SCOUT: Single-cell outlier analysis in cancer
Onzi, G. R.; Faccioni, J. L.; Alvarado, A. G.; Bracco, P. A.; Kornblum, H. L.; Lenz, G.
Show abstract
Outliers are often ignored or even removed from data analysis. In cancer, however, single outlier cells can be of major importance, since they have uncommon characteristics that may confer capacity to invade, metastasize, or resist to therapy. Here we present the Single-Cell OUTlier analysis (SCOUT), a resource for single-cell data analysis focusing on outlier cells, and the SCOUT Selector (SCOUTS), an application to systematically apply SCOUT on a dataset over a wide range of biological markers. Using publicly available datasets of cancer samples obtained from mass cytometry and single-cell RNA-seq platforms, outlier cells for the expression of proteins or RNAs were identified and compared to their non-outlier counterparts among different samples. Our results show that analyzing single-cell data using SCOUT can uncover key information not easily observed in the analysis of the whole population.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- scMuffin: an R package for disentangling solid tumor heterogeneity from single-cell expression data 96%
- annoFuse: an R Package to annotate, prioritize, and interactively explore putative oncogenic RNA fusions 94%
- ScRNAbox: Empowering Single-Cell RNA Sequencing on High Performance Computing Systems 94%
Similar papers in this journal
Similar papers in this journal
- Integration, exploration, and analysis of high-dimensional single-cell cytometry data using Spectre 93%
- CytoNormPy enables a fast and scalable removal of batch effects in cytometry datasets. 93%
- Classification of human white blood cells using machine learning for stain-free imaging flow cytometry 92%
Similar papers in this journal
- Single-Cell Virtual Cytometer allows user-friendly and versatile analysis and visualization of multimodal single cell RNAseq datasets 95%
- CRUX, a platform for visualising, exploring and analysing cancer genome cohort data 94%
- ViCloD, an interactive web tool for visualizing B cell repertoires and analyzing intra-clonal diversities: application to human B-cell tumors 94%
Similar papers in this journal
"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.