EUVIMEDEUVIMED entdecken
Open Access

Galactose-Induced Cataracts in Rats: A Machine Learning Analysis

Ahmed Jasim Mahmood Al-Mashhadani, Qi Gong, Franko Shehaj, Lianhong Zhou

International Journal of Medical Sciences · 2025

DOI: 10.7150/ijms.103892 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Medical Sciences, 2025. Verfasst von Ahmed Jasim Mahmood Al-Mashhadani und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Renmin Hospital of Wuhan University, Wuhan 430060, Hubei Province, P.R. China. Hauptthemen laut MEDLINE: Cataract, Machine Learning, Galactose. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Rat models are widely used to study cataracts due to their cost-effectiveness and prominent physiological and genetic similarities to humans The objective of this study was to identify genes involved in cataractogenesis due to galactose exposure in rats.

Methods

We analyzed four datasets from the Gene Expression Omnibus, including both ex vivo and in vivo models of cataracts in different rat strains.Feature selection tools were used to identify genes potentially relevant in cataract-related gene expression.A decision tree algorithm was implemented, and its predictions were interpreted using SHAP and LIME.To validate gene expression levels, PCR was conducted on six rat lenses cultured in M199 medium and galactose to induce cataract and six lenses cultured in M199 alone.

Results

Using feature selection tools, four key genes-PLAGL2, CMTM7, PCYT1B, and NR1D2-were identified.Only PCYT1B was significantly differentially expressed between the cataract and control groups across analyzed datasets.The model showed strong predictive performance, particularly in ex vivo datasets.SHAP and LIME analyses revealed that CMTM7 had the largest impact on model predictions.PCR results did not show significant differences in gene expression between the cataract and control groups.

Conclusion

The decision tree model trained on an in vivo dataset could predict ex vivo and in vivo cataracts despite no significant gene expression differences found between the cataract and control groups.Given a small number of samples, larger studies are needed to validate our findings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CataractMachine LearningGalactoseAnimalsRatsDisease Models, AnimalHumansLens, CrystallineGene Expression ProfilingTranscription FactorsMaleGene Expression Regulation

Stichwörter der Autor:innen

PCRcataractdecision treeeyerat

Substanzen

GalactoseTranscription Factors

Autor:innen und Institutionen

  • Department of Ophthalmology, Renmin Hospital of Wuhan University, Wuhan 430060, Hubei Province, P.R. China.
  • Department of Orthopedics, Renmin Hospital of Wuhan University, Wuhan 430060, Hubei Province, P.R. China.

Zitieren

APA

Al-Mashhadani, A. J. M., Gong, Q., Shehaj, F., & Zhou, L. (2025). Galactose-Induced Cataracts in Rats: A Machine Learning Analysis. International Journal of Medical Sciences. https://doi.org/10.7150/ijms.103892

Vancouver

Al-Mashhadani AJM, Gong Q, Shehaj F, Zhou L. Galactose-Induced Cataracts in Rats: A Machine Learning Analysis. International Journal of Medical Sciences. 2025. doi:10.7150/ijms.103892

BibTeX
@article{AlMashhadani2025,
  author = {Al-Mashhadani, Ahmed Jasim Mahmood and Gong, Qi and Shehaj, Franko and Zhou, Lianhong},
  title = {Galactose-Induced Cataracts in Rats: A Machine Learning Analysis},
  journal = {International Journal of Medical Sciences},
  year = {2025},
  doi = {10.7150/ijms.103892}
}
Kostenlos starten →