Use of a neural net computer system for analysis of flow cytometric data of phytoplankton populations

Abstract

Flow cytometry has been used over the past 5 years to begin detailed exploration of the distribution and abundance of picoplankton in the oceans. Light scattering and fluorescence measurements on individual plankton cells in seawater samples allow construction of population signatures from size and pigment characteristics. The use of "list mode" data has made these studies possible, but on-shore analysis of copious data does not permit on-site reexamination of important or unexpected observations, and overall effort is greatly handicapped by data analysis time.Here we describe the application of neural net computer technology to the analysis of flow cytometry data. Although the data used in this study are from oceanographic research, the results are general and should be directly applicable to flow cytometry data of any sort.Neural net computers are ideally suited to perform the pattern recognition required for the quantitative analysis of flow cytometry data. Rather than being programmed to perform analysis, the neural net computer is "taught" how to analyze the cell populations by presenting examples of inputs and correct results. Once the system is "trained," similar data sets can be analyzed rapidly and objectively, minimizing the need for laborious user interaction. The neural network described here offers the advantages of 1) adaptability to changing conditions and 2) potential realtime analysis. High accuracy and processing speed near that required for real-time classification have been achieved in a software simulation of the neural network on a Macintosh@ SE personal computer. In the past 5 years, the technology of flow cytometry has been assimilated into oceanography from biomedical research, and it shows great promise for contributions in phytoplankton ecology (3,211. These instruments have begun to serve as a new form of microscope in oceanographic research, one that identifies organisms not through pattern recognition of the human eye, but through multiparameter characterization and discell types over vast regions of the oceans (3,4,12,14), to characterize changes in size and fluorescence properties of cells with depth (lo), to distinguish between cell types that cannot be distinguished by any other methods (12,20), and to detect populations of cells too small to be studied microscopically (4). Flow cytometry has also been used to study plankton physiology and ecology in the laboratory. Cell cycle progression and differcrimination according to predesignated objective criteria. This technology has revolutionized the way phytoplankton and particle dynamics at sea are studied and, in turn, has changed our concepts of the processes we are trving to model and understand.

Automated identification and characterisation of microbial populations using flow cytometry: the AIMS project

“…Whereas multivariate statistical approaches have been used (Demers et al 1992;Carr et al 1996), and can be very successful if the appropriate technique can be found, this is often not simple, and invalid assumptions about distributions can cause major problems. Artificial neural networks (ANNs) on the other hand, do not require a-priori knowledge of underlying distributions, once trained they can make identifications in near real-time and have been shown to have considerable potential for identifying phytoplankton from AFC data (e.g., Frankel et al, 1989Frankel et al, , 1996Boddy et al, 1994;Wilkins et al, 1994Wilkins et al, , 1996 and from morphometric data (e.g., Culverhouse et al, 1994Culverhouse et al, , 1996Williams et al, 1994). Species identification is not always possible based on light scatter and fluorescence characteristics, due either to similarities in the optical characteristics between species or to certain species having a wide range of optical characteristics, such as with clumped cells or chains.…”

Bivariate and trivariate analysis in flow cytometry: Phytoplankton size and fluorescence

“…It is important to point out that the subjective nature of choosing n is not a weakness inherent in the curve-fitting method itself. The same considerations apply when one draws bitmaps by inspection or when one establishes training sets for neural networks that perform machine pattern recognition (Frankel et al 1989).…”

“…Recently, the problem of pattern recognition in phytoplankton sizefluorescence signatures has been addressed by neural network computation (Frankel et al 1989).…”

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

“…In conclusion, until and unless mainstream manufacturers provide an integrated solution to the acquisition and COMMUNICATION TO THE EDITOR automated interpretation of flow cytometric, the application of techniques, such as, ANNs will remain rare, as they have been for the last 20 years (9). As such software is unlikely to become commercially available in the short term the flow cytometry community may benefit from investigating further the tools, such as, ratio calculation, that are provided in data acquisition software.…”