Neural network activation similarity: a new measure to assist decision making in chemical toxicology
Timothy E. H. Allen, Andrew J. Wedlake, Elena Gelžinytė, Charles Gong, Jonathan M. Goodman, Steve Gutsell, Paul Russell
Abstract
Deep learning neural networks, constructed for the prediction of chemical binding at 79 pharmacologically important human biological targets, show extremely high performance on test data (accuracy 92.2 ± 4.2%, MCC 0.814 ± 0.093, ROC-AUC 0.96 ± 0.04).
Topics & Concepts
Artificial neural networkSimilarity (geometry)Measure (data warehouse)Artificial intelligenceMachine learningComputer scienceSimilarity measureData miningImage (mathematics)Computational Drug Discovery MethodsAnimal testing and alternativesBiosimilars and Bioanalytical Methods