The widespread application of frontier technologies such as artificial intelligence and big data has made the research based on the utilization of biological information increasingly sophisticated, and the value of capitalizing on frontier technologies in medical treatment has increased day by day. For example, the combination of human intelligence and machine intelligence can provide rapid and accurate clinical interpretation of images at the molecular level of health, big data analysis and precision medicine. The in-depth integration of artificial intelligence and biomedical information can even change the future of mankind. At present, deep learning has been widely used in biomedical data analysis, providing a feasible direction for the development of biomedical big data. Deep learning uses its unsupervised learning process and multilayer structure to automatically extract abstract features from complex raw data. When there are multiple data sets in the same research question, deep learning can extract different features for different data sets. If multiple data sets are used at the same time, we can capture the effective common features of the research question. The automatic feature extraction of deep learning has excellent rapid generalization ability, which saves the cost of feature extraction while improving the classification effect, providing a way to break through the bottleneck of big data analysis. Biological data are complex and changeable, with diverse features and high dimensions.

The further development of deep learning in the biological field requires the fusion and full use of multimodal information, the collaborative use of data, images, signals, and electronic records, combined with deep learning technologies dedicated to the biological field, which can not only effectively avoid the defects of single-modal data experiments, but also conduct biological data analysis quickly and efficiently. However, some problems may arise when deep learning is applied to biomedical data analysis. The training process of deep learning is not easy for analysis. It is often challenging to find an explanation for the failure of a model on a certain data set and explain the intermediate process of training for a successfully trained model. In the big data era, many scenarios are still small data, such as personalized medical scenarios and single-cell sequence data. Therefore, the development of deep learning models suitable for small sample learning is also a trend in the future. Biological data are often difficult to label, and deep learning models are currently supervised learning models. For data with less sample labels or inaccurate sample labels, it is also essential to develop deep learning models for weakly supervised learning.

This Special Issue aims at collecting papers concerned with Biological and Medical Data Analysis using Deep Learning. We welcome both original research and review articles.

Potential topics include but are not limited to the following:

• Algorithms, models, software, and tools in Bioinformatics
• Biostatistics and Stochastic Models
• Semi-supervised data labeling
• Biological imaging segmentation and analysis
• Semi-supervised techniques for pseudo label generation
• Using deep learning to enhance biological diagnosis and classification
• Computational evolutionary biology
• Comprehensive data analysis of biological using multimodal deep learning
• Model integration from biological databases
• Multi-modal biological data analysis and mining