A large-scale evaluation of computational protein function prediction.

Radivojac, Predrag and Clark, Wyatt T. and Oron, Tal Ronnen and Schnoes, Alexandra M. and Wittkop, Tobias and Sokolov, Artem and Graim, Kiley and Funk, Christopher and Verspoor, Karin and Ben-Hur, Asa and Pandey, Gaurav and Yunes, Jeffrey M. and Talwalkar, Ameet S. and Repo, Susanna and Souza, Michael L. and Piovesan, Damiano and Casadio, Rita and Wang, Zheng and Cheng, Jianlin and Fang, Hai and Gough, Julian and Koskinen, Patrik and Törönen, Petri and Nokso-Koivisto, Jussi and Holm, Liisa and Cozzetto, Domenico and Buchan, Daniel W.A. and Bryson, Kevin and Jones, David T. and Limaye, Bhakti and Inamdar, Harshal and Datta, Avik and Manjari, Sunitha K. and Joshi, Rajendra and Chitale, Meghana and Kihara, Daisuke and Lisewski, Andreas M. and Erdin, Serkan and Venner, Eric and Lichtarge, Olivier and Rentzsch, Robert and Yang, Haixuan and Romero, Alfonso E. and Bhat, Prajwal and Paccanaro, Alberto and Hamp, Tobias and Kaßner, Rebecca and Seemayer, Stefan and Vicedo, Esmeralda and Schaefer, Christian and Achten, Dominik and Auer, Florian and Boehm, Ariane and Braun, Tatjana and Hecht, Maximilian and Heron, Mark and Hönigschmid, Peter and Hopf, Thomas A. and Kaufmann, Stefanie and Kiening, Michael and Krompass, Denis and Landerer, Cedric and Mahlich, Yannick and Roos, Manfred and Björne, Jari and Salakoski, Tapio and Wong, Andrew and Shatkay, Hagit and Gatzmann, Fanny and Sommer, Ingolf and Wass, Mark N. and Sternberg, Michael J.E. and Škunca, Nives and Supek, Fran and Bošnjak, Matko and Panov, Panče and Džeroski, Sašo and Šmuc, Tomislav and Kourmpetis, Yiannis A.I. and van Dijk, Aalt D.J. and ter Braak, Cajo J.F. and Zhou, Yuanpeng and Gong, Qingtian and Dong, Xinran and Tian, Weidong and Falda, Marco and Fontana, Paolo and Lavezzo, Enrico and Di Camillo, Barbara and Toppo, Stefano and Lan, Liang and Djuric, Nemanja and Guo, Yuhong and Vucetic, Slobodan and Bairoch, Amos and Linial, Michal and Babbitt, Patricia C. and Brenner, Steven E. and Orengo, Christine and Rost, Burkhard and Mooney, Sean D. and Friedberg, Iddo (2013) A large-scale evaluation of computational protein function prediction. Nature Methods, 10 (3). pp. 221-227. ISSN 1548-7091. (doi:https://doi.org/10.1038/nmeth.2340) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL


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 11 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.

Item Type: Article
Subjects: Q Science
Divisions: Faculties > Sciences > School of Biosciences
Depositing User: Mark Wass
Date Deposited: 06 Jun 2013 13:25 UTC
Last Modified: 06 Jun 2017 11:16 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/34180 (The current URI for this page, for reference purposes)
Wass, Mark N.: https://orcid.org/0000-0001-5428-6479
  • Depositors only (login required):