Difficulty in chirality recognition for Transformer architectures learning chemical structures from string
arXiv:2303.11593 · doi:10.1038/s41467-024-45102-8
Abstract
Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language processing (NLP) models to SMILES, a literal representation of molecular structure. However, little research has been done on how these models understand chemical structure. To address this black box, we investigated the relationship between the learning progress of SMILES and chemical structure using a representative NLP model, the Transformer. We show that while the Transformer learns partial structures of molecules quickly, it requires extended training to understand overall structures. Consistently, the accuracy of molecular property predictions using descriptors generated from models at different learning steps was similar from the beginning to the end of training. Furthermore, we found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers. These findings are expected to deepen the understanding of NLP models in chemistry.
arXiv comment29 pages, 6 figures
References in corpus (7)
- Automatic chemical design using a data-driven continuous representation of molecules
- Convolutional Networks on Graphs for Learning Molecular Fingerprints
- Machine learning prediction errors better than DFT accuracy
- State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesis
- Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders
- Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention
- Difficulty in chirality recognition for Transformer architectures learning chemical structures from string