Improving DILI prediction methods based on defined daily dose

doi:10.19803/j.1672-8629.20230409

Abstract

Abstract: Objective To evaluate the impact of the defined daily dose on the performance of drug-induced liver injury (DILI) prediction models based on the support vector machine (SVM). Methods A total of 207 pieces of data on the structure and daily defined dose (DDD) were collected from public databases. The dataset was randomly split into a training set and a test set at the ratio of 4 : 1. Quantitative estimates of drug-likeness properties were extracted and the DDD was added as a new feature. The SVM was used to construct a DILI prediction model. Four metrics were used to evaluate the model performance. The dataset was randomly split 100 times to establish the predictive model, and the changes in the predictive performance of the model after DDD features were added were investigated. Results The prediction results of the SVM showed that most metrics were improved after DDD was added so that the mean accuracy, recall, precision and area under the receiver operating characteristic curve were 0.763, 0.773, 0.779 and 0.832, respectively, which were 0.088, 0.103, 0.074 and 0.105 higher than those without DDD, respectively. Conclusion The DDD can significantly improve the accuracy of the DILI prediction model.

Key words: drug induced liver injury, support vector machine, defined daily dosage, prediction model, safety

CLC Number:

R965

HU Xiaowen, ZHANG Caiyu, WANG Fengfeng, PU Hengting, LIU Yang, CHEN Hua. Improving DILI prediction methods based on defined daily dose[J]. Chinese Journal of Pharmacovigilance, 2024, 21(7): 776-780.

Add to citation manager EndNote|Ris|BibTeX

URL: https://zgywjj.magtechjournal.com/EN/10.19803/j.1672-8629.20230409

https://zgywjj.magtechjournal.com/EN/Y2024/V21/I7/776

References

[1] HOOFNAGLE JH, BJORNSSON ES.Drug-induced liver injury - types and phenotypes[J]. N Engl J Med, 2019, 381(3): 264-273.
[2] LIU A, WALTER M, WRIGHT P, et al.Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure[J]. Biol Direct, 2021, 16(1): 6.
[3] PENG H, ZHANG L, HE J, et al.Research progress in adverse outcome pathway related to drug-induced liver injury[J]. Chinese Journal of Pharmacology and Toxicology(中国药理学与毒理学杂志), 2021, 35(11): 868-876.
[4] WATKINS PB.Quantitative systems toxicology approaches to understand and predict drug-induced liver injury[J]. Clin Liver Dis, 2020, 24(1): 49-60.
[5] HU X, DU T, WANG Z, et al.Comprehensive characterization of natural products of Polygonum multiflorum by cheminformatics analysis[J]. Pharmacological Research-Modern Chinese Medicine, 2023, 7: 100249.
[6] CHEN Z, ZHAO M, YOU L, et al.Developing an artificial intelligence method for screening hepatotoxic compounds in traditional Chinese medicine and Western medicine combination[J]. Chin Med, 2022, 17(1): 58.
[7] XU Y, DAI Z, CHEN F, et al.Deep learning for drug-induced liver injury[J]. J Chem Inf Model, 2015, 55(10): 2085-2093.
[8] CHEN M, SUZUKI A, THAKKAR S, et al.DILIrank: the largest reference drug list ranked by the risk for developing drug-induced liver injury in humans[J]. Drug Discov Today, 2016, 21(4): 648-653.
[9] KIM S, CHEN J, CHENG T, et al.PubChem 2023 update[J]. Nucleic Acids Res, 2023, 51(D1): D1373-D1380.
[10] Folkehelseinstituttet. WHO Collaborating Centre for Drug Statistics Methodology [EB/OL].[2023-11-10]. https://www.whocc.no/.
[11] STROMBERGSSON H, LAPINS M, KLEYWEGT GJ, et al.Towards proteome-wide interaction models using the proteochemometrics approach[J]. Mol Inform, 2010, 29(6-7): 499-508.
[12] BICKERTON GR, PAOLINI GV, BESNARD J, et al.Quantifying the chemical beauty of drugs[J]. Nat Chem, 2012, 4(2): 90-98.
[13] HU X, YAN H, WANG X, et al.Machine learning methods to predict the cultivation age of Panacis Quinquefolii Radix[J]. Chin Med, 2021, 16(1): 100.
[14] HU X, DU T, DAI S, et al.Identification of intrinsic hepatotoxic compounds in Polygonum multiflorum Thunb. using machine-learning methods[J]. J Ethnopharmacol, 2022, 298: 115620.
[15] SU R, WU H, LIU X, et al.Predicting drug-induced hepatotoxicity based on biological feature maps and diverse classification strategies[J]. Brief Bioinform, 2021, 22(1): 428-437.
[16] TSUTSUMI K, GOSHTASBI K, AHMED KH, et al.Artificial neural network prediction of post-thyroidectomy outcome[J]. Clin Otolaryngol, 2023, 48(4): 665-671.
[17] TENG L, XIN HW, BLIX HS, et al.Review of the use of defined daily dose concept in drug utilisation research in China[J]. Pharmacoepidemiol Drug Saf, 2012, 21(10): 1118-1124.