Benchmarking the Connectomes of Caenorhabditis elegans within the Reservoir Computing Framework
Authors: Felix S. Reimers, Ola Huse Ramstad, Aliaksandr Hubin, Stefano Nichele
Organizations: Department of Computer Science and Communication, Østfold University College, Halden, 1757, Østfold, Norway. · Faculty of Chemistry, Biotechnology and Food Science, Norwegian University of Life Sciences, ˚As, 1432, Akershus, Norway. · Department of Mathematics, University of Oslo, Oslo, 0316, Oslo, Norway.
The aim of this work is to examine the connectomes of Caenorhabditis elegans through a computational lens using the reservoir computing framework. Connectomes are mappings of biological neural networks; C. elegans is the first organism for which physical connectomes covering the whole nervous system have been published. The connectomes of C. elegans used in this paper have been derived at different ages of the organism and are based on three different ways of measuring inter-cellular connections. They have, with minimal preprocessing, been implemented as reservoirs in the form of echo state networks, which are recurrent neural networks. In reservoir computing, the reservoir itself is not trained, rather the output of the reservoir is passed to a comparatively small read-out module in which training takes place. Training and testing is conducted in different neuro-inspired tasks, with the aim of using these tasks as a benchmark for the connectomes. This process has been repeated with different configurations of the reservoir and equally sized but randomized null models have been used for comparison. The results show that the biological wiring and a bio-informed configuration of input and output nodes of the reservoirs do not necessarily lead to better performance. Contrarily, the randomized null models are often outperforming the original connectomes on the chosen benchmarks. At the same time it becomes clear that the results depend a lot on the configuration of the reservoir and the way the connectome has been derived from the organism. Connectomes from different ages may produce varying outcome, without a clear trend becoming visible.
Figures & tables
Figure 1: The different hyperparameter and configuration choices that have been covered in the experiments. On the left of the figure it is described in which way the reservoirs are derived, on the right of the figure the conditions under which they are tested is depicted. A1a in Ages is color marked as here only the synapse count based connectome is available.
Figure 2: Conceptual depiction of an echo state network. Only the matrix W, connecting the reservoir to the read-out layer, is trained. Taken from Nichele and Molund (2017)
Figure 3: The performance of the connectomes based on the number of synapses and the corresponding null models. The rows correspond to the different tasks, the columns to the different reservoir configurations. In the individual plots, the model-based estimated means ± 95% CI is plotted against the age of the organism.
Figure 4: The performance of the connectomes based on physical contact and the corresponding null models. The rows correspond to the different tasks, the columns to the different reservoir configurations. In the individual plots, the model-based estimated means ± 95% CI is plotted against the age of the organism.
Pearson’s correlation coefficient
RMSE
Connectome
Mean Age
Fav. orig.
Fav. null
Mean Age
Fav. orig.
Fav. null
phys_contact
−0.20
0
7
+0.044
0
7
syn_count
+0.35
7
0
+0.0065
0
4 1 1 1 Three Age levels non-significant.
syn_size
+0.24
5
0 2 2 2 Two Age levels non-significant.
+0.027
0
5 2 2 2 Two Age levels non-significant.
Table 2: Simple contrasts (original −Null1 ) for age for the Memory Capacity Task. Beta regression with Pearson’s correlation coefficient scores: positive ⇒ original better. Gamma/Gaussian regression with RMSE scores: positive ⇒ original worse. 0 0 footnotetext: Note: Counts are Holm-adjusted Age levels with p<0.05 .
Figure 6
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 7
Figure 9: Plots of the time series data associated with each task.
