From Chromatograms to Clinical Decisions: An Artificial Intelligence-Powered Framework for Precision Diagnosis of Maturity-Onset Diabetes of the Young
Journal of Biomedical and Pharmaceutical Research · 16.07.2026 · 15 (4) · 9-14
DOI: 10.32553/33g49966 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biomedical and Pharmaceutical Research, online erschienen am 16.07.2026. Verfasst von Dey Sucharita. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Künstliche Intelligenz in der Pflege, Diabetes mellitus
Abstract (Originalsprache)
Background
Maturity-onset diabetes of the young (MODY) is a monogenic form of diabetes caused by pathogenic variants in genes regulating pancreatic β-cell development and function. Although Sanger sequencing remains the gold standard for validation of genetic variants, manual chromatogram interpretation is labor-intensive, susceptible to observer variability, and time-consuming. Artificial intelligence (AI) has emerged as a promising approach to automate genomic data analysis and improve diagnostic precision.
Objective
This study presents an AI-driven computational framework for automated analysis of Sanger sequencing data to improve the detection, annotation, and pathogenicity assessment of MODY-associated variants.
Methods
An integrated computational workflow was developed for preprocessing Sanger chromatograms, sequence alignment, variant detection, functional annotation, and ACMG-guided variant classification. The framework incorporated deep learning-based signal enhancement, machine learning-assisted variant prioritization, automated quality assessment, and predictive analytics. Five clinically relevant MODY genes (HNF1A, HNF4A, GCK, PDX1, and HNF1B) were included in the analytical pipeline.
Results
The AI-assisted workflow substantially reduced manual interpretation time while improving sequencing quality assessment and variant detection confidence. Automated feature extraction and predictive classification facilitated consistent interpretation of pathogenic and likely pathogenic variants while minimizing subjective bias. Integration of ACMG evidence further enhanced reproducibility and clinical decision-making for personalized diagnosis.
Conclusion
AI-assisted computational analysis of Sanger sequencing data represents a promising strategy for improving molecular diagnosis of MODY. The proposed framework demonstrates the potential of integrating machine learning and computational genomics into routine molecular diagnostics, supporting precision medicine through faster, standardized, and clinically interpretable genetic testing. Keywords: Artificial Intelligence; Computational Genomics; Sanger Sequencing; MODY; Machine Learning; Precision Medicine
Zitieren
APA
Sucharita, D. (2026). From Chromatograms to Clinical Decisions: An Artificial Intelligence-Powered Framework for Precision Diagnosis of Maturity-Onset Diabetes of the Young. Journal of Biomedical and Pharmaceutical Research, 15(4), 9-14. https://doi.org/10.32553/33g49966
Vancouver
Sucharita D. From Chromatograms to Clinical Decisions: An Artificial Intelligence-Powered Framework for Precision Diagnosis of Maturity-Onset Diabetes of the Young. Journal of Biomedical and Pharmaceutical Research. 2026;15(4):9-14. doi:10.32553/33g49966
BibTeX
@article{Sucharita2026,
author = {Sucharita, Dey},
title = {From Chromatograms to Clinical Decisions: An Artificial Intelligence-Powered Framework for Precision Diagnosis of Maturity-Onset Diabetes of the Young},
journal = {Journal of Biomedical and Pharmaceutical Research},
year = {2026},
volume = {15},
number = {4},
pages = {9--14},
doi = {10.32553/33g49966}
}
EUVIMED