Variable selection and multivariate methods for the identification of microorganisms by flow cytometry

Abstract

Background: When exploited fully, flow cytometry can be used to provide multiparametric data for each cell in the sample of interest. While this makes flow cytometry a powerful technique for discriminating between different cell types, the data can be difficult to interpret. Traditionally, dual‐parameter plots are used to visualize flow cytometric data, and for a data set consisting of seven parameters, one should examine 21 of these plots. A more efficient method is to reduce the dimensionality of the data (e.g., using unsupervised methods such as principal components analysis) so that fewer graphs need to be examined, or to use supervised multivariate data analysis methods to give a prediction of the identity of the analyzed particles. Materials and Methods: We collected multiparametric data sets for microbiological samples stained with six cocktails of fluorescent stains. Multivariate data analysis methods were explored as a means of microbial detection and identification. Results: We show that while all cocktails and all methods gave good accuracy of predictions (>94%), careful selection of both the stains and the analysis method could improve this figure (to >99% accuracy), even in a data set that was not used in the formation of the supervised multivariate calibration model. Conclusions: Flow cytometry provides a rapid method of obtaining multiparametric data for distinguishing between microorganisms. Multivariate data analysis methods have an important role to play in extracting the information from the data obtained. Artificial neural networks proved to be the most suitable method of data analysis. Cytometry 35:162–168, 1999. © 1999 Wiley‐Liss, Inc.

Detection of subgroups from flow cytometry measurements of heterotrophic bacterioplankton by image analysis

“…Supervised clustering methods such as artificial neural networks can be superior to unsupervised techniques and have been used successfully for the identification of phytoplankton (10,11) and bacterial groups (12). However, they require a training set with a priori knowledge about the actual group membership of the cells.…”

Using Flow Cytometry to Quantify Microbial Heterogeneity

“…However, while this is advantageous in terms of distinguishing between cell types, the data rapidly become difficult to visualise and advanced data processing techniques are often required to reduce the dimensionality of the data (see e.g. Davey et al, 1999a).…”

“…Nevertheless, even with this more limited approach, multiparametric flow cytometry has been shown to be a very effective means for detecting a given cell type against a background of other biological particles. For example Davey et al (1999a) used cocktails of three fluorescent stains to detect spores of Bacillus globigii in a mixture of other microorganisms. By combining stains with different cellular targets with appropriate multivariate data analysis techniques, the correct identification of >99% of the target organisms was possible.…”

Prospects for the automation of analysis and interpretation of flow cytometric data

“…However, methods, such as, PCA are referred to as "unsupervised" learning methods, because they group individuals on the basis of the overall variance in the measured parameters without any attempt to incorporate prior knowledge. This may lead to clusters that are in fact more difficult to interpret than the raw data (8). In contrast, supervised learning methods take advantage of the fact that the flow cytometer operator usually has some prior knowledge of the identity (e.g., species, physiological status, cell type, etc.)…”

“…Thus, the information from two parameters can essentially be encoded in a single value, the ratio, allowing their display on a 1-D plot or in combination with another parameter (or derived parameter) on a 2-D plot. For example, Figure 1A shows the range of propidium iodide (PI) fluorescence values measured from four different microorganisms acquired using previously reported protocols (8). There was considerable overlap between the organisms and a large degree of intra-species heterogeneity.…”