Adding generate-extract command, 158. Add cell type templates monarch…

…-initiative#159

This PR does two things:

- Add a combined generate-extract command, fixes monarch-initiative#158
- Adds cell type templates, fixes monarch-initiative#159

src/ontogpt/templates/cell_type.py

@@ -0,0 +1,203 @@
+from __future__ import annotations
+from datetime import datetime, date
+from enum import Enum
+from typing import List, Dict, Optional, Any, Union, Literal
+from pydantic import BaseModel as BaseModel, Field
+from linkml_runtime.linkml_model import Decimal
+
+metamodel_version = "None"
+version = "None"
+
+class WeakRefShimBaseModel(BaseModel):
+   __slots__ = '__weakref__'
+
+class ConfiguredBaseModel(WeakRefShimBaseModel,
+                validate_assignment = True, 
+                validate_all = True, 
+                underscore_attrs_are_private = True, 
+                extra = 'forbid', 
+                arbitrary_types_allowed = True):
+    pass                    
+
+
+class BrainRegionIdentifier(str, Enum):
+
+
+    dummy = "dummy"
+
+
+class NullDataOptions(str, Enum):
+
+    UNSPECIFIED_METHOD_OF_ADMINISTRATION = "UNSPECIFIED_METHOD_OF_ADMINISTRATION"
+    NOT_APPLICABLE = "NOT_APPLICABLE"
+    NOT_MENTIONED = "NOT_MENTIONED"
+
+
+
+class CellTypeDocument(ConfiguredBaseModel):
+
+    cell_type: Optional[str] = Field(None, description="""the name of the cell type described""")
+    range: Optional[str] = Field(None)
+    parents: Optional[List[str]] = Field(default_factory=list, description="""categorization""")
+    subtypes: Optional[List[str]] = Field(default_factory=list)
+    localizations: Optional[List[str]] = Field(default_factory=list)
+    genes: Optional[List[str]] = Field(default_factory=list)
+    diseases: Optional[List[str]] = Field(default_factory=list)
+
+
+
+class InterneuronDocument(CellTypeDocument):
+
+    projects_to_or_from: Optional[List[str]] = Field(default_factory=list, description="""Brain structures from which this cell type projects into or receives projections from""")
+    cell_type: Optional[str] = Field(None, description="""the name of the cell type described""")
+    range: Optional[str] = Field(None)
+    parents: Optional[List[str]] = Field(default_factory=list, description="""categorization""")
+    subtypes: Optional[List[str]] = Field(default_factory=list)
+    localizations: Optional[List[str]] = Field(default_factory=list)
+    genes: Optional[List[str]] = Field(default_factory=list)
+    diseases: Optional[List[str]] = Field(default_factory=list)
+
+
+
+class ExtractionResult(ConfiguredBaseModel):
+    """
+    A result of extracting knowledge on text
+    """
+    input_id: Optional[str] = Field(None)
+    input_title: Optional[str] = Field(None)
+    input_text: Optional[str] = Field(None)
+    raw_completion_output: Optional[str] = Field(None)
+    prompt: Optional[str] = Field(None)
+    extracted_object: Optional[Any] = Field(None, description="""The complex objects extracted from the text""")
+    named_entities: Optional[List[Any]] = Field(default_factory=list, description="""Named entities extracted from the text""")
+
+
+
+class NamedEntity(ConfiguredBaseModel):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class Gene(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class Pathway(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class AnatomicalStructure(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class BrainRegion(AnatomicalStructure):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class CellType(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class Disease(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class Drug(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class CompoundExpression(ConfiguredBaseModel):
+
+    None
+
+
+
+class Triple(CompoundExpression):
+    """
+    Abstract parent for Relation Extraction tasks
+    """
+    subject: Optional[str] = Field(None)
+    predicate: Optional[str] = Field(None)
+    object: Optional[str] = Field(None)
+    qualifier: Optional[str] = Field(None, description="""A qualifier for the statements, e.g. \"NOT\" for negation""")
+    subject_qualifier: Optional[str] = Field(None, description="""An optional qualifier or modifier for the subject of the statement, e.g. \"high dose\" or \"intravenously administered\"""")
+    object_qualifier: Optional[str] = Field(None, description="""An optional qualifier or modifier for the object of the statement, e.g. \"severe\" or \"with additional complications\"""")
+
+
+
+class TextWithTriples(ConfiguredBaseModel):
+
+    publication: Optional[Publication] = Field(None)
+    triples: Optional[List[Triple]] = Field(default_factory=list)
+
+
+
+class RelationshipType(NamedEntity):
+
+    id: str = Field(None, description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+
+class Publication(ConfiguredBaseModel):
+
+    id: Optional[str] = Field(None, description="""The publication identifier""")
+    title: Optional[str] = Field(None, description="""The title of the publication""")
+    abstract: Optional[str] = Field(None, description="""The abstract of the publication""")
+    combined_text: Optional[str] = Field(None)
+    full_text: Optional[str] = Field(None, description="""The full text of the publication""")
+
+
+
+class AnnotatorResult(ConfiguredBaseModel):
+
+    subject_text: Optional[str] = Field(None)
+    object_id: Optional[str] = Field(None)
+    object_text: Optional[str] = Field(None)
+
+
+
+
+# Update forward refs
+# see https://pydantic-docs.helpmanual.io/usage/postponed_annotations/
+CellTypeDocument.update_forward_refs()
+InterneuronDocument.update_forward_refs()
+ExtractionResult.update_forward_refs()
+NamedEntity.update_forward_refs()
+Gene.update_forward_refs()
+Pathway.update_forward_refs()
+AnatomicalStructure.update_forward_refs()
+BrainRegion.update_forward_refs()
+CellType.update_forward_refs()
+Disease.update_forward_refs()
+Drug.update_forward_refs()
+CompoundExpression.update_forward_refs()
+Triple.update_forward_refs()
+TextWithTriples.update_forward_refs()
+RelationshipType.update_forward_refs()
+Publication.update_forward_refs()
+AnnotatorResult.update_forward_refs()
+

