Back

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

Karimzadeh, M.; Momen-Roknabadi, A.; Cavazos, T. B.; Fang, Y.; Chen, N.-C.; Multhaup, M.; Yen, J.; Ku, J.; Wang, J.; Zhao, X.; Murzynowski, P.; Wang, K.; Hanna, R.; Huang, A.; Corti, D.; Nguyen, D.; Lam, T.; Kilinc, S.; Arensdorf, P.; Chau, K. H.; Hartwig, A.; Fish, L.; Li, H.; Behsaz, B.; Elemento, O.; Zou, J.; Hormozdiari, F.; Alipanahi, B.; Goodarzi, H.

2024-04-12 oncology
10.1101/2024.04.09.24304531 medRxiv
Show abstract

Liquid biopsies have the potential to revolutionize cancer care through non-invasive early detection of tumors, when the disease can be more effectively managed and cured. 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 that capture true biological signals while removing spurious confounders (e.g., library size, zero-inflation, and batch effects). In this study, we analyzed orphan non-coding RNAs (oncRNAs) from serum samples of 1,050 individuals diagnosed with non-small cell lung cancer (NSCLC) at various stages, as well as sex-, age-, and BMI-matched controls to evaluate the potential use of deep generative models. We demonstrated that our multi-task generative AI model, Orion, surpassed commonly used methods in both overall performance and generalizability to held-out datasets. Orion achieved an overall sensitivity of 92% (95% CI: 85%-97%) at 90% specificity for cancer detection across all stages, outperforming the sensitivity of other methods such as support vector machine (SVM) classifier, ElasticNet, or XGBoost on held-out validation datasets by more than [~]30%.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.