{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:29Z","timestamp":1792790369340,"version":"4.5.0"},"posted":{"date-parts":[[2026,10,1]]},"group-title":"Neuroscience","reference-count":55,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Schmidt Futures","award":["SF857"],"award-info":[{"award-number":["SF857"]}]},{"name":"National Human Genome Research Institute","award":["RM1HG011543"],"award-info":[{"award-number":["RM1HG011543"]}],"id":[{"id":"https:\/\/ror.org\/00baak391","id-type":"ROR","asserted-by":"crossref"}]},{"award":["2134955"],"award-info":[{"award-number":["2134955"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["2034037"],"award-info":[{"award-number":["2034037"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"award":["2515389"],"award-info":[{"award-number":["2515389"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Institute of Mental Health","award":["U24MH132628"],"award-info":[{"award-number":["U24MH132628"]}]},{"name":"National Institute of Neurological Disorders and Stroke","award":["U24NS146314"],"award-info":[{"award-number":["U24NS146314"]}],"id":[{"id":"https:\/\/ror.org\/01s5ya894","id-type":"ROR","asserted-by":"crossref"}]},{"name":"California Institute for Regenerative Medicine","award":["DISC4-16285"],"award-info":[{"award-number":["DISC4-16285"]}],"id":[{"id":"https:\/\/ror.org\/033m8b439","id-type":"ROR","asserted-by":"crossref"}]},{"name":"California Institute for Regenerative Medicine","award":["DISC4-16337"],"award-info":[{"award-number":["DISC4-16337"]}],"id":[{"id":"https:\/\/ror.org\/033m8b439","id-type":"ROR","asserted-by":"crossref"}]},{"name":"California Institute for Regenerative Medicine","award":["DISC4-19334"],"award-info":[{"award-number":["DISC4-19334"]}],"id":[{"id":"https:\/\/ror.org\/033m8b439","id-type":"ROR","asserted-by":"crossref"}]},{"name":"University of California Office of the President","award":["M25PR9045"],"award-info":[{"award-number":["M25PR9045"]}],"id":[{"id":"https:\/\/ror.org\/00dmfq477","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Brain and Behavior Research Foundation","award":["33184"],"award-info":[{"award-number":["33184"]}],"id":[{"id":"https:\/\/ror.org\/03a63f080","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Extracellular recordings carry information about neuronal location, and pooling per-unit predictions across neighboring electrodes improves its readout, but whether this local pooling should be learned is untested. We present MYCEL (Message-passing Yields Cellular Embeddings of Location), a graph neural network whose nodes are spike-sorted units carrying waveform and spike-timing features selected on cell-type ground truth, and whose edges encode recording geometry. On the Allen Brain Observatory Visual Coding Neuropixels dataset, learned message passing outperforms fixed aggregation, with the largest gains where single units are least informative. On the International Brain Laboratory Brain Wide Map, MYCEL matches the strongest population model at one-tenth the pairwise interactions. On held-out animals, the embeddings recover laminar depth within visual cortex. Retrained with only the edge geometry changed, the same framework decodes anatomy in macaque visual cortex and human medial temporal lobe. Thus, how neighboring neurons are combined matters as much as the features that describe them.<\/jats:p>","DOI":"10.64898\/2026.09.26.754562","type":"posted-content","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T04:25:11Z","timestamp":1790915111000},"source":"Crossref","is-referenced-by-count":0,"title":["Decoding brain anatomy from neuronal neighborhoods with MYCEL"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5588-921X","authenticated-orcid":false,"given":"Jesus","family":"Gonzalez-Ferrer","sequence":"first","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Live Cell Biotechnology Discovery Lab, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Biomolecular Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7346-3072","authenticated-orcid":false,"given":"Avelina","family":"Moreno-Ochando","sequence":"additional","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Live Cell Biotechnology Discovery Lab, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2593-6342","authenticated-orcid":false,"given":"John R.","family":"Minnick","sequence":"additional","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Electrical and Computer Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aidan","family":"Schneider","sequence":"additional","affiliation":[{"name":"Department of Statistics & Data Science, Yale University, New Haven, CT, 06511, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7085-5248","authenticated-orcid":false,"given":"Mircea","family":"Teodorescu","sequence":"additional","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Live Cell Biotechnology Discovery Lab, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Biomolecular Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Electrical and Computer Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1533-4575","authenticated-orcid":false,"given":"David","family":"Haussler","sequence":"additional","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Live Cell Biotechnology Discovery Lab, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Biomolecular Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1634-7514","authenticated-orcid":false,"given":"Mohammed A.","family":"Mostajo-Radji","sequence":"additional","affiliation":[{"name":"Genomics Institute, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Live Cell Biotechnology Discovery Lab, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"},{"name":"Department of Biomolecular Engineering, University of California Santa Cruz, Santa Cruz, CA, 95064, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026100606100799000_2026.09.26.754562v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.10.007"},{"key":"2026100606100799000_2026.09.26.754562v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24636"},{"key":"2026100606100799000_2026.09.26.754562v1.3","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.100840"},{"key":"2026100606100799000_2026.09.26.754562v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03171-x"},{"key":"2026100606100799000_2026.09.26.754562v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2007.06.018"},{"key":"2026100606100799000_2026.09.26.754562v1.6","doi-asserted-by":"crossref","first-page":"RP101506","DOI":"10.7554\/eLife.101506","article-title":"Neurons