This Research Topic is part of the Methods in Genetics series.
With the development of single-cell technologies, much sequencing data is available. Machine learning, especially deep learning, has tremendous potential in single-cell sequencing analyses, but numerous challenges and possible new developments remain to be explored.
Though some treatments, such as immune checkpoint blockade, result in durable disease control in a subset of cancer, however, mechanisms driving resistance are poorly understood. Given that single-cell sequencing is suited to investigating cell-type-specific patterns of response to therapy, there is immense potential for further growth and discovery. It is critical to characterize the single-cell transcriptomes of cancer and immune cells and utilize single-cell analyses of patient samples to pinpoint cancer cells of origin and describe immune cells. In similar pursuits, numerous machine learning models were urgently developed to make these predictions. Machine learning methods are important techniques for analyzing single-cell sequencing data and providing some confidence assessments of prediction results, especially in drug response prediction and immune cell description.
This Research Topic welcomes:
• Methods: Describing either new or existing methods that are significantly improved or adapted
• Protocols: Detailed descriptions, including pitfalls and troubleshooting
• Perspective or General Commentaries on methods and protocols relevant for research.
• Reviews and mini-reviews of topical methods and protocols highlighting the important future directions of the field
Potential topics include, but are not limited to:
A. Single-cell immune cell types prediction with machine learning methods
B. Cell-type-specific regulon identification methods
C. Single-cell immune gene and disease relationship prediction
D. Single-cell immune and functional diversity analysis
E. Advanced machine learning methods with the application to single-cell immune
F. Cloud computing and parallel machine learning techniques for single-cell immune and genomics function analysis
This Research Topic is part of the Methods in Genetics series.
With the development of single-cell technologies, much sequencing data is available. Machine learning, especially deep learning, has tremendous potential in single-cell sequencing analyses, but numerous challenges and possible new developments remain to be explored.
Though some treatments, such as immune checkpoint blockade, result in durable disease control in a subset of cancer, however, mechanisms driving resistance are poorly understood. Given that single-cell sequencing is suited to investigating cell-type-specific patterns of response to therapy, there is immense potential for further growth and discovery. It is critical to characterize the single-cell transcriptomes of cancer and immune cells and utilize single-cell analyses of patient samples to pinpoint cancer cells of origin and describe immune cells. In similar pursuits, numerous machine learning models were urgently developed to make these predictions. Machine learning methods are important techniques for analyzing single-cell sequencing data and providing some confidence assessments of prediction results, especially in drug response prediction and immune cell description.
This Research Topic welcomes:
• Methods: Describing either new or existing methods that are significantly improved or adapted
• Protocols: Detailed descriptions, including pitfalls and troubleshooting
• Perspective or General Commentaries on methods and protocols relevant for research.
• Reviews and mini-reviews of topical methods and protocols highlighting the important future directions of the field
Potential topics include, but are not limited to:
A. Single-cell immune cell types prediction with machine learning methods
B. Cell-type-specific regulon identification methods
C. Single-cell immune gene and disease relationship prediction
D. Single-cell immune and functional diversity analysis
E. Advanced machine learning methods with the application to single-cell immune
F. Cloud computing and parallel machine learning techniques for single-cell immune and genomics function analysis