# CRNNTL: convolutional recurrent neural network and transfer learning for QSAR modelling

arXiv: https://arxiv.org/abs/2109.03309 · HTML: https://mlsanity.com/paper/2109.03309/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 46 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 8 of 8)

- [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)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Comparative Study of CNN and RNN for Natural Language Processing](https://mlsanity.com/paper/1702.01923/) (2017)
- [Molecular generative model based on conditional variational autoencoder for de novo molecular design](https://mlsanity.com/paper/1806.05805/) (2018)
- [Convolutional Recurrent Neural Networks for Music Classification](https://mlsanity.com/paper/1609.04243/) (2016)
- [Probably Approximately Correct Constrained Learning](https://mlsanity.com/paper/2006.05487/) (2020)
- [Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders](https://mlsanity.com/paper/1806.09300/) (2018)

## Built on by (most cited first, 1 of 1)

- [Improving VAE based molecular representations for compound property prediction](https://mlsanity.com/paper/2201.04929/) (2022)

## Abstract (arXiv)

In this study, we propose the convolutional recurrent neural network and transfer learning (CRNNTL) for QSAR modelling. The method was inspired by the applications of polyphonic sound detection and electrocardiogram classification. Our strategy takes advantages of both convolutional and recurrent neural networks for feature extraction, as well as the data augmentation method. Herein, CRNNTL is evaluated on 20 benchmark datasets in comparison with baseline methods. In addition, one isomers based dataset is used to elucidate its ability for both local and global feature extraction. Then, knowledge transfer performance of CRNNTL is tested, especially for small biological activity datasets. Finally, different latent representations from other type of AEs were used for versatility study of our model. The results show the effectiveness of CRNNTL using different latent representation. Moreover, efficient knowledge transfer is achieved to overcome data scarcity considering binding site similarity between different targets.