|
This research project introduces a Unified Computational Framework to integrate cell morphology with single-cell transcriptomics. The proposal employs deep learning to perform morphometrics, extracting fine-grained, structural features (shape, size, morphology) of individual cochlear cells from immunofluorescent images. This structural information is then unified with corresponding single-cell genomics data, to reveal the molecular identity of the same cell types through their gene expression profiles. The framework's primary goal is to discover novel cell states or subtle cell changes by correlating visual appearance with molecular alterations, ultimately creating a robust, multi-modal "cell fingerprint." This integrative method offers a holistic understanding of heterogeneous cell types in the cochlear, which is also broadly applicable to many other biological systems.
|
Sign in
to view more information about this project.
