Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Open access

PreFold-dG: estimating binding affinity of protein–protein interaction from intermediate representations of protein folding model

Sungjoon Park Soorin Yim Dongyun Kim Kiwoong Yoo Doyeong Hwang Kyungwook Lee Jongseong Jang Kiyoung Kim
Aug 2026 · Bioinformatics · Vol 42 · 0 citations · 27 references
Medicine

TL;DR

PreFold-dG is presented, a model that estimates binding affinities of protein complexes utilizing intermediate embeddings from Boltz-2, an open-source foundation model for protein structure prediction and achieved state-of-the-art performance on well-established binding affinity prediction benchmarks and demonstrated robustness on independent test sets.

Abstract

Abstract Motivation Binding affinity governs how proteins interact and underlies essential biological processes. Computational approaches have been developed to simulate and predict protein binding, but the scarcity of high-quality data has imposed significant constraints. One consequence is that most methods focus on predicting mutational changes in binding affinity (ΔΔG), rather than binding affinity (ΔG) itself. This practice risks overfitting to skewed data distributions, limiting the generalizability of predictions. Recent advances in protein structure prediction have enabled computational modeling of protein conformations in mass, providing rich structural information from which binding interactions can be largely explained. However, leveraging these advances for effective prediction of binding affinity has yet to translate into reliable predictions. Results We present PreFold-dG, a model that estimates binding affinities of protein complexes utilizing intermediate embeddings from Boltz-2, an open-source foundation model for protein structure prediction. Our approach aggregates residue-level information weighted by interresidue distance, and predicts ΔG directly rather than its derivative, ΔΔG. PreFold-dG achieved state-of-the-art performance on well-established binding affinity prediction benchmarks and demonstrated robustness on independent test sets. Ablation studies suggest that all intermediate embeddings are utilized in the prediction, whereas their contributions to modeling ΔΔG and ΔG vary. We further validated our model through case studies on real-world broadly neutralizing antibody data with evolutionary relevance. Availability https://github.com/LGAI-Research/PreFold-dG.

DOI PubMed Semantic Scholar
Read PDF

Similar papers

Open access Aug 2026

Interpretable multilevel interaction modeling for robust protein–protein affinity

MIRAGE provides an interpretable and robust framework for structure-aware prediction, with potential applications in protein engineering and drug design, and explicitly modeling multi-level interactions is important for accurately capturing the determinants of binding affinity.

Shiwei Wu, Haoliang Liu, Ze-Peng Huang et al. · 0 citations
Open access Sep 2026

ProRB: a structure-free unified framework for joint prediction and design of protein–RNA interactions

Abstract While protein–RNA interactions are fundamental to post-transcriptional processes, achieving a holistic understanding of their regulatory logic remains challenging. Current computational models often treat binding affinity, interface mapping, and RNA design as isolated tasks, thereby failing to provide a unified perspective of the protein–RNA interactome. Here, we introduce ProRB, a unified sequence-based framework that jointly estimates protein–RNA binding affinity, predicts binding interfaces in proteins and RNAs, and generates protein-binding RNA sequences from protein sequences. By fusing protein and RNA embeddings from language models via adaptive cross-modal attention, ProRB learns contextual and relational features for predicting protein–RNA binding affinity and interface contacts, outperforming or achieving competitive performance compared to structure-based methods. Notably, its cross-attention maps reveal interpretable, motif-centric binding logic hidden in protein–RNA interactions. Building on this interpretability, ProRB enables computationally prioritized design of protein-binding RNA sequences with enhanced biophysical properties and functional motifs. By unifying the prediction, interpretation, and generation tasks, ProRB provides a scalable unified model for decoding the protein–RNA interaction and engineering motif-guided RNA therapeutics.

Unknown authors · 0 citations
Open access Aug 2026

Learning Protein–Protein Binding Free Energies from Interface Graphs and Physicochemical Descriptors

Predicting protein–protein binding free energy (ΔG) from structure remains a central challenge in computational biophysics. Here, we present GULP (Graph-based Unified Learning for Protein binding), a graph neural network (GNN) that jointly learns from a residue-level graph representation of the binding interface and global physicochemical descriptors. We systematically investigate how training data distribution affects model performance by comparing a full training set with a balanced subset enriched for extreme-affinity complexes. GULP is computationally efficient and provides interpretable insights into residue-level and physicochemical contributions to binding. On external validation, GULP achieves a mean absolute error (MAE) of 2.31 kcal/mol and shows moderate agreement with experimental ΔG values (Pearson r = 0.54, Spearman ρ = 0.58).

Qingshu Zhao, Arjun Saha · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.