Home » Research » Labs

Computational Causal Discovery Laboratory

Description:

Extensive research in recent years has shown the critical importance of graph-theoretic, computational causal discovery methods for many fields – and, in particular, with respect to the analyses undertaken within NYU Center for Health Informatics and Bioinformatics on behalf of NYULMC researchers. Several varieties exist with causal Bayesian Networks being a dominant paradigm. For example, causal methods can identify biomarkers that are targets for new drug development or SNPs that likely cause disease; they can indicate membership of genes and proteins in disease-related pathways; and they can lead to more compact and better generalizable molecular signatures compared to the first-generation and less sophisticated differential expression/associative/ad hoc or clustering methods. The purpose of the Computation Causal Discovery laboratory is to develop, test and apply causal methods suitable for clinical, molecular, imaging and multi-modal data of high-dimensionality.

Members:

Collaborators outside NYU: