Predictive Multitask Deep Neural Network Models for ADME-Tox Properties: Learning from Large Data Sets (Englisch)

Journal of Chemical Information and Modeling
; 2019
  • Neue Suche nach:

Successful drug discovery projects require control and optimization of compound properties related to pharmacokinetics, pharmacodynamics, and safety. While volume and chemotype coverage of public and corporate ADME-Tox (absorption, distribution, excretion, metabolism, and toxicity) databases are constantly growing, deep neural nets (DNN) emerged as transformative artificial intelligence technology to analyze those challenging data. Relevant features are automatically identified, while appropriate data can also be combined to multitask networks to evaluate hidden trends among multiple ADME-Tox parameters for implicitly correlated data sets. Here we describe a novel, fully industrialized approach to parametrize and optimize the setup, training, application, and visual interpretation of DNNs to model ADME-Tox data. Investigated properties include microsomal lability in different species, passive permeability in Caco-2/TC7 cells, and logD. Statistical models are developed using up to 50?000 compounds from public or corporate databases. Both the choice of DNN hyperparameters and the type and quantity of molecular descriptors were found to be important for successful DNN modeling. Alternate learning of multiple ADME-Tox properties, resulting in a multitask approach, performs statistically superior on most studied data sets in comparison to DNN single-task models and also provides a scalable method to predict ADME-Tox properties from heterogeneous data. For example, predictive quality using external validation sets was improved from R2 of 0.6 to 0.7 comparing single-task and multitask DNN networks from human metabolic lability data. Besides statistical evaluation, a new visualization approach is introduced to interpret DNN models termed "response map", which is useful to detect local property gradients based on structure fragmentation and derivatization. This method is successfully applied to visualize fragmental contributions to guide further design in drug discovery programs, as illustrated by CRCX3 antagonists and renin inhibitors, respectively.

Wie erhalte ich diesen Titel?

Inhaltsverzeichnis – Band 59, Ausgabe 3

Zeige alle Jahrgänge und Ausgaben

Die Inhaltsverzeichnisse werden automatisch erzeugt und basieren auf den im Index des TIB-Portals verfügbaren Nachweisen der enthaltenen Aufsätze. Die Anzeige der Jahrgänge kann aufgrund fehlender Aufsatznachweise unvollständig oder lückenhaft sein, obwohl die Zeitschrift komplett in der TIB verfügbar ist.

