILE", type=str, help="Path to log file")
 @click.option(
     "--log-level",
@@ -229,7 +230,7 @@ def decrypt(
         log.error("GRZ private key path is required for decryption.")
         sys.exit(1)
 
-    log.info("Starting encryption...")
+    log.info("Starting decryption...")
 
     submission_dir = Path(submission_dir)
 

{grz_cli-0.1.4/src/grz_cli/models/v1_0_0 → grz_cli-0.2.0/src/grz_cli/models/v1_1_1}/metadata.py

@@ -1,19 +1,3 @@
-# generated by datamodel-codegen:
-#   filename:  grz-schema.json
-#   timestamp: 2024-11-21T12:40:39+00:00
-#   version:   0.26.2
-### Command run:
-## datamodel-codegen --output-model-type pydantic_v2.BaseModel \
-## --input src/grz_cli/resources/grz-schema.json \
-## --use-schema-description --use-field-description --snake-case-field --use-standard-collections --use-union-operator \
-## --field-constraints --use-annotated --enable-version-header --reuse-model --use-subclass-enum --union-mode smart \
-## --class-name 'GrzSubmissionMetadata' --use-double-quotes --target-python-version 3.12
-### Custom modifications:
-### - disallow extra fields (no additional properties allowed)
-### - validate_assignment (i.e. when setting properties, re-trigger validations)
-### - use_enum_values (use values [strings] instead of enum variants)
-### - remove those aliases which are covered by a global `alias_generator=to_camel` setting
-
 from __future__ import annotations
 
 import json
@@ -23,6 +7,7 @@ from collections.abc import Generator
 from datetime import date
 from enum import StrEnum
 from importlib.resources import files
+from itertools import groupby
 from pathlib import Path
 from typing import Annotated, Any, Self
 
@@ -37,6 +22,8 @@ from pydantic.alias_generators import to_camel
 
 from grz_cli.file_operations import calculate_sha256  # type: ignore
 
+SCHEMA_URL = "https://raw.githubusercontent.com/BfArM-MVH/MVGenomseq/refs/tags/v1.1.1/GRZ/grz-schema.json"
+
 log = logging.getLogger(__name__)
 
 
@@ -80,6 +67,33 @@ class GenomicStudySubtype(StrEnum):
     germline_only = "germline-only"
 
 
+class CoverageType(StrEnum):
+    """
+    Health insurance providers
+    """
+
+    GKV = "GKV"
+    PKV = "PKV"
+    BG = "BG"
+    SEL = "SEL"
+    SOZ = "SOZ"
+    GPV = "GPV"
+    PPV = "PPV"
+    BEI = "BEI"
+    SKT = "SKT"
+    UNK = "UNK"
+
+
+class DiseaseType(StrEnum):
+    """
+    Type of the disease
+    """
+
+    oncological = "oncological"
+    rare = "rare"
+    hereditary = "hereditary"
+
+
 class Submission(StrictBaseModel):
     submission_date: date
     """
@@ -93,14 +107,19 @@ class Submission(StrictBaseModel):
 
     tan_g: Annotated[str, StringConstraints(pattern=r"^[a-fA-F0-9]{64}$")]
     """
-    The VNg of the genomic data of the patient that will be reimbursed --> a unique 32-length byte code represented in a hex string of length 64.
+    The VNg of the genomic data of the index patient that will be reimbursed --> a unique 32-length byte code represented in a hex string of length 64.
     """
 
-    local_case_id: str | None = None
+    local_case_id: str
     """
     A local case identifier for synchronizing locally
     """
 
+    coverage_type: CoverageType
+    """
+    Health insurance provider
+    """
+
     submitter_id: Annotated[str, StringConstraints(pattern=r"^[0-9]{9}$")]
     """
     Institutional ID of the submitter according to §293 SGB V.
@@ -119,6 +138,11 @@ class Submission(StrictBaseModel):
     ID of the clinical data node in the format KDKXXXnnn.
     """
 
+    disease_type: DiseaseType
+    """
+    Type of the disease
+    """
+
     genomic_study_type: GenomicStudyType
     """
     whether additional persons are tested as well
@@ -156,49 +180,103 @@ class Relation(StrEnum):
     brother = "brother"
     sister = "sister"
     child = "child"
-    self = "self"
+    index_ = "index"
     other = "other"
 
