Repurposing High-Throughput Image Assays Enables Biological Activity Prediction for Drug Discovery

Cell Chemical Biology

Volumn 25, Issue 5, 2018, Pages 611-618.e3

  Simm, Jaak ^a   Klambauer, Günter ^b   Arany, Adam ^a   Steijaert, Marvin ^c   Wegner, Jörg Kurt ^d   Gustin, Emmanuel ^d   Chupakhin, Vladimir ^d   Chong, Yolanda T ^d   Vialard, Jorge ^d   Buijnsters, Peter ^d   Velter, Ingrid ^d   Vapirev, Alexander ^a   Singh, Shantanu ^e   Carpenter, Anne E ^e   Wuyts, Roel ^f   Hochreiter, Sepp ^b   Moreau, Yves ^a   Ceulemans, Hugo ^d  

^a UNIVERSITY OF LEUVEN   (Belgium)

^b JOHANNES KEPLER UNIVERSITY LINZ   (Austria)

^c Open Analytics   (Belgium)

^d JANSSEN RESEARCH FOUNDATION   (Belgium)

^e BROAD INSTITUTE OF MIT AND HARVARD   (United States)

^f IMEC   (Belgium)

Author keywords

Bayesian matrix factorization; computational chemistry; deep learning; drug discovery; high content imaging; high throughput screening; machine learning; matrix factorization

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; BIOASSAY; BIOLOGICAL ACTIVITY; COMPUTER MODEL; DRUG DEVELOPMENT; DRUG INDUSTRY; HIGH THROUGHPUT SCREENING; HUMAN; IMMUNOFLUORESCENCE; IN VITRO STUDY; MACHINE LEARNING; PREDICTION; PRIMARY CELL; PRIORITY JOURNAL; RANDOM FOREST; STRUCTURE ACTIVITY RELATION; SUPERVISED MACHINE LEARNING; DRUG REPOSITIONING; IMAGE PROCESSING; NEOPLASM; PROCEDURES; TUMOR CELL LINE;

ANTINEOPLASTIC AGENT;

ANTINEOPLASTIC AGENTS; CELL LINE, TUMOR; DRUG REPOSITIONING; HIGH-THROUGHPUT SCREENING ASSAYS; HUMANS; IMAGE PROCESSING, COMPUTER-ASSISTED; MACHINE LEARNING; NEOPLASMS; NEURAL NETWORKS (COMPUTER);

EID: 85042602612     PISSN: 24519456     EISSN: 24519448     Source Type: Journal    
DOI: 10.1016/j.chembiol.2018.01.015     Document Type: Article

References (29)

