SPIN2: Predicting sequence profiles from protein structures using deep neural networks
- 25 March 2018
- journal article
- research article
- Published by Wiley in Proteins: Structure, Function, and Bioinformatics
- Vol. 86 (6) , 629-633
Abstract
Designing protein sequences that can fold into a given structure is a well‐known inverse protein‐folding problem. One important characteristic to attain for a protein design program is the ability to recover wild‐type sequences given their native backbone structures. The highest average sequence identity accuracy achieved by current protein‐design programs in this problem is around 30%, achieved by our previous system, SPIN. SPIN is a program that predicts sequences compatible with a provided structure using a neural network with fragment‐based local and energy‐based nonlocal profiles. Our new model, SPIN2, uses a deep neural network and additional structural features to improve on SPIN. SPIN2 achieves over 34% in sequence recovery in 10‐fold cross‐validation and independent tests, a 4% improvement over the previous version. The sequence profiles generated from SPIN2 are expected to be useful for improving existing fold recognition and protein design techniques. SPIN2 is available at http://sparks-lab.org.Keywords
Funding Information
- Australian Research Council (LE150100161)
- National Natural Science Foundation of China (61271378)
This publication has 24 references indexed in Scilit:
- Energy Functions in De Novo Protein Design: Current Challenges and Future ProspectsAnnual Review of Biophysics, 2013
- Increasing Sequence Diversity with Flexible Backbone Protein Design: The Complete Redesign of a Protein Hydrophobic CoreStructure, 2012
- Improving computational protein design by using structure-derived sequence profileProteins: Structure, Function, and Bioinformatics, 2010
- Computational protein design as a tool for fold recognitionProteins: Structure, Function, and Bioinformatics, 2009
- Progress in computational protein designCurrent Opinion in Biotechnology, 2007
- RosettaDesign server for protein designNucleic Acids Research, 2006
- Distance‐scaled, finite ideal‐gas reference state improves structure‐derived potentials of mean force for structure selection and stability predictionProtein Science, 2002
- High-Resolution Protein Design with Backbone FreedomScience, 1998
- Bayesian statistical analysis of protein side‐chain rotamer preferencesProtein Science, 1997
- Principles that Govern the Folding of Protein ChainsScience, 1973