Back to results
US 11,636,951 B2Granted
Systems and methods for generating a genotypic causal model of a disease state
AssigneeKpn Innovations, LLC.
InventorKenneth Neumann
Life of this patent
Estimating the term…
Abstract
A system for generating a genotypic causal model of a disease state includes a computing device that generates a causal graph containing genotypic causal nodes and connected symptomatic causal nodes, which contains causal paths from gene combinations to symptomatic datums. Genotypic causal nodes and/or connected symptomatic causal nodes may be generated by feature learning algorithms from training data.
Claims18
A system for generating a genotypic causal model of a disease state, the system comprising a computing device configured to perform the steps of:
- generating a machine-learning model including a causal graph containing a plurality of causal nodes comprising a plurality of genotypic causal nodes and a plurality of symptomatic causal nodes, wherein generating the machine learning model further comprises:
- generating using a first feature learning algorithm, the plurality of genotypic causal nodes, wherein each genotypic causal node includes a disease state and a gene combination correlated with the disease state, wherein generating the plurality of genotypic causal nodes comprises identifying, using the first feature learning algorithm, in genetic training set data, a plurality of pairs of genetic sequences and disease states, and outputting a plurality of gene combinations correlated with each disease state of a plurality of disease states identified in the plurality of pairs, said first feature learning algorithm comprising a neural network configured to identify associations within the genetic training data;
- generating, using a second feature learning algorithm comprising a neural network, the plurality of symptomatic nodes, wherein each symptomatic node includes a disease state and at least a correlated symptom and wherein generating the plurality of symptomatic nodes comprises receiving a symptomatic training set including a plurality of data entries containing a plurality of symptoms and a plurality of disease states, wherein each data entry includes a disease state and at least a correlated symptom;
- and
- connecting the plurality of symptomatic nodes to the plurality of genotypic nodes by instantiating edges connecting disease states of symptomatic nodes to matching disease states of genotypic nodes;
- receiving a genetic sequence comprising a series of genes identified in a nucleotide sequence of chromosomal nucleic acid of a human subject and a first symptomatic datum as inputs;
- outputting at least a path in the causal graph from inputs in the genetic sequence to outputs at the first symptomatic datum, wherein the at least a path contains at least a genotypic node and at least a linked symptomatic node;
- and
- generating a causal model, as a function of the at least a path in the causal graph including the at least a genotypic node and the at least a linked symptomatic node, wherein the causal model comprises a data structure describing disease states and genetic causes.
6 more elements
A method of generating a genotypic causal model of a disease state, the method comprising:
- generating, by a computing device, a machine-learning model including a causal graph containing a plurality of causal nodes comprising a plurality of genotypic causal nodes and a plurality of symptomatic causal nodes, wherein generating the machine learning model further comprises:
- generating, using a first feature learning algorithm, the plurality of genotypic causal nodes, wherein each genotypic causal node includes a disease state and a gene combination correlated with the disease state, wherein generating the plurality of genotypic causal nodes comprises identifying, using the first feature learning algorithm, in genetic training set data, a plurality of pairs of genetic sequences and disease states, and outputting a plurality of gene combinations correlated with each disease state of a plurality of disease states identified in the plurality of pairs, said first feature learning algorithm comprising a neural network configured to identify associations within the genetic training data;
- generating, using a second feature learning algorithm comprising a neural network, the plurality of symptomatic nodes, wherein each symptomatic node includes a disease state and at least a correlated symptom and wherein generating the plurality of symptomatic nodes comprises receiving a symptomatic training set including a plurality of data entries containing a plurality of symptoms and a plurality of disease states, wherein each data entry includes a disease state and at least a correlated symptom;
- and
- connecting the plurality of symptomatic nodes to the plurality of genotypic nodes by instantiating edges connecting disease states of symptomatic nodes to matching disease states of genotypic nodes;
- receiving a genetic sequence comprising a series of genes identified in a nucleotide sequence of chromosomal nucleic acid of a human subject and a first symptomatic datum as inputs;
- outputting at least a path in the causal graph from inputs in the genetic sequence to outputs at the first symptomatic datum, wherein the at least a path contains at least a genotypic node and at least a linked symptomatic node;
- and
- generating a causal model, as a function of the at least a path in the causal graph including the at least a genotypic node and the at least a linked symptomatic node, wherein the causal model comprises a data structure describing disease states and genetic causes.
6 more elements
Dependencies are inferred from the claim text.