C5T5: Controllable Generation of Organic Molecules with Transformers
arXiv:2108.10307
Abstract
Methods for designing organic materials with desired properties have high potential impact across fields such as medicine, renewable energy, petrochemical engineering, and agriculture. However, using generative modeling to design substances with desired properties is difficult because candidate compounds must satisfy multiple constraints, including synthetic accessibility and other metrics that are intuitive to domain experts but challenging to quantify. We propose C5T5, a novel self-supervised pretraining method that enables transformers to make zero-shot select-and-replace edits, altering organic substances towards desired property values. C5T5 operates on IUPAC names -- a standardized molecular representation that intuitively encodes rich structural information for organic chemists but that has been largely ignored by the ML community. Our technique requires no edited molecule pairs to train and only a rough estimate of molecular properties, and it has the potential to model long-range dependencies and symmetric molecular structures more easily than graph-based methods. C5T5 also provides a powerful interface to domain experts: it grants users fine-grained control over the generative process by selecting and replacing IUPAC name fragments, which enables experts to leverage their intuitions about structure-activity relationships. We demonstrate C5T5's effectiveness on four physical properties relevant for drug discovery, showing that it learns successful and chemically intuitive strategies for altering molecules towards desired property values.
References in corpus (13)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- HuggingFace's Transformers: State-of-the-art Natural Language Processing
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- MolGAN: An implicit generative model for small molecular graphs
- Constrained Graph Variational Autoencoders for Molecule Design
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
- Quantifying the Carbon Emissions of Machine Learning
- Molecular Hypergraph Grammar with its Application to Molecular Optimization
- Learning to Extend Molecular Scaffolds with Structural Motifs
- Affect-LM: A Neural Language Model for Customizable Affective Text Generation