 
+class MvConsentScopeType(StrEnum):
+    """
+    Consent or refusal to participate and consent, must be indicated for each option listed in the scope of consent.
+    """
+
+    permit = "permit"
+    deny = "deny"
+
+
+class MvConsentScopeDomain(StrEnum):
+    """
+    Scope of consent or revocation.
+    """
+
+    mv_sequencing = "mvSequencing"
+    re_identification = "reIdentification"
+    case_identification = "caseIdentification"
+
+
 class MvConsentScope(StrictBaseModel):
     """
     The scope of the Modellvorhaben consent given by the donor.
     """
 
-    consent_mv_sequencing: bool
+    type_: Annotated[MvConsentScopeType, Field(alias="type")]
+    """
+    Consent or refusal to participate and consent, must be indicated for each option listed in the scope of consent.
+    """
+
+    date: date
+    """
+    Date of signature of the pilot projects consent; in ISO 8601 format YYYY-MM-DD.
+    """
+
+    domain: MvConsentScopeDomain
+    """
+    Scope of consent or revocation.
+    """
+
+
+class MvConsent(StrictBaseModel):
+    presentation_date: date | None = None
     """
-    The donor's consent to participate in the Modellvorhaben and sequencing.
+    Date of delivery. Date (in ISO 8601 format YYYY-MM-DD) on which the Model Project Declaration of Participation 
+    was presented to the patient, unless identical to the date of signature
     """
 
-    consent_case_identification: bool
+    version: str
     """
-    The donor's consent to identify the case.
+    Version of the declaration of participation. 
+    Name and version of the declaration of participation in the MV GenomSeq, e.g.: 
+    'Patient Info TE Consent MVGenomSeq vers01'
     """
 
-    consent_re_identification: bool
+    scope: list[MvConsentScope]
     """
-    The donor's consent to be re-identified and to be re-contacted in case of new findings.
+    Modules of the consent to MV: must have at least a permit of mvSequencing
     """
 
+    @model_validator(mode="after")
+    def ensure_mv_sequencing_scope_is_present(self):
+        if not any(
+            scope.domain == MvConsentScopeDomain.mv_sequencing and scope.type_ == MvConsentScopeType.permit
+            for scope in self.scope
+        ):
+            raise ValueError("Must have at least a permit of mvSequencing")
+        return self
+
+
+class ResearchConsentSchemaVersion(StrEnum):
+    v_2025_0_1 = "2025.0.1"
+
 
-class MvConsentTerminationScope(StrictBaseModel):
+class ResearchConsent(StrictBaseModel):
     """
-    The scope of the termination of the Modellvorhaben consent.
+    Research consents. Multiple declarations of consent are possible! Must be assigned to the respective data sets.
     """
 
-    consent_mv_sequencing_termination: bool | None = None
+    schema_version: ResearchConsentSchemaVersion
     """
-    The patient's termination of the Modellvorhaben consent to participate in the Modellvorhaben and sequencing
+    Schema version of de.medizininformatikinitiative.kerndatensatz.consent
     """
 
-    consent_case_identification_termination: bool | None = None
+    presentation_date: date | None = None
     """
-    The patient's termination of the Modellvorhaben consent to identify the case
+    Date of the delivery of the research consent in ISO 8601 format (YYYY-MM-DD)
     """
 
-    consent_re_identification_termination: bool | None = None
+    scope: object
     """
-    The patient's termination of the Modellvorhaben consent to re-identify the case and to re-contact the patient in case of new findings
+    Scope of the research consent in JSON format following the MII IG Consent v2025 FHIR schema. 
+    See 'https://www.medizininformatik-initiative.de/Kerndatensatz/KDS_Consent_V2025/MII-IG-Modul-Consent.html' and 
+    'https://packages2.fhir.org/packages/de.medizininformatikinitiative.kerndatensatz.consent'.
     """
 
 
@@ -305,8 +383,8 @@ class TumorCellCountMethod(StrEnum):
     Method used to determine cell count.
     """
 
-    pathology = "Pathology"
-    bioinformatics = "Bioinformatics"
+    pathology = "pathology"
+    bioinformatics = "bioinformatics"
     other = "other"
     unknown = "unknown"
 
@@ -378,6 +456,11 @@ class File(StrictBaseModel):
     Type of the file; if BED file is submitted, only 1 file is allowed.
     """
 
