In a time when vast amounts of bioimaging data are produced in labs around the globe every day, effectively extracting salient information from this growing resource is paramount to understanding complex biological questions. In December 2016 the Cell Atlas was released, mapping the subcellular localization of over 12,000 human proteins and counting. As a part of this effort, gamers within EVE online and scientists in the HPA annotated the subcellular localization of each protein. This has created a massive high-quality atlas of microscopy images together with their subcellular protein localization annotations.

Due to the rapid rate of data production however, this manual annotation is impractical as long-term solution and an automated methods are needed. Researchers at the Cell Atlas are already hard at work on this issue, however as the crowd sourcing of annotations was so widely successful within Project Discovery in EVE online, we have decided to partner with organizers at CYTO 2017 conference to create an open challenge to anyone interested in creating an automated solution for protein localization available here.

In this challenge, you have the opportunity to attempt a series of automated classification tasks for fluorescence microscopy data and present your findings during the final platform session at CYTO 2017. The challenges are staged and while some sub-challenges should be accessible to all, others push the boundaries of what is possible with current technologies in machine learning and image analysis.

Checkout the challenge information here: CYTO 2017 Image Analysis Challenge

Download the datasets and full data description here

Feel free to email any questions to cytochallenge2017(at)gmail.com, and happy automating!

Devin Sullivan