Search

In a previous publication, we trained predictive models based on Raman bulk spectra of microorganisms placed on a silicon dioxide protected silver mirror slide to make predictions for new Raman spectra, unknown to the models, of microorganisms placed on a different substrate, namely stainless steel. Now we have combined large sections of this data and trained a convolutional neural network (CNN) to make predictions for single cell Raman spectra. We show that a database based on microbial bulk material is conditionally suited to make predictions for the same species in terms of single cells. Data of 13 different microorganisms (bacteria and yeasts) were used. Two of the 13 species could be identified 90% correctly and five other species 71%–88%. The six remaining species were correctly predicted by only 0%–49%. Especially stronger fluorescence in bulk material compared to single cells but also photodegradation of carotenoids are some effects that can complicate predictions for single cells based on bulk data. The results could be helpful in assessing universal Raman tools or databases.

Numerous publications showing that robust prediction models for microorganisms based on Raman micro-spectroscopy in combination with chemometric methods are feasible, often with very precise predictions. Advances in machine learning and easier accessibility to software make it increasingly easy for users to generate predictive models from complex data. However, the question regarding why those predictions are so accurate receives much less attention. In our work, we use Raman spectroscopic data of fungal spores and carotenoid-containing microorganisms to show that it is often not the position of the peaks or the subtle differences in the band ratios of the spectra, due to small differences in the chemical composition of the organisms, that allow accurate classification. Rather, it can be characteristic effects on the baselines of Raman spectra in biochemically similar microorganisms that can be enhanced by certain data pretreatment methods or even neutral-looking spectral regions can be of great importance for a convolutional neural network. Using a method called Gradient-weighted Class Activation Mapping, we attempt to peer into the black box of convolutional neural networks in microbiological applications and show which Raman spectral regions are responsible for accurate classification.

An easy, inexpensive, and rapid method to identify microorganisms is in great demand in various areas such as medical diagnostics or in the food industry. In our study, we show the development of several predictive models based on Raman spectroscopy combined with support vector machines (SVM) for 21 species of microorganisms. The microorganisms, grown under standardized conditions, were placed on a silver mirror slide to record the data for model development. Additional data was obtained from microorganisms on a polished stainless-steel slide in order to validate the models in general and to assess possible negative influences of the material change on the predictions. The theoretical prediction accuracies for the most accurate models, based on a five-fold cross-validation, are 98.4%. For practical validation, new spectra (from stainless-steel surfaces) have been used, which were not included in the calibration data set. The overall prediction accuracy in practice was about 80% and the inaccurate predictions were only due to a few species. The development of a database provides the basis for further investigations such as the application and extension to single-cell analytics and for the characterization of biofilms.