Back

DALE-Eval: A comprehensive cell type-specific expression deconvolution benchmark for transcriptomics data

Hu, M.; Chikina, M.; Zhang, M. J.

2025-08-02 bioinformatics
10.1101/2025.07.31.667984 bioRxiv
Show abstract

Deconvolution of bulk transcriptomic data unlocks rich, cell type-specific insights from complex tissue samples. While cell type fraction deconvolution has been extensively developed and bench-marked, the next frontier--cell type-specific expression (CTSE) deconvolution--remains largely underexplored. Here, we introduce DALE-Eval, a comprehensive benchmark of CTSE methods, featuring novel evaluation metrics, identification of key drivers of performance, and practical recommendations for maximizing the value of CTSE in downstream applications.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

1
Nature Methods
○ 385 papers in training set
Top 0.1%
45.8%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 14%
12.9%
Similar papers in this journal
50% of probability mass above
3
Genome Biology
○ 637 papers in training set
Top 1%
7.9%
Similar papers in this journal
4
Nature Biotechnology
○ 172 papers in training set
Top 0.4%
6.7%
Similar papers in this journal
5
Nature
○ 645 papers in training set
Top 4%
3.2%
Similar papers in this journal
6
Cell Systems
○ 201 papers in training set
Top 2%
1.9%
7
Nucleic Acids Research
◐ 1281 papers in training set
Top 8%
1.7%
8
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.7%
9
Genome Research
● 468 papers in training set
Top 4%
1.5%
10
Cell Genomics
○ 172 papers in training set
Top 3%
1.5%
11
Nature Machine Intelligence
○ 70 papers in training set
Top 2%
1.3%
12
Nature Genetics
○ 286 papers in training set
Top 4%
1.3%
13
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 34%
1.1%
14
Cell Reports Methods
○ 165 papers in training set
Top 3%
1.1%
15
Bioinformatics
◐ 1204 papers in training set
Top 8%
1.1%
16
PLOS Computational Biology
● 1863 papers in training set
Top 19%
0.9%
17
eLife
● 5828 papers in training set
Top 64%
0.9%
18
Molecular Systems Biology
○ 162 papers in training set
Top 3%
0.8%
19
Nature Computational Science
○ 55 papers in training set
Top 2%
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.