Vladimir Jojic

TL;DR: This article uses topic models to identify characteristic cell types overrepresented in neighborhoods that serve as proxies for microenvironment and applies this method to uncover anatomically known structures in mouse spleen—identifying distinct population of spleen B cells that are defined by their characteristic neighborhoods.

TL;DR: A Poisson-multivariate normal hierarchical model is developed to learn direct interactions from the count-based output of standard metagenomics sequencing experiments, and concludes that this method provides a structured, accurate, and distributionally reasonable way of modeling correlated count based random variables and capturing direct interactions among them.

TL;DR: The results suggest that antigenic motifs that are scarcely represented in human proteins might represent more immunogenic CTL targets not selected against in the host, as sequences devoid of host-like features might afford superior immune reactivity.

TL;DR: The subject invention as discussed by the authors provides systems and methods that facilitate AIDS vaccine cocktail assembly via machine learning algorithms such as a cost function, a greedy algorithm, an expectation-maximization (EM) algorithm, etc.

TL;DR: This paper proposes a framework to automatically identify and classify regions of bacterial colony images and correspond them across different images from different contexts, and demonstrates that this method outperforms other classical methods on segmentation and classification.