Article

scMILD: Single-cell Multiple Instance Learning for Sample Classification and Associated Subpopulation Discovery

2025-01-11

Abstract excerpt

<h4>SUMMARY</h4> Linking cellular states to clinical phenotypes is a major challenge in single-cell analysis. Here, we present scMILD, a weakly supervised Multiple Instance Learning framework that robustly identifies condition-associated cells using only sample-level labels. After systematically validating scMILD’s accuracy through controlled simulations, we applied it to diverse disease datasets, confirming its...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: d8e7daad-8955-5c49-8498-f03cda77b630
DOI: 10.1101/2025.01.09.632256

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

scMILD: Single-cell Multiple Instance Learning for Sample Classification and Associated Subpopulation DiscoveryDOI 10.1101/2025.01.09.632256Read

Weakly supervised learning uncovers phenotypic signatures in single-cell dataSemantic proximity Read

Exploring phenotype-related single-cells through attention-enhanced representation learningSemantic proximity Read

Exploring phenotype-related single-cells through attention-enhanced representation learning.Semantic proximity Read

CellPhenoX: An eXplainable Cell-specific machine learning method to predict clinical Phenotypes using single-cell multi-omicsSemantic proximity Read

Application and Characterization of the Multiple Instance Learning Framework in Flow CytometrySemantic proximity Read

CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq.Semantic proximity Read

CTDP: Identifying cell types associated with disease phenotypes using scRNA-seq dataSemantic proximity Read

Hierarchical classification of immune cell transcriptomes at population-scaleSemantic proximity Read

Supervised learning of high-confidence phenotypic subpopulations from single-cell dataSemantic proximity Read

Deep interpretable learning of sample representations for characterizing disease states in single-cell transcriptomicsSemantic proximity Read

MICRON learns outcome-associated representations of spatial immune microenvironmentsSemantic proximity Read

Using LLM Models and Explainable ML to Analyse Biomarkers at Single Cell Level for Improved Understanding of DiseasesSemantic proximity Read