SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision
This addresses a bottleneck in molecular representation learning for computational chemistry and drug discovery, offering an incremental but effective improvement over existing SMILES-based methods.
The paper tackles the problem that existing SMILES language models for molecular structures rely on single-token supervision and corrupted inputs, limiting their ability to capture substructural information. The proposed SMI-Editor model uses an edit-based approach with fragment-level supervision and valid SMILES inputs, achieving state-of-the-art performance on multiple downstream molecular tasks and outperforming some 3D models.
SMILES, a crucial textual representation of molecular structures, has garnered significant attention as a foundation for pre-trained language models (LMs). However, most existing pre-trained SMILES LMs focus solely on the single-token level supervision during pre-training, failing to fully leverage the substructural information of molecules. This limitation makes the pre-training task overly simplistic, preventing the models from capturing richer molecular semantic information. Moreover, during pre-training, these SMILES LMs only process corrupted SMILES inputs, never encountering any valid SMILES, which leads to a train-inference mismatch. To address these challenges, we propose SMI-Editor, a novel edit-based pre-trained SMILES LM. SMI-Editor disrupts substructures within a molecule at random and feeds the resulting SMILES back into the model, which then attempts to restore the original SMILES through an editing process. This approach not only introduces fragment-level training signals, but also enables the use of valid SMILES as inputs, allowing the model to learn how to reconstruct complete molecules from these incomplete structures. As a result, the model demonstrates improved scalability and an enhanced ability to capture fragment-level molecular information. Experimental results show that SMI-Editor achieves state-of-the-art performance across multiple downstream molecular tasks, and even outperforming several 3D molecular representation models.