# Improving VAE based molecular representations for compound property prediction

arXiv: https://arxiv.org/abs/2201.04929 · HTML: https://mlsanity.com/paper/2201.04929/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [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)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discovery](https://mlsanity.com/paper/1803.09518/) (2018)
- [Syntax-Directed Variational Autoencoder for Structured Data](https://mlsanity.com/paper/1802.08786/) (2018)
- [All SMILES Variational Autoencoder](https://mlsanity.com/paper/1905.13343/) (2019)
- [Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction](https://mlsanity.com/paper/1712.02734/) (2017)
- [Synergy Effect between Convolutional Neural Networks and the Multiplicity of SMILES for Improvement of Molecular Prediction](https://mlsanity.com/paper/1812.04439/) (2018)
- [CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling](https://mlsanity.com/paper/2109.03309/) (2021)

## Built on by (most cited first, 3 of 3)

- [Generative Model-Driven Synthetic Training Image Generation: An Approach to Cognition in Rail Defect Detection](https://mlsanity.com/paper/2401.00393/) (2023)
- [MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning](https://mlsanity.com/paper/2410.11226/) (2024)
- [Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides](https://mlsanity.com/paper/2511.00209/) (2025)

## Abstract (arXiv)

Collecting labeled data for many important tasks in chemoinformatics is time consuming and requires expensive experiments. In recent years, machine learning has been used to learn rich representations of molecules using large scale unlabeled molecular datasets and transfer the knowledge to solve the more challenging tasks with limited datasets. Variational autoencoders are one of the tools that have been proposed to perform the transfer for both chemical property prediction and molecular generation tasks. In this work we propose a simple method to improve chemical property prediction performance of machine learning models by incorporating additional information on correlated molecular descriptors in the representations learned by variational autoencoders. We verify the method on three property prediction asks. We explore the impact of the number of incorporated descriptors, correlation between the descriptors and the target properties, sizes of the datasets etc. Finally, we show the relation between the performance of property prediction models and the distance between property prediction dataset and the larger unlabeled dataset in the representation space.