Abstract
One of the main reasons for high attrition rate for drug candidates is their toxicity mediated through off-target binding. Thus, in vitro screening against major toxicity-related proteins is conventionally used to filter out problematic compounds at an early stage of drug development. However, in vitro testing is expensive and labour intense. Herein, we present a deep learning model that can effectively predict interaction between a small molecule of interest and a panel of 44 toxicity-associated proteins. Contrary to conventional toxicity prediction models (with one model per one endpoint), we employed a unified approach where a single model predicts activity over multiple targets. We demonstrate that this approach is superior, especially for datasets with unbalanced classes. The model is proposed for large-scale toxicity screening as well as for the elucidation of toxicity mechanisms of drug candidates.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baskin II (2018) Computational toxicology. Springer, Berlin, pp 119–139
Bemis GW, Murcko MA (1996) The properties of known drugs. 1. Molecular frameworks. J Med Chem 39(15):2887–2893
Bendels S, Bissantz C, Fasching B, Gerebtzoff G, Guba W, Kansy M, Migeon J, Mohr S, Peters J-U, Tillier F (2019) Safety screening in early drug discovery: an optimized assay panel. J Pharmacol Toxicol Methods 99:106609
Bowes J, Brown AJ, Hamon J, Jarolimek W, Sridhar A, Waldron G, Whitebread S (2012) Reducing safety-related drug attrition: the use of in vitro pharmacological profiling. Nat Rev Drug Discov 11(12):909–922
Dimasi JA (2001) Risks in new drug development: approval success rates for investigational drugs. Clin Pharmacol Ther 69(5):297–307
Garrido A, Lepailleur A, Mignani SM, Dallemagne P, Rochais C (2020) hERG toxicity assessment: useful guidelines for drug design. Eur J Med Chem 195:112290
Gilson MK, Liu T, Baitaluk M, Nicola G, Hwang L, Chong J (2016) BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res 44(D1):D1045–D1053
Harvey AL (2014) Toxins and drug discovery. Toxicon 92:193–200
Hou J, Adhikari B, Cheng J (2018) DeepSF: deep convolutional neural network for mapping protein sequences to folds. Bioinformatics 34(8):1295–1303
Huang K, Fu T, Glass LM, Zitnik M, Xiao C, Sun J (2020) DeepPurpose: a deep learning library for drug–target interaction prediction. Bioinformatics 36(22–23):5545–5547
Idakwo G, Luttrell J, Chen M, Hong H, Zhou Z, Gong P, Zhang C (2018) A review on machine learning methods for in silico toxicity prediction. J Environ Sci Health C 36(4):169–191
Jiang G, Wang W (2017) Error estimation based on variance analysis of k-fold cross-validation. Pattern Recogn 69:94–106
Kalliokoski T, Kramer C, Vulpetti A, Gedeck P (2013) Comparability of mixed IC50 data—a statistical analysis. PLoS One 8(4):e61007
Kronenberger T, Keminer O, Wrenger C, Windshügel B (2015) Nuclear receptor modulators—current approaches and future perspectives. In: Drug discovery and development-from molecules to medicine
Lin K, May AC, Taylor WR (2002) Amino acid encoding schemes from protein structure alignments: multi-dimensional vectors to describe residue types. J Theor Biol 216(3):361–365
Lounkine E, Keiser MJ, Whitebread S, Mikhailov D, Hamon J, Jenkins JL, Lavan P, Weber E, Doak AK, Côté S (2012) Large-scale prediction and testing of drug activity on side-effect targets. Nature 486(7403):361–367
Mayr A, Klambauer G, Unterthiner T, Hochreiter S (2016) DeepTox: toxicity prediction using deep learning. Front Environ Sci 3:80
Mcmaster A, Ray DW (2008) Drug insight: selective agonists and antagonists of the glucocorticoid receptor. Nat Clin Pract Endocrinol Metab 4(2):91–101
Mendez D, Gaulton A, Bento AP, Chambers J, De Veij M, Félix E, Magariños MP, Mosquera JF, Mutowo P, Nowotka M (2019) ChEMBL: towards direct deposition of bioassay data. Nucleic Acids Res 47(D1):D930–D940
Mullard M, Cadé M, Morice S, Dupuy M, Danieau G, Amiaud J, Renault S, Lézot F, Brion R, Thepault RA (2020) Sonic hedgehog signature in pediatric primary bone tumors: effects of the GLI antagonist GANT61 on Ewing’s sarcoma tumor growth. Cancers 12(11):3438
Park K, Williams DP, Naisbitt DJ, Kitteringham NR, Pirmohamed M (2005) Investigation of toxic metabolites during drug development. Toxicol Appl Pharmacol 207(2):425–434
Paul SM, Mytelka DS, Dunwiddie CT, Persinger CC, Munos BH, Lindborg SR, Schacht AL (2010) How to improve R&D productivity: the pharmaceutical industry’s grand challenge. Nat Rev Drug Discov 9(3):203–214
Peng Y, Zhang Z, Jiang Q, Guan J, Zhou S (2019) Top: towards better toxicity prediction by deep molecular representation learning. IEEE, pp 318–325
Rampe D, Brown AM (2013) A history of the role of the hERG channel in cardiac risk assessment. J Pharmacol Toxicol Methods 68(1):13–22
Redfern WS, Wakefield ID, Prior H, Pollard CE, Hammond TG, Valentin JP (2002) Safety pharmacology—a progressive approach. Fundam Clin Pharmacol 16(3):161–173
Sherman C, Writer NN (2007) The defining features of drug intoxication and addiction can be traced to disruptions in cell-to-cell signaling. NIDA Notes NIH, NIDA 21(4)
Smith DA, Schmid EF (2006) Drug withdrawals and the lessons within. Curr Opin Drug Discov Dev 9(1):38–46
Sorkun MC, Mullaj D, Koelman JVA, Er S (2022) Chemplot, a python library for chemical space visualization
Suleyman H, Demircan B, Karagoz Y (2007) Anti-inflammatory and side effects of cyclo-oxygenase inhibitors. Pharmacol Rep 59(3):247
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol 30
Wang MW, Goodman JM, Allen TE (2020) Machine learning in predictive toxicology: recent applications and future directions for classification models. Chem Res Toxicol 34(2):217–239
Weiss A, Freeman W, Heslin K, Barrett M (2018) Adverse drug events in us hospitals, 2010 versus 2014. HCUP Statistical Brief 234
Wilbraham L, Sprick RS, Jelfs KE, Zwijnenburg MA (2019) Mapping binary copolymer property space with neural networks. Chem Sci 10(19):4973–4984
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Radaeva, M., Pandey, M., MsLati, H., Cherkasov, A. (2023). Deep Learning Model for Prediction of Compound Activities Over a Panel of Major Toxicity-Related Proteins. In: Hong, H. (eds) Machine Learning and Deep Learning in Computational Toxicology. Computational Methods in Engineering & the Sciences. Springer, Cham. https://doi.org/10.1007/978-3-031-20730-3_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-20730-3_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20729-7
Online ISBN: 978-3-031-20730-3
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)