Reproduce “Enhanced Spatial Clustering of Single-Molecule Localizations with Graph Neural Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jesús Pineda, Sergi Masó-Orriols, Montse Masoliver, Joan Bertran, Mattias Goksör, Giovanni Volpe, Carlo Manzo
MIRO improves clustering of single-molecule localization microscopy data by learning to move localizations from the same structure toward a shared center before DBSCAN groups them. This supervised preprocessing helps with challenging shapes, including simulated rings, where cluster-detection Jaccard Index was 0.990 ± 0.012 versus 0.55 ± 0.04 for DBSCAN alone across 50 fields of view. Results depend on training data and parameter selection.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.