A deep multiple instance learning framework improves microsatellite instability detection from tumor next generation sequencing

John Ziegler, Jaclyn F. Hechtman, Satshil Rana, Ryan N. Ptashkin, Gowtham Jayakumaran, Sumit Middha, Shweta S. Chavan, Chad Vanderbilt, Deborah DeLair, Jacklyn Casanova, Jinru Shia, Nicole DeGroat, Ryma Benayed, Marc Ladanyi, Michael F. Berger, Thomas J. Fuchs, A. Rose Brannon () and Ahmet Zehir
Additional contact information
John Ziegler: Memorial Sloan Kettering Cancer Center
Jaclyn F. Hechtman: Memorial Sloan Kettering Cancer Center
Satshil Rana: Memorial Sloan Kettering Cancer Center
Ryan N. Ptashkin: Memorial Sloan Kettering Cancer Center
Gowtham Jayakumaran: Memorial Sloan Kettering Cancer Center
Sumit Middha: Memorial Sloan Kettering Cancer Center
Shweta S. Chavan: Memorial Sloan Kettering Cancer Center
Chad Vanderbilt: Memorial Sloan Kettering Cancer Center
Deborah DeLair: Memorial Sloan Kettering Cancer Center
Jacklyn Casanova: Memorial Sloan Kettering Cancer Center
Jinru Shia: Memorial Sloan Kettering Cancer Center
Nicole DeGroat: Memorial Sloan Kettering Cancer Center
Ryma Benayed: Memorial Sloan Kettering Cancer Center
Marc Ladanyi: Memorial Sloan Kettering Cancer Center
Michael F. Berger: Memorial Sloan Kettering Cancer Center
Thomas J. Fuchs: Memorial Sloan Kettering Cancer Center
A. Rose Brannon: Memorial Sloan Kettering Cancer Center
Ahmet Zehir: Memorial Sloan Kettering Cancer Center

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

Abstract: Abstract Microsatellite instability (MSI) is a critical phenotype of cancer genomes and an FDA-recognized biomarker that can guide treatment with immune checkpoint inhibitors. Previous work has demonstrated that next-generation sequencing data can be used to identify samples with MSI-high phenotype. However, low tumor purity, as frequently observed in routine clinical samples, poses a challenge to the sensitivity of existing algorithms. To overcome this critical issue, we developed MiMSI, an MSI classifier based on deep neural networks and trained using a dataset that included low tumor purity MSI cases in a multiple instance learning framework. On a challenging yet representative set of cases, MiMSI showed higher sensitivity (0.895) and auROC (0.971) than MSISensor (sensitivity: 0.67; auROC: 0.907), an open-source software previously validated for clinical use at our institution using MSK-IMPACT large panel targeted NGS data. In a separate, prospective cohort, MiMSI confirmed that it outperforms MSISensor in low purity cases (P = 8.244e-07).

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-54970-z 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_s41467-024-54970-z

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

DOI: 10.1038/s41467-024-54970-z

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 ().