HyperSBINN: A Hypernetwork-Enhanced Systems Biology-Informed Neural Network for Efficient Drug Cardiosafety Assessment

TL;DR

HyperSBINN is a novel neural network approach that combines hypernetworks and systems biology to efficiently predict drug effects on cardiac electrophysiology, aiding early drug safety assessment.

Contribution

It introduces hyperSBINN, a new method that enhances SBINNs with hypernetworks and meta-learning for faster, data-efficient modeling of cardiac responses to drugs.

Findings

Outperforms traditional solvers in speed

Accurately predicts APD90 values

Handles limited data scenarios effectively

Abstract

Mathematical modeling in systems toxicology enables a comprehensive understanding of the effects of pharmaceutical substances on cardiac health. However, the complexity of these models limits their widespread application in early drug discovery. In this paper, we introduce a novel approach to solving parameterized models of cardiac action potentials by combining meta-learning techniques with Systems Biology-Informed Neural Networks (SBINNs). The proposed method, hyperSBINN, effectively addresses the challenge of predicting the effects of various compounds at different concentrations on cardiac action potentials, outperforming traditional differential equation solvers in speed. Our model efficiently handles scenarios with limited data and complex parameterized differential equations. The hyperSBINN model demonstrates robust performance in predicting APD90 values, indicating its potential as a reliable tool for modeling cardiac electrophysiology and aiding in preclinical drug development. This framework represents an advancement in computational modeling, offering a scalable and efficient solution for simulating and understanding complex biological systems.