ChemFixer: Correcting Invalid Molecules to Unlock Previously Unseen Chemical Space
This addresses a bottleneck in drug discovery by enhancing the practical utility of generative models, though it is incremental as it builds on existing transformer architectures and masking techniques.
The paper tackled the problem of deep learning-based molecular generation models producing chemically invalid molecules, which limits usable chemical space, by proposing ChemFixer, a transformer-based framework that corrects invalid molecules into valid ones, improving validity while preserving chemical and biological properties and enabling application to drug-target interaction prediction.
Deep learning-based molecular generation models have shown great potential in efficiently exploring vast chemical spaces by generating potential drug candidates with desired properties. However, these models often produce chemically invalid molecules, which limits the usable scope of the learned chemical space and poses significant challenges for practical applications. To address this issue, we propose ChemFixer, a framework designed to correct invalid molecules into valid ones. ChemFixer is built on a transformer architecture, pre-trained using masking techniques, and fine-tuned on a large-scale dataset of valid/invalid molecular pairs that we constructed. Through comprehensive evaluations across diverse generative models, ChemFixer improved molecular validity while effectively preserving the chemical and biological distributional properties of the original outputs. This indicates that ChemFixer can recover molecules that could not be previously generated, thereby expanding the diversity of potential drug candidates. Furthermore, ChemFixer was effectively applied to a drug-target interaction (DTI) prediction task using limited data, improving the validity of generated ligands and discovering promising ligand-protein pairs. These results suggest that ChemFixer is not only effective in data-limited scenarios, but also extensible to a wide range of downstream tasks. Taken together, ChemFixer shows promise as a practical tool for various stages of deep learning-based drug discovery, enhancing molecular validity and expanding accessible chemical space.