Predicting Total Drug Clearance and Volumes of Distribution Using the Machine Learning-Mediated Multimodal Method through the Imputation of Various Nonclinical Data

Pharmacokinetic research plays an important role in the development of new drugs. Accurate predictions of human pharmacokinetic parameters are essential for the success of clinical trials. Clearance (CL) and volume of distribution (Vd) are important factors for evaluating pharmacokinetic properties, and many previous studies have attempted to use computational methods to extrapolate these values from nonclinical laboratory animal models to human subjects. However, it is difficult to obtain sufficient, comprehensive experimental data from these animal models, and many studies are missing critical values. This means that studies using nonclinical data as explanatory variables can only apply a small number of compounds to their model training. In this study, we perform missing-value imputation and feature selection on nonclinical data to increase the number of training compounds and nonclinical datasets available for these kinds of studies. We could obtain novel models for total body clearance (CLtot) and steady-state Vd (Vdss) (CLtot: geometric mean fold error [GMFE], 1.92; percentage within 2-fold error, 66.5%; Vdss: GMFE, 1.64; percentage within 2-fold error, 71.1%). These accuracies were comparable to the conventional animal scale-up models. Then, this method differs from animal scale-up methods because it does not require animal experiments, which continue to become more strictly regulated as time passes.

[1]  A. Bender,et al.  Machine Learning Models for Human In Vivo Pharmacokinetic Parameters with In-House Validation. , 2021, Molecular pharmaceutics.

[2]  L. Breiman.  Random Forests , 2001, Machine Learning.

[3]  I. Mahmood.  A Single Animal Species-Based Prediction of Human Clearance and First-in-Human Dose of Monoclonal Antibodies: Beyond Monkey , 2021, Antibodies.

[4]  H. Sasabe,et al.  Pharmacokinetics and metabolism of brexpiprazole, a novel serotonin-dopamine activity modulator and its main metabolite in rat, monkey and human , 2021, Xenobiotica; the fate of foreign compounds in biological systems.

[5]  Maeda Kazuya,et al.  Prediction of total drug clearance in humans using animal data: proposal of a multimodal learning method based on deep learning. , 2021, Journal of pharmaceutical sciences.

[6]  A. Kalgutkar,et al.  Predicting the Human Hepatic Clearance of Acidic and Zwitterionic Drugs. , 2020, Journal of medicinal chemistry.

[7]  Y. Kosugi,et al.  Direct Comparison of Total Clearance Prediction: Computational Machine Learning Model versus Bottom-up Approach Using In Vitro Assay. , 2020, Molecular pharmaceutics.

[8]  H. Loáiciga,et al.  Application of particle swarm optimization to water management: an introduction and overview , 2020, Environmental Monitoring and Assessment.

[9]  Yan Yang,et al.  In Silico Prediction of Human Intravenous Pharmacokinetic Parameters with Improved Accuracy , 2019, J. Chem. Inf. Model..

[10]  Xin Liu,et al.  All-Assay-Max2 pQSAR: Activity Predictions as Accurate as Four-Concentration IC50s for 8558 Novartis Assays , 2019, J. Chem. Inf. Model..

[11]  A. Gunia-Krzyżak,et al.  Metabolic stability and its role in the discovery of new chemical entities , 2019, Acta pharmaceutica.

[12]  Takashi Ishida,et al.  In Silico Prediction of Major Clearance Pathways of Drugs among 9 Routes with Two-Step Support Vector Machines , 2018, Pharmaceutical Research.

[13]  Hirokazu Anai,et al.  Learning Multi-Way Relations via Tensor Decomposition With Neural Networks , 2018, AAAI.

[14]  J. M. Hutzler,et al.  A novel in vitro allometric scaling methodology for aldehyde oxidase substrates to enable selection of appropriate species for traditional allometry , 2018, Xenobiotica; the fate of foreign compounds in biological systems.

[15]  David S. Wishart,et al.  DrugBank 5.0: a major update to the DrugBank database for 2018 , 2017, Nucleic Acids Res..

[16]  S. Iwasaki,et al.  Comparison of predictability for human pharmacokinetics parameters among monkeys, rats, and chimeric mice with humanised liver , 2017, Xenobiotica; the fate of foreign compounds in biological systems.

[17]  J. Calixto,et al.  Non-clinical studies in the process of new drug development - Part II: Good laboratory practice, metabolism, pharmacokinetics, safety and dose translation to clinical studies , 2016, Brazilian journal of medical and biological research = Revista brasileira de pesquisas medicas e biologicas.

