TExCNN: Leveraging Pre-Trained Models to Predict Gene Expression from Genomic Sequences
Guohao Dong, Yuqian Wu, Lan Huang, Fei Li, Fengfeng Zhou · 2024
Read TExCNN: Leveraging Pre-Trained Models to Predict Gene Expression from Genomic Sequences by Guohao Dong, Yuqian Wu, Lan Huang, Fei Li, Fengfeng Zhou (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11675716.txt.
Description
Guohao Dong and four co-authors built TExCNN in two thousand twenty-four to predict gene activity from DNA sequence alone. Linking DNA letters to how strongly a gene is used is a core problem in biology. Older deep learning tools used crude word encoding for DNA, which misses patterns hidden in the sequence.
Their tool feeds DNA chunks through pre-trained DNA language models to get rich encodings, then passes them to a convolutional network. It beat the prior best model on average accuracy, and longer DNA stretches helped more. Adding extra biological features improved scores further. The tool can aid studies of gene control without new lab work.
Catalog record
| CREATOR | Guohao Dong, Yuqian Wu, Lan Huang, Fei Li, Fengfeng Zhou |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |