With recent increase of biomedical data generated from high-throughput single-cell technologies, there is an inevitable need for machine intelligence methods to address problems in the analysis of single-cell data. Several methods have been used in machine intelligence mainly drawn from machine learning and deep learning to address several tasks pertaining to single-cell data. However, most existing tools in these tasks are far from perfect and mostly deal with second-order tensor data represented as a matrix. Recently, an unsupervised-tensor-based method dealing with high-order tensor data has been utilized to integrate profiles of two-different species and find biologically reliable genes related to brain function and diseases. Such genes could be possibly used as biomarkers in disease identification.
This research topic aims to bring state-of-the-art research contributions in machine intelligence to address new problems and improve over existing tasks using single-cell data. Submitted articles will be evaluated based on their quality and relevance to the research topic.
Accordingly, we welcome machine-intelligence related submissions, but not limited to the following:
· Data-Driven Approaches Based on Tensor Data
· Supervised Tensor Learning
· Semi-Supervised Tensor Learning
· Deep Learning
· Machine Learning
Re-analysis of existing genomic, transcriptomic data which attempts to identify a candidate set of diagnostic or prognostic markers for disease will not be considered for review, unless they are either (1) provided via novel machine intelligence methods or (2) extended to provide meaningful insights into gene/protein function and/or the biology of the subject described. Studies relating to the prediction of clinical outcome require some validation of findings
With recent increase of biomedical data generated from high-throughput single-cell technologies, there is an inevitable need for machine intelligence methods to address problems in the analysis of single-cell data. Several methods have been used in machine intelligence mainly drawn from machine learning and deep learning to address several tasks pertaining to single-cell data. However, most existing tools in these tasks are far from perfect and mostly deal with second-order tensor data represented as a matrix. Recently, an unsupervised-tensor-based method dealing with high-order tensor data has been utilized to integrate profiles of two-different species and find biologically reliable genes related to brain function and diseases. Such genes could be possibly used as biomarkers in disease identification.
This research topic aims to bring state-of-the-art research contributions in machine intelligence to address new problems and improve over existing tasks using single-cell data. Submitted articles will be evaluated based on their quality and relevance to the research topic.
Accordingly, we welcome machine-intelligence related submissions, but not limited to the following:
· Data-Driven Approaches Based on Tensor Data
· Supervised Tensor Learning
· Semi-Supervised Tensor Learning
· Deep Learning
· Machine Learning
Re-analysis of existing genomic, transcriptomic data which attempts to identify a candidate set of diagnostic or prognostic markers for disease will not be considered for review, unless they are either (1) provided via novel machine intelligence methods or (2) extended to provide meaningful insights into gene/protein function and/or the biology of the subject described. Studies relating to the prediction of clinical outcome require some validation of findings