Nicholas Hutchins (BLAINEY & LI LABS)

Reconstructing Signaling History and Spatial Organization of Single Cells via Deep Learning

Proper cell-cell communication is the linchpin for the development of multicellular organisms. Mapping these communication networks is crucial for understanding the logic of embryonic development and for directing embryonic stem cells differentiating into desired fates. In the past, cell-cell communication has been primarily mapped through time-consuming animal genetics. Here, by fitting neural network models to scRNA-seq data, we created IRIS (Intracellular Response to Infer Signaling state), a semi-supervised deep learning method for annotating signaling state of individual cells only using its gene expression. We validated that this method recovers existing knowledge in diverse cell types and makes predictions that can be used to improve the signaling conditions for stem cell differentiation protocols.

Christine Wiggins (LAUFFENBURGER LAB)

Elucidating B Lymphocyte Control of Humoral Response: A Systems Biology Approach

While many aspects of antibody functionality are well-studied, questions remain as to how B lymphocyte cell state governs glycosylation-associated antibody functionality. Enhanced understanding of transcriptional regulation of antibody glycosylation may reveal levers through which protective humoral profiles could be induced by appropriate stimuli or perturbations. Here, we present our work towards characterizing an in vitro antigen-specific B cell culture system, including its transcriptional and humoral responses to cytokine perturbations.