1. Sparse dictionary learning recovers pleiotropy from human cell fitness screens
- Author
-
Pan, Joshua, Kwon, Jason J., Talamas, Jessica A., Borah, Ashir A., Vazquez, Francisca, Boehm, Jesse S., Tsherniak, Aviad, Zitnik, Marinka, McFarland, James M., and Hahn, William C.
- Subjects
Quantitative Biology - Quantitative Methods ,Quantitative Biology - Genomics ,Quantitative Biology - Molecular Networks - Abstract
In high-throughput functional genomic screens, each gene product is commonly assumed to exhibit a singular biological function within a defined protein complex or pathway. In practice, a single gene perturbation may induce multiple cascading functional outcomes, a genetic principle known as pleiotropy. Here, we model pleiotropy in fitness screen collections by representing each gene perturbation as the sum of multiple perturbations of biological functions, each harboring independent fitness effects inferred empirically from the data. Our approach ('Webster') recovered pleiotropic functions for DNA damage proteins from genotoxic fitness screens, untangled distinct signaling pathways upstream of shared effector proteins from cancer cell fitness screens, and learned aspects of the cellular hierarchy in an unsupervised manner. Modeling compound sensitivity profiles in terms of genetically defined functions recovered compound mechanisms of action. Our approach establishes a sparse approximation mechanism for unraveling complex genetic architectures underlying high-dimensional gene perturbation readouts., Comment: Accepted to the 16th Machine Learning in Computational Biology (MLCB) meeting 2021, and the Learning Meaningful Representations of Life (LMRL) Workshop at NeurIPS 2021
- Published
- 2021