Multivariate unmixing approaches on Raman images of plant cell walls: new insights or overinterpretation of results?
Batirtze Prats-MateuMartin FelhoferAnna de JuanNotburga GierlingerPublished in: Plant methods (2018)
VCA is recommended as a good preliminary approach, since it is fast, does not require setting many input parameters and the endmember spectra result in good approximations of the raw data. Yet the endmember spectra are more correlated and mixed than those retrieved by NMF and MCR-ALS methods. The latter two give the best model statistics (with lower lack of fit in the models), but care has to be taken about overestimating the rank as it can lead to artificial shapes due to peak splitting or inverted bands.
Keyphrases
- escherichia coli
- density functional theory
- healthcare
- single cell
- palliative care
- deep learning
- data analysis
- electronic health record
- cell therapy
- convolutional neural network
- quality improvement
- multidrug resistant
- big data
- optical coherence tomography
- pain management
- amyotrophic lateral sclerosis
- klebsiella pneumoniae
- machine learning
- artificial intelligence
- molecular dynamics
- raman spectroscopy
- cell wall
- label free