Back

genesorteR: Feature Ranking in Clustered Single Cell Data

Ibrahim, M. M.; Kramann, R.

2019-06-25 bioinformatics
10.1101/676379 bioRxiv
Show abstract

Marker genes identified in single cell experiments are expected to be highly specific to a certain cell type and highly expressed in that cell type. Detecting a gene by differential expression analysis does not necessarily satisfy those two conditions and is typically computationally expensive for large cell numbers.\n\nHere we present genesorteR, an R package that ranks features in single cell data in a manner consistent with the expected definition of marker genes in experimental biology research. We benchmark genesorteR using various data sets and show that it is distinctly more accurate in large single cell data sets compared to other methods. genesorteR is orders of magnitude faster than current implementations of differential expression analysis methods, can operate on data containing millions of cells and is applicable to both single cell RNA-Seq and single cell ATAC-Seq data.\n\ngenesorteR is available at https://github.com/mahmoudibrahim/genesorteR.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

1
Bioinformatics
◐ 1204 papers in training set
Top 0.5%
33.3%
Similar papers in this journal
2
BMC Bioinformatics
○ 457 papers in training set
Top 0.8%
9.5%
Similar papers in this journal
3
Nature Communications
○ 5641 papers in training set
Top 20%
8.6%
Similar papers in this journal
50% of probability mass above
4
Nature Methods
○ 385 papers in training set
Top 1%
7.7%
Similar papers in this journal
5
Bioinformatics Advances
◐ 203 papers in training set
Top 0.7%
6.5%
Similar papers in this journal
6
Genome Biology
○ 637 papers in training set
Top 2%
5.3%
7
PLOS Computational Biology
● 1863 papers in training set
Top 7%
5.0%
8
Cell Reports Methods
○ 165 papers in training set
Top 0.7%
3.1%
9
Nature Computational Science
○ 55 papers in training set
Top 0.4%
2.3%
10
Patterns
○ 78 papers in training set
Top 1%
2.1%
11
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 3%
1.7%
12
GigaScience
◐ 212 papers in training set
Top 3%
1.3%
13
Nucleic Acids Research
◐ 1281 papers in training set
Top 11%
1.1%
14
Genome Research
● 468 papers in training set
Top 5%
1.1%
15
Cell Systems
○ 201 papers in training set
Top 4%
1.1%
16
Nature Biotechnology
○ 172 papers in training set
Top 4%
1.0%
17
Briefings in Bioinformatics
◐ 354 papers in training set
Top 7%
0.8%
18
Scientific Reports
○ 3612 papers in training set
Top 78%
0.6%
19
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 46%
0.6%

"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.