Main Menu (Mobile)- Block

Main Menu - Block

Turaga Lab

janelia7_blocks-janelia7_secondary_menu | block
More in this Lab Landing Page
custom_misc-custom_misc_lab_updates | block

Lab Updates

08/27/19 | Ashok Litwin-Kumar and Srini wrote a review on contraining models of neural computation using connectomic data.
07/08/19 | New paper on using 3D U-Nets, structured loss function, and agglomeration, for segmenting neurons from electron microscopic volumes is published! A fun collaboration with Jan Funke and Stephan Saalfeld.
09/13/17 | Three Turaga lab papers accepted at NIPS 2017! Spike inference, spike and connectivity inference, and really large scale statistical models of neural activity.
09/13/17 | DeepSpike (supervised) is one of 6 winners of the SpikeFinder challenge. Congrats Artur! Code and paper coming soon. SpikeFinder preprint.
node:field_content_header | entity_field
Our Research
node:body | entity_field

Recent technological advances in light and electron microscopy, optogenetics, single cell RNA sequencing, and more allow us to measure and perturb neural networks in unprecedented detail. These new data can be used understand how the structure of a neural circuit gives rise to its function -- how networks of neurons are connected, how cells are organized into cell types, and what activity and computation they produce. Our lab develops machine learning algorithms to map neural connectivity, and statistical models to characterize neural activity and to relate activity to connectivity. Projects currently underway include:

  • Using deep neural networks and variational autoencoders to predict the spiking activity of neurons, infer their connectivity in vivo, and understand how neurons integrate their synaptic inputs.
  • Building statistical models of neural activity and connectivity.
  • Connectome driven computational models of neural circuits to understand their function.
  • Discovering cell types and their basis, from single cell RNA sequencing data.

We have also been developing new computational microscopy techniques based on differentiable wave optical models of programmable microscopes, and deep neural networks. Projects in this space include:

  • New methods for light field microscopy.
  • Deep learning and variational autoencoder based algorithms for single molecule localization microscopy.

Finally, we have recently started building machine learning models for in silico protein engineering, starting with calcium indicators.

Check out some of our lab's collaborative work on GitHub.