We have shown the potential of RS in identifying early transformation changes in oral buccal mucosa, its feasibility in detecting asthma and determining treatment response through serum in asthma McN-A 343 patients, in classifying normal and oral cancer serum and in identifying multidrug resistance HEMADO phenotype in human leukemia and uterine sarcoma cell lines. RS studies related to radiation induced biochemical changes in prostate, lung and breast cancer cell lines irradiated with radiation doses between 15 and 50Gy are reported. These studies were carried out at single doses of radiation that aimed to investigate the in vitro radiation response on human cancer cell lines. On the other hand, we carried out the present study, taking advantage of continuous low dose fractionated irradiation routinely used as standard radiotherapy protocol in clinics for oral cancer treatment. Our aim was to develop in vitro radioresistance character in the cell line over a period of time and then explore the feasibility of Raman spectroscopy to categorize the acquired trait from its parental untreated cells. We have established radioresistant oral cancer sublines of buccal mucosa origin by clinical implementable 2Gy fractionated radiation dose. After establishing the sublines, their radioresistant character was evaluated by clonogenic cell survival assay and Raman spectral profiles were obtained by RS. To the best of our knowledge, we are first to report the utility of RS in acquired radioresistant oral cancer sublines established from parental oral cancer cell line by clinically administered fractionated ionizing radiation. As mentioned above, PCA was used to explore the feasibility of classification among radioresistant 50Gy and 70Gy sublines from the parental cell line. PCA is frequently used method for data compression and visualization to observe the pattern in the data. It is a mathematical analysis by which the features in the whole data set of thousands of points are resolved into a few significant eigenvectors that can express the entire data set with their scores for each spectrum. This can provide imperative clues on biochemical variations among different groups, in our case different classes of macromolecules. Further, the profiles of principal components also known as factor loadings can provide vital clues on biochemical variations among different classes. Loading of factors 1, 2 and 3 that lead to demarcation among groups are presented in Figure-5. Conforming spectral variability as suggested by difference spectra; the loading plots also indicate differences in DNA content, amino acids and protein profiles of parental and radioresistant groups.