Back to results
US 2025/0028984 A1Published application
Method and System for Ontology-Based Dynamic Learning and Knowledge Integration From Measurement Data and Text
AssigneeData4Cure, Inc.
InventorJanusz Jozef DUTKOWSKI
Life of this patent
Estimating the term…
Abstract
Ontology-based dynamic learning and knowledge integration are performed from measurement data and text. Relationships between entities and entity states are inferred from data, text, and user input. Searching, integrating, visualizing and comparing relations are used to extract domain-specific knowledge, particularly in bioinformatics.
Claims23
A computer system comprising at least one hardware processor configured to execute an inference engine, an integration engine connected to the inference engine and to a database, a relation scoring engine connected to the database, and a search engine connected to the database, wherein:
- the database stores entity measurements defined by an ontology, wherein:
- the ontology defines entities and entity measurements, each entity measurement characterizing a corresponding entity, the entities including biological entities and clinical entities, the entity measurements including biological entity measurements and clinical entity measurements,
- the biological entities include genes, proteins, drugs, mRNA, and/or biological pathways,
- the clinical entities include diseases and/or clinical outcomes,
- the biological entity measurements include measurements of genes, proteins, drugs, mRNA, and/or biological pathways, and
- the clinical entity measurements include measurements of diseases and/or clinical outcomes;
- the inference engine is configured to infer a set of relationships between entity measurements from corresponding biological measurement data and clinical measurement data in the database, each relationship between entity measurements relating a biological entity measurement to a clinical entity measurement, each inferred relationship representing a statistical association between co-occurring biological entity and clinical entity measurements determined based on multiple samples or observations;
- the integration engine is configured to update the database by adding the set of inferred relationships between entity measurements to a data structure including entity measurements and relationships between entity measurements;
- the relation scoring engine is configured to generate a score for each inferred relationship, and to update the database with the generated scores;
- and
- the search engine is configured to query the database to identify responsive relationships between entity measurements in response to user queries including entity measurement identifiers.
8 more elements
A method comprising employing at least one hardware processor of a computer system to:
- employ a database to store entity measurements defined by an ontology, wherein:
- the ontology defines entities and entity measurements, each entity measurement characterizing a corresponding entity, the entities including biological entities and clinical entities, the entity measurements including biological entity measurements and clinical entity measurements,
- the biological entities include genes, proteins, drugs, mRNA, and/or biological pathways,
- the clinical entities include diseases and/or clinical outcomes,
- the biological entity measurements include measurements of genes, proteins, drugs, mRNA, and/or biological pathways, and
- the clinical entity measurements include measurements of diseases and/or clinical outcomes;
- infer a set of relationships between entity measurements from corresponding biological measurement data and clinical measurement data in the database, each relationship between entity measurements relating a biological entity measurement to a clinical entity measurement, each inferred relationship representing a statistical association between co-occurring biological entity and clinical entity measurements determined based on multiple samples or observations;
- update the database by adding the set of inferred relationships between entity measurements to a data structure including entity measurements and relationships between entity measurements;
- update the database by adding a set of relationship scores, each relationship score generated for an inferred relationship;
- and
- query the database to identify responsive relationships between entity measurements in response to user queries including entity measurement identifiers.
8 more elements
A non-transitory computer-readable medium storing instructions which, when executed by at least one hardware processor of a computer system causes the computer system to:
- employ a database to store entity measurements defined by an ontology, wherein:
- the ontology defines entities and entity measurements, each entity measurement characterizing a corresponding entity, the entities including biological entities and clinical entities, the entity measurements including biological entity measurements and clinical entity measurements,
- the biological entities include genes, proteins, drugs, mRNA, and/or biological pathways,
- the clinical entities include diseases and/or clinical outcomes,
- the biological entity measurements include measurements of genes, proteins, drugs, mRNA, and/or biological pathways, and
- the clinical entity measurements include measurements of diseases and/or clinical outcomes;
- infer a set of relationships between entity measurements from corresponding biological measurement data and clinical measurement data in the database, each relationship between entity measurements relating a biological entity measurement to a clinical entity measurement, each inferred relationship representing a statistical association between co-occurring biological entity and clinical entity measurements determined based on multiple samples or observations;
- update the database by adding the set of inferred relationships between entity measurements to a data structure including entity measurements and relationships between entity measurements;
- update the database by adding a set of relationship scores, each relationship score generated for an inferred relationship;
- and
- query the database to identify responsive relationships between entity measurements in response to user queries including entity measurement identifiers.
8 more elements
Dependencies are inferred from the claim text.