Machine Learning Based Toxicity Prediction: From Chemical Structural Description to Transcriptome Analysis

Overview

Journal Int J Mol Sci

Publisher MDPI

Specialties Biochemistry
Chemistry
Molecular Biology

Date 2018 Aug 15

PMID 30103448

Citations 39

Authors

Yunyi Wu

Guanyu Wang

Affiliations

Soon will be listed here.

Abstract

Toxicity prediction is very important to public health. Among its many applications, toxicity prediction is essential to reduce the cost and labor of a drug's preclinical and clinical trials, because a lot of drug evaluations (cellular, animal, and clinical) can be spared due to the predicted toxicity. In the era of Big Data and artificial intelligence, toxicity prediction can benefit from machine learning, which has been widely used in many fields such as natural language processing, speech recognition, image recognition, computational chemistry, and bioinformatics, with excellent performance. In this article, we review machine learning methods that have been applied to toxicity prediction, including deep learning, random forests, k-nearest neighbors, and support vector machines. We also discuss the input parameter to the machine learning algorithm, especially its shift from chemical structural description only to that combined with human transcriptome data analysis, which can greatly enhance prediction accuracy.

Citing Articles

Hepatotoxicity Evaluation of Levornidazole and Its Three Main Impurities: Based on Structure-Toxicity Classification Prediction Combined with Zebrafish Toxicity Assessment.

Liu T, Yuan S, Zhang L, Zhang D Molecules. 2025; 30(5).

PMID: 40076220 PMC: 11901814. DOI: 10.3390/molecules30050995.

Bridging organ transcriptomics for advancing multiple organ toxicity assessment with a generative AI approach.

Li T, Chen X, Tong W NPJ Digit Med. 2024; 7(1):310.

PMID: 39501092 PMC: 11538515. DOI: 10.1038/s41746-024-01317-z.

Thyroid Hormone Biomonitoring: A Review on Their Metabolism and Machine-Learning Based Analysis on Effects of Endocrine Disrupting Chemicals.

Chen S, Yu M, Yao Y, Li Y, He A, Zhou Z Environ Health (Wash). 2024; 2(6):350-372.

PMID: 39473465 PMC: 11503987. DOI: 10.1021/envhealth.3c00184.

A Systematic Review of Genetics- and Molecular-Pathway-Based Machine Learning Models for Neurological Disorder Diagnosis.

Aljarallah N, Dutta A, Sait A Int J Mol Sci. 2024; 25(12).

PMID: 38928128 PMC: 11203850. DOI: 10.3390/ijms25126422.

Gap-Δenergy, a New Metric of the Bond Energy State, Assisting to Predict Molecular Toxicity.

Zhang S, Zhao D, Cui Q ACS Omega. 2024; 9(16):17839-17847.

PMID: 38680329 PMC: 11044234. DOI: 10.1021/acsomega.3c07682.

References

Edgar R, Domrachev M, Lash A . Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res. 2001; 30(1):207-10. PMC: 99122. DOI: 10.1093/nar/30.1.207. View

Johnson D . Fusion of nonclinical and clinical data to predict human drug safety. Expert Rev Clin Pharmacol. 2013; 6(2):185-95. DOI: 10.1586/ecp.13.3. View

Cammarata A, Menon G . Pattern recognition. Classification of therapeutic agents according to pharmacophores. J Med Chem. 1976; 19(6):739-48. DOI: 10.1021/jm00228a001. View

Hwang T, Carpenter D, Lauffenburger J, Wang B, Franklin J, Kesselheim A . Failure of Investigational Drugs in Late-Stage Clinical Development and Publication of Trial Results. JAMA Intern Med. 2016; 176(12):1826-1833. DOI: 10.1001/jamainternmed.2016.6008. View

Kim S, Thiessen P, Bolton E, Chen J, Fu G, Gindulyte A . PubChem Substance and Compound databases. Nucleic Acids Res. 2015; 44(D1):D1202-13. PMC: 4702940. DOI: 10.1093/nar/gkv951. View

