automatic discovery of cross-family sequence features associated with protein function自动发现cross-family序列与蛋白质功能特性.pdfVIP

BMC Bioinformatics BioMed Central Methodology article Open Access Automatic discovery of cross-family sequence features associated with protein function Markus Brameier†1,2, Josien Haan†1, Andrea Krings 1 and Robert M MacCallum*1,3 Address: 1Stockholm Bioinformatics Center, Stockholm University, 106 91 Stockholm, Sweden, 2Bioinformatics Research Center, University of Aarhus, 8000 Aarhus C, Denmark and 3Division of Cell and Molecular Biology, Imperial College London, London SW7 2AZ, UK Email: Markus Brameier - brameier@birc.au.dk; Josien Haan - josien@sbc.su.se; Andrea Krings - akr@sbc.su.se; Robert M MacCallum* - maccallr@sbc.su.se * Corresponding author †Equal contributors Published: 12 January 2006 Received: 18 August 2005 Accepted: 12 January 2006 BMC Bioinformatics 2006, 7:16 doi:10.1186/1471-2105-7-16 This article is available from: /1471-2105/7/16 © 2006 Brameier et al; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Abstract Background: Methods for predicting protein function directly from amino acid sequences are useful tools in the study of uncharacterised protein families and in comparative genomics. Until now, this problem has been approached using machine learning techniques that attempt to predict membership, or otherwise, to predefined functional categories or sub