Our mission is to accelerate the advent of 4D high-content screening in live tissues to positively influence human health.
To achieve this goal, we integrate 4D microscopy, human organoid biology, and machine learning .
We use self-supervised deep learning to extract information from microscopy data that has so far been inaccessible.
See our latest paper were we used AI to extract the first mitochondria phenotypic atlas.
We investigate the fundamentals of mitochondrial dynamics and the role of mitochondria in neurological diseases in four dimensions (4D). Our goal is to develop a new generation of drugs based on mitochondria.
See our latest paper on 4D mitochondria temporal network tracking: MitoTNT. Further information on MitoTNT.org
We use endogenously GFP/RFP tagged stem cells to grow tissues (organoids) and then image them live with the lattice light-sheet microscope (LLSM). Shown below is a young brain organoid and a polarized intestinal organoid. LLSM imaging is done at superresolution with seconds frame rates. The resulting large datasets (terabytes) are analyzed using our custom analysis software tools such as pyLattice.
J Schöneberg, D Dambournet, T-L Liu, R Forster, D Hockemeyer, E Betzig, D G Drubin (2018) 4D cell biology: big data image analytics and lattice light-sheet imaging reveal dynamics of clathrin-mediated endocytosis in stem cell derived intestinal organoids. Molecular Biology of the Cell, 29(24).
pyLattice is a python library for advanced lattice light-sheet image analysis. Collaborate with us on gitHub and read about how we solve big data analytics challenges when we analyze big LLSM datasets.
J Schöneberg, G Raghupathi, E Betzig, D G Drubin (2019) 3D Deep Convolutional Neural Networks in Lattice Light-Sheet Data Puncta Segmentation. IEEE Proceedings International Conference on Bioinformatics and Biomedicine (BIBM), in press.