1. UnPaSt: unsupervised patient stratification by differentially expressed biclusters in omics data
- Author
-
Hartung, Michael, Maier, Andreas, Delgado-Chaves, Fernando, Burankova, Yuliya, Isaeva, Olga I., Patroni, Fábio Malta de Sá, He, Daniel, Shannon, Casey, Kaufmann, Katharina, Lohmann, Jens, Savchik, Alexey, Hartebrodt, Anne, Chervontseva, Zoe, Firoozbakht, Farzaneh, Probul, Niklas, Zotova, Evgenia, Tsoy, Olga, Blumenthal, David B., Ester, Martin, Laske, Tanja, Baumbach, Jan, and Zolotareva, Olga
- Subjects
Computer Science - Machine Learning ,Quantitative Biology - Genomics - Abstract
Most complex diseases, including cancer and non-malignant diseases like asthma, have distinct molecular subtypes that require distinct clinical approaches. However, existing computational patient stratification methods have been benchmarked almost exclusively on cancer omics data and only perform well when mutually exclusive subtypes can be characterized by many biomarkers. Here, we contribute with a massive evaluation attempt, quantitatively exploring the power of 22 unsupervised patient stratification methods using both, simulated and real transcriptome data. From this experience, we developed UnPaSt (https://apps.cosy.bio/unpast/) optimizing unsupervised patient stratification, working even with only a limited number of subtype-predictive biomarkers. We evaluated all 23 methods on real-world breast cancer and asthma transcriptomics data. Although many methods reliably detected major breast cancer subtypes, only few identified Th2-high asthma, and UnPaSt significantly outperformed its closest competitors in both test datasets. Essentially, we showed that UnPaSt can detect many biologically insightful and reproducible patterns in omic datasets., Comment: The first two authors listed are joint first authors. The last two authors listed are joint last authors
- Published
- 2024