1. Ansbro, M.R., Shukla, S., Ambudkar, S.V., Yuspa, S.H., Li, L., Screening compounds with a novel high-throughput ABCB1-mediated efflux assay identifies drugs with known therapeutic targets at risk for multidrug resistance interference. PLoS One, 8, 2013, e60334.
2. Baell, J.B., Holloway, G.A., New substructure filters for removal of pan assay interference compounds (PAINS) from screening libraries and for their exclusion in bioassays. J. Med. Chem. 53 (2010), 2719–2740.
3. Baumann, D., Baumann, K., Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validation. J. Cheminformatics, 6, 2014, 47.
4. Breiman, L., Random forests. Mach. Learn. 45 (2001), 5–32.
5. Caicedo, J.C., Singh, S., Carpenter, A.E., Applications in image-based profiling of perturbations. Curr. Opin. Biotechnol. 39 (2016), 134–142.
6. Carpenter, A.E., Jones, T.R., Lamprecht, M.R., Clarke, C., Kang, I.H., Friman, O., Guertin, D.A., Chang, J.H., Lindquist, R.A., Moffat, J., CellProfiler: image analysis software for identifying and quantifying cell phenotypes. Genome Biol., 7, 2006, R100.
7. Caruana, R., Multitask learning. Mach. Learn. 28 (1997), 41–75.
8. Cumming, J.G., Davis, A.M., Muresan, S., Haeberlein, M., Chen, H., Chemical predictive modelling to improve compound quality. Nat. Rev. Drug Discov., 12, 2013, 948.
9. Egan, W.J., Merz, K.M., Baldwin, J.J., Prediction of drug absorption using multivariate statistics. J. Med. Chem. 43 (2000), 3867–3877.
10. Evensen, L., Link, W., Lorens, J.B., Imaged-based high-throughput screening for anti-angiogenic drug discovery. Curr. Pharm. Des. 16 (2010), 3958–3963.
11. Garg, P., Verma, J., In silico prediction of blood brain barrier permeability: an artificial neural network model. J. Chem. Inf. Model. 46 (2006), 289–297.
12. Gustafsdottir, S.M., Ljosa, V., Sokolnicki, K.L., Wilson, J.A., Walpita, D., Kemp, M.M., Seiler, K.P., Carrel, H.A., Golub, T.R., Schreiber, S.L., Multiplex cytological profiling assay to measure diverse cellular states. PLoS One, 8, 2013, e80999.
13. Held, M., Schmitz, M.H., Fischer, B., Walter, T., Neumann, B., Olma, M.H., Peter, M., Ellenberg, J., Gerlich, D.W., CellCognition: time-resolved phenotype annotation in high-throughput live cell imaging. Nat. Methods 7 (2010), 747–754.
14. Hochreiter, S., Obermayer, K., Gene selection for microarray data. Schölkopf, B., Tsuda, K., Vert Kernel, J.P., (eds.) Methods in Computational Biology, 2004, MIT Press, 319–355.
15. Louppe, G., Understanding random forests: from theory to practice. arXiv, 2014 arXiv:14077502.
16. Mayr, A., Klambauer, G., Unterthiner, T., Hochreiter, S., DeepTox: toxicity prediction using deep learning. Front. Environ. Sci., 3, 2016, 10.3389/fenvs.2015.00080.
17. Oshiro, T.M., Perez, P.S., and Baranauskas, J.A. (2012). How many trees in a random forest? Paper presented at: MLDM (Springer).
18. Pepperkok, R., Ellenberg, J., High-throughput fluorescence microscopy for systems biology. Nat. Rev. Mol. Cell Biol., 7, 2006, 690.
19. Polishchuk, P.G., Muratov, E.N., Artemenko, A.G., Kolumbin, O.G., Muratov, N.N., Kuz'min, V.E., Application of random forest approach to QSAR prediction of aquatic toxicity. J. Chem. Inf. Model. 49 (2009), 2481–2488.
20. Rogers, D., Hahn, M., Extended-connectivity fingerprints. J. Chem. Inf. Model. 50 (2010), 742–754.
21. Simm, J., Arany, A., Zakeri, P., Haber, T., Wegner, J.K., Chupakhin, V., Ceulemans, H., and Moreau, Y. (2017). Macau: scalable Bayesian factorization with high-dimensional side information using MCMC. Proceedings of 2017 IEEE International Workshop on Machine Learning for Signal Processing. IEEE. https://doi.org/10.1109/MLSP.2017.8168143.
22. Singh, S., Carpenter, A.E., Genovesio, A., Increasing the content of high-content screening: an overview. J. Biomol. Screen. 19 (2014), 640–650.
23. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15 (2014), 1929–1958.
24. Starkuviene, V., Pepperkok, R., The potential of high-content high-throughput microscopy in drug discovery. Br. J. Pharmacol. 152 (2007), 62–71.
25. Walter, T., Shattuck, D.W., Baldock, R., Bastin, M.E., Carpenter, A.E., Duce, S., Ellenberg, J., Fraser, A., Hamilton, N., Pieper, S., Visualization of image data from cells to organisms. Nat. Methods 7 (2010), S26–S41.
26. Wang, Y., Xing, J., Xu, Y., Zhou, N., Peng, J., Xiong, Z., Liu, X., Luo, X., Luo, C., Chen, K., In silico ADME/T modelling for rational drug design. Q. Rev. Biophys. 48 (2015), 488–515.
27. Wawer, M.J., Li, K., Gustafsdottir, S.M., Ljosa, V., Bodycombe, N.E., Marton, M.A., Sokolnicki, K.L., Bray, M.-A., Kemp, M.M., Winchester, E., Toward performance-diverse small-molecule libraries for cell-based phenotypic screening using multiplexed high-dimensional profiling. Proc. Natl. Acad. Sci. USA 111 (2014), 10911–10916.
28. Wright, M.N., Ziegler, A., Ranger: a fast implementation of random forests for high dimensional data in C++ and R. arXiv, 2015 arXiv:150804409.
29. Yarrow, J., Feng, Y., Perlman, Z., Kirchhausen, T., Mitchison, T., Phenotypic screening of small molecule libraries by high throughput cell imaging. Comb. Chem. High Throughput Screen. 6 (2003), 279–286.