DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning
Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for pre...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Oxford University Press
2022-06-01
|
| Series: | Genomics, Proteomics & Bioinformatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1672022921000498 |
| _version_ | 1827164871469301760 |
|---|---|
| author | Zhongxiao Li Yisheng Li Bin Zhang Yu Li Yongkang Long Juexiao Zhou Xudong Zou Min Zhang Yuhui Hu Wei Chen Xin Gao |
| author_facet | Zhongxiao Li Yisheng Li Bin Zhang Yu Li Yongkang Long Juexiao Zhou Xudong Zou Min Zhang Yuhui Hu Wei Chen Xin Gao |
| author_sort | Zhongxiao Li |
| collection | DOAJ |
| description | Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for predicting the usage level of alternative PASs in the same gene have been proposed. However, all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account. To address this, here we propose a deep learning architecture, Deep Regulatory Code and Tools for Alternative Polyadenylation (DeeReCT-APA), to quantitatively predict the usage of all alternative PASs of a given gene. To accommodate different genes with potentially different numbers of PASs, DeeReCT-APA treats the problem as a regression task with a variable-length target. Based on a convolutional neural network-long short-term memory (CNN-LSTM) architecture, DeeReCT-APA extracts sequence features with CNN layers, uses bidirectional LSTM to explicitly model the interactions among competing PASs, and outputs percentage scores representing the usage levels of all PASs of a gene. In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene, we show that our method consistently outperforms other existing methods on three different tasks for which they are trained: pairwise comparison task, highest usage prediction task, and ranking task. Finally, we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation. Our code and data are available at https://github.com/lzx325/DeeReCT-APA-repo. |
| first_indexed | 2024-03-08T17:50:30Z |
| format | Article |
| id | doaj.art-d83c89d3b1d44e7ea133380d1a29bd5b |
| institution | Directory Open Access Journal |
| issn | 1672-0229 |
| language | English |
| last_indexed | 2025-03-21T01:23:29Z |
| publishDate | 2022-06-01 |
| publisher | Oxford University Press |
| record_format | Article |
| series | Genomics, Proteomics & Bioinformatics |
| spelling | doaj.art-d83c89d3b1d44e7ea133380d1a29bd5b2024-08-03T01:53:18ZengOxford University PressGenomics, Proteomics & Bioinformatics1672-02292022-06-01203483495DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep LearningZhongxiao Li0Yisheng Li1Bin Zhang2Yu Li3Yongkang Long4Juexiao Zhou5Xudong Zou6Min Zhang7Yuhui Hu8Wei Chen9Xin Gao10King Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal 23955-6900, Saudi ArabiaDepartment of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, ChinaCancer Science Institute of Singapore, Singapore 117599, SingaporeKing Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal 23955-6900, Saudi ArabiaKing Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal 23955-6900, Saudi Arabia; Department of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, ChinaDepartment of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, ChinaDepartment of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, ChinaDepartment of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, ChinaDepartment of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, China; Corresponding authors.Department of Biology, Southern University of Science and Technology (SUSTech), Shenzhen 518055, China; Corresponding authors.King Abdullah University of Science and Technology (KAUST), Computational Bioscience Research Center (CBRC), Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Thuwal 23955-6900, Saudi Arabia; Corresponding authors.Alternative polyadenylation (APA) is a crucial step in post-transcriptional regulation. Previous bioinformatic studies have mainly focused on the recognition of polyadenylation sites (PASs) in a given genomic sequence, which is a binary classification problem. Recently, computational methods for predicting the usage level of alternative PASs in the same gene have been proposed. However, all of them cast the problem as a non-quantitative pairwise comparison task and do not take the competition among multiple PASs into account. To address this, here we propose a deep learning architecture, Deep Regulatory Code and Tools for Alternative Polyadenylation (DeeReCT-APA), to quantitatively predict the usage of all alternative PASs of a given gene. To accommodate different genes with potentially different numbers of PASs, DeeReCT-APA treats the problem as a regression task with a variable-length target. Based on a convolutional neural network-long short-term memory (CNN-LSTM) architecture, DeeReCT-APA extracts sequence features with CNN layers, uses bidirectional LSTM to explicitly model the interactions among competing PASs, and outputs percentage scores representing the usage levels of all PASs of a gene. In addition to the fact that only our method can quantitatively predict the usage of all the PASs within a gene, we show that our method consistently outperforms other existing methods on three different tasks for which they are trained: pairwise comparison task, highest usage prediction task, and ranking task. Finally, we demonstrate that our method can be used to predict the effect of genetic variations on APA patterns and sheds light on future mechanistic understanding in APA regulation. Our code and data are available at https://github.com/lzx325/DeeReCT-APA-repo.http://www.sciencedirect.com/science/article/pii/S1672022921000498PolyadenylationGene regulationSequence analysisDeep learningBioinformatics |
| spellingShingle | Zhongxiao Li Yisheng Li Bin Zhang Yu Li Yongkang Long Juexiao Zhou Xudong Zou Min Zhang Yuhui Hu Wei Chen Xin Gao DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning Genomics, Proteomics & Bioinformatics Polyadenylation Gene regulation Sequence analysis Deep learning Bioinformatics |
| title | DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning |
| title_full | DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning |
| title_fullStr | DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning |
| title_full_unstemmed | DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning |
| title_short | DeeReCT-APA: Prediction of Alternative Polyadenylation Site Usage Through Deep Learning |
| title_sort | deerect apa prediction of alternative polyadenylation site usage through deep learning |
| topic | Polyadenylation Gene regulation Sequence analysis Deep learning Bioinformatics |
| url | http://www.sciencedirect.com/science/article/pii/S1672022921000498 |
| work_keys_str_mv | AT zhongxiaoli deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT yishengli deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT binzhang deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT yuli deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT yongkanglong deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT juexiaozhou deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT xudongzou deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT minzhang deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT yuhuihu deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT weichen deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning AT xingao deerectapapredictionofalternativepolyadenylationsiteusagethroughdeeplearning |