Improved protein contact predictions with the MetaPSICOV2 server in CASP12
- Submitting institution
-
Goldsmiths' College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3413
- Type
- D - Journal article
- DOI
-
10.1002/prot.25379
- Title of journal
- Proteins
- Article number
- -
- First page
- 78
- Volume
- 86
- Issue
- S1
- ISSN
- 0887-3585
- Open access status
- Compliant
- Month of publication
- February
- Year of publication
- 2017
- URL
-
http://research.gold.ac.uk/id/eprint/27289/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 23
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper presents a detailed analysis of the performance of the MetaPSICOV2 method in the 12th CASP protein structure prediction community experiment. CASP measures the state of the art in a number of protein structure prediction tasks. The MetaPSICOV2 method was ranked at the top in the Contact Prediction category. This work is part of a paradigm shift in accurate protein contact prediction that is ongoing in the field since 2008. Accurate protein contact prediction has paved the way to significant advances in the accuracy of protein fold prediction, best exemplified by Deepmind’s AlphaFold and the DMPFold software.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -