feat: add taxonomic information about organisms

.gitignore

@@ -15,3 +15,5 @@ postman/
 .coverage
 htmlcov/
 coverage.xml
+.claude/
+.windsurf/

alembic/versions/0010_add_taxonomy_info.py

@@ -0,0 +1,63 @@
+"""Add taxonomy_info table and migrate augustus_dataset_name off organism.
+
+Revision ID: 0010_add_taxonomy_info
+Revises: 0009_use_taxon_id_as_organism_pk
+Create Date: 2026-05-01
+"""
+
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0010_add_taxonomy_info"
+down_revision = "0009_use_taxon_id_as_organism_pk"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # 1. Create taxonomy_info table with PK = FK to organism.taxon_id
+    op.create_table(
+        "taxonomy_info",
+        sa.Column("taxon_id", sa.Integer(), nullable=False),
+        sa.Column("busco_odb10_dataset_name", sa.Text(), nullable=True),
+        sa.Column("busco_odb12_dataset_name", sa.Text(), nullable=True),
+        sa.Column("find_plastid", sa.Boolean(), nullable=True),
+        sa.Column("hic_motif", sa.Text(), nullable=True),
+        sa.Column("mitochondrial_genetic_code_id", sa.Integer(), nullable=True),
+        sa.Column("mitohifi_reference_species", sa.Text(), nullable=True),
+        sa.Column("oatk_hmm_name", sa.Text(), nullable=True),
+        sa.Column("defined_class", sa.Text(), nullable=True),
+        sa.Column("augustus_dataset_name", sa.Text(), nullable=True),
+        sa.Column("genetic_code_id", sa.Integer(), nullable=True),
+        sa.PrimaryKeyConstraint("taxon_id"),
+        sa.ForeignKeyConstraint(
+            ["taxon_id"], ["organism.taxon_id"], ondelete="CASCADE"
+        ),
+    )
+
+    # 2. Migrate existing augustus_dataset_name values from organism into taxonomy_info
+    op.execute("""
+        INSERT INTO taxonomy_info (taxon_id, augustus_dataset_name)
+        SELECT taxon_id, augustus_dataset_name
+        FROM organism
+        WHERE augustus_dataset_name IS NOT NULL
+    """)
+
+    # 3. Drop augustus_dataset_name from organism
+    op.drop_column("organism", "augustus_dataset_name")
+
+
+def downgrade() -> None:
+    # 1. Restore the column on organism
+    op.add_column("organism", sa.Column("augustus_dataset_name", sa.Text(), nullable=True))
+
+    # 2. Copy data back from taxonomy_info
+    op.execute("""
+        UPDATE organism o
+        SET augustus_dataset_name = ti.augustus_dataset_name
+        FROM taxonomy_info ti
+        WHERE o.taxon_id = ti.taxon_id
+    """)
+
+    # 3. Drop the taxonomy_info table
+    op.drop_table("taxonomy_info")

app/api/v1/api.py

@@ -15,6 +15,7 @@
     reads,
     sample_submissions,
     samples,
+    taxonomy_info,
     users,
     xml_export,
 )
@@ -46,6 +47,9 @@
 api_router.include_router(reads.router, prefix="/reads", tags=["reads"])
 api_router.include_router(qc_reads.router, prefix="/qc-reads", tags=["qc-reads"])
 api_router.include_router(genome_notes.router, prefix="/genome-notes", tags=["genome-notes"])
+api_router.include_router(
+    taxonomy_info.router, prefix="/taxonomy-info", tags=["taxonomy-info"]
+)
 
