MHTAPred-SS: A Highly Targeted Autoencoder-Driven Deep Multi-Task Learning Framework for Accurate Protein Secondary Structure Prediction
Runqiu Feng, Xun Wang, Zhijun Xia, Tongyu Han, Hanyu Wang, Wenqian Yu · 2024
Read MHTAPred-SS: A Highly Targeted Autoencoder-Driven Deep Multi-Task Learning Framework for Accurate Protein Secondary Structure Prediction by Runqiu Feng, Xun Wang, Zhijun Xia, Tongyu Han, Hanyu Wang, Wenqian Yu (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-11677681.txt.
Description
Runqiu Feng and co-authors present a deep learning framework that predicts the local shape of proteins. Their 2024 paper tackles secondary structure, the coils and sheets a protein chain forms before folding fully. Accurate shape prediction helps drug work and disease diagnosis.
Older methods lean on alignments of related proteins, which thin out when few relatives exist. Their framework encodes sequences with a targeted autoencoder that does not need such relatives. It blends six feature types, including one from a pre-trained protein language model. A multi-task design, guided by biology, then makes the call. On standard test sets the method set new best scores on several measures. The work aims to keep accuracy high even for orphan proteins.
Catalog record
| CREATOR | Runqiu Feng, Xun Wang, Zhijun Xia, Tongyu Han, Hanyu Wang, Wenqian Yu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 59 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |