Systems and methods for generating a genotypic causal model of a disease state

1. 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.

2. The system of claim 1 , wherein the first feature learning algorithm further comprises a k-means clustering algorithm.

3. The system of claim 1 , wherein each symptomatic causal node includes a plurality of cause link elements, each cause link element of the plurality of cause link elements identifying a causal node of the plurality of causal nodes.

4. The system of claim 1 , wherein outputting the at least a path further comprises:

identifying a plurality of paths in the causal graph from inputs in the genetic sequence to outputs at the symptomatic datum; and

selecting a most probable path from the plurality of paths.

5. The system of claim 4 , wherein selecting the most probable path further comprises:

receiving a second symptomatic datum; and

selecting the most probable path using the second symptomatic datum.

6. The system of claim 5 , wherein selecting the most probable path using the second symptomatic datum further comprises:

identifying a path through the graph from the genetic sequence to the second symptomatic datum; and

determining that the identified path matches a path of the plurality of paths.

7. The system of claim 6 , wherein determining that the identified path matches a path of the plurality of paths further comprises:

identifying a symptomatic sibling node in the identified path, wherein the symptomatic sibling node contains a cause link element matching a causal node in a path of the plurality of paths.

8. The system of claim 5 , wherein selecting the most probable path using the second symptomatic datum further comprises:

determining that the second symptomatic datum contradicts a causal node of a path of the plurality of paths; and

eliminating the path.

9. The system of claim 1 , wherein generating the plurality of symptomatic nodes further comprises generating, by the second feature learning algorithm, a plurality of clusters, each of the plurality of clusters comprising a symptom associated with one or more disease states, said second feature learning algorithm including a fuzzy logic algorithm.

10. 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.

11. The method of claim 10 , wherein the first feature learning algorithm further comprises a k-means clustering algorithm.

12. The method of claim 10 , wherein each symptomatic causal node includes a plurality of cause link elements, each cause link element of the plurality of cause link elements identifying a causal node of the plurality of causal nodes.

13. The method of claim 10 , wherein outputting the at least a path further comprises:

identifying a plurality of paths in the causal graph from inputs in the genetic sequence to outputs at the symptomatic datum; and

selecting a most probable path from the plurality of paths.

14. The method of claim 13 , wherein selecting the most probable path further comprises:

receiving a second symptomatic datum; and

selecting the most probable path using the second symptomatic datum.

15. The method of claim 14 , wherein selecting the most probable path using the second symptomatic datum further comprises:

identifying a path through the graph from the genetic sequence to the second symptomatic datum; and

determining that the identified path matches a path of the plurality of paths.

16. The method of claim 15 , wherein determining that the identified path matches a path of the plurality of paths further comprises:

identifying a symptomatic sibling node in the identified path, wherein the symptomatic sibling node contains a cause link element matching a causal node in a path of the plurality of paths.

17. The method of claim 14 , wherein selecting the most probable path using the second symptomatic datum further comprises:

determining that the second symptomatic datum contradicts a causal node of a path of the plurality of paths; and

eliminating the path.

18. The method of claim 10 , wherein generating the plurality of symptomatic nodes further comprises generating, by the second feature learning algorithm, a plurality of clusters, each of the plurality of clusters comprising a symptom associated with one or more disease states, said second feature learning algorithm including a fuzzy logic algorithm.