Tokenizing Electron Cloud in Protein-Ligand Interaction Learning

TL;DR

ECBind introduces a novel method for tokenizing electron cloud signals into embeddings, enhancing protein-ligand interaction predictions by incorporating quantum chemical properties into deep learning models.

Contribution

The paper presents ECBind, a new approach that encodes electron densities into tokens for improved binding affinity prediction, bridging the gap between quantum chemistry and deep learning.

Findings

Achieves 6.42% improvement in Pearson correlation

Achieves 15.58% improvement in Spearman correlation

Demonstrates state-of-the-art performance on multiple tasks

Abstract

The affinity and specificity of protein-molecule binding directly impact functional outcomes, uncovering the mechanisms underlying biological regulation and signal transduction. Most deep-learning-based prediction approaches focus on structures of atoms or fragments. However, quantum chemical properties, such as electronic structures, are the key to unveiling interaction patterns but remain largely underexplored. To bridge this gap, we propose ECBind, a method for tokenizing electron cloud signals into quantized embeddings, enabling their integration into downstream tasks such as binding affinity prediction. By incorporating electron densities, ECBind helps uncover binding modes that cannot be fully represented by atom-level models. Specifically, to remove the redundancy inherent in electron cloud signals, a structure-aware transformer and hierarchical codebooks encode 3D binding sites enriched with electron structures into tokens. These tokenized codes are then used for specific tasks with labels. To extend its applicability to a wider range of scenarios, we utilize knowledge distillation to develop an electron-cloud-agnostic prediction model. Experimentally, ECBind demonstrates state-of-the-art performance across multiple tasks, achieving improvements of 6.42\% and 15.58\% in per-structure Pearson and Spearman correlation coefficients, respectively.