Add template for alternate gene symbol extraction strategy (#390)

src/ontogpt/templates/gene_extraction.py

@@ -0,0 +1,150 @@
+from __future__ import annotations 
+from datetime import (
+    datetime,
+    date
+)
+from decimal import Decimal 
+from enum import Enum 
+import re
+import sys
+from typing import (
+    Any,
+    List,
+    Literal,
+    Dict,
+    Optional,
+    Union
+)
+from pydantic.version import VERSION  as PYDANTIC_VERSION 
+if int(PYDANTIC_VERSION[0])>=2:
+    from pydantic import (
+        BaseModel,
+        ConfigDict,
+        Field,
+        field_validator
+    )
+else:
+    from pydantic import (
+        BaseModel,
+        Field,
+        validator
+    )
+
+metamodel_version = "None"
+version = "None"
+
+
+class ConfiguredBaseModel(BaseModel):
+    model_config = ConfigDict(
+        validate_assignment = True,
+        validate_default = True,
+        extra = "forbid",
+        arbitrary_types_allowed = True,
+        use_enum_values = True,
+        strict = False,
+    )
+    pass
+
+
+class NullDataOptions(str, Enum):
+    UNSPECIFIED_METHOD_OF_ADMINISTRATION = "UNSPECIFIED_METHOD_OF_ADMINISTRATION"
+    NOT_APPLICABLE = "NOT_APPLICABLE"
+    NOT_MENTIONED = "NOT_MENTIONED"
+
+
+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(..., description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+class CompoundExpression(ConfiguredBaseModel):
+    pass
+
+
+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):
+    """
+    A text containing one or more relations of the Triple type.
+    """
+    publication: Optional[Publication] = Field(None)
+    triples: Optional[List[Triple]] = Field(default_factory=list)
+
+
+class TextWithEntity(ConfiguredBaseModel):
+    """
+    A text containing one or more instances of a single type of entity.
+    """
+    publication: Optional[Publication] = Field(None)
+    entities: Optional[List[str]] = Field(default_factory=list)
+
+
+class RelationshipType(NamedEntity):
+    id: str = Field(..., 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)
+
+
+class AcronymList(NamedEntity):
+    genes: Optional[List[str]] = Field(default_factory=list)
+    id: str = Field(..., description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+class Gene(NamedEntity):
+    """
+    a single gene symbol.
+    """
+    id: str = Field(..., description="""A unique identifier for the named entity""")
+    label: Optional[str] = Field(None, description="""The label (name) of the named thing""")
+
+
+# Model rebuild
+# see https://pydantic-docs.helpmanual.io/usage/models/#rebuilding-a-model
+ExtractionResult.model_rebuild()
+NamedEntity.model_rebuild()
+CompoundExpression.model_rebuild()
+Triple.model_rebuild()
+TextWithTriples.model_rebuild()
+TextWithEntity.model_rebuild()
+RelationshipType.model_rebuild()
+Publication.model_rebuild()
+AnnotatorResult.model_rebuild()
+AcronymList.model_rebuild()
+Gene.model_rebuild()

src/ontogpt/templates/gene_extraction.yaml

@@ -0,0 +1,45 @@
+id: http://w3id.org/ontogpt/gene_extraction
+name: gene_extraction
+title: Gene Extraction Template
+description: >-
+  A template demonstrating a general strategy for extracting gene symbols from
+  ambiguous context.
+license: https://creativecommons.org/publicdomain/zero/1.0/
+prefixes:
+  rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
+  HGNC: http://identifiers.org/hgnc/
+  geneextraction: http://w3id.org/ontogpt/gene_extraction
+  linkml: https://w3id.org/linkml/
+
+default_prefix: geneextraction
+default_range: string
+
+imports:
+  - linkml:types
+  - core
+
+classes:
+  AcronymList:
+    tree_root: true
+    is_a: NamedEntity
+    attributes:
+      genes:
+        annotations:
+          prompt: >-
+            A semicolon-delimited list of potential gene symbols within
+            the text. Include all acronyms that could be gene symbols,
+            i.e., any string of capital letters, particularly if it is
+            followed by a number. Examples of gene symbols include:
+            BRCA1, TP53, EGR2, ITGB6, PRKCD. Gene symbols may resemble
+            acronyms referring to diseases or phenotypes,
+            and may be surrounded by punctuation or other text.
+        range: Gene
+        multivalued: true
+
+  Gene:
+    is_a: NamedEntity
+    description: a single gene symbol.
+    id_prefixes:
+      - HGNC
+    annotations:
+      annotators: bioportal:hgnc-nr, bioportal:gexo