Improving prediction of secondary structure, local backbone angles and solvent accessible surface area of proteins by iterative deep learning

Rhys Heffernan, Kuldip K. Paliwal, James Lyons, Abdollah Dehzangi, Alok K. Sharma, Jihua Wang, Abdul Rahman Sattar, Yuedong Yang, Yaoqi Zhou · 2015

Read Improving prediction of secondary structure, local backbone angles and solvent accessible surface area of proteins by iterative deep learning by Rhys Heffernan, Kuldip K. Paliwal, James Lyons, Abdollah Dehzangi, Alok K. Sharma, Jihua Wang, Abdul Rahman Sattar, Yuedong Yang, Yaoqi Zhou (2015) 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/openalex-w1596947964.txt.

Description

Rhys Heffernan, Yaoqi Zhou, and seven co-authors built this method. Their paper appeared in Scientific Reports in 2015. Predicting protein shape from sequence is a hard problem, they note. Smaller sub-problems can be solved one by one instead. Their tool predicts local shape features of proteins.

The method uses deep learning in three repeated rounds. Each round feeds past predictions back as new inputs. It forecasts backbone angles and surface exposure as well. The abstract reports strong accuracy on a large test set. Its scores beat current leading methods on hard targets. Such forecasts can help judge and rank protein models. The team offers the method for wider research use.

Catalog record

CREATORRhys Heffernan, Kuldip K. Paliwal, James Lyons, Abdollah Dehzangi, Alok K. Sharma, Jihua Wang, Abdul Rahman Sattar, Yuedong Yang, Yaoqi Zhou
YEAR2015
COLLECTIONPAPERS
FORMATTXT
FILE SIZE40 KB
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEOpenAlex / Scientific Reports

Source: https://doi.org/10.1038/srep11476

Browse the full library · About the Tower of Babel