Abstract
Although significant advances in understanding the molecular drivers of acquired and inherited radiosensitivity have occurred in recent decades, a single analytical method which can detect and classify radiosensitivity remains elusive. Raman microspectroscopy has demonstrated capabilities in the objective classification of various diseases, and more recently in the detection and modelling of radiobiological effect. In this study, Raman spectroscopy is presented as a potential tool for the detection of radiosensitivity subpopulations represented by four lymphoblastoid cell lines derived from individuals with ataxia telangiectasia (2 lines), non-Hodgkins lymphoma, and Turner's syndrome. These are classified with respect to a population with mixed radiosensitivity, represented by lymphocytes drawn from both healthy controls, and prostate cancer patients. Raman spectroscopic measurements were made ex-vivo after exposure to X-ray doses of 0 Gy, 50 mGy and 500 mGy, in parallel to radiation-induced G2 chromosomal radiosensitivity scores, for all samples. Support vector machine models developed on the basis of the spectral data were capable of discrimination of radiosensitive populations before and after irradiation, with superior discrimination when spectra were subjected to a non-linear dimensionality reduction (UMAP) as opposed to a linear (PCA) approach. Models developed on spectral data acquired on samples irradiated in-vitro with a dose of 0Gy were found to provide the highest level of performance in discriminating between classes, with performances of F1 = 0.92 ± 0.06 achieved on a held-out test set. Overall, this study suggests that Raman spectroscopy may have potential as a tool for the detection of intrinsic radiosensitivity using liquid biopsies.