Discernable machine learning methods for Raman micro‐spectroscopic stratification of mitoxantrone‐induced drug‐resistant cells in acute myeloid leukemia

• Published in: Journal of Raman Spectroscopy Vol. 55; no. 8; pp. 882 - 890
• Main Authors: Anjikar, Ajinkya, Iwasaki, Keita, Paneerselvam, Rajapandian, Hole, Arti, Chilakapati, Murali Krishna, Noothalapati, Hemanth, Dutt, Shilpee, Yamamoto, Tatsuyuki
• Format: Journal Article
• Language: English; Japanese
• Published: Bognor Regis Wiley 01.08.2024; Wiley Subscription Services, Inc
• Subjects: Acute myeloid leukemia; acute myeloid leukemia (AML); Automation; Cancer; Cancer therapies; cancers; Cell culture; cell discrimination; Diagnosis; Discriminant analysis; Drug resistance; HL60; HL‐60/MX2; Information processing; Learning algorithms; Leukemia; linear discriminant analysis (LDA); logistic regression (LR); Machine learning; Mitoxantrone; principal component analysis (PCA); Principal components analysis; Raman spectroscopy; Spectroscopic analysis; Spectroscopy; Spectrum analysis
• ISSN: 0377-0486; 1097-4555
• DOI: 10.1002/jrs.6680

Drug resistance plays a vital role in both cancer treatment and prognosis. Especially, early insights into such drug‐induced resistance in acute myeloid leukemia (AML) can help to improve treatment plans, reduce costs, and bring overall positive outcomes for patients. Raman spectroscopy provides precise biomolecular information and can provide all these necessities effectively. In this study, we employed machine learning (ML) discrimination of Raman micro‐spectroscopic data of myelocytic leukemia cell line HL‐60 from its drug‐resistant counterpart HL‐60/MX2. Principal component analysis (PCA), linear discriminant analysis (LDA), and logistic regression (LR) methods were evaluated for their ability to identify and discriminate drug resistance in AML cells. Our study demonstrates the power of ML to classify drug‐induced resistance in AML cells utilizing subtle variations in biomolecular information contained in molecular spectroscopic data by obtaining 94.11% and 97.05% classification accuracies by LDA and LR models, respectively. We also showed that the ML methods are discernable. Our findings depict the importance of automation and its optimal usage in cancer study and diagnosis. The results of our study are expected to take ML‐assisted Raman spectroscopy one step closer to making it a generalized tool in medical diagnosis in the future. Acute myeloid leukemia (AML) is a life‐threatening disease with low survival rates. In most cases, disease relapse is observed due to induced drug resistance. Here, we propose a rapid machine learning‐assisted Raman spectroscopy method to discriminate drug‐sensitive AML cell line HL‐60 from drug resistant HL‐60/MX2 cell line which can help to identify development of resistance in early stages. Linear discriminant analysis (LDA) and logistic regression (LR) models were developed for stratification of cellular Raman spectra obtained from these two groups with accuracies over 94%. The misclassified Raman spectra were investigated in detail, and the reasons for misclassification were elucidated at the biomolecular level making the models clearly discernable.