2000 character limit reached
Stable Online and Offline Reinforcement Learning for Antibody CDRH3 Design (2401.05341v1)
Published 29 Nov 2023 in q-bio.BM and cs.LG
Abstract: The field of antibody-based therapeutics has grown significantly in recent years, with targeted antibodies emerging as a potentially effective approach to personalized therapies. Such therapies could be particularly beneficial for complex, highly individual diseases such as cancer. However, progress in this field is often constrained by the extensive search space of amino acid sequences that form the foundation of antibody design. In this study, we introduce a novel reinforcement learning method specifically tailored to address the unique challenges of this domain. We demonstrate that our method can learn the design of high-affinity antibodies against multiple targets in silico, utilizing either online interaction or offline datasets. To the best of our knowledge, our approach is the first of its kind and outperforms existing methods on all tested antigens in the Absolut! database.
- Computational approaches to therapeutic antibody design: established methods and emerging trends. Briefings in Bioinformatics, 21(5), 10 2019. doi: 10.1093/bib/bbz095.
- Unconstrained generation of synthetic antibody-antigen structures to guide machine learning methodology for real-world antibody specificity prediction. bioRxiv, 2022. doi: 10.1101/2021.07.06.451258.
- Antibodies to watch in 2023. mAbs, 15(1), 2023. doi: 10.1080/19420862.2022.2153410.
- Diversity in the cdr3 region of vh is sufficient for most antibody specificities. Immunity, 13(1), 2000. doi: https://doi.org/10.1016/S1074-7613(00)00006-6.
- Reinforcement learning - an introduction. Adaptive computation and machine learning. MIT Press, 1998. ISBN 978-0-262-19398-6.
- Mastering the game of go without human knowledge. Nature, 550(7676), Oct 2017. doi: 10.1038/nature24270.
- Offline reinforcement learning: Tutorial, review, and perspectives on open problems. CoRR, abs/2005.01643, 2020.
- Language models are unsupervised multitask learners. 2019.
- Language models are few-shot learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020.
- Ankh: Optimized protein language model unlocks general-purpose modelling. CoRR, abs/2301.06568, 2023. doi: 10.48550/ARXIV.2301.06568.
- Maxmin q-learning: Controlling the estimation bias of q-learning. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020.
- Uncertainty-based offline reinforcement learning with diversified q-ensemble. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, 2021.
- Efficient online reinforcement learning with offline data. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research. PMLR, 2023.
- Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space. Nature Communications, 13(1), Jul 2022. doi: 10.1038/s41467-022-31457-3.
- Can alphafold2 predict the impact of missense mutations on structure? Nature structural & molecular biology, 29(1), 2022.
- Evolutionary-scale prediction of atomic-level protein structure with a language model. Science, 379(6637), 2023. doi: 10.1126/science.ade2574.
- Structured q-learning for antibody design. CoRR, abs/2209.04698, 2022. doi: 10.48550/ARXIV.2209.04698.
- Antbo: Towards real-world automated antibody design with combinatorial bayesian optimisation. CoRR, abs/2201.12570, 2022.
- Model-based reinforcement learning for biological sequence design. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020.
- Biological sequence design with gflownets. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research. PMLR, 2022.
- Conservative objective models for effective offline model-based optimization. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event, volume 139 of Proceedings of Machine Learning Research. PMLR, 2021.
- Adaptation in protein fitness landscapes is facilitated by indirect paths. eLife, 5, jul 2016. doi: 10.7554/eLife.16965.
- Prioritized experience replay. In 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, 2016.
- Hado van Hasselt. Double q-learning. In Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada. Curran Associates, Inc., 2010.
- Sample-efficient reinforcement learning by breaking the replay ratio barrier. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
- Intrabody and parkinson’s disease. Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease, 1792(7), 2009. doi: https://doi.org/10.1016/j.bbadis.2008.09.001.
- Human-level control through deep reinforcement learning. Nat., 518(7540), 2015. doi: 10.1038/NATURE14236.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.