Enhanced Spatial Clustering of Single-Molecule Localizations with Graph Neural Networks

TL;DR

This paper introduces MIRO, a graph neural network-based algorithm that significantly enhances the accuracy and efficiency of spatial clustering in single-molecule localization microscopy, especially under challenging conditions.

Contribution

The paper presents MIRO, a novel GNN-based method that improves clustering of point clouds with diverse shapes and scales, outperforming traditional techniques.

Findings

MIRO achieves higher clustering accuracy across various datasets.

Supports multi-scale and multi-shape cluster processing.

Demonstrates potential for diverse scientific applications.

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.