1. Deep generative AI models analyzing circulating orphan non-coding RNAs enable detection of early-stage lung cancer.
- Author
-
Karimzadeh, Mehran, Momen-Roknabadi, Amir, Cavazos, Taylor, Fang, Yuqi, Chen, Nae-Chyun, Multhaup, Michael, Yen, Jennifer, Ku, Jeremy, Wang, Jieyang, Zhao, Xuan, Murzynowski, Philip, Wang, Kathleen, Hanna, Rose, Huang, Alice, Corti, Diana, Nguyen, Dang, Lam, Ti, Kilinc, Seda, Arensdorf, Patrick, Chau, Kimberly, Hartwig, Anna, Fish, Lisa, Li, Helen, Behsaz, Babak, Elemento, Olivier, Zou, James, Hormozdiari, Fereydoun, Alipanahi, Babak, and Goodarzi, Hani
- Subjects
Humans ,Lung Neoplasms ,Carcinoma ,Non-Small-Cell Lung ,Biomarkers ,Tumor ,Early Detection of Cancer ,Male ,Female ,Middle Aged ,Liquid Biopsy ,Aged ,Neoplasm Staging ,Deep Learning ,RNA ,Untranslated ,Sensitivity and Specificity ,Artificial Intelligence - 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%.
- Published
- 2024