+    read_length: Annotated[int, Field(strict=True, ge=0)] | None = None
+    """
+    The read length; in the case of long-read sequencing it is the rounded average read length.
+    """
+
     checksum_type: ChecksumType | None = ChecksumType.sha256
     """
     Type of checksum algorithm used
@@ -408,6 +491,12 @@ class File(StrictBaseModel):
     Indicates the lane
     """
 
+    @model_validator(mode="after")
+    def ensure_read_length_is_present_for_bam_and_fastq(self):
+        if self.file_type in {FileType.bam, FileType.fastq} and self.read_length is None:
+            raise ValueError(f"Read length missing for file '{self.file_path}' of type '{self.file_type}'.")
+        return self
+
     def validate_data(self, local_file_path: Path) -> Generator[str]:
         """
         Validates whether the provided file matches this metadata.
@@ -467,6 +556,15 @@ class PercentBasesAboveQualityThreshold(StrictBaseModel):
     """
 
 
+class ReferenceGenome(StrEnum):
+    """
+    Reference genome used according to the Genome Reference Consortium (https://www.ncbi.nlm.nih.gov/grc)
+    """
+
+    GRCh37 = "GRCh37"
+    GRCh38 = "GRCh38"
+
+
 class SequenceData(StrictBaseModel):
     bioinformatics_pipeline_name: str
     """
@@ -478,9 +576,9 @@ class SequenceData(StrictBaseModel):
     Version or commit hash of the bioinformatics pipeline
     """
 
-    reference_genome: str
+    reference_genome: ReferenceGenome
     """
-    Reference genome used
+    Reference genome used according to the Genome Reference Consortium (https://www.ncbi.nlm.nih.gov/grc)
     """
 
     percent_bases_above_quality_threshold: PercentBasesAboveQualityThreshold
@@ -503,11 +601,6 @@ class SequenceData(StrictBaseModel):
     Fraction of targeted regions that are above minimum coverage
     """
 
-    read_length: Annotated[int, Field(strict=True, ge=0)]
-    """
-    The read length; in the case of long-read sequencing it is the rounded average read length.
-    """
-
     non_coding_variants: bool
     """
     The analysis includes non-coding variants -> true or false
@@ -652,14 +745,12 @@ class LabDatum(StrictBaseModel):
 
 
 class Donor(StrictBaseModel):
-    tan_g: Annotated[str, StringConstraints(pattern=r"^[a-fA-F0-9]{64}$")]
-    """
-    The VNg of the genomic data of the donor --> a unique 32-length byte code represented in a hex string of length 64.
-    """
-
-    local_case_id: str | None = None
+    donor_pseudonym: str
     """
-    A local case identifier for synchronizing locally
+    A unique identifier given by the Leistungserbringer for each donor of a single, duo or trio sequencing; 
+    the donorPseudonym needs to be identifiable by the Leistungserbringer 
+    in case of changes to the consents by one of the donors. 
+    For Index patient use TanG.
     """
 
     gender: Gender
@@ -672,64 +763,11 @@ class Donor(StrictBaseModel):
     Relationship of the donor in respect to the index patient, e.g. 'index', 'brother', 'mother', etc.
     """
 
-    mv_consent_date: date
-    """
-    Date of the signature of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD
-    """
-
-    mv_consent_presented_date: date | None = None
-    """
-    Date of the presentation of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD
-    """
-
-    mv_consent_version: str
-    """
-    Version of the research consent
-    """
-
-    mv_consent_scope: MvConsentScope
-    """
-    The scope of the Modellvorhaben consent given by the donor.
-    """
-
-    mv_consent_termination_date: date | None = None
-    """
-    Date of the termination of the Modellvorhaben consent; Date in ISO 8601 format YYYY-MM-DD
-    """
-
-    mv_consent_termination_scope: MvConsentTerminationScope | None = None
-    """
-    The scope of the termination of the Modellvorhaben consent.
-    """
-
-    research_consent_date: date | None = None
-    """
-    Date of the signature of the research consent; Date in ISO 8601 format YYYY-MM-DD
-    """
-
-    research_consent_presented_date: date | None = None
-    """
-    Date of the presentation of the research consent; Date in ISO 8601 format YYYY-MM-DD
-    """
-
-    research_consent_version: str | None = None
-    """
-    Version of the research consent
-    """
-
-    research_consent_scope: dict[str, Any] | None = None
-    """
-    Scope of the research consent given by the patient; shall be given in JSON format.
-    """
-
-    research_consent_revocation_date: date | None = None
-    """
-    Date of the revocation of the research consent; Date in ISO 8601 format YYYY-MM-DD
-    """
+    mv_consent: MvConsent
 
