Improving Scoring-Docking-Screening Powers of Protein-Ligand Scoring Functions using Random Forest

By Cheng Wang, Yingkai Zhang. 2016

271 citations recorded by the source corpus.

The development of new protein–ligand scoring functions using machine learning algorithms, such as random forest, has been of significant interest. By efficiently utilizing expanded feature sets and a large set of experimental data, random forest based scoring functions (RFbScore) can achieve better correlations to experimental protein–ligand binding data with known crystal structures; however, more extensive tests indicate that such enhancement in scoring power comes with significant under‐performance in docking and screening power tests compared to traditional scoring functions. In this work, to improve scoring‐docking‐screening powers of protein–ligand docking functions simultaneously, we have introduced a ΔvinaRF parameterization and feature selection framework based on random forest. Our developed scoring function ΔvinaRF20, which employs 20 descriptors in addition to the AutoDock Vina score, can achieve superior performance in all power tests of both CASF‐2013 and CASF‐2007 benchmarks compared to classical scoring functions. The ΔvinaRF20 scoring function and its code are freely available on the web at: https://www.nyu.edu/projects/yzhang/DeltaVina. © 2016 Wiley Periodicals, Inc.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. David T. Jones
2. Zhifeng Gao
3. Hang Zheng
4. Shaun M. Kandathil
5. Giulio Rastelli
6. Guolin Ke
7. Joe G. Greener
8. Luca Pinzi

In Materials Chemistry

1. Shaun M. Kandathil
2. Joe G. Greener
3. David T. Jones
4. Hang Zheng
5. Giulio Rastelli
6. Guolin Ke
7. Luca Pinzi
8. Lewis Moffat

In Molecular Biology

1. Joe G. Greener
2. Shaun M. Kandathil
3. David T. Jones
4. Lewis Moffat
5. Zhewei Wei
6. Gengmo Zhou
7. Hongteng Xu
8. Linfeng Zhang

Citations in the corpus

• Molecular Docking: Shifting Paradigms in Drug Discovery (2019, methodology): “Moreover, they also demonstrated that the prediction performances of their scoring function improved with the use of larger datasets for the RF-based scoring function correction [123].”
• A guide to machine learning for biologists (2021, methodology): “Another class of robust non-linear methods are ensemble-based models like random forests [39] and XGBoost [40,41].”
• Uni-Mol: A Universal 3D Molecular Representation Learning Framework (2023, methodology): “Also, machine learning-based docking 324 methods, such as ∆V inaRF20 [76], DeepDock [61] and Equibind [77], have also been developed to 325 predict protein-ligand binding poses and assess protein-ligand binding affinity.”