piMGM: incorporating multi-source priors in mixed graphical models for learning disease networks

    loading  Checking for direct PDF access through Ovid

Abstract

Motivation

Learning probabilistic graphs over mixed data is an important way to combine gene expression and clinical disease data. Leveraging the existing, yet imperfect, information in pathway databases for mixed graphical model (MGM) learning is an understudied problem with tremendous potential applications in systems medicine, the problems of which often involve high-dimensional data.

Results

We present a new method, piMGM, which can learn with accuracy the structure of probabilistic graphs over mixed data by appropriately incorporating priors from multiple experts with different degrees of reliability. We show that piMGM accurately scores the reliability of prior information from a given expert even at low sample sizes. The reliability scores can be used to determine active pathways in healthy and disease samples. We tested piMGM on both simulated and real data from TCGA, and we found that its performance is not affected by unreliable priors. We demonstrate the applicability of piMGM by successfully using prior information to identify pathway components that are important in breast cancer and improve cancer subtype classification.

Availability and implementation

http://www.benoslab.pitt.edu/manatakisECCB2018.html

Supplementary information

Supplementary data are available at Bioinformatics online.

Related Topics

    loading  Loading Related Articles