2025-10-02 ミシガン大学
An RNA molecule is illuminated by a laser light near a slide surface nearby a neural network. Image credit: Nils Walter, University of Michigan
<関連情報>
- https://news.umich.edu/scalable-ai-tracks-motion-from-single-molecules-to-wildebeests/
- https://www.nature.com/articles/s41592-025-02839-4
単一分子の時間トレースにおける効率的な生物学的発見のための基礎モデル Foundation model for efficient biological discovery in single-molecule time traces
Jieming Li,Leyou Zhang,Alexander Johnson-Buck & Nils G. Walter
Nature Methods Published:02 October 2025
DOI:https://doi.org/10.1038/s41592-025-02839-4
Abstract
Single-molecule fluorescence microscopy (SMFM) can reveal important biological insights. However, uncovering rare but critical intermediates often demands manual inspection of time traces and iterative ad hoc approaches. To facilitate systematic and efficient discovery from SMFM time traces, we introduce META-SiM, a transformer-based foundation model pretrained on diverse SMFM analysis tasks. META-SiM rivals best-in-class algorithms on a broad range of tasks including trace classification, segmentation, idealization and stepwise photobleaching analysis. Additionally, the model produces embeddings that encapsulate detailed information about each trace, which the web-based META-SiM Projector (https://www.simol-projector.org) casts into lower-dimensional space for efficient whole-dataset visualization, labeling, comparison and sharing. Combining this Projector with the objective metric of local Shannon entropy enables rapid identification of condition-specific behaviors, even if rare or subtle. Applying META-SiM to an existing single-molecule Förster resonance energy transfer dataset, we discover a previously undetected intermediate state in pre-mRNA splicing. META-SiM removes bottlenecks, improves objectivity and both systematizes and accelerates biological discovery in single-molecule data.
