Skip to content

Class: TextMiningStudyResult

Description: A study result that represents information extracted from text using natural language processing techniques. This includes the extracted text, location offsets within the source document, confidence scores, and other metadata related to the text mining process.
classDiagram class TextMiningStudyResult StudyResult <|-- TextMiningStudyResult TextMiningStudyResult : category TextMiningStudyResult : creation_date TextMiningStudyResult : deprecated TextMiningStudyResult : description TextMiningStudyResult : extraction_confidence_score TextMiningStudyResult : format TextMiningStudyResult : full_name TextMiningStudyResult : has_attribute TextMiningStudyResult --|> Attribute : has_attribute TextMiningStudyResult : id TextMiningStudyResult : iri TextMiningStudyResult : license TextMiningStudyResult : name TextMiningStudyResult : object_location_in_text TextMiningStudyResult : provided_by TextMiningStudyResult : rights TextMiningStudyResult : subject_location_in_text TextMiningStudyResult : supporting_document_type TextMiningStudyResult : supporting_document_year TextMiningStudyResult : supporting_text TextMiningStudyResult : supporting_text_section_type TextMiningStudyResult : synonym TextMiningStudyResult : type TextMiningStudyResult : xref

Inheritance

Slots

Name Cardinality and Range Inheritance Examples
supporting_text:
The segment of text from a document that supports the mined assertion.
*
String
direct The administration of 50g/ml bupivacaine promoted maximum breast cancer.
subject_location_in_text:
Character offsets for the text span(s) in the supporting text corresponding to the subject concept of the extracted assertion.
*
Integer
direct 15
object_location_in_text:
Character offsets for the text span(s) in the supporting text corresponding to the object concept of the extracted assertion
*
Integer
direct 15
extraction_confidence_score:
A quantitative confidence value that represents the probability of obtaining a result at least as extreme as that actually obtained, assuming that the actual value was the result of chance alone.
0..1
Integer
direct 15
supporting_document_type:
The document type (e.g., Journal Article, Case Study, Preprint) for the supporting document used in a Text Mining Result.
0..1
String
direct Journal Article
supporting_document_year:
The document year (typically the publication year) for the supporting document used in a Text Mining Result.
0..1
Integer
direct 1999
supporting_text_section_type:
The section of the supporting text of a Text Mining Result within the supporting document. This is in the form of the name of the document section (e.g., Abstract, Introduction) that contains the supporting text.
0..1
String
direct Introduction
license:
None
0..1
String
InformationContentEntity
rights:
None
0..1
String
InformationContentEntity
format:
None
0..1
String
InformationContentEntity
creation_date:
date on which an entity was created. This can be applied to nodes or edges
0..1
Date
InformationContentEntity
provided_by:
The value in this node property represents the knowledge provider that created or assembled the node and all of its attributes. Used internally to represent how a particular node made its way into a knowledge provider or graph.
*
String
NamedThing
xref:
A database cross reference or alternative identifier for a NamedThing or edge between two NamedThings. This property should point to a database record or webpage that supports the existence of the edge, or gives more detail about the edge. This property can be used on a node or edge to provide multiple URIs or CURIE cross references.
*
Uriorcurie
NamedThing
full_name:
a long-form human readable name for a thing
0..1
LabelType
NamedThing
synonym:
Alternate human-readable names for a thing
*
LabelType
NamedThing
id:
A unique identifier for an entity. Must be either a CURIE shorthand for a URI or a complete URI
1
String
Entity
iri:
An IRI for an entity. This is determined by the id using expansion rules.
0..1
IriType
Entity
category:
Name of the high level ontology class in which this entity is categorized. Corresponds to the label for the biolink entity type class. In a neo4j database this MAY correspond to the neo4j label tag. In an RDF database it should be a biolink model class URI. This field is multi-valued. It should include values for ancestors of the biolink class; for example, a protein such as Shh would have category values biolink:Protein, biolink:GeneProduct, biolink:MolecularEntity. In an RDF database, nodes will typically have an rdf:type triples. This can be to the most specific biolink class, or potentially to a class more specific than something in biolink. For example, a sequence feature f may have a rdf:type assertion to a SO class such as TF_binding_site, which is more specific than anything in biolink. Here we would have categories {biolink:GenomicEntity, biolink:MolecularEntity, biolink:NamedThing}
1..*
Uriorcurie
Entity
type:
None
*
String
Entity
name:
A human-readable name for an attribute or entity.
0..1
LabelType
Entity
description:
a human-readable description of an entity
0..1
NarrativeText
Entity
has_attribute:
connects any entity to an attribute
*
Attribute
Entity
deprecated:
A boolean flag indicating that an entity is no longer considered current or valid.
0..1
Boolean
Entity

LinkML Source

name: text mining study result
description: A study result that represents information extracted from text using
  natural language processing techniques. This includes the extracted text, location
  offsets within the source document, confidence scores, and other metadata related
  to the text mining process.
from_schema: https://w3id.org/biolink/biolink-model
is_a: study result
slots:
- supporting text
- subject location in text
- object location in text
- extraction confidence score
- supporting document type
- supporting document year
- supporting text section type