Deep Multiple Sequence Alignment Generation
DeepMSA is a composite approach to generate high quality multiple sequence alignment with large alignment depth and diverse sequence sources by merging sequences from whole-genome sequence databases (Uniclust30
) and from metagenome database (Metaclust
). Large-scale benchmark data show that DeepMSA profiles consistently improves contact prediction, secondary structure prediction, and threading over default HHblits or PSI-BLAST profiles.
Online server (view example output)
- Chengxin Zhang, Wei Zheng, S M Mortuza, Yang Li, Yang Zhang
DeepMSA: constructing deep multiple sequence alignment to improve
contact prediction and fold-recognition for distant-homology proteins. Bioinformatics
36: 2105-2112 (2020).