Pharmaceuticals, Volume 18, Issue 3
2025 March - 160 articles
Cover Story: Accurately predicting how strongly a drug binds to its target protein is essential in drug discovery. Current models rely on intensive protein–ligand interaction characterization but often lack reliability and generalizability. This challenge is exacerbated when structural data for these interactions are unavailable. To address this, we developed GNNSeq, a hybrid machine learning model that relies only on protein sequence data, removing the need for complex structural information. GNNSeq combines Graph Neural Networks (GNNs) with novel kernel-based switching algorithms to improve accuracy and efficiency. It processes large datasets quickly, making it ideal for scalable, cost-effective, virtual drug screening. Additional versions of GNNSeq hybridized with structure- and interaction-based models are freely available online. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.