Deep active learning-based experimental design to uncover synergistic genetic interactions for host-targeted therapeutics
Haonan Zhu, Mary Silva, Jose Cadena, Braden Soper, Michał Lisicki, Braian Peetoom, Sergio E Baranzini, Shivshankar Sundaram, Priyadip Ray, Jeff Drocco, Mingfu Shao · 2026
Read Deep active learning-based experimental design to uncover synergistic genetic interactions for host-targeted therapeutics by Haonan Zhu, Mary Silva, Jose Cadena, Braden Soper, Michał Lisicki, Braian Peetoom, Sergio E Baranzini, Shivshankar Sundaram, Priyadip Ray, Jeff Drocco, Mingfu Shao (2026) 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-13524425.txt.
Description
Haonan Zhu and co-authors present a deep active learning method for finding paired gene knockdowns that fight viruses in a 2026 paper. Turning off two host genes at once can block viral copying, but the pairs worth testing are far too many to try blindly. Experiments must choose their next tests wisely.
Their framework learns gene representations from a large biomedical knowledge graph and a data set of pairwise knockdowns in HIV infection. It balances exploring new pairs against exploiting known good regions. An ensemble variant improved results, and the genes the method picked are interpreted for biological meaning.
Catalog record
| CREATOR | Haonan Zhu, Mary Silva, Jose Cadena, Braden Soper, Michał Lisicki, Braian Peetoom, Sergio E Baranzini, Shivshankar Sundaram, Priyadip Ray, Jeff Drocco, Mingfu Shao |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |