Machine Learning Techniques for High-Throughput Structure and Function Analysis for Proteomics and Genomics

摘要

With the development of high-throughput sequencing techniques, more and more sequencing data is available, such as genomics reads, transcriptomes data, and proteomics sequences. It is critical to use these data to uncover their structure and functions. Genomics function can also be identified from the classification results, such as motif identification, regulatory regions detection, and even epigenomics and disease relationship prediction.Machine learning methods are important techniques for this task, especially for the ensemble learning, large scale data process, various kernel design, and imbalanced classification methods.