Zeng H, Qiu C, Cui Q . Drug-Path: a database for drug-induced pathways. Database (Oxford). 2015; 2015:bav061. PMC: 4485432. DOI: 10.1093/database/bav061. View

Yoo M, Shin J, Kim J, Ryall K, Lee K, Lee S . DSigDB: drug signatures database for gene set analysis. Bioinformatics. 2015; 31(18):3069-71. PMC: 4668778. DOI: 10.1093/bioinformatics/btv313. View

Zhu H, Zhang J, Kim M, Boison A, Sedykh A, Moran K . Big data in chemical toxicity research: the use of high-throughput screening assays to identify potential toxicants. Chem Res Toxicol. 2014; 27(10):1643-51. PMC: 4203392. DOI: 10.1021/tx500145h. View

Ippolito D, AbdulHameed M, Tawa G, Baer C, Permenter M, McDyre B . Gene Expression Patterns Associated With Histopathology in Toxic Liver Fibrosis. Toxicol Sci. 2015; 149(1):67-88. DOI: 10.1093/toxsci/kfv214. View

10.

Svetnik V, Liaw A, Tong C, Culberson J, Sheridan R, Feuston B . Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003; 43(6):1947-58. DOI: 10.1021/ci034160g. View

11.

Durant J, Leland B, Henry D, Nourse J . Reoptimization of MDL keys for use in drug discovery. J Chem Inf Comput Sci. 2002; 42(6):1273-80. DOI: 10.1021/ci010132r. View

12.

Xu Y, Pei J, Lai L . Deep Learning Based Regression and Multiclass Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction. J Chem Inf Model. 2017; 57(11):2672-2685. DOI: 10.1021/acs.jcim.7b00244. View

13.

Chavan S, Friedman R, Nicholls I . Acute Toxicity-Supported Chronic Toxicity Prediction: A k-Nearest Neighbor Coupled Read-Across Strategy. Int J Mol Sci. 2015; 16(5):11659-77. PMC: 4463722. DOI: 10.3390/ijms160511659. View

14.

van Delft J, Gaj S, Lienhard M, Albrecht M, Kirpiy A, Brauers K . RNA-Seq provides new insights in the transcriptome responses induced by the carcinogen benzo[a]pyrene. Toxicol Sci. 2012; 130(2):427-39. DOI: 10.1093/toxsci/kfs250. View

15.

Fonger G, Stroup D, Thomas P, Wexler P . TOXNET: A computerized collection of toxicological and environmental health information. Toxicol Ind Health. 2000; 16(1):4-6. DOI: 10.1177/074823370001600101. View

16.

Akhtar A . The flaws and human harms of animal experimentation. Camb Q Healthc Ethics. 2015; 24(4):407-19. PMC: 4594046. DOI: 10.1017/S0963180115000079. View

17.

Liu J, Xu C, Yang W, Shu Y, Zheng W, Zhou F . Multiple similarly effective solutions exist for biomedical feature selection and classification problems. Sci Rep. 2017; 7(1):12830. PMC: 5634418. DOI: 10.1038/s41598-017-13184-8. View

18.

Marvuglia A, Kanevski M, Benetto E . Machine learning for toxicity characterization of organic chemical emissions using USEtox database: Learning the structure of the input space. Environ Int. 2015; 83:72-85. DOI: 10.1016/j.envint.2015.05.011. View

19.

Zhang J, Berntenis N, Roth A, Ebeling M . Data mining reveals a network of early-response genes as a consensus signature of drug-induced in vitro and in vivo toxicity. Pharmacogenomics J. 2013; 14(3):208-16. PMC: 4034126. DOI: 10.1038/tpj.2013.39. View

20.

Liu R, AbdulHameed M, Wallqvist A . Molecular Structure-Based Large-Scale Prediction of Chemical-Induced Gene Expression Changes. J Chem Inf Model. 2017; 57(9):2194-2202. DOI: 10.1021/acs.jcim.7b00281. View