Neural network activation similarity: a new measure to assist decision making in chemical toxicology

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 and ROC-AUC 0.96 ± 0.04). A new molecular similarity measure, Neural Network Activation Similarity, has been developed, based on signal propagation through the network. This is complementary to standard Tanimoto similarity, and the combined use increases confidence in the computer's prediction of activity for new chemicals by providing a greater understanding of the underlying justification. The in silico prediction of these human molecular initiating events is central to the future of chemical safety risk assessment and improves the efficiency of safety decision making.

[1]  Sepp Hochreiter,et al.  Toxicity Prediction using Deep Learning , 2015, ArXiv.

[2]  Navdeep Jaitly,et al.  Multi-task Neural Networks for QSAR Predictions , 2014, ArXiv.

[3]  Hugo Ceulemans,et al.  Large-scale comparison of machine learning methods for drug target prediction on ChEMBL , 2018, Chemical science.

[4]  Daniel L Villeneuve,et al.  Adverse outcome pathways: A conceptual framework to support ecotoxicology research and risk assessment , 2010, Environmental toxicology and chemistry.

[5]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[6]  Timothy E. H. Allen,et al.  Using 2D Structural Alerts to Define Chemical Categories for Molecular Initiating Events , 2018, Toxicological sciences : an official journal of the Society of Toxicology.

[7]  Timothy E H Allen,et al.  Using Transition State Modeling To Predict Mutagenicity for Michael Acceptors , 2018, J. Chem. Inf. Model..

[8]  Yong Zhao,et al.  The development and application of in silico models for drug induced liver injury , 2018, RSC advances.

[9]  Timothy E H Allen,et al.  Using Molecular Initiating Events To Generate 2D Structure-Activity Relationships for Toxicity Screening. , 2016, Chemical research in toxicology.

[10]  Eva C. Bach,et al.  Enhanced NMDA Receptor-Mediated Modulation of Excitatory Neurotransmission in the Dorsal Vagal Complex of Streptozotocin-Treated, Chronically Hyperglycemic Mice , 2015, PloS one.

[11]  Mark T D Cronin,et al.  The Use of a Chemistry-based Profiler for Covalent DNA Binding in the Development of Chemical Categories for Read-across for Genotoxicity , 2011, Alternatives to laboratory animals : ATLA.

[12]  S. Krähenbühl,et al.  Interaction with the hERG channel and cytotoxicity of amiodarone and amiodarone analogues , 2008, British journal of pharmacology.

[13]  Melvin E Andersen,et al.  Adverse Outcome Pathways can drive non-animal approaches for safety assessment , 2015, Journal of applied toxicology : JAT.

[14]  Timothy E H Allen,et al.  A History of the Molecular Initiating Event. , 2016, Chemical research in toxicology.

[15]  David M. Reif,et al.  Profiling 976 ToxCast Chemicals across 331 Enzymatic and Receptor Signaling Assays , 2013, Chemical research in toxicology.

[16]  George Papadatos,et al.  The ChEMBL bioactivity database: an update , 2013, Nucleic Acids Res..

[17]  G Frank Gerberick,et al.  Quantification of chemical peptide reactivity for screening contact allergens: a classification tree model approach. , 2007, Toxicological sciences : an official journal of the Society of Toxicology.

[18]  Gisbert Schneider,et al.  Deep Learning in Drug Discovery , 2016, Molecular informatics.

[19]  Timothy E. H. Allen,et al.  Structural Alerts and Random Forest Models in a Consensus Approach for Receptor Binding Molecular Initiating Events. , 2019, Chemical research in toxicology.

[20]  J. Dearden,et al.  QSAR modeling: where have you been? Where are you going to? , 2014, Journal of medicinal chemistry.

[21]  R. Luo,et al.  POTASSIUM CHANNEL CURRENTS IN RAT MESENCHYMAL STEM CELLS AND THEIR POSSIBLE ROLES IN CELL PROLIFERATION , 2008, Clinical and experimental pharmacology & physiology.

[22]  D J Rogers,et al.  A Computer Program for Classifying Plants. , 1960, Science.

[23]  Sofía Pérez-Alenda,et al.  Changes in Muscle Activity Patterns and Joint Kinematics During Gait in Hemophilic Arthropathy , 2020, Frontiers in Physiology.

[24]  Luhua Lai,et al.  Deep Learning for Drug-Induced Liver Injury , 2015, J. Chem. Inf. Model..

