Machine learning identification of Pseudomonas aeruginosa strains from colony image data.

When grown on agar surfaces, microbes can produce distinct multicellular spatial structures called colonies, which contain characteristic sizes, shapes, edges, textures, and degrees of opacity and color. For over one hundred years, researchers have used these morphology cues to classify bacteria and guide more targeted treatment of pathogens. Advances in genome sequencing technology have revolutionized our ability to classify bacterial isolates and while genomic methods are in the ascendancy, morphological characterization of bacterial species has made a resurgence due to increased computing capacities and widespread application of machine learning tools. In this paper, we revisit the topic of colony morphotype on the within-species scale and apply concepts from image processing, computer vision, and deep learning to a dataset of 69 environmental and clinical Pseudomonas aeruginosa strains. We find that colony morphology and complexity under common laboratory conditions is a robust, repeatable phenotype on the level of individual strains, and therefore forms a potential basis for strain classification. We then use a deep convolutional neural network approach with a combination of data augmentation and transfer learning to overcome the typical data starvation problem in biological applications of deep learning. Using a train/validation/test split, our results achieve an average validation accuracy of 92.9% and an average test accuracy of 90.7% for the classification of individual strains. These results indicate that bacterial strains have characteristic visual 'fingerprints' that can serve as the basis of classification on a sub-species level. Our work illustrates the potential of image-based classification of bacterial pathogens and highlights the potential to use similar approaches to predict medically relevant strain characteristics like antibiotic resistance and virulence from colony data.

A Hyper-Crosslinked Carbohydrate Polymer Scaffold Facilitates Lineage Commitment and Maintains a Reserve Pool of Proliferating Cardiovascular Progenitors.

BACKGROUND: Cardiovascular progenitor cells (CPCs) have been cultured on various scaffolds to resolve the challenge of cell retention after transplantation and to improve functional outcome after cell-based cardiac therapy. Previous studies have reported successful culture of fully differentiated cardiomyocytes on scaffolds of various types, and ongoing efforts are focused on optimizing the mix of cardiomyocytes and endothelial cells as well as on the identification of a source of progenitors capable of reversing cardiovascular damage. A scaffold culture that fosters cell differentiation into cardiomyocytes and endothelial cells while maintaining a progenitor reserve would benefit allogeneic cell transplantation. METHODS: Isl-1 + c-Kit + CPCs were isolated as clonal populations from human and sheep heart tissue. After hyper-crosslinked carbohydrate polymer scaffold culture, cells were assessed for differentiation, intracellular signaling, cell cycling, and growth factor/chemokine expression using real time polymerase chain reaction, flow cytometry, immunohistochemistry, and calcium staining. RESULTS: Insulin-like growth factor 1, hepatocyte growth factor, and stromal cell derived factor 1α paracrine factors were induced, protein kinase B signaling was activated, extracellular signal-regulated kinase phosphorylation was reduced and differentiation into both cardiomyocytes and endothelial cells was induced by scaffold-based cell culture. Interestingly, movement of CPCs out of the G1 phase of the cell cycle and increased expression of pluripotency genes PLOU5F1 (Oct4) and T (Brachyury) within a portion of the cultured population occurred, which suggests the maintenance of a progenitor population. Two-color immunostaining and 3-color fluorescence-activated cell sorting analysis confirmed the presence of both Isl-1 expressing undifferentiated cells and differentiated cells identified by troponin T and von Willebrand factor expression. Ki-67 labeling verified the presence of proliferating cells that remained in situ alongside the differentiated functional derivatives. CONCLUSIONS: Cloned Isl-1 + c-kit + CPCs maintained on a hyper-cross linked polymer scaffold retain dual potential for proliferation and differentiation, providing a scaffold-based stem cell source for transplantation of committed and proliferating cardiovascular progenitors for functional testing in preclinical models of cell-based repair.