bibliography.bib

@article{Dodd1989,
 ISSN = {00143820, 15585646},
 URL = {http://www.jstor.org/stable/2409365},
 author = {Diane M. B. Dodd},
 journal = {Evolution},
 number = {6},
 pages = {1308--1311},
 publisher = {[Society for the Study of Evolution, Wiley]},
 title = {Reproductive Isolation as a Consequence of Adaptive Divergence in Drosophila pseudoobscura},
 volume = {43},
 year = {1989}
}

@article{Jiang2016,
author = {Jiang, Yuxiang and Oron, Tal Ronnen and Clark, Wyatt T. and Bankapur, Asma R. and D'Andrea, Daniel and Lepore, Rosalba and Funk, Christopher S. and Kahanda, Indika and Verspoor, Karin M. and Ben-Hur, Asa and Koo, Da Chen Emily and Penfold-Brown, Duncan and Shasha, Dennis and Youngs, Noah and Bonneau, Richard and Lin, Alexandra and Sahraeian, Sayed M. E. and Martelli, Pier Luigi and Profiti, Giuseppe and Casadio, Rita and Cao, Renzhi and Zhong, Zhaolong and Cheng, Jianlin and Altenhoff, Adrian and Skunca, Nives and Dessimoz, Christophe and Dogan, Tunca and Hakala, Kai and Kaewphan, Suwisa and Mehryary, Farrokh and Salakoski, Tapio and Ginter, Filip and Fang, Hai and Smithers, Ben and Oates, Matt and Gough, Julian and T{\"{o}}r{\"{o}}nen, Petri and Koskinen, Patrik and Holm, Liisa and Chen, Ching-Tai and Hsu, Wen-Lian and Bryson, Kevin and Cozzetto, Domenico and Minneci, Federico and Jones, David T. and Chapman, Samuel and BKC, Dukka and Khan, Ishita K. and Kihara, Daisuke and Ofer, Dan and Rappoport, Nadav and Stern, Amos and Cibrian-Uhalte, Elena and Denny, Paul and Foulger, Rebecca E. and Hieta, Reija and Legge, Duncan and Lovering, Ruth C. and Magrane, Michele and Melidoni, Anna N. and Mutowo-Meullenet, Prudence and Pichler, Klemens and Shypitsyna, Aleksandra and Li, Biao and Zakeri, Pooya and ElShal, Sarah and Tranchevent, L{\'{e}}on-Charles and Das, Sayoni and Dawson, Natalie L. and Lee, David and Lees, Jonathan G. and Sillitoe, Ian and Bhat, Prajwal and Nepusz, Tam{\'{a}}s and Romero, Alfonso E. and Sasidharan, Rajkumar and Yang, Haixuan and Paccanaro, Alberto and Gillis, Jesse and Sede{\~{n}}o-Cort{\'{e}}s, Adriana E. and Pavlidis, Paul and Feng, Shou and Cejuela, Juan M. and Goldberg, Tatyana and Hamp, Tobias and Richter, Lothar and Salamov, Asaf and Gabaldon, Toni and Marcet-Houben, Marina and Supek, Fran and Gong, Qingtian and Ning, Wei and Zhou, Yuanpeng and Tian, Weidong and Falda, Marco and Fontana, Paolo and Lavezzo, Enrico and Toppo, Stefano and Ferrari, Carlo and Giollo, Manuel and Piovesan, Damiano and Tosatto, Silvio C.E. and del Pozo, Angela and Fern{\'{a}}ndez, Jos{\'{e}} M. and Maietta, Paolo and Valencia, Alfonso and Tress, Michael L. and Benso, Alfredo and {Di Carlo}, Stefano and Politano, Gianfranco and Savino, Alessandro and Rehman, Hafeez Ur and Re, Matteo and Mesiti, Marco and Valentini, Giorgio and Bargsten, Joachim W. and van Dijk, Aalt D. J. and Gemovic, Branislava and Glisic, Sanja and Perovic, Vladmir and Veljkovic, Veljko and Veljkovic, Nevena and Almeida-e-Silva, Danillo C. and Vencio, Ricardo Z. N. and Sharan, Malvika and Vogel, J{\"{o}}rg and Kansakar, Lakesh and Zhang, Shanshan and Vucetic, Slobodan and Wang, Zheng and Sternberg, Michael J. E. and Wass, Mark N. and Huntley, Rachael P. and Martin, Maria J. and O'Donovan, Claire and Robinson, Peter N. and Moreau, Yves and Tramontano, Anna and Babbitt, Patricia C. and Brenner, Steven E. and Linial, Michal and Orengo, Christine A. and Rost, Burkhard and Greene, Casey S. and Mooney, Sean D. and Friedberg, Iddo and Radivojac, Predrag},
doi = {10.1186/s13059-016-1037-6},
issn = {1474-760X},
journal = {Genome Biology},
month = {dec},
number = {1},
pages = {184},
title = {{An expanded evaluation of protein function prediction methods shows an improvement in accuracy}},
url = {http://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-1037-6},
volume = {17},
year = {2016}
}

@article{Yu2018,
author = {Yu, Chun and Li, Xiao and Yang, Hong and Li, Ying and Xue, Wei and Chen, Yu and Tao, Lin and Zhu, Feng},
doi = {10.3390/ijms19010183},
issn = {1422-0067},
journal = {International Journal of Molecular Sciences},
month = {jan},
number = {1},
pages = {183},
title = {{Assessing the Performances of Protein Function Prediction Algorithms from the Perspectives of Identification Accuracy and False Discovery Rate}},
url = {http://www.mdpi.com/1422-0067/19/1/183},
volume = {19},
year = {2018}
}

