Supervised learning methods for the recognition of melanoma cell lines through the analysis of their Raman spectra

• Published in: Journal of biophotonics 2021-03, Vol.14 (3), p.e202000365-n/a
• Main Authors: Baria, Enrico, Cicchi, Riccardo, Malentacchi, Francesca, Mancini, Irene, Pinzani, Pamela, Pazzagli, Marco, Pavone, Francesco S.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Biotechnology; cells; Discriminant analysis; Melanocytes; Melanoma; Mutation; neural network; Neural networks; Raman spectra; Raman spectroscopy; Skin cancer; Spectroscopy; Spectrum analysis; Supervised learning; Tumors
• ISSN: 1864-063X; 1864-0648
• DOI: 10.1002/jbio.202000365

Malignant melanoma is an aggressive form of skin cancer, which develops from the genetic mutations of melanocytes – the most frequent involving BRAF and NRAS genes. The choice and the effectiveness of the therapeutic approach depend on tumour mutation; therefore, its assessment is of paramount importance. Current methods for mutation analysis are destructive and take a long time; instead, Raman spectroscopy could provide a fast, label‐free and non‐destructive alternative. In this study, confocal Raman microscopy has been used for examining three in vitro melanoma cell lines, harbouring different molecular profiles and, in particular, specific BRAF and NRAS driver mutations. The molecular information obtained from Raman spectra has served for developing two alternative classification algorithms based on linear discriminant analysis and artificial neural network. Both methods provide high accuracy (≥90%) in discriminating all cell types, suggesting that Raman spectroscopy may be an effective tool for detecting molecular differences between melanoma mutations. Three in vitro melanoma cell lines – harbouring different BRAF and NRAS driver mutations – has been examined through confocal Raman microscopy in order to investigate their biochemical composition. The recorded Raman spectra has served also for developing two classification algorithms based on Linear Discriminant Analysis and Artificial Neural Network. All cell types have been discriminated with high accuracy, suggesting that Raman spectroscopy may be an effective tool for recognising melanoma mutations.