Mixed Models with Multiple Instance Learning

arXiv:2311.02455v2 Announce Type: replace
Abstract: Predicting patient features from single-cell data can help identify cellular states implicated in health and disease. Linear models and average cell type expressions are typically favored for this task for their efficiency and robustness, but they overlook the rich cell heterogeneity inherent in single-cell data. To address this gap, we introduce MixMIL, a framework integrating Generalized Linear Mixed Models (GLMM) and Multiple Instance Learning (MIL), upholding the advantages of linear models while modeling cell state …

abstract arxiv cellular cs.lg data disease efficiency features gap health identify instance linear mixed multiple patient q-bio.gn q-bio.qm robustness stat.ap type