A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking

By Pedro J. Ballester, John B. O. Mitchell. 2010

Subfields: Computational Biology & Bioinformatics, Computational Chemistry & Drug Discovery

How researchers see this paper

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

In Computational Biology & Bioinformatics

In Computational Chemistry & Drug Discovery

Citations in the corpus

Molecular Docking and Structure-Based Drug Design Strategies (2015, neutral): “…[37] DrugScore [62] GoldScore [35] ChemScore [60] PMF_Score [83] ICM [46] X_Score [66] MotifScore [84] LigandFit [47] F_Score [73] RF_Score [85] Molegro Virtual Docker [48] Fresno [75] PESD_SVM [86] SYBYL_G-Score [73] SCORE [76] PoseScore [87] SYBYL_D-Score [73] LUDI [77] MedusaScore [74]…”
Artificial intelligence in drug discovery: recent advances and future perspectives (2021, background): “…models, such as random forests or support vector machines, appeared in the 2000s [72], and became popular in the early 2010s, coupled with a wide range of descriptors such as protein-ligand atom pair counts [73], property-encoded shape distributions [74], or basic atomic interactions [75].”
Random Forests for Genomic Data Analysis (2012, methodology): “RF has been successfully applied to predict protein–DNA binding sites [28], protein–RNA binding sites [29], protein–protein interaction sites [30], and protein–ligand binding affinity [31].”
Key Topics in Molecular Docking for Drug Design (2019, methodology): “In other words, parametric methods fit the input variables (such as van der Waals and electrostatic energy terms) to the output (binding energy score) into a function whose form is already specified, and which is adjusted during the development of the SF in a theory-inspired fashion [77].”
Neural Networks for the Prediction of Organic Chemistry Reactions (2016, unknown): “While methods that are guided by quantum calculations have the potential to explore a wider range of reactions than the heuristic-based methods, these algorithms would require new calculations for each additional reaction family and will be prohibitively costly over a large set of new reactions.”
Boosting Docking-Based Virtual Screening with Deep Learning (2016, methodology): “1,3 The main strategies used in virtual screening are neural networks - NN, 13 support vector machines - SVM 12 and random forest - RF. 14 One of the main advantages of employing ML is the capacity to explain the non-linear dependence of the molecular interactions between ligand and receptor.”
Combining Machine Learning Systems and Multiple Docking Simulation Packages to Improve Docking Prediction Reliability for Network Pharmacology (2013, methodology): “Application of external re-scoring functions (i.e. X-Score and RF-Score) improved correlations compared with the employment of docking simulations alone using the default functions equipped in the docking tools (Figure 1).”
A geometric deep learning approach to predict binding conformations of bioactive molecules (2021, methodology): “In particular, LMDN minimizes the negative log-likelihood of dr,s, which represents the distance separating the target node vr from the ligand node vs, computed using the mixture model formed by k = 10 Gaussians and parametrized by the αr,s, μr,s and σr,s that were predicted by the model (equation (”