5sev › Citations

A high quality, industrial data set for binding affinity prediction: performance comparison in different early drug discovery scenarios.

Tosstorff A, Rudolph MG, Cole JC, Reutlinger M, Kramer C, Schaffhauser H, Nilly A, Flohr A, Kuhn B
J Comput Aided Mol Des (2022)

Cited: 8 times
EuropePMC logo PMID: 36153472

Abstract

We release a new, high quality data set of 1162 PDE10A inhibitors with experimentally determined binding affinities together with 77 PDE10A X-ray co-crystal structures from a Roche legacy project. This data set is used to compare the performance of different 2D- and 3D-machine learning (ML) as well as empirical scoring functions for predicting binding affinities with high throughput. We simulate use cases that are relevant in the lead optimization phase of early drug discovery. ML methods perform well at interpolation, but poorly in extrapolation scenarios-which are most relevant to a real-world application. Moreover, we find that investing into the docking workflow for binding pose generation using multi-template docking is rewarded with an improved scoring performance. A combination of 2D-ML and 3D scoring using a modified piecewise linear potential shows best overall performance, combining information on the protein environment with learning from existing SAR data.

Articles citing this publication (8)

  1. Combining IC50 or Ki Values from Different Sources Is a Source of Significant Noise. Landrum GA, Riniker S. J Chem Inf Model 64 1560-1567 (2024)
  2. Prospective de novo drug design with deep interactome learning. Atz K, Cotos L, Isert C, Håkansson M, Focht D, Hilleke M, Nippa DF, Iff M, Ledergerber J, Schiebroek CCG, Romeo V, Hiss JA, Merk D, Schneider P, Kuhn B, Grether U, Schneider G. Nat Commun 15 3408 (2024)
  3. Exploring protein-ligand binding affinity prediction with electron density-based geometric deep learning. Isert C, Atz K, Riniker S, Schneider G. RSC Adv 14 4492-4502 (2024)
  4. Benchmarking compound activity prediction for real-world drug discovery applications. Tian T, Li S, Zhang Z, Chen L, Zou Z, Zhao D, Zeng J. Commun Chem 7 127 (2024)
  5. Expanding Training Data for Structure-Based Receptor-Ligand Binding Affinity Regression through Imputation of Missing Labels. Francoeur PG, Koes DR. ACS Omega 8 41680-41688 (2023)
  6. From mundane to surprising nonadditivity: drivers and impact on ML models. Guasch L, Maeder N, Cumming JG, Kramer C. J Comput Aided Mol Des 38 26 (2024)
  7. Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry. Atz K, Nippa DF, Müller AT, Jost V, Anelli A, Reutlinger M, Kramer C, Martin RE, Grether U, Schneider G, Wuitschik G. RSC Med Chem 15 2310-2321 (2024)
  8. The Impact of Data on Structure-Based Binding Affinity Predictions Using Deep Neural Networks. Libouban PY, Aci-Sèche S, Gómez-Tamayo JC, Tresadern G, Bonnet P. Int J Mol Sci 24 16120 (2023)


Quick links