Back

Representing cells as sentences enables natural-language processing for single-cell transcriptomics

Dhodapkar, R. M.

2022-09-19 bioinformatics
10.1101/2022.09.18.508438 bioRxiv
Show abstract

AO_SCPLOWBSTRACTC_SCPLOWGene expression matrices commonly used in single-cell transcriptomics, cannot be directly analyzed with tools developed for natural languages. By restructuring these matrices as abundance-ordered sequences of genes, we generate cell sentences: rank-normalized, positionally encoded expression data. We show that these cell sentences can be analyzed using existing tools from natural language processing to unify cell and gene representations across species.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Bioinformatics Advances
◐ 203 papers in training set
Top 0.1%
18.0%
Similar papers in this journal
2
Genome Biology
○ 637 papers in training set
Top 0.6%
14.7%
Similar papers in this journal
3
Bioinformatics
◐ 1204 papers in training set
Top 3%
9.4%
Similar papers in this journal
4
PLOS Computational Biology
● 1863 papers in training set
Top 6%
6.5%
Similar papers in this journal
5
Briefings in Bioinformatics
◐ 354 papers in training set
Top 2%
5.3%
50% of probability mass above
6
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 0.7%
5.3%
Similar papers in this journal
7
Nature Communications
○ 5641 papers in training set
Top 29%
5.0%
8
BMC Bioinformatics
○ 457 papers in training set
Top 2%
4.2%
9
Nature Methods
○ 385 papers in training set
Top 2%
4.2%
10
Nucleic Acids Research
◐ 1281 papers in training set
Top 6%
3.1%
11
PLOS ONE
● 5266 papers in training set
Top 42%
2.3%
12
GigaScience
◐ 212 papers in training set
Top 2%
2.3%
13
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 3%
2.1%
14
Scientific Reports
○ 3612 papers in training set
Top 47%
2.1%
15
iScience
○ 1154 papers in training set
Top 22%
1.5%
16
Patterns
○ 78 papers in training set
Top 2%
1.1%
17
Cell Reports Methods
○ 165 papers in training set
Top 3%
0.9%
18
Genome Research
● 468 papers in training set
Top 6%
0.8%
19
BMC Genomics
○ 406 papers in training set
Top 8%
0.8%
20
Frontiers in Genetics
○ 230 papers in training set
Top 6%
0.8%
21
Communications Biology
○ 993 papers in training set
Top 37%
0.6%
22
Nature Biotechnology
○ 172 papers in training set
Top 5%
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.