Evaluation of DNA "fingerprinting" for predicting the potential of E. coli O157:H7 isolates to cause hemolytic uremic syndrome (HUS).

Escherichia coli O157:H7 has been recognized since 1982 as a serious human pathogen spread by contaminated food and water. Pulsed-field gel electrophoresis has proven useful for identification of specific isolates/strains of this organism. Hemolytic uremic syndrome (HUS), generally occurring in children or the aged, is the most severe sequela associated with E. coli O157:H7 infection. The presently described work was designed to compare the genomic profile of isolates known to have caused HUS with those having had no such involvement. We asked the question: "Can we develop the means to recognize an 'HUS-prone' E. coli isolate and thereby alert medical personnel to the increased risk?" Twenty-two HUS-related and 10 HUS-unrelated E. coli O157:H7 samples were chosen for genomic analysis. Isolates were cultured overnight prior to being embedded in agarose gel plugs. Plugs were digested, using Xbal restriction endonuclease, and subjected to pulsed-field gel electrophoresis (PFGE) for 20 hours. Gels were stained with ethidium bromide, photographed under ultraviolet light, and Southern blotted. Radiolabeled toxin gene probes were used for hybridization assays. The two classes of isolates were compared by optical imaging software. A computer-generated dendrogram, based on restriction profiles, offered strong initial evidence that the HUS sequela may be produced by a particularly virulent and identifiable clone. The predictive value of this finding appears to be substantial.

Escherichia coli O157:H7 restriction pattern recognition by artificial neural network.

An artificial neural network model for the recognition of Escherichia coli O157:H7 restriction patterns was designed. In the training phase, images of two classes of E. coli isolates (O157:H7 and non-O157:H7) were digitized and transmitted to the neural network. The system was then tested for recognition of images not included in the training set. Promising results were achieved with the designed network configuration, providing a basis for further study. This application of a new generation of computation technology serves as an example of its usefulness in microbiology.