Discovering cell types underlying rare disease phenotypes using scRNA-seq data from non-diseased tissues
Novoa, J.; Pazos, F.; Chagoyen, M.
Show abstract
Despite their low individual prevalence, rare diseases collectively pose a significant health burden, affecting millions of people worldwide. These conditions often result from single-gene mutations, yet the cellular contexts in which these alterations act remain largely unknown--information crucial for improving diagnosis and treatment. As patient-derived samples are scarce, we use single-cell RNA sequencing (scRNA-seq) data from non-diseased tissues to identify relevant cell populations. We introduce Cell4Rare, a computational framework that integrates these healthy scRNA-seq datasets with known phenotype-associated genes to map disease phenotypes to specific cell types. Applied across diverse tissues and phenotypes, Cell4Rare was validated against literature-based associations, achieving robust performance with an AUC of 0.71. These results highlight the potential of computational analyses of non-diseased scRNA-seq data to uncover the cellular basis of rare disease phenotypes, paving the way for improved diagnostics and therapeutic strategies.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Data- and knowledge-derived functional landscape of human solute carriers 94%
- A tissue-aware machine learning framework enhances the mechanistic understanding and genetic diagnosis of Mendelian and rare diseases 94%
- KDML: a machine-learning framework for inference of multi-scale gene functions from genetic perturbation screens 94%
Similar papers in this journal
- An atlas connecting shared genetic architecture of human diseases and molecular phenotypes provides insight into COVID-19 susceptibility 95%
- Mendelian gene identification through mouse embryo viability screening 93%
- A polyclonal allelic expression assay for detecting regulatory effects of transcript variants 92%
Similar papers in this journal
Similar papers in this journal
- Affected cell types for hundreds of Mendelian diseases revealed by analysis of human and mouse single-cell data 96%
- Dynamic effects of genetic variation on gene expression revealed following hypoxic stress in cardiomyocytes 94%
- Regulatory dissection of the severe COVID-19 risk locus introgressed by Neanderthals 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.