Analytical Chemistry · 2020 · 27 citations · 31 references
Life SciencesBiophysicsCell BiologyCell DifferentiationCellular NeuroscienceStem Cell BiologyEmbryonic Stem CellsNeural Stem CellsPluripotent Stem CellsRaman SpectroscopyStem Cell DifferentiationStem Cell ReprogrammingCell State Transition AnalysisDifferentiation State AnalysisEmbryonic Stem Cell DifferentiationMouse Embryonic Stem CellsRaman Scattering
Monitoring cell-state transition in pluripotent cells is invaluable for application and basic research. In this study, we demonstrate the pertinence of noninvasive, label-free Raman spectroscopy to monitor and characterize the cell-state transition of mouse stem cells undergoing reprogramming. Using an isogenic cell line of mouse stem cells, reprogramming from neuronal cells was performed, and we showcase a comparative analysis of living single-cell spectral data of the original stem cells, their neuronal progenitors, and reprogrammed cells. Neural network, regression models, and ratiometric analyses were used to discriminate the cell states and extract several important biomarkers specific to differentiation or reprogramming. Our results indicated that the Raman spectrum allowed us to build a low-dimensional space allowing us to monitor and characterize the dynamics of cell-state transition at a single-cell level, scattered in heterogeneous populations. The ability of monitoring pluripotency by Raman spectroscopy and distinguishing differences between ES and reprogrammed cells is also discussed.
31
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das et al. · 2017 · 21.6K citations
Takuya Akiba, Shotaro Sano, Toshihiko Yanase et al. · 2019 · 7.4K citations