Work

Weakly supervised learning uncovers phenotypic signatures in single-cell data

Year: 2024
Type: preprint
Abstract: To deliver clinically relevant insights from large patient cohorts profiled with single-cell technologies, a key challenge is to relate sample-level and single-cell measurements. We present MultiMIL, a deep learning framework that applies attention-based multiple-instance learning for phenotype prediction and cell state identification. We applied MultiMIL to peripheral blood mononuclear cells from COVID-19 patients, the Human Lung Cell Atlas, and a spatial proteomics breast cancer dataset, demonstrating how our model can be utilized to find phenotype-associated cell states, learn phenotype-informed sample representations, and expand disease signatures.
Language: English
Open Access status: green
Award: G989548112
OpenAlex ID: W4401159754
Cites: 93
Cited by: 20
Related to: 10