Label-Free Identification of Biochemical Footprints of Key Mutations in Acute Myeloid Leukemia Using Raman Spectroscopy

Introduction: With increasing understanding of the complexity and heterogeneity of acute myeloid leukemia (AML), the diagnostic process becomes more complicated and time-consuming. Therefore, there is a need to supplement AML diagnostics with a quick method to identify key, druggable genetic lesions that serve as a target for small molecule drugs. To address this need, we used Raman spectroscopy (RS)-based imaging methods. RS uses non-elastic scattering of laser light on cell biomolecules. When coupled to computational image segmentation and analysis, composition of the analyzed fragment of the cytoplasm can be characterized. In this way, by mapping the focal surface of the cell, we obtain a multidimensional image containing information about the distribution of its biochemical components. In our study, we utilized RS microscopy to investigate how single mutations affect the Raman spectral images of leukemic cells. The primary objective was to determine whether this technique could be utilized to identify mutations in key genes related to leukemia development. Methods: Genetic models of AML were generated by introducing wild-type and mutated forms of three frequently mutated and/or druggable genes (FLT3, IDH1/2, and MLL) into myeloid cell lines (THP1, HEL, HL60). The presence of the desired phenotype was confirmed using flow cytometry, immunoblotting, high-throughput kinase activity assay (Pamgene), and confocal microscopy. For RS experiments, the cells were fixed, and subjected to Raman imaging measurements using the WITec Alpha 300 microscope. Reference or control samples consisted of cells with wild-type genes (WT). The recorded hyperspectral data was subjected to multidimensional chemometric analysis, including k-means cluster analysis (KMCA), principal component analysis (PCA) and partial least squares discriminant analysis (PLS-DA). To validate the findings from the cell models, primary AML cells from 30 patients diagnosed with FLT-3 ITD, MLL or IDH1/2 mutations were examined with RS. Peripheral blood mononuclear cells (PBMC) isolated from healthy donors blood served as reference. Results: The spectral differences between cells with wild-type FLT3 and FLT3/ITD were subtle, yet significant. The results revealed distinct variances in lipid (1440, 1240, 1660, and 2850 cm -1) and hemoprotein content (740-760 cm -1). Additionally, we successfully distinguished cells harboring IDH1/2 and MLL mutations from those with the wild-type genes. In these cases Raman bands corresponding to protein and nucleic acids composition were changed in comparison to control cells. Raman features in PCA loadings were also related to proteins and nucleic acids. Using the PLS-DA method and simple AI model, we built successful algorithm for distinguishing transgenic models carrying mutation from wild-type cells. PCA analysis also enabled us to distinguish AML primary cells from PBMC. Analysis weather primary cells carrying the selected mutations can be distinguished from non-mutated AML cells is concordant with our findings on models, however, it requires further analysis in larger group of patients to increase statistical power of these observations. Conclusions: Collectively, these findings suggest that Raman spectroscopy coupled with appropriate chemometric analysis may serve as rapid, label-free tool for identification of key druggable mutations in AML. Acknowledgements: The studies were performed as a part of the “ Label-free and rapid optical imaging, detection and sorting of leukemia cells” project carried out within the Team-Net programme of the Foundation for Polish Science co-financed by the European Union under the European Regional Development Fund.