Enhanced spatial clustering of single-molecule localizations with graph neural networks

2024/11/29 by Jesús Pineda, Sergi Masó-Orriols, Pineda, Jesús +11 · 1 voice · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Fluorescence Microscopy Techniques #Advanced Graph Neural Networks #Topological and Geometric Data Analysis

paper · pdf · doi:10.1038/s41467-025-65557-7

openalex created_date 2025/11/03 · openalex publication_date 2025/11/03 · openalex updated_date 2026/08/01

Abstract

Single-molecule localization microscopy generates point clouds corresponding to fluorophore localizations. Spatial cluster identification and analysis of these point clouds are crucial for extracting insights about molecular organization. However, this task becomes challenging in the presence of localization noise, high point density, or complex biological structures. Here, we introduce MIRO (Multifunctional Integration through Relational Optimization), an algorithm that uses recurrent graph neural networks to transform the point clouds in order to improve clustering efficiency when applying conventional clustering techniques. We show that MIRO supports simultaneous processing of clusters of different shapes and at multiple scales, demonstrating improved performance across varied datasets. Our comprehensive evaluation demonstrates MIRO's transformative potential for single-molecule localization applications, showcasing its capability to revolutionize cluster analysis and provide accurate, reliable details of molecular architecture. In addition, MIRO's robust clustering capabilities hold promise for applications in various fields such as neuroscience, for the analysis of neural connectivity patterns, and environmental science, for studying spatial distributions of ecological data.

Citations

• A Generalization of Transformer Networks to Graphs
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• A Survey on Oversmoothing in Graph Neural Networks
• Graph Neural Networks in Network Neuroscience
• Localization microscopy: a review of the progress in methods and applications
• Optuna: A Next-generation Hyperparameter Optimization Framework
• Relational inductive biases, deep learning, and graph networks
• Adjusting for Chance Clustering Comparison Measures

Cited by

• Objective clustering protocol for single-molecule data: A lifetime vs. intensity study

Discussions

• MIRO is a graph neural network method that enhances spatial clustering for single-molecule localisation microscopy datasets. #BiotechNatureComms @cmanzo.bsky.social @qubilab.bsky.social @giovannivol [bsky, 5 points, 0 comments]

Related

• Teaching deep neural networks to localize single molecules for super-resolution microscopy
• Fast and robust multiplane single molecule localization microscopy using deep neural network
• Localization of Ultra-dense Emitters with Neural Networks
• MolCluster: Integrating Graph Neural Network with Community Detection for Coarse-Grained Mapping
• Neural network-assisted single-molecule localization microscopy with a weak-affinity protein tag