-    research_consent_revocation_scope: dict[str, Any] | None = None
+    research_consents: list[ResearchConsent]
     """
-    Scope of the revocation of the research consent given by the patient; shall be given in JSON format
+    Research consents. Multiple declarations of consent are possible! Must be assigned to the respective data sets.
     """
 
     lab_data: list[LabDatum]
@@ -742,7 +780,7 @@ class Donor(StrictBaseModel):
         for lab_datum in self.lab_data:
             if not lab_datum.has_sequence_data():
                 log.warning(
-                    f"No sequence data found for lab datum '{lab_datum.lab_data_name}' in donor '{self.tan_g}'. "
+                    f"No sequence data found for lab datum '{lab_datum.lab_data_name}' in donor '{self.donor_pseudonym}'. "
                     "Is this a submission without sequence data?"
                 )
         return self
@@ -767,7 +805,9 @@ class Donor(StrictBaseModel):
                 and lab_datum.library_type in lib_types
                 and not lab_datum.sequence_data.contains_files(FileType.bed)
             ):
-                raise ValueError(f"BED file missing for lab datum '{lab_datum.lab_data_name}' in donor '{self.tan_g}'.")
+                raise ValueError(
+                    f"BED file missing for lab datum '{lab_datum.lab_data_name}' in donor '{self.donor_pseudonym}'."
+                )
 
         return self
 
@@ -778,12 +818,14 @@ class Donor(StrictBaseModel):
         """
         for lab_datum in self.lab_data:
             if lab_datum.has_sequence_data() and not lab_datum.sequence_data.contains_files(FileType.vcf):
-                raise ValueError(f"VCF file missing for lab datum '{lab_datum.lab_data_name}' in donor '{self.tan_g}'.")
+                raise ValueError(
+                    f"VCF file missing for lab datum '{lab_datum.lab_data_name}' in donor '{self.donor_pseudonym}'."
+                )
 
         return self
 
     @model_validator(mode="after")
-    def validate_fastq_file_exists(self):
+    def validate_fastq_file_exists(self):  # noqa: C901
         """
         Check if there is a FASTQ file
         """
@@ -800,20 +842,44 @@ class Donor(StrictBaseModel):
                 for i in fastq_files:
                     if i.read_order is None:
                         raise ValueError(
-                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.tan_g}': "
+                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.donor_pseudonym}': "
                             f"No read order specified for FASTQ file '{i.file_path}'!"
                         )
 
-                # check if there is an equal number of R1 and R2 files
-                r1_fastq_files = [i for i in fastq_files if i.read_order == ReadOrder.r1]
-                r2_fastq_files = [i for i in fastq_files if i.read_order == ReadOrder.r2]
+                key = lambda f: (f.flowcell_id, f.lane_id)
+                fastq_files.sort(key=key)
+                for _key, group in groupby(fastq_files, key):
+                    flowcell_id = _key[0]
+                    lane_id = _key[1]
+                    files = list(group)
+
+                    # separate R1 and R2 files
+                    fastq_r1_files = [f for f in files if f.read_order == ReadOrder.r1]
+                    fastq_r2_files = [f for f in files if f.read_order == ReadOrder.r2]
+
+                    # check that there are exactly one R1 and on R2 file present
+                    if len(fastq_r1_files) > 1:
+                        raise ValueError(
+                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.donor_pseudonym}': "
+                            f"Paired end sequencing layout but multiple R1 files for flowcell id '{flowcell_id}', lane id '{lane_id}'!"
+                        )
+                    elif len(fastq_r1_files) < 1:
+                        raise ValueError(
+                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.donor_pseudonym}': "
+                            f"Paired end sequencing layout but missing R1 file for flowcell id '{flowcell_id}', lane id '{lane_id}'!"
+                        )
+
+                    if len(fastq_r2_files) > 1:
+                        raise ValueError(
+                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.donor_pseudonym}': "
+                            f"Paired end sequencing layout but multiple R2 files for flowcell id '{flowcell_id}', lane id '{lane_id}'!"
+                        )
+                    elif len(fastq_r2_files) < 1:
+                        raise ValueError(
+                            f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.donor_pseudonym}': "
+                            f"Paired end sequencing layout but missing R2 file for flowcell id '{flowcell_id}', lane id '{lane_id}'!"
+                        )
 
