@article{Kolmogorov01112018, author = {Kolmogorov, Mikhail and Armstrong, Joel and Raney, Brian J. and Streeter, Ian and Dunn, Matthew and Yang, Fengtang and Odom, Duncan and Flicek, Paul and Keane, Thomas M. and Thybert, David and Paten, Benedict and Pham, Son}, title = {Chromosome assembly of large and complex genomes using multiple references}, volume = {28}, number = {11}, pages = {1720-1732}, year = {2018}, doi = {10.1101/gr.236273.118}, abstract ={Despite the rapid development of sequencing technologies, the assembly of mammalian-scale genomes into complete chromosomes remains one of the most challenging problems in bioinformatics. To help address this difficulty, we developed Ragout 2, a reference-assisted assembly tool that works for large and complex genomes. By taking one or more target assemblies (generated from an NGS assembler) and one or multiple related reference genomes, Ragout 2 infers the evolutionary relationships between the genomes and builds the final assemblies using a genome rearrangement approach. By using Ragout 2, we transformed NGS assemblies of 16 laboratory mouse strains into sets of complete chromosomes, leaving <5% of sequence unlocalized per set. Various benchmarks, including PCR testing and realigning of long Pacific Biosciences (PacBio) reads, suggest only a small number of structural errors in the final assemblies, comparable with direct assembly approaches. We applied Ragout 2 to the Mus caroli and Mus pahari genomes, which exhibit karyotype-scale variations compared with other genomes from the Muridae family. Chromosome painting maps confirmed most large-scale rearrangements that Ragout 2 detected. We applied Ragout 2 to improve draft sequences of three ape genomes that have recently been published. Ragout 2 transformed three sets of contigs (generated using PacBio reads only) into chromosome-scale assemblies with accuracy comparable to chromosome assemblies generated in the original study using BioNano maps, Hi-C, BAC clones, and FISH.}, URL = {http://genome.cshlp.org/content/28/11/1720.abstract}, eprint = {http://genome.cshlp.org/content/28/11/1720.full.pdf+html}, journal = {Genome Research} }