@article {Bern{\'a}279174, author = {Luisa Bern{\'a} and Mat{\'\i}as Rodr{\'\i}guez and Mar{\'\i}a Laura Chiribao and Adriana Parodi-Talice and Sebasti{\'a}n Pita and Gast{\'o}n Rijo and Fernando Alvarez-Valin and Carlos Robello}, title = {Expanding an expanded genome: long-read sequencing of Trypanosoma cruzi}, elocation-id = {279174}, year = {2018}, doi = {10.1101/279174}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Although the genome of Trypanosoma cruzi, the causative agent of Chagas disease, was first made available in 2005, with additional strains reported later, the intrinsic genome complexity of this parasite (abundance of repetitive sequences and genes organized in tandem) has traditionally hindered high-quality genome assembly and annotation. This also limits diverse types of analyses that require high degree of precision. Long reads generated by third-generation sequencing technologies are particularly suitable to address the challenges associated with T. cruzi{\textasciiacute}s genome since they permit directly determining the full sequence of large clusters of repetitive sequences without collapsing them. This, in turn, allows not only accurate estimation of gene copy numbers but also circumvents assembly fragmentation. Here, we present the analysis of the genome sequences of two T. cruzi clones: the hybrid TCC (DTU TcVI) and the non-hybrid Dm28c (DTU TcI), determined by PacBio SMRT technology. The improved assemblies herein obtained permitted us to accurately estimate gene copy numbers, abundance and distribution of repetitive sequences (including satellites and retroelements). We found that the genome of T. cruzi is composed of a "core compartment" and a "disruptive compartment" which exhibit opposite gene and GC content composition. New tandem and disperse repetitive sequences were identified, including some located inside coding sequences. Additionally, homologous chromosomes were separately assembled, allowing us to retrieve haplotypes as separate contigs instead of a unique mosaic sequence. Finally, manual annotation of surface multigene families MUC and trans-sialidases allows now a better overview of these complex groups of genes.}, URL = {https://www.biorxiv.org/content/early/2018/03/10/279174}, eprint = {https://www.biorxiv.org/content/early/2018/03/10/279174.full.pdf}, journal = {bioRxiv} }