PANTHER: Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning

TL;DR

PANTHER is a novel tensor factorization method that models genetic pathways and variants jointly, improving interpretability and accuracy in disease prediction from genomic data.

Contribution

It introduces a pathway-augmented nonnegative tensor factorization approach that captures higher-order molecular interactions for better disease classification.

Findings

PANTHER significantly outperforms state-of-the-art models (p<0.05).

Demonstrates wide applicability on large-scale genomic datasets.

Provides insights into molecular mechanisms through pathway group analysis.

Abstract

Genetic pathways usually encode molecular mechanisms that can inform targeted interventions. It is often challenging for existing machine learning approaches to jointly model genetic pathways (higher-order features) and variants (atomic features), and present to clinicians interpretable models. In order to build more accurate and better interpretable machine learning models for genetic medicine, we introduce Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning (PANTHER). PANTHER selects informative genetic pathways that directly encode molecular mechanisms. We apply genetically motivated constrained tensor factorization to group pathways in a way that reflects molecular mechanism interactions. We then train a softmax classifier for disease types using the identified pathway groups. We evaluated PANTHER against multiple state-of-the-art constrained tensor/matrix factorization models, as well as group guided and Bayesian hierarchical models. PANTHER outperforms all state-of-the-art comparison models significantly (p<0.05). Our experiments on large scale Next Generation Sequencing (NGS) and whole-genome genotyping datasets also demonstrated wide applicability of PANTHER. We performed feature analysis in predicting disease types, which suggested insights and benefits of the identified pathway groups.