@article{Earl16092011, author = {Earl, Dent and Bradnam, Keith and St. John, John and Darling, Aaron and Lin, Dawei and Fass, Joseph and Yu, Hung On Ken and Buffalo, Vince and Zerbino, Daniel R. and Diekhans, Mark and Nguyen, Ngan and Ariyaratne, Pramila Nuwantha and Sung, Wing-Kin and Ning, Zemin and Haimel, Matthias and Simpson, Jared T. and Fonseca, Nuno A. and Birol, İnanç and Docking, T. Roderick and Ho, Isaac Y. and Rokhsar, Daniel S. and Chikhi, Rayan and Lavenier, Dominique and Chapuis, Guillaume and Naquin, Delphine and Maillet, Nicolas and Schatz, Michael C. and Kelley, David R. and Phillippy, Adam M. and Koren, Sergey and Yang, Shiaw-Pyng and Wu, Wei and Chou, Wen-Chi and Srivastava, Anuj and Shaw, Timothy I. and Ruby, J. Graham and Skewes-Cox, Peter and Betegon, Miguel and Dimon, Michelle T. and Solovyev, Victor and Seledtsov, Igor and Kosarev, Petr and Vorobyev, Denis and Ramirez-Gonzalez, Ricardo and Leggett, Richard and MacLean, Dan and Xia, Fangfang and Luo, Ruibang and Li, Zhenyu and Xie, Yinlong and Liu, Binghang and Gnerre, Sante and MacCallum, Iain and Przybylski, Dariusz and Ribeiro, Filipe J. and Yin, Shuangye and Sharpe, Ted and Hall, Giles and Kersey, Paul J. and Durbin, Richard and Jackman, Shaun D. and Chapman, Jarrod A. and Huang, Xiaoqiu and DeRisi, Joseph L. and Caccamo, Mario and Li, Yingrui and Jaffe, David B. and Green, Richard E. and Haussler, David and Korf, Ian and Paten, Benedict}, title = {Assemblathon 1: A competitive assessment of de novo short read assembly methods}, year = {2011}, doi = {10.1101/gr.126599.111}, abstract ={Low-cost short read sequencing technology has revolutionized genomics, though it is only just becoming practical for the high-quality de novo assembly of a novel large genome. We describe the Assemblathon 1 competition, which aimed to comprehensively assess the state of the art in de novo assembly methods when applied to current sequencing technologies. In a collaborative effort, teams were asked to assemble a simulated Illumina HiSeq data set of an unknown, simulated diploid genome. A total of 41 assemblies from 17 different groups were received. Novel haplotype aware assessments of coverage, contiguity, structure, base calling, and copy number were made. We establish that within this benchmark: (1) It is possible to assemble the genome to a high level of coverage and accuracy, and that (2) large differences exist between the assemblies, suggesting room for further improvements in current methods. The simulated benchmark, including the correct answer, the assemblies, and the code that was used to evaluate the assemblies is now public and freely available from http://www.assemblathon.org/.}, URL = {http://genome.cshlp.org/content/early/2011/11/02/gr.126599.111.abstract}, eprint = {http://genome.cshlp.org/content/early/2011/11/02/gr.126599.111.full.pdf+html}, journal = {Genome Research} }