[18]  Franco Lombardo,et al.  In Silico Prediction of Volume of Distribution in Humans. Extensive Data Set and the Exploration of Linear and Nonlinear Methods Coupled with Molecular Interaction Fields Descriptors , 2016, J. Chem. Inf. Model..

[19]  Yoshihiro Yamanishi,et al.  Target-Based Drug Repositioning Using Large-Scale Chemical-Protein Interactome Data , 2015, J. Chem. Inf. Model..

[20]  Gang Fu,et al.  PubChem Substance and Compound databases , 2015, Nucleic Acids Res..

[21]  Fabian Pedregosa,et al.  Scikit-learn: Machine Learning Without Learning the Machinery , 2015, GETMBL.

[22]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[23]  Dolores Diaz,et al.  An algorithm for evaluating potential tissue drug distribution in toxicology studies from readily available pharmacokinetic parameters. , 2013, Journal of pharmaceutical sciences.

[24]  Vijay K. Gombar,et al.  Quantitative Structure − Activity Relationship Models of Clinical Pharmacokinetics : Clearance and Volume of Distribution , 2013 .

[25]  Franco Lombardo,et al.  Comprehensive Assessment of Human Pharmacokinetic Prediction Based on In Vivo Animal Pharmacokinetic Data, Part 2: Clearance , 2013, Journal of clinical pharmacology.

[26]  Franco Lombardo,et al.  Comprehensive Assessment of Human Pharmacokinetic Prediction Based on In Vivo Animal Pharmacokinetic Data, Part 1: Volume of Distribution at Steady State , 2013, Journal of clinical pharmacology.

[27]  Peter Ballard,et al.  The right compound in the right assay at the right time: an integrated discovery DMPK strategy , 2012, Drug metabolism reviews.

[28]  Ingo Muegge,et al.  DemQSAR: predicting human volume of distribution and clearance of drugs , 2011, J. Comput. Aided Mol. Des..

[29]  Malcolm Rowland,et al.  PhRMA CPCDC initiative on predictive models of human pharmacokinetics, part 2: comparative assessment of prediction methods of human volume of distribution. , 2011, Journal of pharmaceutical sciences.

[30]  John P. Overington,et al.  ChEMBL: a large-scale bioactivity database for drug discovery , 2011, Nucleic Acids Res..

[31]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[32]  Peter Bühlmann,et al.  MissForest - non-parametric missing value imputation for mixed-type data , 2011, Bioinform..

[33]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[34]  R. Obach,et al.  Physicochemical determinants of human renal clearance. , 2009, Journal of medicinal chemistry.

[35]  Walter Schmitt,et al.  General approach for the calculation of tissue to plasma partition coefficients. , 2008, Toxicology in vitro : an international journal published in association with BIBRA.

[36]  K Rowland-Yeo,et al.  Prediction of metabolic drug clearance in humans: In vitro–in vivo extrapolation vs allometric scaling , 2006, Xenobiotica; the fate of foreign compounds in biological systems.

[37]  M. Rowland,et al.  Physiologically based pharmacokinetic modelling 2: predicting the tissue distribution of acids, very weak bases, neutrals and zwitterions. , 2006, Journal of pharmaceutical sciences.

[38]  Huadong Tang,et al.  A NOVEL MODEL FOR PREDICTION OF HUMAN DRUG CLEARANCE BY ALLOMETRIC SCALING , 2005, Drug Metabolism and Disposition.

[39]  L. Berezhkovskiy,et al.  Volume of distribution at steady state for a linear pharmacokinetic system with peripheral elimination. , 2004, Journal of pharmaceutical sciences.

[40]  Russ B. Altman,et al.  Missing value estimation methods for DNA microarrays , 2001, Bioinform..

[41]  F. Theil,et al.  Prediction of adipose tissue: plasma partition coefficients for structurally unrelated drugs. , 2001, Journal of pharmaceutical sciences.

[42]  J L Schafer,et al.  Multiple Imputation for Multivariate Missing-Data Problems: A Data Analyst's Perspective. , 1998, Multivariate behavioral research.

[43]  D J Rance,et al.  The prediction of human pharmacokinetic parameters from preclinical and in vitro metabolism data. , 1997, The Journal of pharmacology and experimental therapeutics.

[44]  K Krishnan,et al.  A biologically-based algorithm for predicting human tissue: blood partition coefficients of organic chemicals , 1995, Human & experimental toxicology.

[45]  W. Russell,et al.  The Principles of Humane Experimental Technique , 1960 .

[46]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[47]  F. Theil,et al.  A priori prediction of tissue:plasma partition coefficients of drugs to facilitate the use of physiologically-based pharmacokinetic models in drug discovery. , 2000, Journal of pharmaceutical sciences.