Computer vision is a branch of computer science that studies how computers can ‘see’. It is a field that provides significant value for advancements in academia and artificial intelligence by processing images captured with a camera. In other words, the purpose of computer vision is to impart computers with the functions of human eyes and realise ‘vision’ among computers. Deep learning is a method of realising computer vision using image recognition and object detection technologies. Since its emergence, computer vision has evolved rapidly with the development of deep learning and has significantly improved image recognition accuracy. Moreover, an expert system can imitate and reproduce the flow of reasoning and decision making executed in human experts’ brains to derive optimal solutions. Machine learning, including deep learning, has made it possible to ‘acquire the tacit knowledge of experts’, which was not previously achievable with conventional expert systems. Machine learning ‘systematises tacit knowledge’ based on big data and measures phenomena from multiple angles and in large quantities. In this review, we discuss some knowledge-based computer vision techniques that employ deep learning.

Extracellular vesicles (EVs) produced by various immune cells, including B and T cells, macrophages, dendritic cells (DCs), natural killer (NK) cells, and mast cells, mediate intercellular communication and have attracted much attention owing to the novel delivery system of molecules in vivo. DCs are among the most active exosome-secreting cells of the immune system. EVs produced by cancer cells contain cancer antigens; therefore, the development of vaccine therapy that does not require the identification of cancer antigens using cancer-cell-derived EVs may have significant clinical implications. In this review, we summarise the molecular mechanisms underlying EV-based immune responses and their therapeutic effects on tumour vaccination.

Extracellular vesicles (EV) are membrane vesicles surrounded by a lipid bilayer membrane and include microvesicles, apoptotic bodies, exosomes, and exomeres. Exosome-encapsulated microRNAs (miRNAs) released from cancer cells are involved in the proliferation and metastasis of tumor cells via angiogenesis. On the other hand, mesenchymal stem cell (MSC) therapy, which is being employed in regenerative medicine owing to the ability of MSCs to differentiate into various cells, is due to humoral factors, including messenger RNA (mRNA), miRNAs, proteins, and lipids, which are encapsulated in exosomes derived from transplanted cells. New treatments that advocate cell-free therapy using MSC-derived exosomes will significantly improve clinical practice. Therefore, using highly purified exosomes that perform their original functions is desirable. In this review, we summarized advances in the purification, modification, and application of EVs as novel strategies to treat some diseases.

The adoption of “artificial intelligence (AI) in drug discovery”, where AI is used in the process of pharmaceutical research and development, is progressing. By using the ability to process large amounts of data, which is a characteristic of AI, and achieving advanced data analysis and inference, there are benefits such as shortening development time, reducing costs, and reducing the workload of researchers. There are various problems in drug development, but the following two issues are particularly problematic: (1) the yearly increases in development time and cost of drugs and (2) the difficulty in finding highly accurate target genes. Therefore, screening and simulation using AI are expected. Researchers have high demands for data collection and the utilization of infrastructure for AI analysis. In the field of drug discovery, for example, interest in data use increases with the amount of chemical or biological data available. The application of AI in drug discovery is becoming more active due to improvement in computer processing power and the development and spread of machine-learning frameworks, including deep learning. To evaluate performance, various statistical indices have been introduced. However, the factors affected in performance have not been revealed completely. In this study, we summarized and reviewed the applications of deep learning for drug discovery with BigData.

Extracellular vesicles (EVs), including exosomes, mediate intercellular communication by delivering their contents, such as nucleic acids, proteins, and lipids, to distant target cells. EVs play a role in the progression of several diseases. In particular, programmed death-ligand 1 (PD-L1) levels in exosomes are associated with cancer progression. Furthermore, exosomes are being used for new drug-delivery systems by modifying their membrane peptides to promote their intracellular transduction via micropinocytosis. In this review, we aim to show that an efficient drug-delivery system and a useful therapeutic strategy can be established by controlling the molecular docking and intracellular translocation of exosomes. We summarise the mechanisms of molecular docking of exosomes, the biological effects of exosomes transmitted into target cells, and the current state of exosomes as drug delivery systems.

Protein three-dimensional structural analysis using artificial intelligence is attracting attention in various fields, such as the estimation of vaccine structure and stability. In particular, when using the spike protein in vaccines, the major issues in the construction of SARS-CoV-2 vaccines are their weak abilities to attack the virus and elicit immunity for a short period. Structural information about new viruses is essential for understanding their properties and creating effective vaccines. However, determining the structure of a protein through experiments is a lengthy and laborious process. Therefore, a new computational approach accelerated the elucidation process and made predictions more accurate. Using advanced machine learning technology called deep neural networks, it has become possible to predict protein structures directly from protein and gene sequences. We summarize the advances in antiviral therapy with the SARS-CoV-2 vaccine and extracellular vesicles via computational analysis.