Prediction of drug-induced eosinophilia adverse effect by using SVM and naïve Bayesian approaches
- 281 Downloads
Drug-induced eosinophilia is a potentially life-threatening adverse effect; clinical manifestations, eosinophilia–myalgia syndrome, mainly include severe skin eruption, fever, hematologic abnormalities, and organ system dysfunction. Using experimental methods to evaluate drug-induced eosinophilia is very complicated, time-consuming, and costly in the early stage of drug development. Thus, in this investigation, we established computational prediction models of drug-induced eosinophilia using SVM and naïve Bayesian approaches. For the SVM modeling, the overall prediction accuracy for the training set by means of fivefold cross-validation is 91.6 and for the external test set is 82.9 %. For the naïve Bayesian modeling, the overall prediction accuracy for the training set is 92.5 and for the external test set is 85.4 %. Moreover, some molecular descriptors and substructures considered as important for drug-induced eosinophilia were identified. Thus, we hope the prediction models of drug-induced eosinophilia built in this work should be applied to filter early-stage molecules for potential eosinophilia adverse effect, and the selected molecular descriptors and substructures of toxic compounds should be taken into consideration in the design of new candidate drugs to help medicinal chemists rationally select the chemicals with the best prospects to be effective and safe.
KeywordsDrug-induced eosinophilia Support vector machine Naïve Bayesian Important features Prediction
This work was supported by the Project for Enhancing the Research Capability of Young Teachers in Northwest Normal University (NWNU-LKQN-12-7).
Conflict of interest
The authors declare that there are no conflicts of interest.
- 1.Allen JA, Varga J (2014) Encyclopedia of toxicology, 3rd edition from Philip Wexler. Elsevier, New YorkGoogle Scholar
- 4.Box GEP, Tiao GC (1973) Bayesian inference in statistical analysis. Addison-Wesley, ReadingGoogle Scholar
- 11.Hardman JG, Limbird LE, Gilman AG (1996) Goodman and Gilman’s the pharmacological basis of therapeutics. McGraw-Hill, New YorkGoogle Scholar
- 12.Keerthi S, Sindhwani V, Chapelle O (2007) An efficient method for gradient-based adaptation of hyperparameters in SVM models. In: Schölkopf B, Platt J, Hofmann T (eds) Advances in neural information processing systems ~20 (NIPS ~2006), Vancouver, CanadaGoogle Scholar
- 14.Li AP (2011) Drug discovery and development—present and future. In: Kapetanović I (ed) Critical human hepatocyte-based in vitro assays for the evaluation of adverse drug effects. InTech, USAGoogle Scholar
- 23.Singh V, Gomez VV, Swamy SG, Vikas B (2009) Approach to a case of eosinophilia. Ind J Aerospace Med 53:58–64Google Scholar
- 25.Valent P, Gleich GJ, Reiter A, Roufosse F, Weller PF, Hellmann A, Metzgeroth G, Leiferman KM, Arock M, Sotlar K, Butterfield JH, Cerny-Reiterer S, Mayerhofer M, Vandenberghe P, Haferlach T, Bochner BS, Gotlib J, Horny HP, Simon HU, Klion AD (2012) Pathogenesis and classification of eosinophil disorders: a review of recent developments in the field. Expert Rev Hematol 5:157–176CrossRefPubMedPubMedCentralGoogle Scholar
- 26.Vapnik V (1998) Statistical learning theory. Wiley, New YorkGoogle Scholar
- 27.VCCLAB (2005) Virtual computational chemistry laboratory. Available at : http://www.vcclab.org
- 30.Yang SY, Huang Q, Li LL, Ma CY, Zhang H, Bai R, Teng QZ, Xiang ML, Wei YQ (2009) An integrated scheme for feature selection and parameter setting in the support vector machine modeling and its application to the prediction of pharmacokinetic properties of drugs. Artif Intell Med 46:155–163CrossRefPubMedGoogle Scholar
- 34.Zurlo J, Rudacille D, Goldberg AM (1994) Animals and alternatives in testing: history: science and ethics. Mary Ann Liebert, New YorkGoogle Scholar