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

## TL;DR

The paper introduces MIRO, a new algorithm using graph neural networks to improve clustering of single-molecule microscopy data for better analysis of molecular structures.

## Contribution

MIRO uses recurrent graph neural networks to enhance spatial clustering of single-molecule localization data across different scales and structures.

## Key findings

- MIRO improves clustering efficiency in single-molecule localization microscopy data.
- The algorithm handles clusters of different shapes and scales simultaneously.
- MIRO shows potential for applications in neuroscience and environmental science.

## 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.

Single-molecule localisation microscopy enables nanoscale mapping of molecular organisation, but clustering stochastic data remains challenging. Here, authors present a graph neural network method that enhances clustering across complex biological datasets.