EUVIMEDEUVIMED entdecken
Crossref

Can molecular dynamics simulations improve predictions of protein-ligand binding affinity with machine learning?

Shukai Gu, Chao Shen iD, Jiahui Yu, Hong Zhao, Huanxiang Liu iD, Liwei Liu, Rong Sheng, Lei Xu, Zhe Wang, Tingjun Hou iD, Yu Kang

Briefings in Bioinformatics · 19.03.2023 · 24 (2)

DOI: 10.1093/bib/bbad008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 21.01.2023. Verfasst von Shukai Gu und 10 weiteren Autor:innen. Beteiligte Einrichtung: Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzho…. Hauptthemen laut MEDLINE: Molecular Dynamics Simulation, Proteins. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Zhejiang Provincial Natural Science Foundation, National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Binding affinity prediction largely determines the discovery efficiency of lead compounds in drug discovery. Recently, machine learning (ML)-based approaches have attracted much attention in hopes of enhancing the predictive performance of traditional physics-based approaches. In this study, we evaluated the impact of structural dynamic information on the binding affinity prediction by comparing the models trained on different dimensional descriptors, using three targets (i.e. JAK1, TAF1-BD2 and DDR1) and their corresponding ligands as the examples. Here, 2D descriptors are traditional ECFP4 fingerprints, 3D descriptors are the energy terms of the Smina and NNscore scoring functions and 4D descriptors contain the structural dynamic information derived from the trajectories based on molecular dynamics (MD) simulations. We systematically investigate the MD-refined binding affinity prediction performance of three classical ML algorithms (i.e. RF, SVR and XGB) as well as two common virtual screening methods, namely Glide docking and MM/PBSA. The outcomes of the ML models built using various dimensional descriptors and their combinations reveal that the MD refinement with the optimized protocol can improve the predictive performance on the TAF1-BD2 target with considerable structural flexibility, but not for the less flexible JAK1 and DDR1 targets, when taking docking poses as the initial structure instead of the crystal structures. The results highlight the importance of the initial structures to the final performance of the model through conformational analysis on the three targets with different flexibility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Dynamics SimulationProteinsLigandsProtein BindingMachine LearningMolecular Docking Simulation

Stichwörter der Autor:innen

binding affinity predictionenhanced samplingmachine learningmolecular dynamics simulationsscoring functionstructural flexibility

Substanzen

LigandsProteins

Autor:innen und Institutionen

  • Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou 310058, Zhejiang, China.
  • Faculty of Applied Science, Macao Polytechnic University, Macao, SAR, China.
  • Advanced Computing and Storage Laboratory, Central Research Institute, 2012 Laboratories, Huawei Technologies Co., Ltd., Shenzhen 518129, Guangdong, China.
  • Health Technology Development Dept, Huawei Device Co., Ltd., Dongguan 523808, Guangdong, China.
  • Institute of Bioinformatics and Medical Engineering, School of Electrical and Information Engineering, Jiangsu University of Technology, Changzhou 213001, China.

ORCID-Profile: Chao Shen, Huanxiang Liu, Tingjun Hou

Förderung

  • Zhejiang Provincial Natural Science Foundation
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Gu, S., Shen, C., Yu, J., Zhao, H., Liu, H., Liu, L., Sheng, R., Xu, L., Wang, Z., Hou, T., & Kang, Y. (2023). Can molecular dynamics simulations improve predictions of protein-ligand binding affinity with machine learning?. Briefings in Bioinformatics, 24(2). https://doi.org/10.1093/bib/bbad008

Vancouver

Gu S, Shen C, Yu J, Zhao H, Liu H, Liu L, et al. Can molecular dynamics simulations improve predictions of protein-ligand binding affinity with machine learning?. Briefings in Bioinformatics. 2023;24(2). doi:10.1093/bib/bbad008

BibTeX
@article{Gu2023,
  author = {Gu, Shukai and Shen, Chao and Yu, Jiahui and Zhao, Hong and Liu, Huanxiang and Liu, Liwei and Sheng, Rong and Xu, Lei and Wang, Zhe and Hou, Tingjun and Kang, Yu},
  title = {Can molecular dynamics simulations improve predictions of protein-ligand binding affinity with machine learning?},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {24},
  number = {2},
  doi = {10.1093/bib/bbad008}
}
Kostenlos starten →