Performance of machine-learning scoring functions in structure-based virtual screening

By Maciej Wójcikowski, Pedro J. Ballester, Pawel Siedlecki. Scientific Reports, 2017

303 citations recorded by the source corpus.

Classical scoring functions have reached a plateau in their performance in virtual screening and binding affinity prediction. Recently, machine-learning scoring functions trained on protein-ligand complexes have shown great promise in small tailored studies. They have also raised controversy, specifically concerning model overfitting and applicability to novel targets. Here we provide a new ready-to-use scoring function (RF-Score-VS) trained on 15 426 active and 893 897 inactive molecules docked to a set of 102 targets. We use the full DUD-E data sets along with three docking tools, five classical and three machine-learning scoring functions for model building and performance assessment. Our results show RF-Score-VS can substantially improve virtual screening performance: RF-Score-VS top 1% provides 55.6% hit rate, whereas that of Vina only 16.2% (for smaller percent the difference is even more encouraging: RF-Score-VS top 0.1% achieves 88.6% hit rate for 27.5% using Vina). In addition, RF-Score-VS provides much better prediction of measured binding affinity than Vina (Pearson correlation of 0.56 and −0.18, respectively). Lastly, we test RF-Score-VS on an independent test set from the DEKOIS benchmark and observed comparable results. We provide full data sets to facilitate further research in this area (http://github.com/oddt/rfscorevs) as well as ready-to-use RF-Score-VS (http://github.com/oddt/rfscorevs_binary).

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

View Paper: https://www.semanticscholar.org/paper/b48d01865e0f2cf330309e43186b2e4e3b6d334d

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

In Materials Chemistry

In Molecular Biology

Citations in the corpus

Benchmarking AlphaFold‐enabled molecular docking predictions for antibiotic discovery (2022, methodology): “…in integrating machine learning with docking have resulted in machine learning-based scoring functions, and their use to rescore poses generated by other docking platforms (Ballester & Mitchell, 2010 ; Durrant & McCammon, 2010 ; Pereira et al , 2016 ; W (cid:2) ojcikowski et al , 2017 , 2019 ).”
Molecular Docking: Shifting Paradigms in Drug Discovery (2019, methodology): “In particular, machine learning (ML) approaches, including Random Forest (RF) [116] and Support Vector Machines (SVM) [117], have been applied for improving the docking-based binding affinity predictions [29,118].”
Artificial intelligence to deep learning: machine intelligence approach for drug discovery (2021, methodology): “Further, ML models such as PARASHIFT, HEX, USR, and ShaPE algorithms have been constructed for LBVS [168, 169].”
Are Deep Learning Structural Models Sufficiently Accurate for Virtual Screening? Application of Docking Algorithms to AlphaFold2 Predicted Structures (2022, methodology): “These are applied to many of the stages of the DD pipeline, from binding site characterization and prediction of ligand aﬃnities to calculations of ADMET properties [1,2] and development and analysis of clinical trials [3,4].”
Key Topics in Molecular Docking for Drug Design (2019, background): “This outperformance grew, however, when predicting more difficult targets with less active ligands [185].”