Deep generative AI models analyzing circulating orphan non-coding RNAs enable detection of early-stage lung cancer

Mehran Karimzadeh, Amir Momen-Roknabadi, Taylor B. Cavazos, Yuqi Fang, Nae-Chyun Chen, Michael Multhaup, Jennifer Yen, Jeremy Ku, Jieyang Wang, Xuan Zhao, Philip Murzynowski, Kathleen Wang, Rose Hanna, Alice Huang, Diana Corti, Dang Nguyen, Ti Lam, Seda Kilinc, Patrick Arensdorf, Kimberly H. Chau, Anna Hartwig, Lisa Fish, Helen Li, Babak Behsaz, Olivier Elemento, James Zou, Fereydoun Hormozdiari (), Babak Alipanahi () and Hani Goodarzi ()
Additional contact information
Mehran Karimzadeh: Exai Bio Inc.
Amir Momen-Roknabadi: Exai Bio Inc.
Taylor B. Cavazos: Exai Bio Inc.
Yuqi Fang: Exai Bio Inc.
Nae-Chyun Chen: Exai Bio Inc.
Michael Multhaup: Exai Bio Inc.
Jennifer Yen: Exai Bio Inc.
Jeremy Ku: Exai Bio Inc.
Jieyang Wang: Exai Bio Inc.
Xuan Zhao: Exai Bio Inc.
Philip Murzynowski: Exai Bio Inc.
Kathleen Wang: Exai Bio Inc.
Rose Hanna: Exai Bio Inc.
Alice Huang: Exai Bio Inc.
Diana Corti: Exai Bio Inc.
Dang Nguyen: Exai Bio Inc.
Ti Lam: Exai Bio Inc.
Seda Kilinc: Exai Bio Inc.
Patrick Arensdorf: Exai Bio Inc.
Kimberly H. Chau: Exai Bio Inc.
Anna Hartwig: Exai Bio Inc.
Lisa Fish: Exai Bio Inc.
Helen Li: Exai Bio Inc.
Babak Behsaz: Exai Bio Inc.
Olivier Elemento: Weill Cornell Medicine
James Zou: Stanford University
Fereydoun Hormozdiari: Exai Bio Inc.
Babak Alipanahi: Exai Bio Inc.
Hani Goodarzi: University of California

Nature Communications, 2024, vol. 15, issue 1, 1-12

Abstract: Abstract Liquid biopsies have the potential to revolutionize cancer care through non-invasive early detection of tumors. Developing a robust liquid biopsy test requires collecting high-dimensional data from a large number of blood samples across heterogeneous groups of patients. We propose that the generative capability of variational auto-encoders enables learning a robust and generalizable signature of blood-based biomarkers. In this study, we analyze orphan non-coding RNAs (oncRNAs) from serum samples of 1050 individuals diagnosed with non-small cell lung cancer (NSCLC) at various stages, as well as sex-, age-, and BMI-matched controls. We demonstrate that our multi-task generative AI model, Orion, surpasses commonly used methods in both overall performance and generalizability to held-out datasets. Orion achieves an overall sensitivity of 94% (95% CI: 87%–98%) at 87% (95% CI: 81%–93%) specificity for cancer detection across all stages, outperforming the sensitivity of other methods on held-out validation datasets by more than ~ 30%.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-53851-9 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:15:y:2024:i:1:d:10.1038_s41467-024-53851-9

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

DOI: 10.1038/s41467-024-53851-9

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 ().