TMBquant: an explainable AI-powered caller advancing tumor mutation burden quantification across heterogeneous samples
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf455 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Shenjie Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Respiratory Medicine, The Second Affiliated Hospital of Xi'an Jiaotong University, No. 157, Xiwu Road, Xincheng District, Xi'an 710004,…. Hauptthemen laut MEDLINE: Mutation, Lung Neoplasms, Biomarkers, Tumor, Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Basic Research Program of Shaanxi.
Abstract (Originalsprache)
Accurate tumor mutation burden (TMB) quantification is critical for immunotherapy stratification, yet remains challenging due to variability across sequencing platforms, tumor heterogeneity, and variant calling pipelines. Here, we introduce TMBquant, an explainable AI-powered caller designed to optimize TMB estimation through dynamic feature selection, ensemble learning, and automated strategy adaptation. Built upon the H2O AutoML framework, TMBquant integrates variant features, minimizes classification errors, and enhances both accuracy and stability across diverse datasets. We benchmarked TMBquant against nine widely used variant callers, including traditional tools (e.g. Mutect2, VarScan2, Strelka2) and recent AI-based methods (DeepSomatic, Octopus), using 706 whole-exome sequencing tumor–control pairs. To evaluate clinical relevance, we further assessed TMBquant through survival analyses across immunotherapy-treated cohorts of non–small cell lung cancer (NSCLC), nasopharyngeal carcinoma (NPC), and the two NSCLC subtypes: lung adenocarcinoma and lung squamous cell carcinoma. In each cohort, TMBquant consistently achieved the highest hazard ratios, demonstrating superior patient stratification compared to all other methods. Importantly, TMBquant maintained robust predictive performance across both high-TMB (NSCLC) and low-TMB (NPC) settings, highlighting its generalizability across cancer types with distinct biological characteristics. These findings establish TMBquant as a reliable, reproducible, and clinically actionable tool for precision oncology. The software is open source and freely available at https://github.com/SomaticCaller/SomaticCaller. To enhance reproducibility, we provide detailed usage instructions and representative code snippets for TMBquant in the Methods section (see Code Availability).
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Respiratory Medicine, The Second Affiliated Hospital of Xi'an Jiaotong University, No. 157, Xiwu Road, Xincheng District, Xi'an 710004, China.
- School of Computer Science and Technology, Xi'an Jiaotong University, 28 Xianning West Road, Beilin, Xi'an 710049, China.
- Shaanxi Engineering Research Center of Medical and Health Big Data, Xi'an Jiaotong University, 28 Xianning West Road, Beilin, Xi'an 710049, China.
- Nanjing Geneseeq Technology Inc., 128 Huakang Road, Pukou, Nanjing 211800, China.
- Department of Respiratory Medicine, Tangdu Hospital, The Fourth Military Medical University, 569 Xinsi Road, Baqiao District, Xi'an, Shaanxi 710038, China.
ORCID-Profile: Yang Shao, Jiayin Wang
Förderung
- National Natural Science Foundation of China
- Natural Science Basic Research Program of Shaanxi
Zitieren
APA
Wang, S., Wang, X., Zhu, X., Wang, X., Liu, Y., Zhao, M., Chang, Z., Shao, Y., Zhang, H., Yang, S., & Wang, J. (2025). TMBquant: an explainable AI-powered caller advancing tumor mutation burden quantification across heterogeneous samples. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf455
Vancouver
Wang S, Wang X, Zhu X, Wang X, Liu Y, Zhao M, et al. TMBquant: an explainable AI-powered caller advancing tumor mutation burden quantification across heterogeneous samples. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf455
BibTeX
@article{Wang2025,
author = {Wang, Shenjie and Wang, Xiaonan and Zhu, Xiaoyan and Wang, Xuwen and Liu, Yuqian and Zhao, Minchao and Chang, Zhili and Shao, Yang and Zhang, Haitao and Yang, Shuanying and Wang, Jiayin},
title = {TMBquant: an explainable AI-powered caller advancing tumor mutation burden quantification across heterogeneous samples},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf455}
}
EUVIMED