Quantification of microbial productivity via multi-angle light scattering and supervised learning

Abstract

This article describes the use of chemometric methods for prediction of biological parameters of cell suspensions on the basis of their light scattering profiles. Laser light is directed into a vial or flow cell containing media from the suspension. The intensity of the scattered light is recorded at 18 angles. Supervised learning methods are then used to calibrate a model relating the parameter of interest to the intensity values. Using such models opens up the possibility of estimating the biological properties of fermentor broths extremely rapidly (typically every 4 sec), and, using the flow cell, without user interaction. Our work has demonstrated the usefulness of this approach for estimation of yeast cell counts over a wide range of values (105–109 cells mL−1), although it was less successful in predicting cell viability in such suspensions. © 1998 John Wiley & Sons, Inc. Biotechnol Bioeng 59:131–143, 1998.

Psychiatric disorders in advanced cancer

“…Traditionally, these methods relied on observable characteristics of the individual colony, such as: Color, shape, and growth rate. Since Wyatt (Wyatt, 1969), light scattering has been widely used to provide fast, accurate, and non‐disruptive interrogation of biological samples (Bronk et al, 1992, 2001; Jones et al, 1998; Kottmeier et al, 2009; Samorski et al, 2005). While these examples mostly dealt with cells in liquid state, our group introduced a new concept of using laser to interrogate the bacterial colonies to generate unique scattering patterns which worked as an individual “fingerprint” for each bacterial kind (Bae et al, 2007, 2009, 2010).…”

On-line monitoring equipment for wastewater treatment processes: state of the art

“…Sample dilution may be necessary at higher concentration (Yano et al, 1993). Recently, Jones et al (1998) were able to measure wider concentrations ranges by combining multiple angle laser light scattering with chemometric techniques.…”

Genomic Computing. Explanatory Analysis of Plant Expression Profiling Data Using Machine Learning

“…(An equivalent procedure can be used, for example, in spectroscopy for high-throughput screening, where the output is continuous and is the concentration of a substance of interest [Gilbert et al, 1997;Taylor et al, 1998b;Woodward et al, 1999].) The special power of GP, which we have found particularly valuable (Gilbert et al, 1997(Gilbert et al, , 1998(Gilbert et al, , 1999Jones et al, 1998;Taylor et al, 1998aTaylor et al, , 1998bGoodacre and Gilbert, 1999;Woodward et al, 1999;Goodacre et al, 2000;Johnson et al, 2000), stems from the fact that both the (potentially small number of) explanatory variables and the functional form of the relationship between them are evolved together. As suggested by a referee, and to avoid confusion, we note that genetic programming differs significantly from methods such as genetic algorithms.…”