# Learning to estimate sample-specific transcriptional networks for 7,000 tumors

## TL;DR

This paper introduces a new method for estimating gene regulatory networks in tumors that accounts for individual differences and improves precision medicine by analyzing 7,000 tumors.

## Contribution

The novel approach, contextualized network inference, uses multiview metadata to infer sample-specific gene regulatory networks and generalize to unseen cancer types.

## Key findings

- Contextualized networks improve accuracy and identify additional prognostic tumor subtypes.
- The method generalizes to unseen cancer types using a pan-cancer model of mutation effects on gene regulation.
- A Python package and interactive tools are provided for learning and exploring contextualized models.

## Abstract

Network estimation is essential for understanding the structure and function of biological systems, but current statistical approaches fail to capture intersubject heterogeneity or cross-modality information flow, both of which are needed for understanding complex phenotypes and pathologies. We introduce contextualized network inference, leveraging multiview contextual metadata to capture similarities and differences among heterogeneous observations during network estimation. Sharing information across contexts enables inference at sample-specific resolution, thus quantifying variation between subjects and revealing context-specific network rewiring. Applied to tumor-specific transcriptional network inference using clinical, molecular, and multiomic data, contextualized networks improve accuracy, generalize to unseen cancer types, and identify additional prognostic tumor subtypes. By tailoring disease models to each sample, contextualized networks promise to enable precision medicine at extreme resolution.

Cancers are shaped by somatic mutations, microenvironment, and patient background, each altering gene expression and regulation in complex ways, resulting in heterogeneous cellular states and dynamics. Inferring gene regulatory networks (GRNs) from expression data can help characterize this regulation-driven heterogeneity, but network inference requires many statistical samples, limiting GRNs to cluster-level analyses that ignore intracluster heterogeneity. We propose to move beyond coarse analyses of predefined subgroups by using contextualized learning, a multitask learning paradigm that uses multiview contexts including phenotypic, molecular, and environmental information to infer personalized models. With sample-specific contexts, contextualization enables sample-specific models and even generalizes at test time to predict network models for entirely unseen contexts. We unify three network model classes (Correlation, Markov, and Neighborhood Selection) and estimate context-specific GRNs for 7,997 tumors across 25 tumor types, using copy number and driver mutation profiles, tumor microenvironment, and patient demographics as model context. Our generative modeling approach allows us to predict GRNs for unseen tumor types based on a pan-cancer model of how somatic mutations affect gene regulation. Finally, contextualized networks enable GRN-based precision oncology by providing a structured view of expression dynamics at sample-specific resolution, explaining known biomarkers in terms of network-mediated effects and leading to subtypings that improve survival prognosis. We provide a SKLearn-style Python package https://contextualized.ml for learning and analyzing contextualized models, as well as interactive plotting tools for pan-cancer data exploration at https://github.com/cnellington/CancerContextualized.