ImJoy: an open-source computational platform for the deep learning era

Deep learning methods have shown extraordinary potential for analyzing very diverse biomedical data, but their dissemination beyond developers is hindered by important computational hurdles. We introduce ImJoy ( https://imjoy.io/), a flexible and open-source browser-based platform designed to facilitate widespread reuse of deep learning solutions in biomedical research. We highlight ImJoy's main features and illustrate its functionalities with deep learning plugins for mobile and interactive image analysis and genomics. These and other early advances generate considerable interest and a strong demand by biomedical researchers to apply and adapt deep learning methods to new data sets and questions. However, making full use of recent deep learning approaches faces considerable bottlenecks. A distinctive challenge of machine learning methods arises from their strong reliance on training data. While these tools are useful, they do not allow researchers to retrain models on their own data or on public data sets. Therefore, enabling users to retrain existing models on other data is essential to realizing the full promise of deep learning in biomedical research. Many deep learning approaches provide open-source code, typically written in Python and using libraries such as Tensorflow or Pytorch, which in theory enables retraining.