2015

Toxicity Prediction using Deep Learning

Unterthiner, Thomas, Mayr, Andreas, Klambauer, Günter et al.

Understand

Everyday we are exposed to various chemicals via food additives, cleaning and cosmetic products and medicines -- and some of them might be toxic.

However testing the toxicity of all existing compounds by biological experiments is neither financially nor logistically feasible.
Therefore the government agencies NIH, EPA and FDA launched the Tox21 Data Challenge within the "Toxicology in the 21st Century" (Tox21) initiative.
The goal of this challenge was to assess the performance of computational methods in predicting the toxicity of chemical compounds.

Built on

Molecular orbital theory in drug research
Kier, L.B · 1971
Earlier work this paper cites.
Multitask learning
Caruana, R · 1997
Earlier work this paper cites.
Pharmacophore perception, development and use in drug design. edited by osman f. güner
Lin, SK · 2000
Earlier work this paper cites.
Prediction of biological activity for high-throughput screening using binary kernel discrimination
Harper, G., Bradshaw, J., Gittins, J., Green, D., and Leach, A · 2001
Earlier work this paper cites.
Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification
Byvatov, E., Fechner, U., Sadowski, J., and Schneider, G · 2003
Earlier work this paper cites.
Docking and scoring in virtual screening for drug discovery: methods and applications
Kitchen, D., Decornez, H., Furr, J., and Bajorath, J · 2004
Earlier work this paper cites.
Can the pharmaceutical industry reduce attrition rates?
Kola, I. and Landis, J · 2004
Earlier work this paper cites.
Classification of Kinase Inhibitors Using a Bayesian Model
Xia, X., Maliski, E., Gallant, P., and Rogers, D · 2004
Earlier work this paper cites.
Derivation and validation of toxicophores for mutagenicity prediction
Kazius, J., McGuire, R., and Bursi, R · 2005
Earlier work this paper cites.
Quantitative high-throughput screening: a titration-based approach that efficiently identifies biological activities in large chemical libraries
Inglese, J., Auld, D. S., Jadhav, A., Johnson, R. L., Simeonov, A., Yasgar, A., Zheng, W., and Austin, C. P · 2006
Earlier work this paper cites.
Toxicity Testing in the 21st Century: A Vision and a Strategy
Committee on Toxicity Testing and Assessment of Environmental Agents, National Research Council · 2007
Earlier work this paper cites.
In silico target fishing: Predicting biological targets from chemical structure
Jenkins, J., Bender, A., and Davies, J · 2007
Earlier work this paper cites.

Similar

Genomic profiling in nuclear receptor-mediated toxicity
Woods, C. G., Vanden H., John P., and Rusyn, I · 2007
Cited alongside, same era.
Mold2, molecular descriptors from 2d structures for chemoinformatics and toxicoinformatics
Hong, H., Xie, Q., Ge, W., Qian, F., Fang, H., Shi, L., Su, Z., Perkins, R., and Tong, W · 2008
Cited alongside, same era.
Ligand-target prediction using winnow and naive bayesian algorithms and the implications of overall performance statistics
Nigsch, F., Bender, A., Jenkins, J., and Mitchell, J · 2008
Cited alongside, same era.
Rectified linear units improve restricted boltzmann machines
Nair, V. and Hinton, G · 2010
Cited alongside, same era.
Extended-connectivity fingerprints
Rogers, D. and Hahn, M · 2010
Cited alongside, same era.
Trial watch: phase III and submission failures: 2007–2010
Arrowsmith, J · 2011
Cited alongside, same era.
Deep sparse rectifier neural networks
Glorot, X., Bordes, A., and Bengio, Y · 2011
Cited alongside, same era.
Classifying molecules using a sparse probabilistic kernel binary classifier
Lowe, R, Mussa, H., Mitchell, J., and Glen, R · 2011
Cited alongside, same era.
Improving neural networks by preventing co-adaptation of feature detectors
Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R · 2012
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., and Hinton, G · 2012
Cited alongside, same era.
Predicting the mechanism of phospholipidosis
R., Lowe, Y., Mussa, F., Nigsch, Glen, R., and Mitchell, J · 2012
Cited alongside, same era.
Deep learning of representations: Looking forward
Bengio, Y · 2013
Cited alongside, same era.

Then

Representation learning: A review and new perspectives
Bengio, Y., Courville, A., and Vincent, P · 2013
Later among the works it cites.
ChemoPy: freely available python package for computational biology and chemoinformatics
Cao, DS., Xu, QS., Hu, QN., and Liang, YZ · 2013
Later among the works it cites.
Recent advances in deep learning for speech research at microsoft
Deng, L., Li, J., Huang, JT., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, Xiaodong, Williams, J., Gong, Y., and Acero, A · 2013
Later among the works it cites.
Full ”Laplacianised” posterior naive Bayesian algorithm
Mussa, H., Mitchell, J., and Glen, R · 2013
Later among the works it cites.
Multi-task neural networks for QSAR predictions
Original
Dahl, G., Jaitly, N., and Salakhutdinov, R · 2014
Later among the works it cites.
Dropout: A simple way to prevent neural networks from overfitting
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R · 2014
Later among the works it cites.
Deep learning as an opportunity in virtual screening
Unterthiner, T., Mayr, A., Klambauer, G., Steijaert, M., Wegner, J. K., Ceulemans, H., and Hochreiter, S · 2014
Later among the works it cites.
Tox21 Data Challenge 2014
National Center for Advancing Translational Sciences · 2015
Closest in time.
NCATS Announces Tox21 Data Challenge Winners
National Center for Advancing Translational Sciences · 2015
Closest in time.
Massively Multitask Networks for Drug Discovery
Original
Ramsundar, B., Kearnes, S., Riley, P., Webster, D., Konerding, D., and Pande, V · 2015
Closest in time.
Using transcriptomics to guide lead optimization in drug discovery projects: Lessons learned from the QSTAR project
Verbist, B., Klambauer, G., Vervoort, L., Talloen, W., Shkedy, Z., Thas, O., Bender, A., Göhlmann, H., and Hochreiter, S · 2015
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…