STUART: Sequence Triage and qUAntification of Read Transcripts for Rapid Ionizing Radiation Exposure Assessment
Abstract
Rapid medical triage following ionizing radiation exposure is critical for emergency management, yet traditional alignment-based bioinformatics are too computationally intensive for mass-casualty scenarios. To address this, we developed STUART (Sequence Triage and qUAntification of Read Transcripts), a mapping-free machine learning framework optimized for mobile biological dosimetry. Inspired by Natural Language Processing (NLP), the system converts raw sequencing reads into k-mer-based numerical profiles, completely bypassing standard alignment. While the architecture is universally applicable to any transcriptomic biomarker, this study focused on radiation exposure using the FDXR gene model. Evaluating Logistic Regression, Random Forest, and XGBoost, advanced signature selection strategies drastically reduced the initial 1024-dimensional feature space by over 98%. Highly robust performance - characterized by near-perfect balanced accuracy and F1-scores within the 95-100% range - was consistently achieved while retaining as few as 17 transcriptomic signatures. Crucially, learning curve analysis demonstrated that complete signal stabilization requires aggregating merely 1000 potentially related reads. Furthermore, external validation on an independent dataset yielded over 99% specificity, confirming the tissue-agnostic nature of the extracted signatures despite different cellular origins. The framework's exceptionally low data threshold enables a real-time, analyze-as-you-sequence diagnostic paradigm compatible with portable sequencers. By minimizing time-to-decision, this decentralized tool bridges the gap between advanced biomarkers and practical on-site biomonitoring, offering a scalable foundation for rapid epidemiological response and routine occupational radiation monitoring.
Related
- Molecular profile of micronutrient-producing microorganisms following Martian mission-relevant ionizing radiation dose rate exposure
- BRN2 preserves the melanocyte lineage following ionizing radiation
- Determinants of bacteriophage Qβ survival under ionizing radiation: roles of hydration, mineral matrices, and viral features
- Multicenter Assessment of Combined Brain and Cervical Spinal cord 3T MP2RAGE T1 Measurements for Reliable Tissue Microstructure Quantification
- Reliability assessment and multicenter clinical application of magnetic resonance methods for knee cartilage quantification
BibTeX
@misc{strzoda2026stuart,
title = {{STUART: Sequence Triage and qUAntification of Read Transcripts for Rapid Ionizing Radiation Exposure Assessment}},
author = {Tomasz Strzoda and Lourdes Cruz-Garcia and Mustafa Najim and Christophe Badie and Joanna Polanska},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.19139},
eprint = {2609.19139},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.19139},
}
RIS
TY - UNPB
TI - STUART: Sequence Triage and qUAntification of Read Transcripts for Rapid Ionizing Radiation Exposure Assessment
AU - Tomasz Strzoda
AU - Lourdes Cruz-Garcia
AU - Mustafa Najim
AU - Christophe Badie
AU - Joanna Polanska
PY - 2026
DA - 2026/09/16
PB - arXiv
DO - 10.48550/arxiv.2609.19139
UR - https://arxiv.org/abs/2609.19139
AB - Rapid medical triage following ionizing radiation exposure is critical for emergency management, yet traditional alignment-based bioinformatics are too computationally intensive for mass-casualty scenarios. To address this, we developed STUART (Sequence Triage and qUAntification of Read Transcripts), a mapping-free machine learning framework optimized for mobile biological dosimetry. Inspired by Natural Language Processing (NLP), the system converts raw sequencing reads into k-mer-based numerical profiles, completely bypassing standard alignment. While the architecture is universally applicable to any transcriptomic biomarker, this study focused on radiation exposure using the FDXR gene model. Evaluating Logistic Regression, Random Forest, and XGBoost, advanced signature selection strategies drastically reduced the initial 1024-dimensional feature space by over 98%. Highly robust performance - characterized by near-perfect balanced accuracy and F1-scores within the 95-100% range - was consistently achieved while retaining as few as 17 transcriptomic signatures. Crucially, learning curve analysis demonstrated that complete signal stabilization requires aggregating merely 1000 potentially related reads. Furthermore, external validation on an independent dataset yielded over 99% specificity, confirming the tissue-agnostic nature of the extracted signatures despite different cellular origins. The framework's exceptionally low data threshold enables a real-time, analyze-as-you-sequence diagnostic paradigm compatible with portable sequencers. By minimizing time-to-decision, this decentralized tool bridges the gap between advanced biomarkers and practical on-site biomonitoring, offering a scalable foundation for rapid epidemiological response and routine occupational radiation monitoring.
ER -