DMCA
A large-scale evaluation of computational protein function prediction. (2013)
| Venue: | Nat. Methods |
| Citations: | 31 - 2 self |
BibTeX
@ARTICLE{Radivojac13alarge-scale,
author = {Predrag Radivojac and Wyatt T Clark and Tal Ronnen Oron and Alexandra M Schnoes and Tobias Wittkop and Artem Sokolov and Kiley Graim and Christopher Funk and Karin Verspoor and Asa Ben-Hur and Gaurav Pandey and Jeffrey M Yunes and Ameet S Talwalkar and Susanna Repo and Michael L Souza and Damiano Piovesan and Rita Casadio and Zheng Wang and Jianlin Cheng and Hai Fang and Julian Gough and Patrik Koskinen and Petri Törönen and Jussi Nokso-Koivisto and Liisa Holm and Domenico Cozzetto and Daniel W A Buchan and Kevin Bryson and David T Jones and Bhakti Limaye and Avik Datta and Sunitha K Manjari and Rajendra Joshi and Meghana Chitale and Daisuke Kihara and Andreas M Lisewski and Serkan Erdin and Eric Venner and Olivier Lichtarge and Robert Rentzsch and Haixuan Yang and Alfonso E Romero and Prajwal Bhat and Alberto Paccanaro and Tobias Hamp and Rebecca Kaßner and Stefan Seemayer and Esmeralda Vicedo and Christian Schaefer and Dominik Achten and Florian Auer and Ariane Boehm and Tatjana Braun and Maximilian Hecht and Mark Heron and Peter Hönigschmid and Thomas A Hopf and Stefanie Kaufmann and Michael Kiening and Denis Krompass and Cedric Landerer and Yannick Mahlich and Manfred Roos and Jari Björne and Tapio Salakoski and Andrew Wong and Hagit Shatkay and Fanny Gatzmann and Ingolf Sommer and Mark N Wass and Michael J E Sternberg and Nives Škunca and Fran Supek and Matko Bošnjak and Panče Panov and Sašo Džeroski and Tomislav Šmuc and Yiannis A I Kourmpetis and Aalt D J Van Dijk and Cajo J F Ter Braak and Yuanpeng Zhou and Qingtian Gong and Xinran Dong and Weidong Tian and Marco Falda and Paolo Fontana and Enrico Lavezzo and Barbara Di Camillo and Stefano Toppo and Liang Lan and Nemanja Djuric and Yuhong Guo and Slobodan Vucetic and Amos Bairoch and Michal Linial and Patricia C Babbitt and Steven E Brenner and Christine Orengo and Burkhard Rost and Sean D Mooney},
title = {A large-scale evaluation of computational protein function prediction.},
journal = {Nat. Methods},
year = {2013},
pages = {221--227}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
AnAlysis nAture methods | ADVANCE ONLINE PUBLICATION | Automated annotation of protein function is challenging. As the number of sequenced genomes rapidly grows, the overwhelming majority of protein products can only be annotated computationally. if computational predictions are to be relied upon, it is crucial that the accuracy of these methods be high. here we report the results from the first large-scale community-based critical assessment of protein function annotation (CAFA) experiment. Fifty-four methods representing the state of the art for protein function prediction were evaluated on a target set of 866 proteins from organisms. two findings stand out: (i) today's best protein function prediction algorithms substantially outperform widely used first-generation methods, with large gains on all types of targets; and (ii) although the top methods perform well enough to guide experiments, there is considerable need for improvement of currently available tools. The accurate annotation of protein function is key to understanding life at the molecular level and has great biomedical and pharmaceutical implications. However, with its inherent difficulty and expense, experimental characterization of function cannot scale up to accommodate the vast amount of sequence data already available 1 . The computational annotation of protein function has therefore emerged as a problem at the forefront of computational and molecular biology. Many solutions have been proposed in the last four decades 2-10 , yet the task of computational functional inference in a laboratory often relies on traditional approaches such as identifying domains or finding Basic Local Alignment Search Tool (BLAST) 11 hits among proteins with experimentally determined function. Recently, the availability of genomic-level sequence information for thousands of species, coupled with massive high-throughput experimental data, has created new opportunities for function prediction. A large number of methods have been proposed to exploit these data, including function prediction from amino acid sequence
