AI-driven discovery of synergistic drug combinations against pancreatic cancer

Mohsen Pourmousa, Sankalp Jain, Elena Barnaeva, Wengong Jin, Joshua Hochuli, Zina Itkin, Travis Maxfield, Cleber Melo-Filho, Andrew Thieme, Kelli Wilson, Carleen Klumpp-Thomas, Sam Michael, Noel Southall, Tommi Jaakkola, Eugene N. Muratov, Regina Barzilay, Alexander Tropsha, Marc Ferrer and Alexey V. Zakharov ()
Additional contact information
Mohsen Pourmousa: 9800 Medical Center Drive
Sankalp Jain: 9800 Medical Center Drive
Elena Barnaeva: 9800 Medical Center Drive
Wengong Jin: Massachusetts Institute of Technology
Joshua Hochuli: University of North Carolina
Zina Itkin: 9800 Medical Center Drive
Travis Maxfield: University of North Carolina
Cleber Melo-Filho: University of North Carolina
Andrew Thieme: University of North Carolina
Kelli Wilson: 9800 Medical Center Drive
Carleen Klumpp-Thomas: 9800 Medical Center Drive
Sam Michael: 9800 Medical Center Drive
Noel Southall: 9800 Medical Center Drive
Tommi Jaakkola: Massachusetts Institute of Technology
Eugene N. Muratov: University of North Carolina
Regina Barzilay: Massachusetts Institute of Technology
Alexander Tropsha: University of North Carolina
Marc Ferrer: 9800 Medical Center Drive
Alexey V. Zakharov: 9800 Medical Center Drive

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract 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.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-56818-6 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-56818-6

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-56818-6

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().