AI-driven discovery of synergistic drug combinations against pancreatic cancer
Pancreatic cancer treatment often relies on multi-drug regimens, but optimal combinations remain elusive. This study evaluates predictive approaches to identify synergistic drug combinations using a dataset from the National Center for Advancing Translational Sciences (NCATS). Screening 496 combinations of 32 anticancer compounds against the PANC-1 cells experimentally determined the degree of synergism and antagonism. Three research groups (NCATS, University of North Carolina, and Massachusetts Institute of Technology) leverage these data to apply machine learning (ML) approaches, predicting synergy across 1.6 million combinations. Of the 88 tested, 51 show synergy, with graph convolutional networks achieving the best hit rate and random forest the highest precision. Beyond highlighting the potential of ML, this work delivers 307 experimentally validated synergistic combinations, demonstrating its practical impact in treating pancreatic cancer.
Authors
- Marc Ferrer (ORCID: https://orcid.org/0000-0003-4569-9137)
- Kelli M. Wilson (ORCID: https://orcid.org/0000-0003-2636-2766)
- Regina Barzilay
- Cleber C. Melo‐Filho (ORCID: https://orcid.org/0000-0003-0056-6971)
- Travis Maxfield (ORCID: https://orcid.org/0000-0002-7105-0246)
- Eugene Muratov (ORCID: https://orcid.org/0000-0003-4616-7036)
- Wengong Jin (ORCID: https://orcid.org/0000-0002-0555-3056)
- Noel Southall (ORCID: https://orcid.org/0000-0003-4500-880X)
- Zina Itkin (ORCID: https://orcid.org/0000-0003-1686-1326)
- Carleen Klumpp‐Thomas (ORCID: https://orcid.org/0000-0002-6646-6132)
- Tommi Jaakkola (ORCID: https://orcid.org/0000-0002-2199-0379)
- Andrew Thieme
- Sam Michael (ORCID: https://orcid.org/0000-0002-1070-6563)
- Joshua E. Hochuli (ORCID: https://orcid.org/0000-0003-4487-3228)
- Elena Barnaeva
- Mohsen Pourmousa (ORCID: https://orcid.org/0000-0002-6103-2976)
- Alexander Tropsha (ORCID: https://orcid.org/0000-0003-3802-8896)
- Alexey Zakharov (ORCID: https://orcid.org/0000-0003-2466-1711)
- Sankalp Jain (ORCID: https://orcid.org/0000-0002-9370-9611)
Institutions
- University of North Carolina at Chapel Hill (US)
- National Institutes of Health (US)
- Université Bourgogne Franche-Comté (FR)
- National Center for Advancing Translational Sciences (US)
- Predictive Science (United States) (US)
- Massachusetts Institute of Technology (US)
Publication Details
- Journal
- Nature Communications
- Published
- 2025-04-29
- DOI
- https://doi.org/10.1038/s41467-025-56818-6
- Citations
- 14
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 21.06
Funders
- National Institutes of Health
- National Institute of Environmental Health Sciences
- National Center for Advancing Translational Sciences