VI-VS: calibrated identification of feature dependencies in single-cell multiomics
Name
13059_2024_Article_3419.pdf
Size
2.88 MB
Format
Adobe PDF
Checksum (MD5)
83ad76903346c0112a45b7798dff3359
Author(s)
Boyeau, Pierre
Bates, Stephen
Ergen, Can
Jordan, Michael I.
Yosef, Nir
Date Issued
November 15, 2024
Journal
Genome Biology
Publisher
BioMed Central
Citation
Boyeau, P., Bates, S., Ergen, C. et al. VI-VS: calibrated identification of feature dependencies in single-cell multiomics. Genome Biol 25, 294 (2024).
Version
Final published version
Abstract
Unveiling functional relationships between various molecular cell phenotypes from data using machine learning models is a key promise of multiomics. Existing methods either use flexible but hard-to-interpret models or simpler, misspecified models. VI-VS (Variational Inference for Variable Selection) balances flexibility and interpretability to identify relevant feature relationships in multiomic data. It uses deep generative models to identify conditionally dependent features, with false discovery rate control. VI-VS is available as an open-source Python package, providing a robust solution to identify features more likely representing genuine causal relationships.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1186/s13059-024-03419-z