[25]  Jaap Keijer,et al.  Diet-Independent Correlations between Bacteria and Dysfunction of Gut, Adipose Tissue, and Liver: A Comprehensive Microbiota Analysis in Feces and Mucosa of the Ileum and Colon in Obese Mice with NAFLD , 2018, International journal of molecular sciences.

[26]  Friedrich Rippmann,et al.  Interpretable Deep Learning in Drug Discovery , 2019, Explainable AI.

[27]  V. Rogiers,et al.  Proposal of an in silico profiler for categorisation of repeat dose toxicity data of hair dyes , 2015, Archives of Toxicology.

[28]  Alan A. Wilson,et al.  Imaging the serotonin transporter with positron emission tomography: initial human studies with [11C]DAPP and [11C]DASB , 2000, European Journal of Nuclear Medicine.

[29]  Guanyu Wang,et al.  Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis , 2018, International journal of molecular sciences.

[30]  Vijay S. Pande,et al.  Low Data Drug Discovery with One-Shot Learning , 2016, ACS central science.

[31]  K. Johnson.  An Update. , 1984, Journal of food protection.

[32]  David Rogers,et al.  Extended-Connectivity Fingerprints , 2010, J. Chem. Inf. Model..

[33]  Günter Klambauer,et al.  DeepTox: Toxicity Prediction using Deep Learning , 2016, Front. Environ. Sci..

[34]  Steven J Enoch,et al.  Development of an in Silico Profiler for Mitochondrial Toxicity. , 2015, Chemical research in toxicology.

[35]  Chaoyang Zhang,et al.  Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data , 2019, Front. Physiol..

[36]  Gareth J Waldron,et al.  Reducing safety-related drug attrition: the use of in vitro pharmacological profiling , 2012, Nature Reviews Drug Discovery.

[37]  Cengiz Öztireli,et al.  Towards better understanding of gradient-based attribution methods for Deep Neural Networks , 2017, ICLR.

[38]  Katarzyna R Przybylak,et al.  In silico models for drug-induced liver injury – current status , 2012, Expert opinion on drug metabolism & toxicology.

[39]  J. Dalton,et al.  Discovery and therapeutic promise of selective androgen receptor modulators. , 2005, Molecular interventions.

[40]  Hongbin Yang,et al.  In silico prediction of chemical genotoxicity using machine learning methods and structural alerts. , 2018, Toxicology research.

[41]  Abdul Sattar,et al.  Efficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees , 2019, ACS Omega.

[42]  Zengrui Wu,et al.  In Silico Estimation of Chemical Carcinogenicity with Binary and Ternary Classification Methods , 2015, Molecular informatics.

[43]  Mosé Casalegno,et al.  Determination of Toxicant Mode of Action by Augmented Top Priority Fragment Class , 2013, J. Chem. Inf. Model..

[44]  M. Alpers,et al.  Alternative methods in toxicology: pre-validated and validated methods , 2011, Interdisciplinary toxicology.

[45]  Hui Zhang,et al.  Development of novel in silico model for developmental toxicity assessment by using naïve Bayes classifier method. , 2017, Reproductive toxicology.

[46]  Timothy E H Allen,et al.  Defining molecular initiating events in the adverse outcome pathway framework for risk assessment. , 2014, Chemical research in toxicology.

[47]  Fabian P. Steinmetz,et al.  Using Molecular Initiating Events to Develop a Structural Alert Based Screening Workflow for Nuclear Receptor Ligands Associated with Hepatic Steatosis. , 2016, Chemical research in toxicology.

[48]  H. Kulik,et al.  A Quantitative Uncertainty Metric Controls Error in Neural Network-Driven Chemical Discovery , 2019 .

[49]  Guo-Wei Wei,et al.  Quantitative Toxicity Prediction Using Topology Based Multitask Deep Neural Networks , 2017, J. Chem. Inf. Model..

[50]  Thomas Hartung,et al.  Machine Learning of Toxicological Big Data Enables Read-Across Structure Activity Relationships (RASAR) Outperforming Animal Test Reproducibility , 2018, Toxicological sciences : an official journal of the Society of Toxicology.

[51]  Tianyuan Ye,et al.  An In Silico Model for Predicting Drug-Induced Hepatotoxicity , 2019, International journal of molecular sciences.

[52]  Chuipu Cai,et al.  Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity , 2019, J. Chem. Inf. Model..

[53]  David W. Roberts,et al.  A Minireview of Available Skin Sensitization (Q)SARs/Expert Systems , 2008 .