KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks
- PMID: 29309725
- DOI: 10.1021/acs.jcim.7b00650
KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks
Abstract
Accurately predicting protein-ligand binding affinities is an important problem in computational chemistry since it can substantially accelerate drug discovery for virtual screening and lead optimization. We propose here a fast machine-learning approach for predicting binding affinities using state-of-the-art 3D-convolutional neural networks and compare this approach to other machine-learning and scoring methods using several diverse data sets. The results for the standard PDBbind (v.2016) core test-set are state-of-the-art with a Pearson's correlation coefficient of 0.82 and a RMSE of 1.27 in pK units between experimental and predicted affinity, but accuracy is still very sensitive to the specific protein used. KDEEP is made available via PlayMolecule.org for users to test easily their own protein-ligand complexes, with each prediction taking a fraction of a second. We believe that the speed, performance, and ease of use of KDEEP makes it already an attractive scoring function for modern computational chemistry pipelines.
Similar articles
-
A Comparative Assessment of Predictive Accuracies of Conventional and Machine Learning Scoring Functions for Protein-Ligand Binding Affinity Prediction.IEEE/ACM Trans Comput Biol Bioinform. 2015 Mar-Apr;12(2):335-47. doi: 10.1109/TCBB.2014.2351824. IEEE/ACM Trans Comput Biol Bioinform. 2015. PMID: 26357221
-
BgN-Score and BsN-Score: bagging and boosting based ensemble neural networks scoring functions for accurate binding affinity prediction of protein-ligand complexes.BMC Bioinformatics. 2015;16 Suppl 4(Suppl 4):S8. doi: 10.1186/1471-2105-16-S4-S8. Epub 2015 Feb 23. BMC Bioinformatics. 2015. PMID: 25734685 Free PMC article.
-
Machine learning in computational docking.Artif Intell Med. 2015 Mar;63(3):135-52. doi: 10.1016/j.artmed.2015.02.002. Epub 2015 Feb 16. Artif Intell Med. 2015. PMID: 25724101
-
Machine learning models for drug-target interactions: current knowledge and future directions.Drug Discov Today. 2020 Apr;25(4):748-756. doi: 10.1016/j.drudis.2020.03.003. Epub 2020 Mar 12. Drug Discov Today. 2020. PMID: 32171918 Review.
-
Prediction of protein-ligand binding affinity with deep learning.Comput Struct Biotechnol J. 2023 Nov 20;21:5796-5806. doi: 10.1016/j.csbj.2023.11.009. eCollection 2023. Comput Struct Biotechnol J. 2023. PMID: 38213884 Free PMC article. Review.
Cited by
-
A New Hybrid Neural Network Deep Learning Method for Protein-Ligand Binding Affinity Prediction and De Novo Drug Design.Int J Mol Sci. 2022 Nov 11;23(22):13912. doi: 10.3390/ijms232213912. Int J Mol Sci. 2022. PMID: 36430386 Free PMC article.
-
Potential Anticancer Lipoxygenase Inhibitors from the Red Sea-Derived Brown Algae Sargassum cinereum: An In-Silico-Supported In-Vitro Study.Antibiotics (Basel). 2021 Apr 10;10(4):416. doi: 10.3390/antibiotics10040416. Antibiotics (Basel). 2021. PMID: 33920213 Free PMC article.
-
Multi-task bioassay pre-training for protein-ligand binding affinity prediction.Brief Bioinform. 2023 Nov 22;25(1):bbad451. doi: 10.1093/bib/bbad451. Brief Bioinform. 2023. PMID: 38084920 Free PMC article.
-
Improving structure-based protein-ligand affinity prediction by graph representation learning and ensemble learning.PLoS One. 2024 Jan 17;19(1):e0296676. doi: 10.1371/journal.pone.0296676. eCollection 2024. PLoS One. 2024. PMID: 38232063 Free PMC article.
-
From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction.J Chem Inf Model. 2024 Apr 8;64(7):2496-2507. doi: 10.1021/acs.jcim.3c01208. Epub 2023 Nov 20. J Chem Inf Model. 2024. PMID: 37983381 Free PMC article.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources
