GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation

Haitao Lin, Lirong Wu, Yufei Huang, Yunfan Liu, Odin Zhang, Yuanqing Zhou, Rui Sun, Stan Z. Li
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30346-30361, 2024.

Abstract

Increasing works for antibody design are emerging to generate sequences and structures in Complementarity Determining Regions (CDRs), but problems still exist. We focus on two of them: (i) authenticity of the generated structure and (ii) rationality of the affinity maturation, and propose GeoAB as a solution. In specific, GeoAB-Designergenerates CDR structures with realistic internal geometries, composed of a generative geometry initializer (Geo-Initializer) and a position refiner (Geo-Refiner); GeoAB-Optimizer achieves affinity maturation by accurately predicting both the mutation effects and structures of mutant antibodies with the same network architecture as Geo-Refiner. Experiments show that GeoAB achieves state-of-the-art performance in CDR co-design and mutation effect predictions, and fulfills the discussed tasks effectively.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lin24s, title = {{G}eo{AB}: Towards Realistic Antibody Design and Reliable Affinity Maturation}, author = {Lin, Haitao and Wu, Lirong and Huang, Yufei and Liu, Yunfan and Zhang, Odin and Zhou, Yuanqing and Sun, Rui and Li, Stan Z.}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30346--30361}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lin24s/lin24s.pdf}, url = {https://proceedings.mlr.press/v235/lin24s.html}, abstract = {Increasing works for antibody design are emerging to generate sequences and structures in Complementarity Determining Regions (CDRs), but problems still exist. We focus on two of them: (i) authenticity of the generated structure and (ii) rationality of the affinity maturation, and propose GeoAB as a solution. In specific, GeoAB-Designergenerates CDR structures with realistic internal geometries, composed of a generative geometry initializer (Geo-Initializer) and a position refiner (Geo-Refiner); GeoAB-Optimizer achieves affinity maturation by accurately predicting both the mutation effects and structures of mutant antibodies with the same network architecture as Geo-Refiner. Experiments show that GeoAB achieves state-of-the-art performance in CDR co-design and mutation effect predictions, and fulfills the discussed tasks effectively.} }
Endnote
%0 Conference Paper %T GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation %A Haitao Lin %A Lirong Wu %A Yufei Huang %A Yunfan Liu %A Odin Zhang %A Yuanqing Zhou %A Rui Sun %A Stan Z. Li %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lin24s %I PMLR %P 30346--30361 %U https://proceedings.mlr.press/v235/lin24s.html %V 235 %X Increasing works for antibody design are emerging to generate sequences and structures in Complementarity Determining Regions (CDRs), but problems still exist. We focus on two of them: (i) authenticity of the generated structure and (ii) rationality of the affinity maturation, and propose GeoAB as a solution. In specific, GeoAB-Designergenerates CDR structures with realistic internal geometries, composed of a generative geometry initializer (Geo-Initializer) and a position refiner (Geo-Refiner); GeoAB-Optimizer achieves affinity maturation by accurately predicting both the mutation effects and structures of mutant antibodies with the same network architecture as Geo-Refiner. Experiments show that GeoAB achieves state-of-the-art performance in CDR co-design and mutation effect predictions, and fulfills the discussed tasks effectively.
APA
Lin, H., Wu, L., Huang, Y., Liu, Y., Zhang, O., Zhou, Y., Sun, R. & Li, S.Z.. (2024). GeoAB: Towards Realistic Antibody Design and Reliable Affinity Maturation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30346-30361 Available from https://proceedings.mlr.press/v235/lin24s.html.

Related Material