Precision medicine combines biomedicine and bioinformatics and deploys data-driven machine learning techniques for data analysis. The multi-modal complex medical big data with the intertwined feature relationships need to be tackled using novel statistics methods instead of traditional statistical trials.

Deep learning was once considered a “black box”. However, it works better than simple statistical methods and traditional machine learning. Recently, big data-driven deep learning techniques have developed rapidly and achieved impressive performance in several fields, including imaging, automatic speech recognition, and bioinformatics. Precision medicine is becoming an increasingly important application. In particular, interpretable deep learning neural networks have been well explored recently, showing great potential to provide more insights into the disease mechanisms.

This Special Issue aims to describe the latest deep learning methods and biological and biomedicine applications. We hope that codes from methodology and data from real-world applications can all be presented in this issue. The Issue also aims to guide machine learning researchers to examine more biomedical engineering applications and expand the vision of medical researchers in the field of machine learning. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Methods in multi-modal data integration
• Tool development for bioinformatics analysis
• Latest deep learning algorithms with applications in disease diagnosis and treatment
• Big data analysis techniques for disease diagnosis and treatment
• Parallel computing in biomedicine and bioinformatics
• Reviews or surveys with benchmark datasets in biomedicine
• Advanced deep learning models in health informatics
• Feature representation learning algorithms in disease diagnosis
• Medical image processing with deep learning
• Server and database construction