A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Jingqi, Han, Keqi, Wang, Yun, Mi, Lu, Yang, Carl
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914364398764032
author Lu, Jingqi
Han, Keqi
Wang, Yun
Mi, Lu
Yang, Carl
author_facet Lu, Jingqi
Han, Keqi
Wang, Yun
Mi, Lu
Yang, Carl
contents This study establishes a benchmark for Caenorhabditis elegans neuron classification, comparing four graph methods (GCN, GraphSAGE, GAT, GraphTransformer) against four non-graph methods (Logistic Regression, MLP, LOLCAT, NeuPRINT). Using the functional connectome, we classified Sensory, Interneuron, and Motor neurons based on Spatial, Connection, and Neuronal Activity features. Results show that attention-based GNNs significantly outperform baselines on the Spatial and Connection features. The Neuronal Activity features yielded poor performance, likely due to the low temporal resolution of the underlying neuronal activity data. Our benchmark validates the use of GNNs and highlights that Spatial and Connection features are key predictors for Caenorhabditis elegans neuron classes. Code is available at: https://github.com/JingqiLuu/neuronclf-gnn-benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02241
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification
Lu, Jingqi
Han, Keqi
Wang, Yun
Mi, Lu
Yang, Carl
Neurons and Cognition
Artificial Intelligence
This study establishes a benchmark for Caenorhabditis elegans neuron classification, comparing four graph methods (GCN, GraphSAGE, GAT, GraphTransformer) against four non-graph methods (Logistic Regression, MLP, LOLCAT, NeuPRINT). Using the functional connectome, we classified Sensory, Interneuron, and Motor neurons based on Spatial, Connection, and Neuronal Activity features. Results show that attention-based GNNs significantly outperform baselines on the Spatial and Connection features. The Neuronal Activity features yielded poor performance, likely due to the low temporal resolution of the underlying neuronal activity data. Our benchmark validates the use of GNNs and highlights that Spatial and Connection features are key predictors for Caenorhabditis elegans neuron classes. Code is available at: https://github.com/JingqiLuu/neuronclf-gnn-benchmark.
title A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification
topic Neurons and Cognition
Artificial Intelligence
url https://arxiv.org/abs/2603.02241