{
  "id": 8841947,
  "title": "miRstring: An RNA language model enables mature miRNA decoding and artificial small RNA design across species",
  "url": "https://urgent.news/2026/09/20/mirstring-an-rna-language-model-enables-mature-mirna-decoding-and",
  "topic": "science",
  "section": "Science",
  "published": "2026-09-20T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.09.17.752258v1?rss=1"
  },
  "original_language": "en",
  "account": "MicroRNAs (miRNAs) are processed from structured precursors and loaded into Argonaute proteins to repress target mRNAs. However, current computational frameworks are unable to decode mature miRNAs from precursor context, limiting cross-species annotation and rational artificial miRNA design. Researchers have now introduced miRstring, an RNA language framework that considers the four boundaries defining the miRNA/miRNA duplex. This model was trained on 77,708 miRNA precursors from 414 species and surpasses existing methods in family- and species-held-out evaluations. It can accurately identify the first nucleotide of mature miRNAs. Importantly, its attention mechanism identifies the miRNA/miRNA* boundary sites cleaved by endonucleases, suggesting that the model captures biologically meaningful features. Furthermore, miRstring was used to design optimal pre-miRNA scaffolds for artificial miRNAs, which were later validated to repress target mRNAs. In conclusion, miRstring offers a scalable route from cross-species mature-miRNA annotation to predictive design, enabling AI-driven miRNA engineering and extending computational miRNA analysis to a broader range of small-RNA biotechnology applications.",
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}