Systems and methods for identifying drug targets using biological networks
View Patent ↗Certain embodiments of the invention may include systems and methods for identifying drug targets using biological networks. According to an example embodiment of the invention, a method is provided for predicting the effects of drug targets on treating a disease. The method can include constructing a structure of a Bayesian network based at least in part on knowledge of drug inhibiting effects on a disease; associating a set of parameters with the constructed Bayesian network; determining values of a joint probability distribution of the Bayesian network via an automatic procedure; deriving a mean Bayesian network with one or more averaged parameters based at least in part on the joint probability values; and calculating a quantitative prediction based at least in part on the mean Bayesian network.
1. A method, comprising executing computer executable instructions by one or more processors for predicting gene expression profile changes upon inhibiting proteins or genes of drug targets on treating a disease, the method further comprising:
constructing a genetic network comprising a structure of a dynamic Bayesian network based at least in part on knowledge of drug inhibiting effects on a disease;
associating a set of parameters with the constructed dynamic Bayesian network;
determining values of a joint probability distribution of the dynamic Bayesian network via an automatic procedure;
deriving a mean dynamic Bayesian network with one or more averaged parameters based at least in part on the joint probability values; and
calculating a quantitative prediction based at least in part on the mean dynamic Bayesian network,
wherein said method searches for an optimal combination of drug targets whose perturbed gene expression profiles are most similar to healthy cells.
2. The method of claim 1 , wherein constructing the structure of the Bayesian network comprises adding directed edges between variables according to domain expert knowledge.
3. The method of claim 1 , wherein associating the set of parameters with the constructed Bayesian network comprises denoting joint probabilities of a value of one or more variables in conjunction with values of other variables in the Bayesian network.
4. The method of claim 1 , wherein determining values of a joint probability distribution is based on local structures comprising a number of activating parents and a number of inhibiting parents associated with the Bayesian network.
5. The method of claim 1 , wherein deriving the mean Bayesian network comprises averaging over joint probability values associated with the network.
6. The method of claim 1 , wherein calculating the quantitative prediction comprises integrating over a set of Bayesian networks and multiplying the result by an apriori probability of the Bayesian network set.
7. The method of claim 6 , wherein integrating over a set of Bayesian networks comprises applying limits of integration in a relative order based at least in part on a child node probability under a combination of activating and inhibiting parent nodes.