@inproceedings{9226a2bfc4154afcbadeed1b5df02fd9,
title = "An improvement method based on OrthoMCL by adding the domain information",
abstract = "Existing clustering methods have so far not separated paralogs from orthologs effectively. Since proteins evolve with their structural and functional domains as independent units, to achieve a higher level of sensitivity and specificity in assessing the similarity, it is necessary to add the domain information. We presented a method to improve the clustering results of the orthologs and paralogs from multiple species by adding the domain information. First, we do the all-against-all blast between the protein sequences. At the same time, we make the blast between the sequences and Pfam-A database to find which of the sequences share the same domain. Then we use this information as an additional criterion for filtering false relationships in all-against-all BLASTP results, and generate a similarity matrix. Final, the MCL algorithm is applied to group orthologs from multiple species. Our preliminary results show that our method can improve strikingly the precision of sequence clustering.",
keywords = "Clustering, Domain, Ortholog, Paralog, Sequence similarity",
author = "Xinyu Que and Fa Zhang and Shengzhong Feng and Bo Yuan and Zhiyong Liu",
year = "2008",
language = "English",
isbn = "1601320558",
series = "Proceedings of the 2008 International Conference on Bioinformatics and Computational Biology, BIOCOMP 2008",
pages = "418--423",
booktitle = "Proceedings of the 2008 International Conference on Bioinformatics and Computational Biology, BIOCOMP 2008",
note = "2008 International Conference on Bioinformatics and Computational Biology, BIOCOMP 2008 ; Conference date: 14-07-2008 Through 17-07-2008",
}