MPVNN: Mutated Pathway Visible Neural Network architecture for interpretable prediction of cancer-specific survival risk

Shan He*, Gourab Ghosh Roy, Nicholas Geard, Karin Verspoor

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

39 Downloads (Pure)

Abstract

Motivation: Survival risk prediction using gene expression data is important in making treatment decisions in cancer. Standard neural network (NN) survival analysis models are black boxes with a lack of interpretability. More interpretable visible neural network architectures are designed using biological pathway knowledge. But they do not model how pathway structures can change for particular cancer types.

Results: We propose a novel Mutated Pathway Visible Neural Network (MPVNN) architecture, designed using prior signaling pathway knowledge and random replacement of known pathway edges using gene mutation data simulating signal flow disruption. As a case study, we use the PI3K-Akt pathway and demonstrate overall improved cancer-specific survival risk prediction of MPVNN over other similar-sized NN and standard survival analysis methods. We show that trained MPVNN architecture interpretation, which points to smaller sets of genes connected by signal flow within the PI3K-Akt pathway that is important in risk prediction for particular cancer types, is reliable.

Availability and implementation: The data and code are available at https://github.com/gourabghoshroy/MPVNN.
Original languageEnglish
Article numberbtac636
JournalBioinformatics
Early online date19 Sept 2022
DOIs
Publication statusE-pub ahead of print - 19 Sept 2022

Fingerprint

Dive into the research topics of 'MPVNN: Mutated Pathway Visible Neural Network architecture for interpretable prediction of cancer-specific survival risk'. Together they form a unique fingerprint.

Cite this