The majority of tools for pathogen sensing and recognition are based on physiological or genetic properties
of microorganisms. However, there is enormous interest in devising label-free and reagentless biosensors that
would operate utilizing the biophysical signatures of samples without the need for labeling and reporting biochemistry.
Optical biosensors are closest to realizing this goal and vibrational spectroscopies are examples of
well-established optical label-free biosensing techniques. A recently introduced forward-scatter phenotyping
(FSP) also belongs to the broad class of optical sensors. However, in contrast to spectroscopies, the remarkable
specificity of FSP derives from the morphological information that bacterial material encodes on a coherent
optical wavefront passing through the colony. The system collects elastically scattered light patterns that, given
a constant environment, are unique to each bacterial species and/or serovar. Both FSP technology and spectroscopies
rely on statistical machine learning to perform recognition and classification. However, the commonly
used methods utilize either simplistic unsupervised learning or traditional supervised techniques that assume
completeness of training libraries. This restrictive assumption is known to be false for real-life conditions, resulting
in unsatisfactory levels of accuracy, and consequently limited overall performance for biodetection and
classification tasks. The presented work demonstrates preliminary studies on the use of FSP system to classify
selected serotypes of non-O157 Shiga toxin-producing E. coli in a nonexhaustive framework, that is, without
full knowledge about all the possible classes that can be encountered. Our study uses a Bayesian approach to
learning with a nonexhaustive training dataset to allow for the automated and distributed detection of unknown
bacterial classes.
|