Cao L, Zhang Q, Song H, Lin K, Pang E. DeepASmRNA: Reference-free prediction of alternative splicing events with a scalable and interpretable deep learning model.
iScience 2022;
25:105345. [PMID:
36325068 PMCID:
PMC9619290 DOI:
10.1016/j.isci.2022.105345]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Revised: 08/20/2022] [Accepted: 10/11/2022] [Indexed: 11/30/2022] Open
Abstract
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.
DeepASmRNA uses only the transcriptome to predict alternative splicing events
DeepASmRNA identifies adjacent HSPs to greatly improve the recall
DeepASmRNA uses attention-based convolutional neural network to classify AS events
Transfer learning is used to increase the predictive power of a target species
Collapse