A blinded, prospective benchmark of in silico antibody discovery anchored to experimental affinity and developability
Open Access
- 19 August 2026
- journal article
- research article
- Published by Springer Nature in Nature Biotechnology
- p. 1-13
Abstract
Experimentally validated prospective, blinded benchmarks are needed to separate durable advances from hype in computational antibody design. Here AIntibody, a challenge inspired by the Critical Assessment of Structure Prediction, tests 511 artificial intelligence (AI)-designed or predicted antibodies from 29 organizations on three tasks: in silico affinity maturation from phase 1 sequencing outputs, affinity ranking within heavy-chain complementarity-determining region 3 (HCDR3) clusters of a selection output and CDR design of proteins not included in a selection output. Validated with diverse experimental assays, several groups produced developable antibodies with affinities <100 pM. However, these successes were exceptions that did not transfer across tasks. Affinity-matured antibodies were modeled effectively. Except for one model, predicting high-affinity clones from clustered HCDR3 datasets was worse than random clone picking. Out-of-library design was highly variable for most method submissions, with many failing to outperform standard selections. The AIntibody challenge shows that AI can optimize antibodies in defined, biologically grounded regimes, in addition to highlighting critical gaps including affinity prediction and library-inspired antibody design and cross-task generalization.Keywords
This publication has 37 references indexed in Scilit:
- Improving antibody language models with native pairingPatterns, 2024
- Linear-Scaling Kernels for Protein Sequences and Small Molecules Outperform Deep Learning While Providing Uncertainty Quantitation and Improved InterpretabilityJournal of Chemical Information and Modeling, 2023
- Observed Antibody Space: A diverse database of cleaned, annotated, and translated unpaired and paired antibody sequencesProtein Science, 2021
- Critical assessment of methods of protein structure prediction (CASP)—Round XIIIProteins: Structure, Function, and Bioinformatics, 2019
- D3R grand challenge 2015: Evaluation of protein–ligand pose and affinity predictionsJournal of Computer-Aided Molecular Design, 2016
- Consensus-Based Engineering of Protein Stability: From Intrabodies to Thermostable Enzymes2004
- Predicting protein three-dimensional structureCurrent Opinion in Biotechnology, 1999
- Intrabody construction and expression. I. The critical role of VL domain stabilityJournal of Molecular Biology, 1999
- Intrabody construction and expression. II. A synthetic catalytic Fv fragmentJournal of Molecular Biology, 1999
- Drosophila lebanonensis ADH: analysis of recombinant wild‐type enzyme and site‐directed mutantsFEBS Letters, 1994