MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Yanru Qu; Keyue Qiu; Yuxuan Song; Jingjing Gong; Jiawei Han; Mingyue Zheng; Hao Zhou; Wei-Ying Ma

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Yanru Qu (Co-first Author)
, Keyue Qiu (Co-first Author)
, Yuxuan Song (Co-first Author)
, Jingjing Gong^*
, Jiawei Han
, Mingyue Zheng
, Hao Zhou^*
, Wei-Ying Ma

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

11 Citations (Scopus)

Abstract

Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D poses and resulting in false positives. We conduct thorough studies on key factors of ill-conformational problems when applying autoregressive methods and diffusion to SBDD, including mode collapse and hybrid continuous-discrete space. In this paper, we introduce MolCRAFT, the first SBDD model that operates in the continuous parameter space, together with a novel noise reduced sampling strategy. Empirical results show that our model consistently achieves superior performance in binding affinity with more stable 3D structure, demonstrating our ability to accurately model interatomic interactions. To our best knowledge, MolCRAFT is the first to achieve reference-level Vina Scores (-6.59 kcal/mol) with comparable molecular size, outperforming other strong baselines by a wide margin (-0.84 kcal/mol). Code is available at https://github.com/AlgoMole/MolCRAFT. © 2024 by the author(s).

Original language	English
Title of host publication	ICML'24: Proceedings of the 41st International Conference on Machine Learning
Editors	Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, Felix Berkenkamp
Publisher	JMLR.org
Pages	41749-41768
Publication status	Published - Jul 2024
Externally published	Yes
Event	41st International Conference on Machine Learning (ICML 2024) - Messe Wien Exhibition Congress Center, Vienna, Austria Duration: 21 Jul 2024 → 27 Jul 2024 https://proceedings.mlr.press/v235/ https://icml.cc/

Publication series

Name	Proceedings of Machine Learning Research
Volume	235
ISSN (Print)	2640-3498

Conference

Conference	41st International Conference on Machine Learning (ICML 2024)
Place	Austria
City	Vienna
Period	21/07/24 → 27/07/24
Internet address	https://proceedings.mlr.press/v235/ https://icml.cc/

Funding

This work is supported by the National Science and Technology Major Project (2022ZD0117502), Natural Science Foundation of China (62376133) and Guoqiang Research Institute General Project, Tsinghua University (No. 2021GQG1012). Jiawei Han's work is supported by U.S. National Science Foundation IIS-19-56151, and the Molecule Maker Lab Institute: An AI Research Institutes program supported by U.S. NSF under Award No. 2019897. The authors would like to thank Xiangyu Li for his valuable comments on this work.

Access Output

https://proceedings.mlr.press/v235/qu24a.html

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Qu, Y., Qiu, K., Song, Y., Gong, J., Han, J., Zheng, M., Zhou, H., & Ma, W.-Y. (2024). MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space. In R. Salakhutdinov, Z. Kolter, K. Heller, A. Weller, N. Oliver, J. Scarlett, & F. Berkenkamp (Eds.), ICML'24: Proceedings of the 41st International Conference on Machine Learning (pp. 41749-41768). (Proceedings of Machine Learning Research; Vol. 235). JMLR.org. https://proceedings.mlr.press/v235/qu24a.html

Qu, Yanru ; Qiu, Keyue ; Song, Yuxuan et al. / MolCRAFT : Structure-Based Drug Design in Continuous Parameter Space. ICML'24: Proceedings of the 41st International Conference on Machine Learning. editor / Ruslan Salakhutdinov ; Zico Kolter ; Katherine Heller ; Adrian Weller ; Nuria Oliver ; Jonathan Scarlett ; Felix Berkenkamp. JMLR.org, 2024. pp. 41749-41768 (Proceedings of Machine Learning Research).

@inproceedings{d6f337791f6346349cab1b2085ed91a6,

title = "MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space",

abstract = "Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D poses and resulting in false positives. We conduct thorough studies on key factors of ill-conformational problems when applying autoregressive methods and diffusion to SBDD, including mode collapse and hybrid continuous-discrete space. In this paper, we introduce MolCRAFT, the first SBDD model that operates in the continuous parameter space, together with a novel noise reduced sampling strategy. Empirical results show that our model consistently achieves superior performance in binding affinity with more stable 3D structure, demonstrating our ability to accurately model interatomic interactions. To our best knowledge, MolCRAFT is the first to achieve reference-level Vina Scores (-6.59 kcal/mol) with comparable molecular size, outperforming other strong baselines by a wide margin (-0.84 kcal/mol). Code is available at https://github.com/AlgoMole/MolCRAFT. {\textcopyright} 2024 by the author(s).",

author = "Yanru Qu and Keyue Qiu and Yuxuan Song and Jingjing Gong and Jiawei Han and Mingyue Zheng and Hao Zhou and Wei-Ying Ma",