-                if len(r1_fastq_files) != len(r2_fastq_files):
-                    raise ValueError(
-                        f"Error in lab datum '{lab_datum.lab_data_name}' of donor '{self.tan_g}': "
-                        f"Paired end sequencing layout but number of R1 FASTQ files ({len(r1_fastq_files)})"
-                        f" differs from number of R2 FASTQ files ({len(r2_fastq_files)})!"
-                    )
         return self
 
 
@@ -822,6 +888,8 @@ class GrzSubmissionMetadata(StrictBaseModel):
     General metadata schema for submissions to the GRZ
     """
 
+    schema_: Annotated[str, Field(alias="$schema")] = SCHEMA_URL
+
     submission: Submission
 
     donors: list[Donor]
@@ -829,6 +897,12 @@ class GrzSubmissionMetadata(StrictBaseModel):
     List of donors including the index patient.
     """
 
+    @model_validator(mode="after")
+    def check_schema(self):
+        if self.schema_ != SCHEMA_URL:
+            log.warning(f"Unknown GRZ metadata schema URL: {self.schema_}")
+        return self
+
     @model_validator(mode="after")
     def validate_donor_count(self):
         """
@@ -858,11 +932,11 @@ class GrzSubmissionMetadata(StrictBaseModel):
         Check if oncology samples have tumor cell counts.
         """
         for donor in self.donors:
-            case_id = donor.tan_g
+            pseudonym = donor.donor_pseudonym
             for lab_datum in donor.lab_data:
                 if lab_datum.sequence_subtype == SequenceSubtype.somatic and lab_datum.tumor_cell_count is None:
                     raise ValueError(
-                        f"Missing tumor cell count for donor '{case_id}', lab datum '{lab_datum.lab_data_name}'!"
+                        f"Missing tumor cell count for donor '{pseudonym}', lab datum '{lab_datum.lab_data_name}'!"
                     )
 
         return self
@@ -873,11 +947,11 @@ class GrzSubmissionMetadata(StrictBaseModel):
         Check if the submission contains lab data with the same name within one donor.
         """
         for donor in self.donors:
-            case_id = donor.tan_g
+            pseudonym = donor.donor_pseudonym
             lab_data_names = set()
             for lab_datum in donor.lab_data:
                 if lab_datum.lab_data_name in lab_data_names:
-                    raise ValueError(f"Duplicate lab datum '{lab_datum.lab_data_name}' in donor '{case_id}'")
+                    raise ValueError(f"Duplicate lab datum '{lab_datum.lab_data_name}' in donor '{pseudonym}'")
                 else:
                     lab_data_names.add(lab_datum.lab_data_name)
 
@@ -908,7 +982,7 @@ class GrzSubmissionMetadata(StrictBaseModel):
                     )
                     info = dict(zip(names, key, strict=True))
                     log.warning(
-                        f"No thresholds for the specified combination {info} found (donor {donor.tan_g})!\n"
+                        f"No thresholds for the specified combination {info} found (donor {donor.donor_pseudonym})!\n"
                         f"Valid combinations:\n{allowed_combinations}.\n"
                         f"See https://www.bfarm.de/SharedDocs/Downloads/DE/Forschung/modellvorhaben-genomsequenzierung/Qs-durch-GRZ.pdf?__blob=publicationFile for more details.\n"
                         f"Skipping threshold validation."
@@ -919,12 +993,29 @@ class GrzSubmissionMetadata(StrictBaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def validate_reference_genome_compatibility(self):
+        reference_genomes = {
+            (donor.donor_pseudonym, lab_datum.lab_data_name): lab_datum.sequence_data.reference_genome
+            for donor in self.donors
+            for lab_datum in donor.lab_data
+        }
+        unique_reference_genomes = set(reference_genomes.values())
+        if len(unique_reference_genomes) > 1:
+            raise ValueError(
+                f"Incompatible reference genomes found: {unique_reference_genomes}.\n"
+                f"Reference genomes must be consistent within a submission.\n"
+                f"Reference genomes: {reference_genomes}"
+            )
+
+        return self
+
 
