On fine-tuning Boltz-2 for protein-protein affinity prediction

• URL: http://arxiv.org/abs/2512.06592v1
• Date: Sat, 06 Dec 2025 23:07:10 GMT
• Title: On fine-tuning Boltz-2 for protein-protein affinity prediction
• Authors: James King, Lewis Cornwall, Andrei Cristian Nica, James Day, Aaron Sim, Neil Dalchau, Lilly Wollman, Joshua Meyers,
• Abstract summary: We adapt Boltz-2, a structure-based protein-ligand affinity predictor, for protein-protein affinity regression.<n>Despite high structural accuracy, Boltz-2-PPI underperforms relative to sequence-based alternatives in both small- and larger-scale data regimes.<n>Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction.
• Score: 1.7607577951969595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate prediction of protein-protein binding affinity is vital for understanding molecular interactions and designing therapeutics. We adapt Boltz-2, a state-of-the-art structure-based protein-ligand affinity predictor, for protein-protein affinity regression and evaluate it on two datasets, TCR3d and PPB-affinity. Despite high structural accuracy, Boltz-2-PPI underperforms relative to sequence-based alternatives in both small- and larger-scale data regimes. Combining embeddings from Boltz-2-PPI with sequence-based embeddings yields complementary improvements, particularly for weaker sequence models, suggesting different signals are learned by sequence- and structure-based models. Our results echo known biases associated with training with structural data and suggest that current structure-based representations are not primed for performant affinity prediction.

Related papers

• S$^2$Drug: Bridging Protein Sequence and 3D Structure in Contrastive Representation Learning for Virtual Screening [72.89086338778098]
  We propose a two-stage framework for protein-ligand contrastive representation learning.<n>In the first stage, we perform protein sequence pretraining on ChemBL using an ESM2-based backbone.<n>In the second stage, we fine-tune on PDBBind by fusing sequence and structure information through a residue-level gating module.<n>This auxiliary task guides the model to accurately localize binding residues within the protein sequence and capture their 3D spatial arrangement.
  arXiv  Detail & Related papers  (2025-11-10T11:57:47Z)
• Conformation-Aware Structure Prediction of Antigen-Recognizing Immune Proteins [4.747546562792329]
  We introduce Ibex, a pan-immunoglobulin structure prediction model.<n>It achieves state-of-the-art accuracy in modeling the variable domains of antibodies, nanobodies, and T-cell receptors.
  arXiv  Detail & Related papers  (2025-07-11T22:09:03Z)
• PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs [88.98041407783502]
  PRING is the first benchmark that evaluates protein-protein interaction prediction from a graph-level perspective.<n> PRING curates a high-quality, multi-species PPI network dataset comprising 21,484 proteins and 186,818 interactions.
  arXiv  Detail & Related papers  (2025-07-07T15:21:05Z)
• KEPLA: A Knowledge-Enhanced Deep Learning Framework for Accurate Protein-Ligand Binding Affinity Prediction [60.23701115249195]
  KEPLA is a novel deep learning framework that integrates prior knowledge from Gene Ontology and ligand properties to enhance prediction performance.<n> Experiments on two benchmark datasets demonstrate that KEPLA consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-16T08:02:42Z)
• SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation [97.99658944212675]
  We introduce a novel pre-training strategy for protein foundation models. It emphasizes the interactions among amino acid residues to enhance the extraction of both short-range and long-range co-evolutionary features. Trained on a large-scale protein sequence dataset, our model demonstrates superior generalization ability.
  arXiv  Detail & Related papers  (2024-10-31T15:22:03Z)
• CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction [23.1499716310298]
  We build the largest protein-RNA binding affinity dataset PRA310 for performance evaluation.<n>We provide extensive analyses and verify that CoPRA can (1) accurately predict the protein-RNA binding affinity; (2) understand the binding affinity change caused by mutations; and (3) benefit from scaling data and model size.
  arXiv  Detail & Related papers  (2024-08-21T09:48:22Z)
• PSC-CPI: Multi-Scale Protein Sequence-Structure Contrasting for Efficient and Generalizable Compound-Protein Interaction Prediction [63.50967073653953]
  Compound-Protein Interaction prediction aims to predict the pattern and strength of compound-protein interactions for rational drug discovery. Existing deep learning-based methods utilize only the single modality of protein sequences or structures. We propose a novel multi-scale Protein Sequence-structure Contrasting framework for CPI prediction.
  arXiv  Detail & Related papers  (2024-02-13T03:51:10Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Multimodal Pre-Training Model for Sequence-based Prediction of Protein-Protein Interaction [7.022012579173686]
  Pre-training a protein model to learn effective representation is critical for protein-protein interactions. Most pre-training models for PPIs are sequence-based, which naively adopt the language models used in natural language processing to amino acid sequences. We propose a multimodal protein pre-training model with three modalities: sequence, structure, and function.
  arXiv  Detail & Related papers  (2021-12-09T10:21:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.