Affinity Fine-Tuning of Boltz-2: An Open Framework for Protein-Ligand Potency Prediction in Drug Discovery
Amini, S.; Sciabola, S.; Wang, Y.
Show abstract
Boltz-2 has enabled accurate binding affinity prediction by leveraging co-folded protein-ligand structures, but the absence of a public training recipe has limited its use in active drug discovery projects, where new experimental measurements and congeneric ligand series continually arrive during lead optimization. We present an open framework for affinity fine-tuning of Boltz-2, showing that adapting only the affinity prediction components with project-specific experimental data can make the model substantially more useful for lead optimization. We evaluate the approach in two internal studies: a multi-target retrospective benchmark against physics-based and machine learning baselines, and a large single-target study with up to 1,700 ligands. In both settings, fine-tuned Boltz-2 improves correlation over the off-the-shelf model, and in some cases reaches performance competitive with free energy perturbation (FEP) methods. By releasing this framework, we aim to enable the community to adapt Boltz-2 to the specific targets and data of their own drug discovery campaigns. The code is available at: https://github.com/molecularinformatics/Boltz2_affinity
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DiffDock-Glide: a hybrid physics-based and data-driven approach to molecular docking 96%
- DENVIS: scalable and high-throughput virtual screening using graph neural networks with atomic and surface protein pocket features 96%
- Dataset Augmentation Allows Deep Learning-Based Virtual Screening To Better Generalize To Unseen Target Classes, And Highlight Important Binding Interactions 95%
Similar papers in this journal
- Semantical and Geometrical Protein Encoding Toward Enhanced Bioactivity and Thermostability 93%
- Death by a Thousand Cuts -- Combining Kinase Inhibitors for Selective Target Inhibition and Rational Polypharmacology 93%
- Expanding Automated Multiconformer Ligand Modeling to Macrocycles and Fragments 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.