UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design
Abstract The 5′ UTR is critical for mRNA stability and translation efficiency in therapeutics. We developed UTR-Insight, a model integrating a pretrained language model with a CNN-Transformer architecture, explaining 89.1% of the mean ribosome load (MRL) variation in random 5′ UTRs and 82.8% in endo...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-02-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12864-025-11269-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863318341746688 |
|---|---|
| author | Saichao Pan Hanyu Wang Hang Zhang Zan Tang Lianqiang Xu Zhixiang Yan Yong Hu |
| author_facet | Saichao Pan Hanyu Wang Hang Zhang Zan Tang Lianqiang Xu Zhixiang Yan Yong Hu |
| author_sort | Saichao Pan |
| collection | DOAJ |
| description | Abstract The 5′ UTR is critical for mRNA stability and translation efficiency in therapeutics. We developed UTR-Insight, a model integrating a pretrained language model with a CNN-Transformer architecture, explaining 89.1% of the mean ribosome load (MRL) variation in random 5′ UTRs and 82.8% in endogenous 5′ UTRs, surpassing existing models. Using UTR-Insight, we performed high-throughput in silico screening of hundreds of thousands of endogenous 5′ UTRs from primates, mice, and viruses. The screened sequences increased protein expression by up to 319% compared to the human α-globin 5′ UTR, and UTR-Insight-designed sequences achieved even greater expression levels than high-performing endogenous 5′ UTRs. |
| format | Article |
| id | doaj-art-ea7aafd767f745159aedd87e137bc984 |
| institution | Kabale University |
| issn | 1471-2164 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj-art-ea7aafd767f745159aedd87e137bc9842025-02-09T12:13:52ZengBMCBMC Genomics1471-21642025-02-0126111510.1186/s12864-025-11269-7UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and designSaichao Pan0Hanyu Wang1Hang Zhang2Zan Tang3Lianqiang Xu4Zhixiang Yan5Yong Hu6Shenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdShenzhen Rhegen Biotechnology Co. LtdAbstract The 5′ UTR is critical for mRNA stability and translation efficiency in therapeutics. We developed UTR-Insight, a model integrating a pretrained language model with a CNN-Transformer architecture, explaining 89.1% of the mean ribosome load (MRL) variation in random 5′ UTRs and 82.8% in endogenous 5′ UTRs, surpassing existing models. Using UTR-Insight, we performed high-throughput in silico screening of hundreds of thousands of endogenous 5′ UTRs from primates, mice, and viruses. The screened sequences increased protein expression by up to 319% compared to the human α-globin 5′ UTR, and UTR-Insight-designed sequences achieved even greater expression levels than high-performing endogenous 5′ UTRs.https://doi.org/10.1186/s12864-025-11269-75′ UTRMean ribosome loadDeep learningmRNA therapeuticsIn silico screening |
| spellingShingle | Saichao Pan Hanyu Wang Hang Zhang Zan Tang Lianqiang Xu Zhixiang Yan Yong Hu UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design BMC Genomics 5′ UTR Mean ribosome load Deep learning mRNA therapeutics In silico screening |
| title | UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design |
| title_full | UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design |
| title_fullStr | UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design |
| title_full_unstemmed | UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design |
| title_short | UTR-Insight: integrating deep learning for efficient 5′ UTR discovery and design |
| title_sort | utr insight integrating deep learning for efficient 5 utr discovery and design |
| topic | 5′ UTR Mean ribosome load Deep learning mRNA therapeutics In silico screening |
| url | https://doi.org/10.1186/s12864-025-11269-7 |
| work_keys_str_mv | AT saichaopan utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT hanyuwang utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT hangzhang utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT zantang utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT lianqiangxu utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT zhixiangyan utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign AT yonghu utrinsightintegratingdeeplearningforefficient5utrdiscoveryanddesign |