Predicting Breast Cancer Phenotypes from Single-cell RNA-seq Data Using CloudPred

2024/02/17 by Hossein Moghimianavval, Baharan Meghdadi, Moghimianavval, Hossein +4
Biochemistry, Genetics and Molecular Biology · Computer Science · #AI in cancer detection #FOS: Biological sciences #Gene expression and cancer classification #Genomics (q-bio.GN) #Single-cell and spatial transcriptomics

paper · pdf · doi:10.48550/arxiv.2402.11289

openalex publication_date 2024/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Numerous tools have been recently developed to predict disease phenotypes using single-cell RNA sequencing (RNA-seq) data. CloudPred is an end-to-end differentiable learning algorithm coupled with a biologically informed mixture model, originally tested on lupus data. This study extends CloudPred's applications to breast cancer disease phenotype prediction to test its robustness and applicability on untested and unrelated biological data. When applying a breast cancer single-cell RNA seq dataset, CloudPred achieved an area under the ROC curve (AUC) of 1 in predicting cancer status and performed better than a linear and Deepset models.

Related

• CloudPred: Predicting Patient Phenotypes From Single-cell RNA-seq
• Predicting Molecular Phenotypes with Single Cell RNA Sequencing Data: an Assessment of Unsupervised Machine Learning Models
• UnPaSt: unsupervised patient stratification by differentially expressed biclusters in omics data
• Analysis of ensemble feature selection for correlated high-dimensional\n RNA-Seq cancer data
• A Pipeline for Integrated Theory and Data-Driven Modeling of Genomic and Clinical Data