Designing Novel Compound Candidates Against SARS-CoV-2 Using Generative Deep Neural Networks and Cheminformatics
Shang-Yang Li, Chin-Mao Hung, Hsin-Yi Hung, Chih-Wei Lai, Meng-Chang Lee, Vincenzo Bramanti · 2025
Read Designing Novel Compound Candidates Against SARS-CoV-2 Using Generative Deep Neural Networks and Cheminformatics by Shang-Yang Li, Chin-Mao Hung, Hsin-Yi Hung, Chih-Wei Lai, Meng-Chang Lee, Vincenzo Bramanti (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12732431.txt.
Description
Shang-Yang Li and co-authors use generative AI and cheminformatics to design candidate drugs against SARS-CoV-2, in a 2025 study. Few approved drugs exist for COVID-19, and their use carries limits. The team started from the structure of molnupiravir, an authorized antiviral. A similarity search pulled over sixty thousand related structures from a chemical directory. Those structures trained a deep generative model.
Reinforcement learning then steered the model to draft six thousand fresh molecules. Screening narrowed the field to thirty-eight candidates with likely antiviral traits. Safety and uptake filters cut the list further. One unpatented compound passed every screen and bound the viral copying enzyme more strongly than molnupiravir in models. The authors stress that lab validation must come next. They present the pipeline as a fast way to seed antiviral discovery.
Catalog record
| CREATOR | Shang-Yang Li, Chin-Mao Hung, Hsin-Yi Hung, Chih-Wei Lai, Meng-Chang Lee, Vincenzo Bramanti |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |