@article {Ramesh2023.01.23.525209, author = {B Ramesh and CM Small and H Healey and B Johnson and E Barker and M Currey and S Bassham and M Myers and WA Cresko and AG Jones}, title = {Improvements to the Gulf Pipefish Syngnathus scovelli Genome}, elocation-id = {2023.01.23.525209}, year = {2023}, doi = {10.1101/2023.01.23.525209}, publisher = {Cold Spring Harbor Laboratory}, abstract = {The Gulf pipefish Syngnathus scovelli has emerged as an important species in the study of sexual selection, development, and physiology, among other topics. The fish family Syngnathidae, which includes pipefishes, seahorses, and seadragons, has become an increasingly attractive target for comparative research in ecological and evolutionary genomics. These endeavors depend on having a high-quality genome assembly and annotation. However, the first version of the S. scovelli genome assembly was generated by short-read sequencing and annotated using a small set of RNA-sequence data, resulting in limited contiguity and a relatively poor annotation. Here, we present an improved genome assembly and an enhanced annotation, resulting in a new official gene set for S. scovelli. By using PacBio long-read high-fidelity (Hi-Fi) sequences and a proximity ligation (Hi-C) library, we fill small gaps and join the contigs to obtain 22 chromosome-level scaffolds. Compared to the previously published genome, the gaps in our novel genome assembly are smaller, the N75 is much larger (13.3 Mb), and this new genome is around 95\% BUSCO complete. The precision of the gene models in the NCBI{\textquoteright}s eukaryotic annotation pipeline was enhanced by using a large body of RNA-Seq reads from different tissue types, leading to the discovery of 28,162 genes, of which 8,061 were non-coding genes. This new genome assembly and the annotation are tagged as a RefSeq genome by NCBI and thus provide substantially enhanced genomic resources for future research involving S. scovelli.Competing Interest StatementThe authors have declared no competing interest.List of abbreviationsMbMega basepairGbGiga basepairRNARibo Nucleic AcidDNADeoxyribo Nucleic AcidBUSCOBenchmarking Universal Single-Copy OrthologsQUASTQuality Assessment ToolCCSCircular Consensus SequenceHi-FiHigh-FidelitySMRTSingle Molecule Real TimeNCBINational Center for Biotechnology Information}, URL = {https://www.biorxiv.org/content/early/2023/01/24/2023.01.23.525209}, eprint = {https://www.biorxiv.org/content/early/2023/01/24/2023.01.23.525209.full.pdf}, journal = {bioRxiv} }