Location: Plant, Soil and Nutrition ResearchTitle: Deep learning for plant genomics and crop improvement
|WANG, HAI - CHINA AGRICULTURAL UNIVERSITY|
|CIMEN, EMRE - CORNELL UNIVERSITY - NEW YORK|
|SINGH, NISHA - CORNELL UNIVERSITY - NEW YORK|
|Buckler, Edward - Ed|
Submitted to: Current Opinion in Plant Biology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/1/2020
Publication Date: 4/1/2020
Citation: Wang, H., Cimen, E., Singh, N., Buckler IV, E.S. 2020. Deep learning for plant genomics and crop improvement. Current Opinion in Plant Biology. 54:34-41. https://doi.org/10.1016/j.pbi.2019.12.010.
Interpretive Summary: Deep learning is a machine learning model that imitates the working mechanism of the human/animal brain. Deep learning models are relatively new types of models in machine learning, and they achieve state of the art performances in many fields. Although there are successful applications of deep learning in biology, there is still a long way to go in deep learning studies in plant biology. Because there was a gap in the literature, this study aimed to fill this gap with a review paper that presents the authors’ current opinion about deep learning methods in plant biology.
Technical Abstract: Our era has witnessed tremendous advances in plant genomics characterized by an explosion of high-throughput techniques to identify multi-dimensional genome-wide molecular phenotypes at low costs. More importantly, genomics is not merely acquiring molecular phenotypes, but also leveraging powerful data mining tools to predict and explain them. In recent years, deep learning has been found extremely effective in these tasks. This review highlights two prominent questions at the intersection of genomics and deep learning: 1) how can the flow of information from genomic DNA sequences to molecular phenotypes be modeled; 2) how can we identify functional variants in natural populations using deep learning models? Additionally, we discuss the possibility of unleashing the power of deep learning in synthetic biology to create novel genomic elements with desirable functions. Taken together, we propose a central role of deep learning in future plant genomics research and crop genetic improvement.