SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision

2024-12-07

arXiv.org

AI Summary

Existing SMILES pretraining models rely solely on single-token supervision, neglecting substructural semantics, and are trained only on corrupted SMILES strings—leading to weak supervisory signals and train-inference mismatch. To address these limitations, we propose SMI-Editor, an edit-based pretraining paradigm that randomly perturbs molecular substructures (rather than individual atoms or bonds) and reconstructs the original valid SMILES, thereby enabling fragment-level supervision and joint modeling of chemical validity. Built upon a Transformer architecture, SMI-Editor explicitly incorporates SMILES syntactic constraints and chemical substructure priors. This work is the first to introduce edit operations into molecular language modeling. Evaluated across multiple downstream tasks, SMI-Editor achieves state-of-the-art performance—outperforming several 3D-aware representation models—and significantly enhances molecular semantic understanding and generation capabilities.

Technology Category

• Machine Learning: Structured Learning
• Computer Vision: Diffusion Models for Vision
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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.

Problem

• Existing SMILES LMs lack fragment-level molecular supervision.
• Current models suffer from train-inference mismatch with invalid SMILES.
• SMI-Editor improves molecular representation via edit-based fragment reconstruction.

Innovation

• Edit-based SMILES LM with fragment-level supervision
• Uses valid SMILES inputs for training
• Randomly disrupts substructures for reconstruction