@Article{duepublico_mods_00082415, author = {Thomas, Alexander and Battenfeld, Thomas and Kraiselburd, Ivana and Anastasiou, Olympia and Dittmer, Ulf and D{\"o}rr, Ann-Kathrin and D{\"o}rr, Adrian and Elsner, Carina and Gosch, Jule and Le-Trilling, Vu Thuy Khanh and Magin, Simon and Scholtysik, Ren{\'e} and Yilmaz, Pelin and Trilling, Mirko and Sch{\"o}ler, Lara and K{\"o}ster, Johannes and Meyer, Folker}, title = {UnCoVar: A reproducible and scalable workflow for transparent and robust virus variant calling and lineage assignment using SARS-CoV-2 as an example}, year = {2024}, month = {Jun}, day = {28}, keywords = {SARS-CoV-2; Workflow; Variant calling; Lineage assignment; Next generation sequencing}, abstract = {Background: At a global scale, the SARS-CoV-2 virus did not remain in its initial genotype for a long period of time, with the first global reports of variants of concern (VOCs) in late 2020. Subsequently, genome sequencing has become an indispensable tool for characterizing the ongoing pandemic, particularly for typing SARS-CoV-2 samples obtained from patients or environmental surveillance. For such SARS-CoV-2 typing, various in vitro and in silico workflows exist, yet to date, no systematic cross-platform validation has been reported. Results: In this work, we present the first comprehensive cross-platform evaluation and validation of in silico SARS-CoV-2 typing workflows. The evaluation relies on a dataset of 54 patient-derived samples sequenced with several different in vitro approaches on all relevant state-of-the-art sequencing platforms. Moreover, we present UnCoVar, a robust, production-grade reproducible SARS-CoV-2 typing workflow that outperforms all other tested approaches in terms of precision and recall. Conclusions: In many ways, the SARS-CoV-2 pandemic has accelerated the development of techniques and analytical approaches. We believe that this can serve as a blueprint for dealing with future pandemics. Accordingly, UnCoVar is easily generalizable towards other viral pathogens and future pandemics. The fully automated workflow assembles virus genomes from patient samples, identifies existing lineages, and provides high-resolution insights into individual mutations. UnCoVar includes extensive quality control and automatically generates interactive visual reports. UnCoVar is implemented as a Snakemake workflow. The open-source code is available under a BSD 2-clause license at github.com/IKIM-Essen/uncovar.}, note = {<p>This work was partially supported by the WBEready consortium{\&}{\#}xa0;(grant no. ZMII2-2523COR10A-E), funded by the German Federal Ministry for Health (Bundesministerium f{\"u}r Gesundheit, BMG), and by the SMITH-Medizininformatik-Konsortium-Nachwuchsgruppe Vorhersage von Sepsis auf Basis von Mikrobiomsequenzdaten (MicrobiomSepsisPred, grant no.{\&}{\#}xa0;01ZZ2013){\&}{\#}xa0;, funded by the German Federal Ministry of Education and Research (Bundesministerium f{\"u}r Bildung und Forschung, BMBF).</p> <p>Open Access funding enabled and organized by Projekt DEAL.</p>}, note = {<p>Thomas, A., Battenfeld, T., Kraiselburd, I. <em>et al.</em> UnCoVar: a reproducible and scalable workflow for transparent and robust virus variant calling and lineage assignment using SARS-CoV-2 as an example. <em>BMC Genomics</em><strong> 25</strong>, 647 (2024). <a href="https://doi.org/10.1186/s12864-024-10539-0">https://doi.org/10.1186/s12864-024-10539-0</a></p> <p>Published: 28 June 2024</p>}, note = {Version of Record / Verlagsversion}, doi = {10.1186/s12864-024-10539-0}, url = {https://duepublico2.uni-due.de/receive/duepublico_mods_00082415}, url = {https://doi.org/10.1186/s12864-024-10539-0}, file = {:https://duepublico2.uni-due.de/servlets/MCRFileNodeServlet/duepublico_derivate_00082683/BMC_Genomics_2024_25_647.pdf:PDF}, language = {en} }