DeepASmRNA: Reference-free prediction of alternative splicing events with a scalable and interpretable deep learning model
Lei Cao,
Quanbao Zhang,
Hongtao Song,
Kui Lin,
Erli Pang
Affiliations
Lei Cao
MOE Key Laboratory for Biodiversity Science and Ecological Engineering and Beijing Key Laboratory of Gene Resource and Molecular Development, College of Life Sciences, Beijing Normal University, Beijing 100875, China
Quanbao Zhang
MOE Key Laboratory for Biodiversity Science and Ecological Engineering and Beijing Key Laboratory of Gene Resource and Molecular Development, College of Life Sciences, Beijing Normal University, Beijing 100875, China
Hongtao Song
MOE Key Laboratory for Biodiversity Science and Ecological Engineering and Beijing Key Laboratory of Gene Resource and Molecular Development, College of Life Sciences, Beijing Normal University, Beijing 100875, China
Kui Lin
MOE Key Laboratory for Biodiversity Science and Ecological Engineering and Beijing Key Laboratory of Gene Resource and Molecular Development, College of Life Sciences, Beijing Normal University, Beijing 100875, China
Erli Pang
MOE Key Laboratory for Biodiversity Science and Ecological Engineering and Beijing Key Laboratory of Gene Resource and Molecular Development, College of Life Sciences, Beijing Normal University, Beijing 100875, China; Corresponding author
Summary: Alternative splicing is crucial for a wide range of biological processes. However, limited by the availability of reference genomes, genome-wide patterns of alternative splicing remain unknown in most nonmodel organisms. We present an attention-based convolutional neural network model, DeepASmRNA, for predicting alternative splicing events using only transcriptomic data. DeepASmRNA consists of two parts: identification of alternatively spliced transcripts and classification of alternative splicing events, which outperformed the state-of-the-art method, AStrap, and other deep learning models. Then, we utilize transfer learning to increase the performance in species with limited training data and use an interpretation method to decipher splicing codes. Finally, applying Amborella, DeepASmRNA can identify more AS events than AStrap while maintaining the same level of precision, suggesting that DeepASmRNA has superior sensitivity to identify alternative splicing events. In summary, DeepASmRNA is scalable and interpretable for detecting genome-wide patterns of alternative splicing in species without a reference genome.
