Timezone: »

 
Sample-Specific Contextualized Graphical Models Using Clinical and Molecular Data Reveal Transcriptional Network Heterogeneity Across 7000 Tumors
Caleb Ellington · Ben Lengerich · Thomas Watkins · Jiekun Yang · Manolis Kellis · Eric Xing

Fri Dec 09 03:48 PM -- 04:00 PM (PST) @
in Graph Learning for Industrial Applications: Finance, Crime Detection, Medicine and Social Media »

Cancers are shaped by somatic mutations, microenvironment, and patient background, each altering both gene expression and gene regulatory networks (GRNs) in complex ways, resulting in highly-variable cellular states and dynamics. Inferring GRNs from expression data can help characterize this regulation-driven heterogeneity, but network inference is intractable without many statistical samples, limiting GRNs to cluster-level analyses that ignore intra-cluster heterogeneity. We propose to move beyond cluster-based analyses by using \emph{contextualized} learning, a meta-learning paradigm, to generate sample-specific network models from sample contexts. We unify three network classes (correlation, Markov, Bayesian) and estimate sample-specific GRNs for 7000 tumours across 25 tumor types, with each network contextualized by copy number and driver mutation profiles, tumor microenvironment and patient demographics. Sample-specific networks provide a de-noised view of gene expression dynamics at sample-specific resolution, which reveal co-expression modules in correlation networks (CNs), clique structures and neighborhood selection in Markov Networks (MNs), and causal ordering and probability factorization in Bayesian Networks (BNs). Sample-specific networks enable GRN-based precision oncology, including brain tumor subtyping that improves survival prognosis.

[ Poster] 

Author Information

Caleb Ellington (Carnegie Mellon University)
Ben Lengerich (MIT)
Thomas Watkins (MIT)
Jiekun Yang (MIT)
Manolis Kellis (Massachusetts Institute of Technology)
Eric Xing (Petuum Inc. / Carnegie Mellon University)

More from the Same Authors