CTD: An information-theoretic algorithm to interpret sets of metabolomic and transcriptomic perturbations in the context of graphical models.
Lillian R. ThistlethwaiteVarduhi PetrosyanXiqi LiMarcus J. MillerSarah H. ElseaAleksandar MilosavljevicPublished in: PLoS Comput. Biol. (2021)
Keyphrases
- graphical models
- information theoretic
- probabilistic model
- information bottleneck
- optimal solution
- log likelihood
- similarity measure
- mutual information
- belief propagation
- factor graphs
- loopy belief propagation
- information theory
- information theoretic measures
- structure learning
- expectation maximization
- k means
- objective function
- missing values
- probabilistic inference
- random variables
- graph cuts
- kullback leibler divergence
- markov random field