Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue–residue contacts

AUTOR(ES)

Björkholm, Patrik

FONTE

Oxford University Press

RESUMO

Motivation:Correct prediction of residue–residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail.

Documentos Relacionados

• Identifying residue–residue clashes in protein hybrids by using a second-order mean-field approach
• Preparation of name and address data for record linkage using hidden Markov models
• Mining Bacillus subtilis chromosome heterogeneities using hidden Markov models
• Using multi-state markov models to identify credit card risk
• Using 3D Hidden Markov Models that explicitly represent spatial coordinates to model and compare protein structures