Comprehensive large-scale datasets for 26 viral families for fine-tuning BERT-infect models

<p>These datasets were constructed in the paper "Hidden Challenges in Evaluating Spillover Risk of Zoonotic Viruses using Machine Learning Models" (doi: https://doi.org/10.1101/2024.04.25.591033). The details were also described in the git-hub (https://github.com/Junna-Kawasaki/BERT-infect_2024).</p> <ul> <li>The compressed files, such as ${virus}.tar.xz, contain fasta and genbank files.</li> </ul>