20. Automated detection of multi-class membrane proteins in cryo-ET

 

Tingying Peng

 Our group’s goal to create new AI methods to help life scientists and pathologists to analyse microscopic images more quantitatively and efficiently, allowing them to extract more knowledge.

What is the data science project’s research question?  Developing deep learning-based particle detection algorithm for Cryo-ET to allow for a more efficient down-stream analysis

What data will be worked on?  Cryo-electron tomography (cryo-ET)

What tasks will this project involve?  Extend the current deep-learning based method for particle detection from single class into multi-classes

What makes this project interesting to work on?    Cryo-ET is a revolutionary imaging technique that enables 3D visualization of the native cellular environment. Deep learning-based methods enable an automatic detection and classification of membrane particles from cryo-ET, thus facilitating the investigation of fundamental biological mechanisms in membranes, ranging from protein production in the endoplasmic reticulum, to the bioenergetic reactions in mitochondrial cristae and chloroplast thylakoids.

What is the expected outcome?   Contribution to research paper, Contribution to software development

What infrastructure, programs and tools will be used? Can they be used remotely?    Python, Pytorch, Matlab and can be used remotely

What skills are necessary for this project?   Deep learning

Is the data open source?  Currently the data is till in house and will be made to public later

Interested candidates should be at Phd level. Tingying Peng is looking for 1 visiting scientist, working on the project together with the team.