EUVIMEDEUVIMED entdecken
Crossref

Paired CYP1A2/3A4-HepG2 phenotyping supports machine-learning classification of literature-curated hepatotoxicity categories

Er-Chong Li, Jing Long, Ting Yu, Si-Tong Qian, Fang-Ning Qiu, Chun-Lu Liu, Yan Jiang, Hui-Jun Li

Food and Chemical Toxicology · 2026

DOI: 10.1016/j.fct.2026.116413 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Food and Chemical Toxicology, 2026. Verfasst von Er-Chong Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: lec1…. Hauptthemen laut MEDLINE: Machine Learning, Cytochrome P-450 CYP1A2, Chemical and Drug Induced Liver Injury, Cytochrome P-450 CYP3A. Die Arbeit nennt 53 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Limited CYP1A2/3A4 activity in wild-type HepG2 cells can obscure hepatotoxic responses that require metabolic activation. We established matched CYP1A2/3A4-co-expressing and empty-vector (EV) HepG2 cells and profiled 81 compounds with six high-content imaging readouts and three extracellular injury biomarkers. Absolute responses and paired CYP/EV differences were encoded as 54 compound-level features for random forest (RF) classification of three literature-curated study labels: CYP1A2/3A4 metabolic activation-associated hepatotoxic compounds (MAHC), CYP1A2/3A4-independent hepatotoxic compounds (IDHC), and non-hepatotoxic compounds (NHC). In 62 model-development compounds (26 MAHC, 12 IDHC, 24 NHC), the primary nested analysis yielded macro-F1 values of 0.959 for three-class classification and 0.911 for MAHC-IDHC; across 10 nested-cross-validation runs, means were 0.945 ± 0.014 and 0.920 ± 0.030. Feature-set ablation showed that paired CYP/EV information was nonredundant: neither EV-only (macro-F1 0.572) nor CYP-only (0.367) reproduced MAHC-IDHC discrimination, which the differential features alone retained. The final RF classified all 19 same-laboratory held-out compounds under common Cmax-based dosing (accuracy 1.00; 95% CI, 0.82-1.00), although only three were IDHC. Zebrafish CYP modulation produced responses consistent with the assigned labels in the three compounds tested. These data support matched CYP/EV phenotyping for classifying these literature-curated categories.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningCytochrome P-450 CYP1A2Chemical and Drug Induced Liver InjuryCytochrome P-450 CYP3ALiverHumansHep G2 CellsAnimalsPhenotypeZebrafishRandom Forest

Stichwörter der Autor:innen

Cytochrome P450HepG2HepatotoxicityHigh-content imagingMachine learningMetabolic bioactivation

Substanzen

Cytochrome P-450 CYP1A2Cytochrome P-450 CYP3ACYP3A4 protein, humanCYP1A2 protein, human

Autor:innen und Institutionen

  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: lec1079513189@126.com.
  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: longjing052525@126.com.
  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: cpu_yt@126.com.
  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: qianlu_2009_hi@126.com.
  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: qiu_fn@163.com.
  • State Key Laboratory of Natural Medicines, China Pharmaceutical University, No. 639 Longmian Avenue, Nanjing, 211198, China. Electronic address: tianlu379@163.com.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, E. C., Long, J., Yu, T., Qian, S. T., Qiu, F. N., Liu, C. L., Jiang, Y., & Li, H. J. (2026). Paired CYP1A2/3A4-HepG2 phenotyping supports machine-learning classification of literature-curated hepatotoxicity categories. Food and Chemical Toxicology. https://doi.org/10.1016/j.fct.2026.116413

Vancouver

Li EC, Long J, Yu T, Qian ST, Qiu FN, Liu CL, et al. Paired CYP1A2/3A4-HepG2 phenotyping supports machine-learning classification of literature-curated hepatotoxicity categories. Food and Chemical Toxicology. 2026. doi:10.1016/j.fct.2026.116413

BibTeX
@article{Li2026,
  author = {Li, Er-Chong and Long, Jing and Yu, Ting and Qian, Si-Tong and Qiu, Fang-Ning and Liu, Chun-Lu and Jiang, Yan and Li, Hui-Jun},
  title = {Paired CYP1A2/3A4-HepG2 phenotyping supports machine-learning classification of literature-curated hepatotoxicity categories},
  journal = {Food and Chemical Toxicology},
  year = {2026},
  doi = {10.1016/j.fct.2026.116413}
}
Kostenlos starten →