RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA
One of the most abundant non-canonical bases widely occurring on various RNA molecules is 5-methyluridine (m5U). Recent studies have revealed its influences on the development of breast cancer, systemic lupus erythematosus, and the regulation of stress responses. The accurate identification of m<...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/23/21/13493 |
| _version_ | 1797467869290692608 |
|---|---|
| author | Zhirou Li Jinge Mao Daiyun Huang Bowen Song Jia Meng |
| author_facet | Zhirou Li Jinge Mao Daiyun Huang Bowen Song Jia Meng |
| author_sort | Zhirou Li |
| collection | DOAJ |
| description | One of the most abundant non-canonical bases widely occurring on various RNA molecules is 5-methyluridine (m5U). Recent studies have revealed its influences on the development of breast cancer, systemic lupus erythematosus, and the regulation of stress responses. The accurate identification of m<sup>5</sup>U sites is crucial for understanding their biological functions. We propose RNADSN, the first transfer learning deep neural network that learns common features between tRNA m<sup>5</sup>U and mRNA m<sup>5</sup>U to enhance the prediction of mRNA m<sup>5</sup>U. Without seeing the experimentally detected mRNA m<sup>5</sup>U sites, RNADSN has already outperformed the state-of-the-art method, m5UPred. Using mRNA m<sup>5</sup>U classification as an additional layer of supervision, our model achieved another distinct improvement and presented an average area under the receiver operating characteristic curve (AUC) of 0.9422 and an average precision (AP) of 0.7855. The robust performance of RNADSN was also verified by cross-technical and cross-cellular validation. The interpretation of RNADSN also revealed the sequence motif of common features. Therefore, RNADSN should be a useful tool for studying m<sup>5</sup>U modification. |
| first_indexed | 2024-03-09T18:59:52Z |
| format | Article |
| id | doaj.art-ac5e9ca8cc974aceacb80aa6c92cbdc5 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-09T18:59:52Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-ac5e9ca8cc974aceacb80aa6c92cbdc52023-11-24T05:08:52ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672022-11-0123211349310.3390/ijms232113493RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNAZhirou Li0Jinge Mao1Daiyun Huang2Bowen Song3Jia Meng4School of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaSchool of AI and Advanced Computing, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Biological Sciences, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Biological Sciences, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaDepartment of Biological Sciences, Xi’an Jiaotong-Liverpool University, Suzhou 215123, ChinaOne of the most abundant non-canonical bases widely occurring on various RNA molecules is 5-methyluridine (m5U). Recent studies have revealed its influences on the development of breast cancer, systemic lupus erythematosus, and the regulation of stress responses. The accurate identification of m<sup>5</sup>U sites is crucial for understanding their biological functions. We propose RNADSN, the first transfer learning deep neural network that learns common features between tRNA m<sup>5</sup>U and mRNA m<sup>5</sup>U to enhance the prediction of mRNA m<sup>5</sup>U. Without seeing the experimentally detected mRNA m<sup>5</sup>U sites, RNADSN has already outperformed the state-of-the-art method, m5UPred. Using mRNA m<sup>5</sup>U classification as an additional layer of supervision, our model achieved another distinct improvement and presented an average area under the receiver operating characteristic curve (AUC) of 0.9422 and an average precision (AP) of 0.7855. The robust performance of RNADSN was also verified by cross-technical and cross-cellular validation. The interpretation of RNADSN also revealed the sequence motif of common features. Therefore, RNADSN should be a useful tool for studying m<sup>5</sup>U modification.https://www.mdpi.com/1422-0067/23/21/134935-methyluridinedeep neural networktransfer learningRNA modificationsite prediction |
| spellingShingle | Zhirou Li Jinge Mao Daiyun Huang Bowen Song Jia Meng RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA International Journal of Molecular Sciences 5-methyluridine deep neural network transfer learning RNA modification site prediction |
| title | RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA |
| title_full | RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA |
| title_fullStr | RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA |
| title_full_unstemmed | RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA |
| title_short | RNADSN: Transfer-Learning 5-Methyluridine (m<sup>5</sup>U) Modification on mRNAs from Common Features of tRNA |
| title_sort | rnadsn transfer learning 5 methyluridine m sup 5 sup u modification on mrnas from common features of trna |
| topic | 5-methyluridine deep neural network transfer learning RNA modification site prediction |
| url | https://www.mdpi.com/1422-0067/23/21/13493 |
| work_keys_str_mv | AT zhirouli rnadsntransferlearning5methyluridinemsup5supumodificationonmrnasfromcommonfeaturesoftrna AT jingemao rnadsntransferlearning5methyluridinemsup5supumodificationonmrnasfromcommonfeaturesoftrna AT daiyunhuang rnadsntransferlearning5methyluridinemsup5supumodificationonmrnasfromcommonfeaturesoftrna AT bowensong rnadsntransferlearning5methyluridinemsup5supumodificationonmrnasfromcommonfeaturesoftrna AT jiameng rnadsntransferlearning5methyluridinemsup5supumodificationonmrnasfromcommonfeaturesoftrna |