@article {Chin056887, author = {Chen-Shan Chin and Paul Peluso and Fritz J. Sedlazeck and Maria Nattestad and Gregory T. Concepcion and Alicia Clum and Christopher Dunn and Ronan O{\textquoteright}Malley and Rosa Figueroa-Balderas and Abraham Morales-Cruz and Grant R. Cramer and Massimo Delledonne and Chongyuan Luo and Joseph R. Ecker and Dario Cantu and David R. Rank and Michael C. Schatz}, title = {Phased Diploid Genome Assembly with Single Molecule Real-Time Sequencing}, elocation-id = {056887}, year = {2016}, doi = {10.1101/056887}, publisher = {Cold Spring Harbor Laboratory}, abstract = {While genome assembly projects have been successful in a number of haploid or inbred species, one of the current main challenges is assembling non-inbred or rearranged heterozygous genomes. To address this critical need, we introduce the open-source FALCON and FALCON-Unzip algorithms (https://github.com/PacificBiosciences/FALCON/) to assemble Single Molecule Real-Time (SMRT{\textregistered}) Sequencing data into highly accurate, contiguous, and correctly phased diploid genomes. We demonstrate the quality of this approach by assembling new reference sequences for three heterozygous samples, including an F1 hybrid of the model species Arabidopsis thaliana, the widely cultivated V. vinifera cv. Cabernet Sauvignon, and the coral fungus Clavicorona pyxidata that have challenged short-read assembly approaches. The FALCON-based assemblies were substantially more contiguous and complete than alternate short or long-read approaches. The phased diploid assembly enabled the study of haplotype structures and heterozygosities between the homologous chromosomes, including identifying widespread heterozygous structural variations within the coding sequences.}, URL = {https://www.biorxiv.org/content/early/2016/06/03/056887}, eprint = {https://www.biorxiv.org/content/early/2016/06/03/056887.full.pdf}, journal = {bioRxiv} }