Evaluating Methods for Predicting Protein Functions

International teams assess computational tools to speed up annotations.

The Science

The accurate annotation of protein function from genomic sequences is key to understanding biological processes at the molecular level. However, experimental characterization of protein function is challenging and costly and thus cannot keep pace with the amount of sequencing data being produced.

The Impact

Numerous computational methods to predict protein function have been developed over the past decade to address the growing divide between sequence data and protein functional annotations. Recently, the scientific community came together to provide an unbiased evaluation of these new methods. This effort, named Critical Assessment of Protein Function Annotation (CAFA), consisted of 30 international teams of scientists who evaluated various computational methods on a target set of 866 protein sequences from 11 species, both eukaryotic and prokaryotic.


The organizers gave the research community four months to provide computational predictions of protein function, and then CAFA assessors obtained experimental validations of the targeted protein functions. The results suggest that predicting protein function is difficult because proteins can behave differently depending on environmental factors, such as pH, temperature, or the presence of interacting partners. This was evident across all targets studied, although predictions of molecular function (e.g., protein binding) outperformed predictions of biological processes (e.g., dynamics as a function of temperature). The CAFA community concluded that one way to improve annotation would be to integrate a variety of experimental evidence and data into new computational methods.

Principal Investigator

Predrag Radivojac
Indiana University
[email protected]


The CAFA activity and Automated Function Prediction Special Interest Group meeting at the ISMB 2011 conference were supported jointly by the U.S. National Institutes of Health (grant R13 HG006079-01A1) and the Office of Biological and Environmental Research within the U.S. Department of Energy’s Office of Science (grant DE-SC0006807TDD).


Radivojac, P., W. T. Clark, T. R. Oron, A. M. Schnoes, T. Wittkop, A. Sokolov, K. Graim, C. Funk, K. Verspoor, A. Ben-Hur, G. Pandey, J. M. Yunes, A. S. Talwalkar, S. Repo, M. L. Souza, D. Piovesan, R. Casadio, Z. Wang, J. Cheng, H. Fang, J. Gough, P. Koskinen, P. Törönen, J. Nokso-Koivisto, L. Holm, D. Cozzetto, D. W. A. Buchan, K. Bryson, D. T. Hones, B. Limaye, H. Inamdar, A. Datta, S. K. Manjari, R. Joshi, M. Chitale, D. Kihara, A. M. Lisewski, S. Erdin, E. Venner, O. Lichtarge, R. Rentzsch, H. Yang, A. E. Romero, P. Bhat, A. Paccanaro, T. Hamp, R. Kaßner, S. Seemayer, E. Vicedo, C. Schaefer, D. Achten, F. Auer, A. Boehm, T. Braun, M. Hecht, M. Heron, P. Hönigschmid, T. A. Hopf, S. Kaufmann, M. Kiening, D. Krompass, C. Landerer, Y. Mahlick, M. Roos, J. Björne, T. Salakoski, A. Wong, H. Shatkay, F. Gatzmann, I. Sommer, M. N. Wass, M. J. E. Sternberg, N. Škunca, F. Supek, M. Bošnjak, P. Panov, S. Džeroski, T. Šmuc, Y. A. I. Kourmpetis, A. D. J. van Dijk, C. J. F. ter Braak, Y. Zhou, Q. Gong, X. Dong, W. Tian, M. Falda, P. Fontana, E. Lavezzo, B. Di Camillo, S. Toppo, L. Lan, N, Djuric, Y. Guo, S. Vucetic, A. Bairoch, M. Linial, P. C. Babbitt, S. E. Brenner, C. Orengo, B. Rost, S. D. Mooney, and I. Friedberg. 2013. “A Large-Scale Evaluation of Computational Protein Function Prediction,” Nature Methods 10(3), 221–7. DOI:10.1038/nmeth.2340.