# Balancing Exploration and Exploitation: Disentangled β-CVAE in De Novo Drug Design

arXiv: https://arxiv.org/abs/2306.01683 · HTML: https://mlsanity.com/paper/2306.01683/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 20 of 20)

- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Variational Autoencoder for Deep Learning of Images, Labels and Captions](https://mlsanity.com/paper/1609.08976/) (2016)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models](https://mlsanity.com/paper/1705.10843/) (2017)
- [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model](https://mlsanity.com/paper/1801.07299/) (2018)
- [MolecularRNN: Generating realistic molecular graphs with optimized properties](https://mlsanity.com/paper/1905.13372/) (2019)
- [Molecular generative model based on conditional variational autoencoder for de novo molecular design](https://mlsanity.com/paper/1806.05805/) (2018)
- [NeVAE: A Deep Generative Model for Molecular Graphs](https://mlsanity.com/paper/1802.05283/) (2018)
- [Molecular Generation with Recurrent Neural Networks (RNNs)](https://mlsanity.com/paper/1705.04612/) (2017)
- [MGCVAE: Multi-objective Inverse Design via Molecular Graph Conditional Variational Autoencoder](https://mlsanity.com/paper/2202.07476/) (2022)
- [Conditional β-VAE for De Novo Molecular Generation](https://mlsanity.com/paper/2205.01592/) (2022)
- [ControlVAE: Tuning, Analytical Properties, and Performance Analysis](https://mlsanity.com/paper/2011.01754/) (2020)
- [Dynamic β-VAEs for quantifying biodiversity by clustering optically recorded insect signals](https://mlsanity.com/paper/2102.05526/) (2021)

## Abstract (arXiv)

Deep generative models have recently emerged as a promising de novo drug design method. In this respect, deep generative conditional variational autoencoder (CVAE) models are a powerful approach for generating novel molecules with desired drug-like properties. However, molecular graph-based models with disentanglement and multivariate explicit latent conditioning have not been fully elucidated. To address this, we proposed a molecular-graph β-CVAE model for de novo drug design. Here, we empirically tuned the value of disentanglement and assessed its ability to generate molecules with optimised univariate- or-multivariate properties. In particular, we optimised the octanol-water partition coefficient (ClogP), molar refractivity (CMR), quantitative estimate of drug-likeness (QED), and synthetic accessibility score (SAS). Results suggest that a lower β value increases the uniqueness of generated molecules (exploration). Univariate optimisation results showed our model generated molecular property averages of ClogP = 41.07% ± 0.01% and CMR 66.76% ± 0.01% by the Ghose filter. Multivariate property optimisation results showed that our model generated an average of 30.07% ± 0.01% molecules for both desired properties. Furthermore, our model improved the QED and SAS (exploitation) of molecules generated. Together, these results suggest that the β-CVAE could balance exploration and exploitation through disentanglement and is a promising model for de novo drug design, thus providing a basis for future studies.