@article{Oliver2000,
author = {Oliver, Stephen},
doi = {10.1038/35001165},
file = {:home/george/.local/share/data/Mendeley Ltd./Mendeley Desktop/Downloaded/Oliver - 2000 - Guilt-by-association goes global.pdf:pdf},
issn = {0028-0836},
journal = {Nature},
month = {feb},
number = {6770},
pages = {601--602},
title = {{Guilt-by-association goes global}},
url = {http://www.nature.com/articles/35001165},
volume = {403},
year = {2000}
}

@article{Piovesan2015,
author = {Piovesan, Damiano and Giollo, Manuel and Leonardi, Emanuela and Ferrari, Carlo and Tosatto, Silvio C.E.},
doi = {10.1093/nar/gkv523},
issn = {0305-1048},
journal = {Nucleic Acids Research},
month = {jul},
number = {W1},
pages = {W134--W140},
title = {{INGA: protein function prediction combining interaction networks, domain assignments and sequence similarity}},
url = {https://academic.oup.com/nar/article-lookup/doi/10.1093/nar/gkv523},
volume = {43},
year = {2015}
}

@article{Engelhardt2011,
abstract = {The Statistical Inference of Function Through Evolutionary Relationships (SIFTER) framework uses a statistical graphical model that applies phylogenetic principles to automate precise protein function prediction. Here we present a revised approach (SIFTER version 2.0) that enables annotations on a genomic scale. SIFTER 2.0 produces equivalently precise predictions compared to the earlier version on a carefully studied family and on a collection of 100 protein families. We have added an approximation method to SIFTER 2.0 and show a 500-fold improvement in speed with minimal impact on prediction results in the functionally diverse sulfotransferase protein family. On the Nudix protein family, previously inaccessible to the SIFTER framework because of the 66 possible molecular functions, SIFTER achieved 47.4{\%} accuracy on experimental data (where BLAST achieved 34.0{\%}). Finally, we used SIFTER to annotate all of the Schizosaccharomyces pombe proteins with experimental functional characterizations, based on annotations from proteins in 46 fungal genomes. SIFTER precisely predicted molecular function for 45.5{\%} of the characterized proteins in this genome, as compared with four current function prediction methods that precisely predicted function for 62.6{\%}, 30.6{\%}, 6.0{\%}, and 5.7{\%} of these proteins. We use both precision-recall curves and ROC analyses to compare these genome-scale predictions across the different methods and to assess performance on different types of applications. SIFTER 2.0 is capable of predicting protein molecular function for large and functionally diverse protein families using an approximate statistical model, enabling phylogenetics-based protein function prediction for genome-wide analyses. The code for SIFTER and protein family data are available at http://sifter.berkeley.edu.},
author = {Engelhardt, Barbara E. and Jordan, Michael I. and Srouji, John R. and Brenner, Steven E.},
doi = {10.1101/gr.104687.109},
isbn = {1549-5469},
issn = {10889051},
journal = {Genome Research},
number = {11},
pages = {1969--1980},
pmid = {21784873},
title = {{Genome-scale phylogenetic function annotation of large and diverse protein families}},
volume = {21},
year = {2011}
}

@article{Engelhardt2005,
abstract = {We present a statistical graphical model to infer specific molecular function for unannotated protein sequences using homology. Based on phylogenomic principles, SIFTER (Statistical Inference of Function Through Evolutionary Relationships) accurately predicts molecular function for members of a protein family given a reconciled phylogeny and available function annotations, even when the data are sparse or noisy. Our method produced specific and consistent molecular function predictions across 100 Pfam families in comparison to the Gene Ontology annotation database, BLAST, GOtcha, and Orthostrapper. We performed a more detailed exploration of functional predictions on the adenosine-5′-monophosphate/adenosine deaminase family and the lactate/malate dehydrogenase family, in the former case comparing the predictions against a gold standard set of published functional characterizations. Given function annotations for 3{\%} of the proteins in the deaminase family, SIFTER achieves 96{\%} accuracy in predicting molecular function for experimentally characterized proteins as reported in the literature. The accuracy of SIFTER on this dataset is a significant improvement over other currently available methods such as BLAST (75{\%}), GeneQuiz (64{\%}), GOtcha (89{\%}), and Orthostrapper (11{\%}). We also experimentally characterized the adenosine deaminase from Plasmodium falciparum, confirming SIFTER's prediction. The results illustrate the predictive power of exploiting a statistical model of function evolution in phylogenomic problems. A software implementation of SIFTER is available from the authors.},
author = {Engelhardt, Barbara E and Jordan, Michael I and Muratore, Kathryn E and Brenner, Steven E},
doi = {10.1371/journal.pcbi.0010045},
journal = {PLOS Computational Biology},
number = {5},
publisher = {Public Library of Science},
title = {{Protein Molecular Function Prediction by Bayesian Phylogenomics}},
url = {https://doi.org/10.1371/journal.pcbi.0010045},
volume = {1},
year = {2005}
}

@article{Pesaranghader2016,
author = {Pesaranghader, Ahmad and Matwin, Stan and Sokolova, Marina and Beiko, Robert G.},
doi = {10.1093/bioinformatics/btv755},
issn = {1367-4803},
journal = {Bioinformatics},
month = {may},
number = {9},
pages = {1380--1387},
title = {{simDEF: definition-based semantic similarity measure of gene ontology terms for functional similarity analysis of genes}},
url = {https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btv755},
volume = {32},
year = {2016}
}