Incorporating network based protein complex discovery into automated model construction

TL;DR

This paper introduces a novel method that integrates protein complex discovery from network biology into the construction of computational graphs for gene expression analysis, improving cancer phenotype classification.

Contribution

It presents a scalable, network-informed approach for building interpretable computational models that outperform traditional methods in cancer phenotype analysis.

Findings

Outperforms SVM, MLP, and random models in cancer phenotype tasks

Enables differential protein complex activity analysis

Provides interpretable insights into gene/protein contributions

Abstract

We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs. The structural construction of the computational graphs is driven by the use of topological clustering algorithms on protein-protein networks which incorporate inductive biases stemming from network biology research in protein complex discovery. This structurally constrains the hypothesis space over the possible computational graph factorisation whose parameters can then be learned through supervised or unsupervised task settings. The sparse construction of the computational graph enables the differential protein complex activity analysis whilst also interpreting the individual contributions of genes/proteins involved in each individual protein complex. In our experiments analysing a variety of cancer phenotypes, we show that the proposed methods outperform SVM, Fully-Connected MLP, and Randomly-Connected MLPs in all tasks. Our work introduces a scalable method for incorporating large interaction networks as prior knowledge to drive the construction of powerful computational models amenable to introspective study.