System and method for the contextualization of molecules
Inventors
Tal, Roy • Jocys, Zygimantas • Macer, Sam Christian
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11710049-B2
Publication Date
2023-07-25
Expiration Date
Abstract
A system and method that given one or more input molecules, produces a contextualized summary of characteristics of related target molecules, e.g., proteins. Using a knowledge graph which is populated with all known molecules, input molecules are analyzed according to various similarity indexes which relate the input molecules to target proteins or other biological entities. The knowledge graph may also comprise scientific literature, governmental data (FDA clinical phase data), private research endeavors (general assays, etc.), and other related biological data. The summary produced may comprise target proteins that satisfy certain biological properties, general assay results (ADMET characteristics), related diseases, off-target molecule interactions (non-targeted molecules involved in a specific pathway or cascade), market opportunities, patents, experiments, and new hypothesis.
Core Innovation
A pharmaceutical research platform contextualizes one or more received molecules by constructing a knowledge graph populated with molecules, diseases, biological mechanisms, and scientific literature. The platform identifies one or more molecules existing within the knowledge graph that are structurally or chemically similar to the received molecules and generates a report that provides contextual information linking the similar molecules to associated diseases, biological mechanisms, and scientific literature.
The contextual information in the generated report includes contextual details relating each similar molecule with its associated diseases, biological mechanisms, and scientific literature. Similarity identification is performed using structurally or chemically similarity within the knowledge graph.
The platform architecture includes web/database crawling and NLP-driven extraction of molecule-protein-disease relationships for knowledge-graph construction. It also includes data analysis models for contextualization, including graph neural networks and sequence models, and supports similarity computations using various similarity indexes and approaches.
Claims Coverage
The document includes two independent claims covering a system and a method for contextualizing molecules. Across the independent claims, three core inventive elements recur: building a knowledge graph, identifying structurally or chemically similar molecules within that graph, and generating a contextual report linking the similar molecules to associated diseases, biological mechanisms, and scientific literature.
Pharmaceutical research platform for molecule contextualization
A pharmaceutical research platform that receives data representing one or more molecules, constructs a knowledge graph comprising molecules, diseases, biological mechanisms, and scientific literature, identifies one or more molecules existing within the knowledge graph that is structurally or chemically similar to the one or more received molecules, and generates a report detailing the similar molecules and their associated diseases, biological mechanisms, and scientific literature with contextual information relating the similar molecule with its associated diseases, biological mechanisms, and scientific literature.
Method for contextualization of molecules
A method that receives data representing one or more molecules, constructs a knowledge graph comprising molecules, diseases, biological mechanisms, and scientific literature, identifies one or more molecules existing within the knowledge graph that is structurally or chemically similar to the one or more received molecules, and generates a report detailing the similar molecules and their associated diseases, biological mechanisms, and scientific literature with contextual information relating the similar molecule with its associated diseases, biological mechanisms, and scientific literature.
Both independent claims define contextualization by constructing a knowledge graph over molecules, diseases, biological mechanisms, and scientific literature; finding structurally or chemically similar molecules within that graph; and generating a report that provides contextual information connecting the similar molecules to associated diseases, biological mechanisms, and scientific literature.
Stated Advantages
Documented Applications
Pharmaceutical research using a platform that contextualizes input molecules and generates reports linking similar molecules to associated diseases, biological mechanisms, and scientific literature.
Interested in licensing this patent?