year = "2024",

month = jul,

language = "English",

series = "Proceedings of Machine Learning Research",

publisher = "JMLR.org",

pages = "41749--41768",

editor = "Ruslan Salakhutdinov and Zico Kolter and Katherine Heller and Adrian Weller and Nuria Oliver and Jonathan Scarlett and Felix Berkenkamp",

booktitle = "ICML'24: Proceedings of the 41st International Conference on Machine Learning",

note = "41st International Conference on Machine Learning (ICML 2024) ; Conference date: 21-07-2024 Through 27-07-2024",

url = "https://proceedings.mlr.press/v235/, https://icml.cc/",

}

Qu, Y, Qiu, K, Song, Y, Gong, J, Han, J, Zheng, M, Zhou, H & Ma, W-Y 2024, MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space. in R Salakhutdinov, Z Kolter, K Heller, A Weller, N Oliver, J Scarlett & F Berkenkamp (eds), ICML'24: Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 235, JMLR.org, pp. 41749-41768, 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, 21/07/24. <https://proceedings.mlr.press/v235/qu24a.html>

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space. / Qu, Yanru (Co-first Author); Qiu, Keyue (Co-first Author); Song, Yuxuan (Co-first Author) et al.
ICML'24: Proceedings of the 41st International Conference on Machine Learning. ed. / Ruslan Salakhutdinov; Zico Kolter; Katherine Heller; Adrian Weller; Nuria Oliver; Jonathan Scarlett; Felix Berkenkamp. JMLR.org, 2024. p. 41749-41768 (Proceedings of Machine Learning Research; Vol. 235).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - MolCRAFT

T2 - 41st International Conference on Machine Learning (ICML 2024)

AU - Qu, Yanru

AU - Qiu, Keyue

AU - Song, Yuxuan

AU - Gong, Jingjing

AU - Han, Jiawei

AU - Zheng, Mingyue

AU - Zhou, Hao

AU - Ma, Wei-Ying

PY - 2024/7

Y1 - 2024/7

N2 - Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D poses and resulting in false positives. We conduct thorough studies on key factors of ill-conformational problems when applying autoregressive methods and diffusion to SBDD, including mode collapse and hybrid continuous-discrete space. In this paper, we introduce MolCRAFT, the first SBDD model that operates in the continuous parameter space, together with a novel noise reduced sampling strategy. Empirical results show that our model consistently achieves superior performance in binding affinity with more stable 3D structure, demonstrating our ability to accurately model interatomic interactions. To our best knowledge, MolCRAFT is the first to achieve reference-level Vina Scores (-6.59 kcal/mol) with comparable molecular size, outperforming other strong baselines by a wide margin (-0.84 kcal/mol). Code is available at https://github.com/AlgoMole/MolCRAFT. © 2024 by the author(s).

AB - Generative models for structure-based drug design (SBDD) have shown promising results in recent years. Existing works mainly focus on how to generate molecules with higher binding affinity, ignoring the feasibility prerequisites for generated 3D poses and resulting in false positives. We conduct thorough studies on key factors of ill-conformational problems when applying autoregressive methods and diffusion to SBDD, including mode collapse and hybrid continuous-discrete space. In this paper, we introduce MolCRAFT, the first SBDD model that operates in the continuous parameter space, together with a novel noise reduced sampling strategy. Empirical results show that our model consistently achieves superior performance in binding affinity with more stable 3D structure, demonstrating our ability to accurately model interatomic interactions. To our best knowledge, MolCRAFT is the first to achieve reference-level Vina Scores (-6.59 kcal/mol) with comparable molecular size, outperforming other strong baselines by a wide margin (-0.84 kcal/mol). Code is available at https://github.com/AlgoMole/MolCRAFT. © 2024 by the author(s).

UR - https://www.scopus.com/pages/publications/85203821079

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85203821079&origin=recordpage

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - Proceedings of Machine Learning Research

SP - 41749

EP - 41768

BT - ICML'24: Proceedings of the 41st International Conference on Machine Learning

A2 - Salakhutdinov, Ruslan

A2 - Kolter, Zico

A2 - Heller, Katherine

A2 - Weller, Adrian

A2 - Oliver, Nuria

A2 - Scarlett, Jonathan

A2 - Berkenkamp, Felix

PB - JMLR.org

Y2 - 21 July 2024 through 27 July 2024

ER -

Qu Y, Qiu K, Song Y, Gong J, Han J, Zheng M et al. MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space. In Salakhutdinov R, Kolter Z, Heller K, Weller A, Oliver N, Scarlett J, Berkenkamp F, editors, ICML'24: Proceedings of the 41st International Conference on Machine Learning. JMLR.org. 2024. p. 41749-41768. (Proceedings of Machine Learning Research). Epub 2024 Jul 21.

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Abstract

Publication series

Conference

Funding

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this