 # XML export endpoints
 api_router.include_router(xml_export.router, prefix="/xml-export", tags=["xml-export"])

app/api/v1/endpoints/taxonomy_info.py

@@ -0,0 +1,110 @@
+from typing import Any, Dict, List
+
+from fastapi import APIRouter, Depends, HTTPException, status
+from sqlalchemy.orm import Session
+
+from app.core.dependencies import get_current_active_user, get_db
+from app.core.pagination import Pagination, apply_pagination, pagination_params
+from app.core.policy import policy
+from app.models.taxonomy_info import TaxonomyInfo
+from app.models.user import User
+from app.schemas.bulk_import import BulkImportResponse
+from app.schemas.taxonomy_info import (
+    TaxonomyInfo as TaxonomyInfoSchema,
+)
+from app.schemas.taxonomy_info import (
+    TaxonomyInfoCreate,
+    TaxonomyInfoUpdate,
+)
+from app.services.taxonomy_info_service import taxonomy_info_service
+
+router = APIRouter()
+
+
+@router.get("/", response_model=List[TaxonomyInfoSchema])
+def list_taxonomy_info(
+    db: Session = Depends(get_db),
+    pagination: Pagination = Depends(pagination_params),
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """List taxonomy info records."""
+    query = db.query(TaxonomyInfo)
+    query = apply_pagination(query, pagination)
+    return query.all()
+
+
+@router.post("/bulk-import", response_model=BulkImportResponse)
+@policy("taxonomy_info:bulk_import")
+def bulk_import_taxonomy_info(
+    *,
+    db: Session = Depends(get_db),
+    data: Dict[str, Dict[str, Any]],
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """
+    Bulk import taxonomy info from a dictionary keyed by taxon_id.
+
+    Insert-only — existing rows are skipped and reported as errors.
+    The taxon_id key must reference an existing organism.
+    """
+    return taxonomy_info_service.bulk_import(db, data=data)
+
+
+@router.get("/{taxon_id}", response_model=TaxonomyInfoSchema)
+def get_taxonomy_info(
+    *,
+    db: Session = Depends(get_db),
+    taxon_id: int,
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """Get taxonomy info by taxon_id."""
+    ti = taxonomy_info_service.get(db, taxon_id)
+    if not ti:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="TaxonomyInfo not found")
+    return ti
+
+
+@router.post("/", response_model=TaxonomyInfoSchema, status_code=status.HTTP_201_CREATED)
+@policy("taxonomy_info:create")
+def create_taxonomy_info(
+    *,
+    db: Session = Depends(get_db),
+    ti_in: TaxonomyInfoCreate,
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """Create taxonomy info for an existing organism."""
+    try:
+        return taxonomy_info_service.create(db, ti_in=ti_in)
+    except ValueError as e:
+        raise HTTPException(status_code=status.HTTP_409_CONFLICT, detail=str(e))
+
+
+@router.patch("/{taxon_id}", response_model=TaxonomyInfoSchema)
+@policy("taxonomy_info:update")
+def update_taxonomy_info(
+    *,
+    db: Session = Depends(get_db),
+    taxon_id: int,
+    ti_in: TaxonomyInfoUpdate,
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """Update taxonomy info by taxon_id."""
+    ti = taxonomy_info_service.update(db, taxon_id=taxon_id, ti_in=ti_in)
+    if not ti:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="TaxonomyInfo not found")
+    return ti
+
+
+@router.delete("/{taxon_id}", response_model=TaxonomyInfoSchema)
+@policy("taxonomy_info:delete")
+def delete_taxonomy_info(
+    *,
+    db: Session = Depends(get_db),
+    taxon_id: int,
+    current_user: User = Depends(get_current_active_user),
+) -> Any:
+    """Delete taxonomy info by taxon_id."""
+    ti = taxonomy_info_service.delete(db, taxon_id=taxon_id)
+    if not ti:
+        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="TaxonomyInfo not found")
+    return ti

app/core/policy.py

@@ -59,6 +59,11 @@
     "admin:expire_leases": ["admin", "superuser"],
     # Broker
     "broker:claim": ["broker"],
+    # Taxonomy info
+    "taxonomy_info:create": ["curator", "admin"],
+    "taxonomy_info:update": ["curator", "admin"],
+    "taxonomy_info:delete": ["admin", "superuser"],
+    "taxonomy_info:bulk_import": ["curator", "admin"],
 }
 
 

app/models/__init__.py

@@ -5,6 +5,7 @@
 from app.models.experiment import Experiment, ExperimentSubmission
 from app.models.genome_note import GenomeNote
 from app.models.organism import Organism
+from app.models.taxonomy_info import TaxonomyInfo
 from app.models.project import Project
 from app.models.qc_read import QcRead, QcReadFile, QcReadSubmission
 from app.models.read import Read

app/models/organism.py

@@ -1,7 +1,6 @@
-import uuid
-
 from sqlalchemy import Column, DateTime, Integer, Text, func
-from sqlalchemy.dialects.postgresql import JSONB, UUID
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import relationship
 
 from app.db.session import Base
 
@@ -29,7 +28,6 @@ class Organism(Base):
     ncbi_order = Column(Text, nullable=True)
     ncbi_family = Column(Text, nullable=True)
     busco_dataset_name = Column(Text, nullable=True)
-    augustus_dataset_name = Column(Text, nullable=True)
     bpa_json = Column(JSONB, nullable=True)
     taxonomy_lineage_json = Column(JSONB, nullable=True)
     created_at = Column(DateTime(timezone=True), nullable=False, server_default=func.now())
@@ -39,3 +37,10 @@ class Organism(Base):
         server_default=func.now(),
         onupdate=func.now(),
     )
+
+    taxonomy_info = relationship(
+        "TaxonomyInfo",
+        back_populates="organism",
+        uselist=False,
+        cascade="all, delete-orphan",
+    )

app/models/taxonomy_info.py

@@ -0,0 +1,24 @@
+from sqlalchemy import Boolean, Column, ForeignKey, Integer, Text
+from sqlalchemy.orm import relationship
+
+from app.db.session import Base
+
+
+class TaxonomyInfo(Base):
+    __tablename__ = "taxonomy_info"
+
+    taxon_id = Column(
+        Integer, ForeignKey("organism.taxon_id", ondelete="CASCADE"), primary_key=True
+    )
+    busco_odb10_dataset_name = Column(Text, nullable=True)
+    busco_odb12_dataset_name = Column(Text, nullable=True)
+    find_plastid = Column(Boolean, nullable=True)
+    hic_motif = Column(Text, nullable=True)
+    mitochondrial_genetic_code_id = Column(Integer, nullable=True)
+    mitohifi_reference_species = Column(Text, nullable=True)
+    oatk_hmm_name = Column(Text, nullable=True)
+    defined_class = Column(Text, nullable=True)
+    augustus_dataset_name = Column(Text, nullable=True)
+    genetic_code_id = Column(Integer, nullable=True)
+
+    organism = relationship("Organism", back_populates="taxonomy_info")

