A geometric deep learning approach to predict binding conformations of bioactive molecules

Méndez‐Lucio, Oscar; Ahmad, Mazen; Rio‐Chanona, Ehecatl Antonio del; Wegner, Jörg K.

doi:10.1038/s42256-021-00409-9

Cited by 109 publications

(109 citation statements)

References 38 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…ML is a branch of artificial intelligence that has gained attention in diverse research fields, including CADD. With the rapid progress of computational power and exponential increase of data, ML has been applied in many branches of CADD, such as chemical space exploration, molecular property prediction, protein structure prediction and VS [ 92 , 93 , 94 , 95 , 96 , 97 ]. ML algorithms have also been widely employed in SBDD, such as pose prediction, binder/nonbinder identification and binding affinity prediction [ 46 , 96 ].…”

Section: Machine-learning Scoring Functionmentioning

confidence: 99%

“…With the rapid progress of computational power and exponential increase of data, ML has been applied in many branches of CADD, such as chemical space exploration, molecular property prediction, protein structure prediction and VS [ 92 , 93 , 94 , 95 , 96 , 97 ]. ML algorithms have also been widely employed in SBDD, such as pose prediction, binder/nonbinder identification and binding affinity prediction [ 46 , 96 ]. This review will focus on the discussion of ML scoring functions, a supervised learning method that learns from structure data labeled with experimental measured binding affinities.…”

Section: Machine-learning Scoring Functionmentioning

confidence: 99%

See 1 more Smart Citation

Protein–Ligand Docking in the Machine-Learning Era

2022

View full text Add to dashboard Cite

Molecular docking plays a significant role in early-stage drug discovery, from structure-based virtual screening (VS) to hit-to-lead optimization, and its capability and predictive power is critically dependent on the protein–ligand scoring function. In this review, we give a broad overview of recent scoring function development, as well as the docking-based applications in drug discovery. We outline the strategies and resources available for structure-based VS and discuss the assessment and development of classical and machine learning protein–ligand scoring functions. In particular, we highlight the recent progress of machine learning scoring function ranging from descriptor-based models to deep learning approaches. We also discuss the general workflow and docking protocols of structure-based VS, such as structure preparation, binding site detection, docking strategies, and post-docking filter/re-scoring, as well as a case study on the large-scale docking-based VS test on the LIT-PCBA data set.

show abstract

Section: Machine-learning Scoring Functionmentioning

confidence: 99%

Section: Machine-learning Scoring Functionmentioning

confidence: 99%

Protein–Ligand Docking in the Machine-Learning Era

2022

View full text Add to dashboard Cite

show abstract

“…Despite this, extensive efforts have been made to develop MLSFs with a wider application domain during the past few years. − In 2017 and 2019, Zhang’s group successively developed Δ Vina RF 20 and Δ Vina XGB, which employ ML algorithms to fit correction terms to AutoDock Vina scores rather than conventionally fit the final binding scores. These two methods could rank the top three in all four tasks (i.e., scoring, docking, ranking, and screening) in the Comparative Assessment of Scoring Functions (CASF) benchmark, although their VS performance in our previous assessment was unsatisfactory .…”

Section: Introductionmentioning

confidence: 99%

Boosting Protein–Ligand Binding Pose Prediction and Virtual Screening Based on Residue–Atom Distance Likelihood Potential and Graph Transformer

Shen

Zhang

Deng³

et al. 2022

J. Med. Chem.

102

View full text Add to dashboard Cite

The past few years have witnessed enormous progress toward applying machine learning approaches to the development of protein–ligand scoring functions. However, the robust performance and wide applicability of scoring functions remain a big challenge for increasing the success rate of docking-based virtual screening. Herein, a novel scoring function named RTMScore was developed by introducing a tailored residue-based graph representation strategy and several graph transformer layers for the learning of protein and ligand representations, followed by a mixture density network to obtain residue–atom distance likelihood potential. Our approach was resolutely validated on the CASF-2016 benchmark, and the results indicate that RTMScore can outperform almost all of the other state-of-the-art methods in terms of both the docking and screening powers. Further evaluation confirms the robustness of our approach that can not only retain its docking power on cross-docked poses but also achieve improved performance as a rescoring tool in larger-scale virtual screening.

show abstract

“…Recently, Wegner et al. proposed DeepDock, a method based on geometric deep learning to predict the ligand binding poses using distance potential, achieving a very good docking power (success rate = 87.0%) and screening power (EF 1% = 16.41). Scoring and ranking powers are not evaluated since DeepDock is not trained to predict binding affinities.…”

Section: Resultsmentioning

confidence: 99%

Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein–Ligand Scoring Functions

Cao

Zhang

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Protein–ligand scoring functions are widely used in structure-based drug design for fast evaluation of protein–ligand interactions, and it is of strong interest to develop scoring functions with machine-learning approaches. In this work, by expanding the training set, developing physically meaningful features, employing our recently developed linear empirical scoring function Lin_F9 (YangC. Yang, C. J. Chem. Inf. Model.20216146304644) as the baseline, and applying extreme gradient boosting (XGBoost) with Δ-machine learning, we have further improved the robustness and applicability of machine-learning scoring functions. Besides the top performances for scoring-ranking-screening power tests of the CASF-2016 benchmark, the new scoring function ΔLin_F9XGB also achieves superior scoring and ranking performances in different structure types that mimic real docking applications. The scoring powers of ΔLin_F9XGB for locally optimized poses, flexible redocked poses, and ensemble docked poses of the CASF-2016 core set achieve Pearson’s correlation coefficient (R) values of 0.853, 0.839, and 0.813, respectively. In addition, the large-scale docking-based virtual screening test on the LIT-PCBA data set demonstrates the reliability and robustness of ΔLin_F9XGB in virtual screening application. The ΔLin_F9XGB scoring function and its code are freely available on the web at ().

show abstract

A geometric deep learning approach to predict binding conformations of bioactive molecules

Cited by 109 publications

References 38 publications

Protein–Ligand Docking in the Machine-Learning Era

Protein–Ligand Docking in the Machine-Learning Era

Boosting Protein–Ligand Binding Pose Prediction and Virtual Screening Based on Residue–Atom Distance Likelihood Potential and Graph Transformer

Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein–Ligand Scoring Functions

Contact Info

Product

Resources

About