Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion

Bowen Gao, Minsi Ren, Yuyan Ni, Yanwen Huang, Bo Qiang, Zhi-Ming Ma, Wei-Ying Ma, Yanyan Lan
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:14811-14825, 2024.

Abstract

In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-gao24k, title = {Rethinking Specificity in {SBDD}: Leveraging Delta Score and Energy-Guided Diffusion}, author = {Gao, Bowen and Ren, Minsi and Ni, Yuyan and Huang, Yanwen and Qiang, Bo and Ma, Zhi-Ming and Ma, Wei-Ying and Lan, Yanyan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {14811--14825}, 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/gao24k/gao24k.pdf}, url = {https://proceedings.mlr.press/v235/gao24k.html}, abstract = {In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.} }
Endnote
%0 Conference Paper %T Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion %A Bowen Gao %A Minsi Ren %A Yuyan Ni %A Yanwen Huang %A Bo Qiang %A Zhi-Ming Ma %A Wei-Ying Ma %A Yanyan Lan %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-gao24k %I PMLR %P 14811--14825 %U https://proceedings.mlr.press/v235/gao24k.html %V 235 %X In the field of Structure-based Drug Design (SBDD), deep learning-based generative models have achieved outstanding performance in terms of docking score. However, further study shows that the existing molecular generative methods and docking scores both have lacked consideration in terms of specificity, which means that generated molecules bind to almost every protein pocket with high affinity. To address this, we introduce the Delta Score, a new metric for evaluating the specificity of molecular binding. To further incorporate this insight for generation, we develop an innovative energy-guided approach using contrastive learning, with active compounds as decoys, to direct generative models toward creating molecules with high specificity. Our empirical results show that this method not only enhances the delta score but also maintains or improves traditional docking scores, successfully bridging the gap between SBDD and real-world needs.
APA
Gao, B., Ren, M., Ni, Y., Huang, Y., Qiang, B., Ma, Z., Ma, W. & Lan, Y.. (2024). Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:14811-14825 Available from https://proceedings.mlr.press/v235/gao24k.html.

Related Material