src/ontogpt/templates/cell_type.yaml

@@ -0,0 +1,143 @@
+id: http://w3id.org/ontogpt/cell_type
+name: cell_type
+title: Composite Disease
+description: >-
+  A template for representing cell types
+license: https://creativecommons.org/publicdomain/zero/1.0/
+prefixes:
+  linkml: https://w3id.org/linkml/
+  cell_type: http://w3id.org/ontogpt/cell_type/
+keywords:
+  - disease
+  - indication
+
+default_prefix: cell_type
+default_range: string
+
+imports:
+  - linkml:types
+  - core
+
+classes:
+  CellTypeDocument:
+    tree_root: true
+    attributes:
+      cell_type:
+        description: the name of the cell type described
+      range: CellType
+
+      parents:
+        description: categorization
+        annotations:
+          prompt: semicolon-separated list of parent (broader) cell types
+        multivalued: true
+        range: CellType
+
+      subtypes:
+        annotations:
+          prompt: semicolon-separated list of the main subtypes
+        multivalued: true
+        range: CellType
+
+      localizations:
+        annotations:
+          prompt: semicolon-separated list of anatomical structures in which this cell type is localized
+        multivalued: true
+        range: AnatomicalStructure
+
+      genes:
+        annotations:
+          prompt: semicolon-separated list of genes expressed in cells of this type
+        multivalued: true
+        range: Gene
+
+      diseases:
+        annotations:
+          prompt: semicolon-separated list of diseases in which this cell type is implicated
+        multivalued: true
+        range: Disease
+
+  InterneuronDocument:
+    is_a: CellTypeDocument
+
+    attributes:
+      projects_to_or_from:
+        description: Brain structures from which this cell type projects into or receives projections from
+        annotations:
+          prompt: semicolon-separated list of anatomical structures from which this cell type projects from or into
+        multivalued: true
+        range: BrainRegion
+
+  Gene:
+    is_a: NamedEntity
+    id_prefixes:
+      - HGNC
+      - MGI
+      - PR
+      - UniProtKB
+    annotations:
+      annotators: sqlite:obo:hgnc, bioportal:hgnc-nr
+
+  Pathway:
+    is_a: NamedEntity
+    id_prefixes:
+      - GO
+      - PW
+    annotations:
+      annotators: sqlite:obo:go, sqlite:obo:pw
+
+  AnatomicalStructure:
+    is_a: NamedEntity
+    id_prefixes:
+      - UBERON
+      - FBbt
+      - WBbt
+    annotations:
+      annotators: sqlite:obo:uberon, sqlite:obo:fbbt, sqlite:obo:wbbt
+
+  BrainRegion:
+    is_a: AnatomicalStructure
+    id_prefixes:
+      - UBERON
+      - FBbt
+      - WBbt
+    annotations:
+      annotators: sqlite:obo:uberon, sqlite:obo:fbbt, sqlite:obo:wbbt
+    slot_usage:
+      id:
+        values_from:
+          - BrainRegionIdentifier
+
+  CellType:
+    is_a: NamedEntity
+    id_prefixes:
+      - CL
+      - FBbt
+      - WBbt
+    annotations:
+      annotators: sqlite:obo:cl, sqlite:obo:fbbt, sqlite:obo:wbbt
+
+  Disease:
+    is_a: NamedEntity
+    id_prefixes:
+      - MONDO
+      - HP
+    annotations:
+      annotators: sqlite:obo:mondo, sqlite:obo:hp
+
+  Drug:
+    is_a: NamedEntity
+    annotations:
+      annotators: sqlite:obo:chebi, sqlite:obo:drugbank
+
+enums:
+
+  BrainRegionIdentifier:
+    description: Brain region (or for now, any nervous system part)
+    reachable_from:
+      source_ontology: obo:uberon
+      relationship_types:
+        - rdfs:subClassOf
+        - BFO:0000050
+      source_nodes:
+        - UBERON:0001016  ## nervous system