app/schemas/organism.py

@@ -1,15 +1,16 @@
+from __future__ import annotations
+
 from datetime import datetime
-from enum import Enum
-from typing import Dict, Optional
-from uuid import UUID
+from typing import TYPE_CHECKING, Dict, Optional
 
 from pydantic import BaseModel, ConfigDict, model_validator
 
-# Enum for submission status
-from app.schemas.common import SubmissionStatus
+from app.schemas.common import SubmissionStatus  # noqa: F401 – kept for consumers
+
+if TYPE_CHECKING:
+    from app.schemas.taxonomy_info import TaxonomyInfo as TaxonomyInfoSchema
 
 
-# Base Organism schema
 class OrganismBase(BaseModel):
     """Base Organism schema with common attributes."""
 
@@ -27,7 +28,6 @@ class OrganismBase(BaseModel):
     ncbi_order: Optional[str] = None
     ncbi_family: Optional[str] = None
     busco_dataset_name: Optional[str] = None
-    augustus_dataset_name: Optional[str] = None
     bpa_json: Optional[Dict] = None
     taxonomy_lineage_json: Optional[Dict] = None
 
@@ -40,14 +40,12 @@ def _coerce_legacy_keys(cls, data):
         return data
 
 
-# Schema for creating a new organism
 class OrganismCreate(OrganismBase):
     """Schema for creating a new organism."""
 
     pass
 
 
-# Schema for updating an existing organism
 class OrganismUpdate(BaseModel):
     """Schema for updating an existing organism."""
 
@@ -64,12 +62,10 @@ class OrganismUpdate(BaseModel):
     ncbi_order: Optional[str] = None
     ncbi_family: Optional[str] = None
     busco_dataset_name: Optional[str] = None
-    augustus_dataset_name: Optional[str] = None
     bpa_json: Optional[Dict] = None
     taxonomy_lineage_json: Optional[Dict] = None
 
 
-# Schema for organism in DB
 class OrganismInDBBase(OrganismBase):
     """Base schema for Organism in DB, includes id and timestamps."""
 
@@ -79,8 +75,13 @@ class OrganismInDBBase(OrganismBase):
     model_config = ConfigDict(from_attributes=True, populate_by_name=True)
 
 
-# Schema for returning organism information
 class Organism(OrganismInDBBase):
     """Schema for returning organism information."""
 
-    pass
+    taxonomy_info: Optional[TaxonomyInfoSchema] = None
+
+
+# Resolve forward references now that all schemas are defined.
+from app.schemas.taxonomy_info import TaxonomyInfo as TaxonomyInfoSchema  # noqa: E402
+
+Organism.model_rebuild()

app/schemas/taxonomy_info.py

@@ -0,0 +1,34 @@
+from typing import Optional
+
+from pydantic import BaseModel, ConfigDict
+
+
+class TaxonomyInfoBase(BaseModel):
+    busco_odb10_dataset_name: Optional[str] = None
+    busco_odb12_dataset_name: Optional[str] = None
+    find_plastid: Optional[bool] = None
+    hic_motif: Optional[str] = None
+    mitochondrial_genetic_code_id: Optional[int] = None
+    mitohifi_reference_species: Optional[str] = None
+    oatk_hmm_name: Optional[str] = None
+    defined_class: Optional[str] = None
+    augustus_dataset_name: Optional[str] = None
+    genetic_code_id: Optional[int] = None
+
+
+class TaxonomyInfoCreate(TaxonomyInfoBase):
+    taxon_id: int
+
+
+class TaxonomyInfoUpdate(TaxonomyInfoBase):
+    pass
+
+
+class TaxonomyInfoInDBBase(TaxonomyInfoBase):
+    taxon_id: int
+
+    model_config = ConfigDict(from_attributes=True, populate_by_name=True)
+
+
+class TaxonomyInfo(TaxonomyInfoInDBBase):
+    pass

app/services/assembly_helper.py

@@ -64,9 +64,10 @@ def determine_assembly_data_types(experiments: List[Experiment]) -> AssemblyData
     elif has_nanopore:
         return AssemblyDataTypes.OXFORD_NANOPORE
     else:
+        # TODO decide if we relax this requirement and still return the manifest noting the available data types are not supported
         raise ValueError(
-            "No valid sequencing platforms detected in experiments. "
-            "Expected PACBIO_SMRT, OXFORD_NANOPORE, or ILLUMINA with Hi-C library strategy."
+            "No valid data types detected in experiments. "
+            "Expected PACBIO_SMRT (with or without Hi-C), OXFORD_NANOPORE (with or without Hi-C), or ILLUMINA with Hi-C."
         )