@article{Earl01122014,
author = {Earl, Dent and Nguyen, Ngan and Hickey, Glenn and Harris, Robert S. and Fitzgerald, Stephen and Beal, Kathryn and Seledtsov, Igor and Molodtsov, Vladimir and Raney, Brian J. and Clawson, Hiram and Kim, Jaebum and Kemena, Carsten and Chang, Jia-Ming and Erb, Ionas and Poliakov, Alexander and Hou, Minmei and Herrero, Javier and Kent, William James and Solovyev, Victor and Darling, Aaron E. and Ma, Jian and Notredame, Cedric and Brudno, Michael and Dubchak, Inna and Haussler, David and Paten, Benedict}, 
title = {Alignathon: a competitive assessment of whole-genome alignment methods},
volume = {24}, 
number = {12}, 
pages = {2077-2089}, 
year = {2014}, 
doi = {10.1101/gr.174920.114}, 
abstract ={Multiple sequence alignments (MSAs) are a prerequisite for a wide variety of evolutionary analyses. Published assessments and benchmark data sets for protein and, to a lesser extent, global nucleotide MSAs are available, but less effort has been made to establish benchmarks in the more general problem of whole-genome alignment (WGA). Using the same model as the successful Assemblathon competitions, we organized a competitive evaluation in which teams submitted their alignments and then assessments were performed collectively after all the submissions were received. Three data sets were used: Two were simulated and based on primate and mammalian phylogenies, and one was comprised of 20 real fly genomes. In total, 35 submissions were assessed, submitted by 10 teams using 12 different alignment pipelines. We found agreement between independent simulation-based and statistical assessments, indicating that there are substantial accuracy differences between contemporary alignment tools. We saw considerable differences in the alignment quality of differently annotated regions and found that few tools aligned the duplications analyzed. We found that many tools worked well at shorter evolutionary distances, but fewer performed competitively at longer distances. We provide all data sets, submissions, and assessment programs for further study and provide, as a resource for future benchmarking, a convenient repository of code and data for reproducing the simulation assessments.}, 
URL = {http://genome.cshlp.org/content/24/12/2077.abstract}, 
eprint = {http://genome.cshlp.org/content/24/12/2077.full.pdf+html}, 
journal = {Genome Research} 
}