Back

miRstring: An RNA language model enables mature miRNA decoding and artificial small RNA design across species

Peng, R.; Li, X.; fang, t.; Yu, X.

2026-09-20 bioinformatics
10.64898/2026.09.17.752258 bioRxiv
Show abstract

MicroRNAs (miRNAs) are processed from structured precursors and subsequently loaded into Argonaute proteins to repress target mRNAs. Yet generalized computational frameworks capable of decoding mature miRNAs from precursor context remain limited, constraining both cross-species annotation and rational artificial miRNA design. Here, we present miRstring, a biogenesis-aware RNA language framework that decodes the four boundaries defining the miRNA/miRNA duplex. Trained on 77,708 miRNA precursors spanning 414 species, miRstring outperforms existing methods under family- and species-held-out evaluations and accurately identifies the first nucleotide of mature miRNAs. Importantly, its attention mechanism highlights the miRNA/ miRNA* boundary sites cleaved by endonucleases, indicating that the model captures biologically meaningful features. Furthermore, we employed miRstring to design optimal pre-miRNA scaffolds for artificial miRNAs and validated its efficacy in repressing target mRNAs. Taken together, miRstring establishes a scalable route from cross-species mature-miRNA annotation to predictive design, enabling artificial intelligence-driven miRNA engineering and extending computational miRNA analysis toward broadly applicable small-RNA biotechnology.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nucleic Acids Research
◐ 1281 papers in training set
Top 1%
14.9%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 14%
12.8%
Similar papers in this journal
3
Genome Biology
○ 637 papers in training set
Top 2%
6.2%
Similar papers in this journal
4
Molecular Therapy Nucleic Acids
○ 39 papers in training set
Top 0.1%
5.4%
Similar papers in this journal
5
RNA Biology
○ 78 papers in training set
Top 0.2%
4.8%
Similar papers in this journal
6
Nature Methods
○ 385 papers in training set
Top 2%
4.8%
7
Nature Biotechnology
○ 172 papers in training set
Top 1%
4.3%
50% of probability mass above
8
RNA
● 189 papers in training set
Top 0.6%
3.2%
9
PLOS Computational Biology
● 1863 papers in training set
Top 10%
3.2%
10
Computational and Structural Biotechnology Journal
● 242 papers in training set
Top 2%
2.6%
11
Nature Machine Intelligence
○ 70 papers in training set
Top 1%
2.4%
12
Bioinformatics Advances
◐ 203 papers in training set
Top 2%
2.4%
13
Genomics, Proteomics & Bioinformatics
188 papers in training set
Top 0.8%
2.3%
14
NAR Genomics and Bioinformatics
◐ 242 papers in training set
Top 2%
2.1%
15
Bioinformatics
◐ 1204 papers in training set
Top 6%
1.9%
16
Advanced Science
○ 286 papers in training set
Top 4%
1.9%
17
Scientific Reports
○ 3612 papers in training set
Top 55%
1.7%
18
Proceedings of the National Academy of Sciences
● 2444 papers in training set
Top 31%
1.5%
19
Briefings in Bioinformatics
◐ 354 papers in training set
Top 5%
1.3%
20
PLOS ONE
● 5266 papers in training set
Top 53%
1.1%
21
Journal of Molecular Biology
○ 232 papers in training set
Top 3%
1.1%
22
Nature Structural & Molecular Biology
236 papers in training set
Top 3%
1.0%
23
Cell Systems
○ 201 papers in training set
Top 4%
1.0%
24
Science Advances
● 1243 papers in training set
Top 31%
0.8%
25
Cell Genomics
○ 172 papers in training set
Top 4%
0.8%
26
NAR Molecular Medicine
◐ 22 papers in training set
Top 0.5%
0.6%
27
eLife
● 5828 papers in training set
Top 71%
0.6%
28
BMC Genomics
○ 406 papers in training set
Top 9%
0.6%
29
ACS Synthetic Biology
● 287 papers in training set
Top 3%
0.6%
30
Nature
○ 645 papers in training set
Top 12%
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.