 def _check_thresholds(donor: Donor, lab_datum: LabDatum, thresholds: dict[str, Any]):
     if not lab_datum.has_sequence_data():
         # Skip if no sequence data is present; warning issues in the validator `warn_empty_sequence_data` of `Donor`.
         return
-    case_id = donor.tan_g
+    pseudonym = donor.donor_pseudonym
     lab_data_name = lab_datum.lab_data_name
     # mypy cannot reason about the `has_sequence_data` check
     sequence_data = typing.cast(SequenceData, lab_datum.sequence_data)
@@ -933,17 +1024,18 @@ def _check_thresholds(donor: Donor, lab_datum: LabDatum, thresholds: dict[str, A
     mean_depth_of_coverage_v = sequence_data.mean_depth_of_coverage
     if mean_depth_of_coverage_t and mean_depth_of_coverage_v < mean_depth_of_coverage_t:
         raise ValueError(
-            f"Mean depth of coverage for donor '{case_id}', lab datum '{lab_data_name}' "
+            f"Mean depth of coverage for donor '{pseudonym}', lab datum '{lab_data_name}' "
             f"below threshold: {mean_depth_of_coverage_v} < {mean_depth_of_coverage_t}"
         )
 
     read_length_t = thresholds.get("readLength")
-    read_length_v = sequence_data.read_length
-    if read_length_t and read_length_v < read_length_t:
-        raise ValueError(
-            f"Read length for donor '{case_id}', lab datum '{lab_data_name}' "
-            f"below threshold: {read_length_v} < {read_length_t}"
-        )
+    for f in sequence_data.list_files(FileType.fastq) + sequence_data.list_files(FileType.bam):
+        read_length_v = f.read_length
+        if read_length_t and read_length_v < read_length_t:
+            raise ValueError(
+                f"Read length for donor '{pseudonym}', lab datum '{lab_data_name}' "
+                f"below threshold: {read_length_v} < {read_length_t}"
+            )
 
     if t := thresholds.get("targetedRegionsAboveMinCoverage"):
         min_coverage_t = t.get("minCoverage")
@@ -954,12 +1046,12 @@ def _check_thresholds(donor: Donor, lab_datum: LabDatum, thresholds: dict[str, A
 
         if min_coverage_t and min_coverage_v < min_coverage_t:
             raise ValueError(
-                f"Minimum coverage for donor '{case_id}', lab datum '{lab_data_name}' "
+                f"Minimum coverage for donor '{pseudonym}', lab datum '{lab_data_name}' "
                 f"below threshold: {min_coverage_v} < {min_coverage_t}"
             )
         if fraction_above_t and fraction_above_v < fraction_above_t:
             raise ValueError(
-                f"Fraction of targeted regions above minimum coverage for donor '{case_id}', "
+                f"Fraction of targeted regions above minimum coverage for donor '{pseudonym}', "
                 f"lab datum '{lab_data_name}' below threshold: "
                 f"{fraction_above_v} < {fraction_above_t}"
             )

{grz_cli-0.1.4 → grz_cli-0.2.0}/src/grz_cli/parser.py

@@ -15,7 +15,7 @@ from .download import S3BotoDownloadWorker
 from .fastq_validation import validate_paired_end_reads, validate_single_end_reads
 from .file_operations import Crypt4GH, calculate_sha256
 from .models.config import ConfigModel
-from .models.v1_0_0.metadata import (
+from .models.v1_1_1.metadata import (
     File,
     FileType,
     GrzSubmissionMetadata,
@@ -23,7 +23,7 @@ from .models.v1_0_0.metadata import (
     SequenceData,
     SequencingLayout,
 )
-from .models.v1_0_0.metadata import File as SubmissionFileMetadata
+from .models.v1_1_1.metadata import File as SubmissionFileMetadata
 from .progress_logging import FileProgressLogger
 from .states import DecryptionState, EncryptionState, ValidationState
 from .upload import S3BotoUploadWorker

{grz_cli-0.1.4 → grz_cli-0.2.0}/src/grz_cli/progress_logging.py

@@ -10,7 +10,7 @@ from os import PathLike
 from pathlib import Path
 
 from .file_operations import read_multiple_json
-from .models.v1_0_0.metadata import File as SubmissionFileMetadata
+from .models.v1_1_1.metadata import File as SubmissionFileMetadata
 from .states import State
 
 Index = tuple[str, float, int]