Sensitive detection of rare disease-associated cell subsets via representation learning.
Journal:
Nature communications
PMID:
28382969
Abstract
Rare cell populations play a pivotal role in the initiation and progression of diseases such as cancer. However, the identification of such subpopulations remains a difficult task. This work describes CellCnn, a representation learning approach to detect rare cell subsets associated with disease using high-dimensional single-cell measurements. Using CellCnn, we identify paracrine signalling-, AIDS onset- and rare CMV infection-associated cell subsets in peripheral blood, and extremely rare leukaemic blast populations in minimal residual disease-like situations with frequencies as low as 0.01%.
Authors
Keywords
Acquired Immunodeficiency Syndrome
Cytokines
Cytomegalovirus Infections
Humans
Immunologic Memory
Killer Cells, Natural
Leukemia
Monocytes
Neoplasm, Residual
Neural Networks, Computer
Prognosis
Rare Diseases
Signal Transduction
Single-Cell Analysis
Supervised Machine Learning
Survival Analysis
T-Lymphocyte Subsets