# Integrating Multiview Information for Enhanced Deep Learning-Based Acute Dermal Toxicity Prediction

## TL;DR

This paper introduces MVIToxNet, a deep learning model that improves acute dermal toxicity prediction by integrating multiview molecular data and using a weighted model averaging strategy.

## Contribution

MVIToxNet is a novel model that integrates multiview features and uses weighted model averaging to enhance toxicity prediction.

## Key findings

- MVIToxNet significantly outperforms existing baselines in acute dermal toxicity prediction.
- The use of multiview features and weighted model averaging improves generalization on small and imbalanced datasets.
- The proposed methods show potential for data-driven model design in toxicity prediction.

## Abstract

Accurate prediction of acute dermal toxicity is vital
for the safe
and effective development of contact drugs. While numerous deep learning
models have been created to replace costly and ethically challenging
animal toxicity tests, most approaches overlook the multiview information
on molecules. To overcome this limitation, we introduce a novel model
named MVIToxNet, which integrates multiview features from both molecular
fingerprints and SMILES sequences. To capture the multiview information
on SMILES, MVIToxNet incorporates character-level and atom-level features.
In addition, byte-pair encoding tokenization is utilized to capture
substructural details within molecules, allowing the model to differentiate
similar SMILES by assigning distinct tokens to different substructures.
Since the data sets in this study are small and imbalanced, we argue
that selecting a single model based solely on the best validation
performance may not reliably reflect the best generalization for test
sets. Therefore, we propose a weighted model averaging approach that
combines multiple trained models according to their top-K validation
scores into one model, yielding an improved model for inference. Extensive
experimental results demonstrate that MVIToxNet significantly outperforms
existing baselines in acute dermal toxicity prediction, validating
the effectiveness of utilizing multiview features and the weighted
model averaging strategy. Furthermore, our proposed methods demonstrate
the potential for data-driven model design.