Reservoir computing exploits the fixed dynamics of a recurrent network for temporal processing, requiring only a trained linear readout. Biological neural connectomes, shaped by millions of years of evolution, may encode computational structure beyond what random reservoirs provide, yet whether that structure can be further enhanced by principled optimisation remains an open question. We address it by applying four gradient-free, bio-inspired optimisers (Particle Swarm Optimisation, Differential Evolution, Grey Wolf Optimiser, and Whale Optimisation Algorithm) to the edge weights of connectome-based echo-state networks across six species spanning six orders of magnitude in neural complexity: C. elegans (279 neurons), Drosophila (49 nodes), mouse (112), rat (73), macaque (29 regions, continuous FLNe synaptic strengths), and human structural MRI connectivity (83 parcels). Each connectome is evaluated on four canonical reservoir computing benchmarks: Memory Capacity (MC), Lorenz attractor prediction, NARMA-10 system identification, and Mackey-Glass chaotic time-series prediction. All four optimisers consistently outperform unoptimised biological baselines across every task and species when initialised from biological weights. WOA achieves the largest gains on every task: up to a 17x MC improvement (C. elegans: 1.39 to 23.91) and up to 89% NRMSE reduction (Mackey-Glass, human), corresponding to an average 214% improvement across all species and tasks. Crucially, random initialisation on the same topology reliably underperforms biology, establishing biological weight values as an essential inductive bias that topology alone cannot recover. These results position bio-inspired, biologically-initialised optimisation as a principled and broadly effective strategy for connectome reservoir computing across the animal kingdom.
Anmol Guragain, Savvas Kakalis, Juan Ignacio Godino-Llorente
ETSI de Telecomunicación, Universidad Politécnica de Madrid, Madrid, Spain
Connectomes, graph-level maps of neurons and their synaptic connections, provide a structural basis for understanding how brain circuits support function and computation. However, mapping connectome structure to computation remains difficult because these graphs are high-dimensional, sparse, and sensitive to local structural variation. Existing approaches often depend on hand-crafted structural descriptors or task-specific predictors, which limits their ability to represent connectomes in a form that is both generative and functionally meaningful. We propose a conditional generative latent framework that encodes connectome graphs into a compact structural space while using available node-level conditions to guide reconstruction and generation. From this space, the model can reconstruct observed connectivity with a mean edge-reconstruction AUC up to 0.910 and generate new candidate connectomes, enabling a unified analysis of graph structure and computational behavior. Using connectome-derived graphs as recurrent computational substrates, we found that the learned latent space captures functional variation across reservoir-computing experiments, with cross-validated R2 values up to approximately 0.87. Interpretability analysis further revealed task-specific structural mechanisms: in our examples, memory performance is associated with reciprocal recurrent connectivity, whereas prediction and classification are more strongly associated with spectral properties of the recurrent network. These findings suggest an AI-for-science approach to linking neural connectivity to computation and provide a generative and interpretable basis for studying how distinct structural mechanisms shape computational capacity.
Zhuolin Yu, Xingyu Liu, Yuanhao Jia +4
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China · School of Electronics Engineering and Computer Science, Peking University, Beijing, China · School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China +2
Can a biological wiring diagram serve as a useful computational substrate beyond the behaviors for which it evolved? We use the publicly released MaleCNS v1.0 connectome, reconstructed from a single adult male Drosophila specimen, as the fixed recurrent topology of an artificial network. We train separate models for bounded addition and for a controlled grounded relational language task built from a fixed 100-word lexicon. In both models, one scalar is learned per anatomical edge. The anatomical graph reaches 92.77% mean accuracy on held-out addition, compared with 67.93% for directed degree-preserving rewires. On the strict paired language endpoint, which matches original and order-reversed scenes to their corresponding descriptions, it reaches 61.59% across four fixed interfaces, compared with 44.17% for matched rewires. At the canonical interface, it ranks first in a fixed 21-graph comparison. On the matched 48-group intervention subset, shuffling task-defined sensory features reduces its score from 60.94% to 19.27%. Together, these results show that higher-order MaleCNS wiring provides a reusable inductive bias for bounded addition and grounded relational language.
Joonghui Cho, Minchan Kang, Daeshik Kim
Korea Advanced Institute of Science and Technology (KAIST)