Skip to content

Low-Dose Understanding, Cellular Insights, and Molecular Discoveries (LUCID)

Description

This is a multidisciplinary research initiative designed to improve mechanistic understanding of cellular responses to low-dose ionizing radiation. It combines controlled biological experiments with advanced data analysis, artificial intelligence, machine learning, and high-performance computing to identify how radiation-induced effects emerge, evolve over time, and connect across molecular, genomic, and cellular scales. Although low-dose exposures are common from natural, occupational, and medical sources, their relationship to long-term biological effects and cancer risk remains difficult to characterize.

LUCID addresses this challenge through an integrated experimental, computational, and data-driven approach. The project brings together curated biological datasets, scientific literature, computational resources, and advanced artificial intelligence and machine-learning methods within a unified research framework. This framework is intended to help researchers discover relationships across diverse data types, identify biomarkers and molecular patterns associated with radiation exposure, and develop predictive models of altered cellular function.

A central goal of LUCID is to make low-dose radiation research more systematic and efficient by partially automating scientific knowledge synthesis and hypothesis generation. Natural-language processing and other AI methods will be used to connect relevant findings, reveal knowledge gaps, recommend potentially valuable collaborations, and prioritize follow-up experiments or analyses. By linking experimental evidence with computational modeling and machine-assisted discovery, LUCID seeks to provide a more mechanistic foundation for understanding low-dose radiation effects and, ultimately, to support improved health-risk prediction and radiation-protection strategies.

References

Publications

  • Jantre, S., Wang, T., Park, G., Chopra, K., Jeon, N., Qian, X., Urban, N. M., & Yoon, B.-J. (2025). Uncertainty-aware adaptation of large language models for protein-protein interaction analysis. In 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 1–7). IEEE. https://doi.org/10.1109/EMBC58623.2025.11253873
  • Merzky, A., Titov, M., Turilli, M., Kilic, O., Wang, T., & Jha, S. (2025). Scalable runtime architecture for data-driven, hybrid HPC and ML workflow applications. In IEEE International Parallel and Distributed Processing Symposium Workshops. IEEE. https://doi.org/10.1109/IPDPSW66978.2025.00150
  • Zhao, G., Yu, X., Titov, M., Weinberg, R., Forrester, S., Wu, M., Zhu, Y., Turilli, M., Jha, S., Schabacker, D. S., Brettin, T., Yoo, S., Qian, X., & Yoon, B.-J. (2026). An integrated and configurable end-to-end pipeline for longitudinal Cell Painting analysis. bioRxiv. https://doi.org/10.64898/2026.02.21.707179
  • Chopra, K., Cucinell, C., Titov, M., Weinberg, R., Forrester, S., Kilic, O. O., Zhu, Y., Turilli, M., Jha, S., Schabacker, D. S., Brettin, T., & Yoon, B.-J. (2026). A spatio-temporal analysis framework for characterizing radiation-induced genomic instability. bioRxiv. https://doi.org/10.64898/2026.02.21.707188
  • Jantre, S., Chopra, K., Zhao, G., Cucinell, C., Weinburg, R., Forrester, S., Brettin, T., Urban, N. M., Qian, X., & Yoon, B.-J. (2026). Interpretable transcriptome-to-phenotype modeling of cell-painting nuclear morphology features from RNA-seq under low-dose radiation exposure. bioRxiv. https://doi.org/10.64898/2026.02.23.707284