945
Machine Learning in Drug Discovery
Klambauer, Günter / Hochreiter, Sepp / Rarey, Matthias | 2019
947
In Need of Bias Control: Evaluating Chemical Data for Machine Learning in Structure-Based Virtual Screening
Sieg, Jochen / Flachsenberg, Florian / Rarey, Matthias | 2019
962
Application of Bioactivity Profile-Based Fingerprints for Building Machine Learning Models
Sturm, Noé / Sun, Jiangming / Vandriessche, Yves / Mayr, Andreas / Klambauer, Günter / Carlsson, Lars / Engkvist, Ola / Chen, Hongming | 2019
973
In Silico Prediction of Endocrine Disrupting Chemicals Using Single-Label and Multilabel Models
Sun, Lixia / Yang, Hongbin / Cai, Yingchun / Li, Weihua / Liu, Guixia / Tang, Yun | 2019
983
Exploring Alternative Strategies for the Identification of Potent Compounds Using Support Vector Machine and Regression Modeling
Miyao, Tomoyuki / Funatsu, Kimito / Bajorath, Jürgen | 2019
993
Three-Dimensional Activity Landscape Models of Different Design and Their Application to Compound Mapping and Potency Prediction
Miyao, Tomoyuki / Funatsu, Kimito / Bajorath, Jürgen | 2019
1005
Exploring Tunable Hyperparameters for Deep Neural Networks with Industrial ADME Data Sets
Zhou, Yadi / Cahya, Suntara / Combs, Steven A. / Nicolaou, Christos A. / Wang, Jibo / Desai, Prashant V. / Shen, Jie | 2019
1017
Molecular Structure Extraction from Documents Using Deep Learning
Staker, Joshua / Marshall, Kyle / Abel, Robert / McQuaw, Carolyn M. | 2019
1030
Hit Dexter 2.0: Machine-Learning Models for the Prediction of Frequent Hitters
Stork, Conrad / Chen, Ya / Šícho, Martin / Kirchmair, Johannes | 2019
1044
DeepChemStable: Chemical Stability Prediction with an Attention-Based Graph Convolution Network
Li, Xiuming / Yan, Xin / Gu, Qiong / Zhou, Huihao / Wu, Di / Xu, Jun | 2019
1050
Improved Method of Structure-Based Virtual Screening via Interaction-Energy-Based Learning
Yasuo, Nobuaki / Sekijima, Masakazu | 2019
1062
Comparative Study of Multitask Toxicity Modeling on a Broad Chemical Space
Sosnin, Sergey / Karlov, Dmitry / Tetko, Igor V. / Fedorov, Maxim V. | 2019
1073
Deep Learning-Based Prediction of Drug-Induced Cardiotoxicity
Cai, Chuipu / Guo, Pengfei / Zhou, Yadi / Zhou, Jingwei / Wang, Qi / Zhang, Fengxue / Fang, Jiansong / Cheng, Feixiong | 2019
1085
Computational Prediction of Site of Metabolism for UGT-Catalyzed Reactions
Cai, Yingchun / Yang, Hongbin / Li, Weihua / Liu, Guixia / Lee, Philip W. / Tang, Yun | 2019
1096
GuacaMol: Benchmarking Models for de Novo Molecular Design
Brown, Nathan / Fiscato, Marco / Segler, Marwin H.S. / Vaucher, Alain C. | 2019
1109
Modeling Antibacterial Activity with Machine Learning and Fusion of Chemical Structure Information with Microorganism Metabolic Networks
Nocedo-Mena, Deyani / Cornelio, Carlos / Camacho-Corona, María del Rayo / Garza-González, Elvira / Waksman de Torres, Noemi / Arrasate, Sonia / Sotomayor, Nuria / Lete, Esther / González-Díaz, Humbert | 2019
1121
Machine Learning Guided Atom Mapping of Metabolic Reactions
Litsa, Eleni E. / Peña, Matthew I. / Moll, Mark / Giannakopoulos, George / Bennett, George N. / Kavraki, Lydia E. | 2019
1136
De Novo Molecule Design by Translating from Reduced Graphs to SMILES
Pogány, Peter / Arad, Navot / Genway, Sam / Pickett, Stephen D. | 2019
1147
Prediction of Membrane Permeation of Drug Molecules by Combining an Implicit Membrane Model with Machine Learning
Brocke, Stephanie A. / Degen, Alexandra / MacKerell, Alexander D. / Dutagaci, Bercem / Feig, Michael | 2019
1163
Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional Networks
Hofmarcher, Markus / Rumetshofer, Elisabeth / Clevert, Djork-Arné / Hochreiter, Sepp / Klambauer, Günter | 2019
1172
PathwayMap: Molecular Pathway Association with Self-Normalizing Neural Networks
Jiménez, José / Sabbadin, Davide / Cuzzolin, Alberto / Martínez-Rosell, Gerard / Gora, Jacob / Manchester, John / Duca, José / De Fabritiis, Gianni | 2019
1182
De Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping
Sattarov, Boris / Baskin, Igor I. / Horvath, Dragos / Marcou, Gilles / Bjerrum, Esben Jannik / Varnek, Alexandre | 2019
1197
Imputation of Assay Bioactivity Data Using Deep Learning
Whitehead, T. M. / Irwin, B. W. J. / Hunt, P. / Segall, M. D. / Conduit, G. J. | 2019
1205
Shape-Based Generative Modeling for de Novo Drug Design
Skalic, Miha / Jiménez, José / Sabbadin, Davide / De Fabritiis, Gianni | 2019
1215
Computational Prediction of a New ADMET Endpoint for Small Molecules: Anticommensal Effect on Human Gut Microbiota
Zheng, Suqing / Chang, Wenping / Liu, Wenxin / Liang, Guang / Xu, Yong / Lin, Fu | 2019
1221
Drug Discovery Maps, a Machine Learning Model That Visualizes and Predicts Kinome–Inhibitor Interaction Landscapes
Janssen, Antonius P. A. / Grimm, Sebastian H. / Wijdeven, Ruud H. M. / Lenselink, Eelke B. / Neefjes, Jacques / van Boeckel, Constant A. A. / van Westen, Gerard J. P. / van der Stelt, Mario | 2019
1230
Accurate Hit Estimation for Iterative Screening Using Venn–ABERS Predictors
Buendia, Ruben / Kogej, Thierry / Engkvist, Ola / Carlsson, Lars / Linusson, Henrik / Johansson, Ulf / Toccaceli, Paolo / Ahlberg, Ernst | 2019
1238
The Development of Target-Specific Machine Learning Models as Scoring Functions for Docking-Based Target Prediction
Nogueira, Mauro S. / Koch, Oliver | 2019
1253
Predictive Multitask Deep Neural Network Models for ADME-Tox Properties: Learning from Large Data Sets
Wenzel, Jan / Matter, Hans / Schmidt, Friedemann | 2019
1269
Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Prediction Errors for Deep Neural Networks
Cortés-Ciriano, Isidro / Bender, Andreas | 2019
Issue Editorial Masthead
| 2019
Issue Publication Information
| 2019

Ähnliche Titel