# Modeling Industrial ADMET Data with Multitask Networks

arXiv: https://arxiv.org/abs/1606.08793 · HTML: https://mlsanity.com/paper/1606.08793/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2016.

## Built on by (most cited first, 4 of 4)

- [Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation](https://mlsanity.com/paper/2305.09790/) (2023)
- [Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical Spaces](https://mlsanity.com/paper/2111.13964/) (2021)
- [Integrating Chemical Language and Molecular Graph in Multimodal Fused Deep Learning for Drug Property Prediction](https://mlsanity.com/paper/2312.17495/) (2023)
- [QComp: A QSAR-Based Data Completion Framework for Drug Discovery](https://mlsanity.com/paper/2405.11703/) (2024)

## Abstract (arXiv)

Deep learning methods such as multitask neural networks have recently been applied to ligand-based virtual screening and other drug discovery applications. Using a set of industrial ADMET datasets, we compare neural networks to standard baseline models and analyze multitask learning effects with both random cross-validation and a more relevant temporal validation scheme. We confirm that multitask learning can provide modest benefits over single-task models and show that smaller datasets tend to benefit more than larger datasets from multitask learning. Additionally, we find that adding massive amounts of side information is not guaranteed to improve performance relative to simpler multitask learning. Our results emphasize that multitask effects are highly dataset-dependent, suggesting the use of dataset-specific models to maximize overall performance.