Multi-omics data have revolutionized the human medical research field by integrating multi-dimensional data underlying the development and progression of the disease. With the advancement of computing power and graphic processing technologies, AI techniques are being increasingly utilized to analyze large-scale omics data including high-throughput sequencing data derived from genome, epigenome, transcriptome, proteome, and metabolome. In addition, AI has also been deeply applied in the analysis of medical images such as endoscopic, pathological, and radiological images. AI techniques provide new methods to process images and translate them into quantitative omics data, allowing the identification of microscopic features invisible to human eyes. However, there are still some intractable challenges yet to be addressed in translating AI techniques from bench to bedside. For example, most deep learning-based models suffer from a lack of explainability and interpretability and need a large amount of data for model development. Therefore, there is still a need for further exploration for promoting the clinical translation of AI techniques.
This research topic aims to highlight novel findings of AI application in clinical pan-omics data analysis (genomics, proteomics, metabolomics, transcriptomics, and the integration of their combined use), development of AI-based methods, as well as reviews of the current status and challenges of the application of AI-based methods in omics data management. We welcome Original Research as well as Review articles on the topics including but not limited to the following:
• New machine or deep learning methods for omics data (genome, epigenome, transcriptome, proteome, metabolome, and phenome) analysis
• Application of machine or deep learning methods for sequencing (genome, epigenome, transcriptome, proteome, metabolome, and phenome) data analysis
• Application of machine or deep learning methods for medical imaging (endoscopic, pathological, radiological, and ultrasonic images) data analysis
• New machine or deep learning methods for clinical applications, such as diagnosis, differential diagnosis, prediction of treatment efficacy, and prognosis
• Development of machine or deep learning methods for multi-omics (genome, epigenome, transcriptome, proteome, metabolome, and phenome) data fusion analysis for clinical applications
Multi-omics data have revolutionized the human medical research field by integrating multi-dimensional data underlying the development and progression of the disease. With the advancement of computing power and graphic processing technologies, AI techniques are being increasingly utilized to analyze large-scale omics data including high-throughput sequencing data derived from genome, epigenome, transcriptome, proteome, and metabolome. In addition, AI has also been deeply applied in the analysis of medical images such as endoscopic, pathological, and radiological images. AI techniques provide new methods to process images and translate them into quantitative omics data, allowing the identification of microscopic features invisible to human eyes. However, there are still some intractable challenges yet to be addressed in translating AI techniques from bench to bedside. For example, most deep learning-based models suffer from a lack of explainability and interpretability and need a large amount of data for model development. Therefore, there is still a need for further exploration for promoting the clinical translation of AI techniques.
This research topic aims to highlight novel findings of AI application in clinical pan-omics data analysis (genomics, proteomics, metabolomics, transcriptomics, and the integration of their combined use), development of AI-based methods, as well as reviews of the current status and challenges of the application of AI-based methods in omics data management. We welcome Original Research as well as Review articles on the topics including but not limited to the following:
• New machine or deep learning methods for omics data (genome, epigenome, transcriptome, proteome, metabolome, and phenome) analysis
• Application of machine or deep learning methods for sequencing (genome, epigenome, transcriptome, proteome, metabolome, and phenome) data analysis
• Application of machine or deep learning methods for medical imaging (endoscopic, pathological, radiological, and ultrasonic images) data analysis
• New machine or deep learning methods for clinical applications, such as diagnosis, differential diagnosis, prediction of treatment efficacy, and prognosis
• Development of machine or deep learning methods for multi-omics (genome, epigenome, transcriptome, proteome, metabolome, and phenome) data fusion analysis for clinical applications