Mathematical deep learning for pose and binding affinity prediction and ranking in D3R Grand Challenges

2018/04/27 by Duc Duy Nguyen, Zixuan Cang, Nguyen, Duc Duy +11 · 10 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · #Biomolecules (q-bio.BM) #Computational Drug Discovery Methods #FOS: Biological sciences #Microbial Natural Products and Biosynthesis #Protein Structure and Dynamics #q-bio.BM

paper · pdf · doi:10.48550/arxiv.1804.10647

15 pages, 4 figures

arxiv created 2018/04/27 · openalex publication_date 2018/04/27 · arxiv updated 2018/05/01 · openalex created_date 2018/05/07 · openalex updated_date 2026/07/28

Abstract

Advanced mathematics, such as multiscale weighted colored graph and element specific persistent homology, and machine learning including deep neural networks were integrated to construct mathematical deep learning models for pose and binding affinity prediction and ranking in the last two D3R grand challenges in computer-aided drug design and discovery. D3R Grand Challenge 2 (GC2) focused on the pose prediction and binding affinity ranking and free energy prediction for Farnesoid X receptor ligands. Our models obtained the top place in absolute free energy prediction for free energy Set 1 in Stage 2. The latest competition, D3R Grand Challenge 3 (GC3), is considered as the most difficult challenge so far. It has 5 subchallenges involving Cathepsin S and five other kinase targets, namely VEGFR2, JAK2, p38-α, TIE2, and ABL1. There is a total of 26 official competitive tasks for GC3. Our predictions were ranked 1st in 10 out of 26 official competitive tasks.

Citations

• Empirical scoring functions: I. The development of a fast empirical scoring function to estimate the binding affinity of ligands in receptor complexes
• AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility
• AutoDock Vina: Improving the speed and accuracy of docking with a new scoring function, efficient optimization, and multithreading

Cited by

• GBNL: Graded Betti Number Learning of Complex Biological Data
• CAP: Commutative Algebra Prediction of Protein-Nucleic Acid Binding Affinities
• Interpretability and Representability of Commutative Algebra, Algebraic Topology, and Topological Spectral Theory for Real-World Data
• A review of topological data analysis and topological deep learning in molecular sciences
• Topological Learning Prediction of Virus-like Particle Stoichiometry and Stability
• Topological Data Analysis and Topological Deep Learning Beyond Persistent Homology -- A Review
• Unreduced Persistence Diagrams for Topological Machine Learning
• Topological Machine Learning for Protein-Nucleic Acid Binding Affinity Changes Upon Mutation
• Persistent local Laplacian prediction of protein-ligand binding affinities
• CAML: Commutative algebra machine learning -- a case study on protein-ligand binding affinity prediction

Related

• MathDL: Mathematical deep learning for D3R Grand Challenge 4
• DeepGS: Deep Representation Learning of Graphs and Sequences for Drug-Target Binding Affinity Prediction
• PotentialNet for Molecular Property Prediction
• Improved Protein-ligand Binding Affinity Prediction with Structure-Based Deep Fusion Inference
• Deep learning is competing random forest in computational docking