throughout the brain embed robust signatures of their anatomical location into spike trains","volume":"13","year":"2025","journal-title":"Elife"},{"key":"2026100606100799000_2026.09.26.754562v1.7","doi-asserted-by":"crossref","first-page":"5241","DOI":"10.1038\/s41467-026-71331-0","article-title":"A multimodal approach for visualizing and identifying electrophysiological cell types in vivo","volume":"17","year":"2026","journal-title":"Nat. Commun"},{"key":"2026100606100799000_2026.09.26.754562v1.8","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.1016\/j.cell.2025.01.041","article-title":"A deep learning strategy to identify cell types across species from high-density extracellular recordings","volume":"188","year":"2025","journal-title":"Cell"},{"key":"2026100606100799000_2026.09.26.754562v1.9","first-page":"77001","article-title":"In vivo cell-type and brain region classification via multimodal contrastive learning","volume":"2025","year":"2025","journal-title":"In International Conference on Learning Representations"},{"key":"2026100606100799000_2026.09.26.754562v1.10","doi-asserted-by":"crossref","unstructured":"Gonzalez-Ferrer, J. et al. Hippie: a generative model for electrophysiological analysis across species, technologies, and modalities. Nat. Commun. 17, 10007 (2026).","DOI":"10.1038\/s41467-026-76939-w"},{"key":"2026100606100799000_2026.09.26.754562v1.11","doi-asserted-by":"crossref","unstructured":"Schneider, A. et al. Transcriptomic cell type structures in vivo neuronal activity across multiple timescales. Cell reports 42 (2023).","DOI":"10.1016\/j.celrep.2023.112318"},{"key":"2026100606100799000_2026.09.26.754562v1.12","first-page":"46007","article-title":"Learning time-invariant representations for individual neurons from population dynamics","volume":"36","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026100606100799000_2026.09.26.754562v1.13","first-page":"39826","article-title":"Neuron platonic intrinsic representation from dynamics using contrastive learning","volume":"2025","year":"2025","journal-title":"In International Conference on Learning Representations"},{"key":"2026100606100799000_2026.09.26.754562v1.14","first-page":"99472","article-title":"Know thyself by knowing others: Learning neuron identity from population context","volume":"38","year":"2026","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026100606100799000_2026.09.26.754562v1.15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1948"},{"key":"2026100606100799000_2026.09.26.754562v1.16","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.85550"},{"key":"2026100606100799000_2026.09.26.754562v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09235-0"},{"key":"2026100606100799000_2026.09.26.754562v1.18","unstructured":"Brody, S. , Alon, U. & Yahav, E. How attentive are graph attention networks? arXiv preprint arXiv:2105.14491 (2021)."},{"key":"2026100606100799000_2026.09.26.754562v1.19","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"2026100606100799000_2026.09.26.754562v1.20","unstructured":"Hamilton, W. , Ying, Z. & Leskovec, J . Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017)."},{"key":"2026100606100799000_2026.09.26.754562v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3785"},{"key":"2026100606100799000_2026.09.26.754562v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.12.013"},{"key":"2026100606100799000_2026.09.26.754562v1.23","doi-asserted-by":"crossref","unstructured":"Li, Y. et al. Triple-N dataset: large-scale fMRI-guided dense recordings of nonhuman primate neural responses to natural scenes. Nature Neuroscience 1\u201313 (2026).","DOI":"10.1038\/s41593-026-02322-z"},{"key":"2026100606100799000_2026.09.26.754562v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3862"},{"key":"2026100606100799000_2026.09.26.754562v1.25","doi-asserted-by":"crossref","unstructured":"Hernandez, S. , et al. Establishing mouse forebrain organoids as models of intrinsic cortical network assembly. Stem Cell Reports 21 (2026).","DOI":"10.1016\/j.stemcr.2026.102832"},{"key":"2026100606100799000_2026.09.26.754562v1.26","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1038\/nmeth.3415","article-title":"Functional cortical neurons and astrocytes from human pluripotent stem cells in 3D culture","volume":"12","year":"2015","journal-title":"Nature methods"},{"key":"2026100606100799000_2026.09.26.754562v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/nature22330"},{"key":"2026100606100799000_2026.09.26.754562v1.28","doi-asserted-by":"crossref","first-page":"1105","DOI":"10.1038\/s41597-026-07955-0","article-title":"Human neuron activity during an 83-minute movie from 2,286 neurons and 29 patients","volume":"13","year":"2026","journal-title":"Scientific Data"},{"key":"2026100606100799000_2026.09.26.754562v1.29","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41592-021-01255-8","article-title":"SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network","volume":"18","year":"2021","journal-title":"Nature methods"},{"key":"2026100606100799000_2026.09.26.754562v1.30","doi-asserted-by":"crossref","first-page":"8536","DOI":"10.1038\/s41467-025-64259-4","article-title":"Data-driven fine-grained region discovery in the mouse brain with transformers","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2026100606100799000_2026.09.26.754562v1.31","doi-asserted-by":"crossref","unstructured":"Marquez-Legorreta, E. et al. Whole-brain co-mapping of gene expression and neuronal activity at cellular resolution in behaving zebrafish. bioRxiv 2026\u201302 (2026).","DOI":"10.64898\/2026.02.07.704095"},{"key":"2026100606100799000_2026.09.26.754562v1.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.12.009"},{"key":"2026100606100799000_2026.09.26.754562v1.33","first-page":"42271","article-title":"Towards robust and generalizable representations of extracellular data using contrastive learning","volume":"36","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"2026100606100799000_2026.09.26.754562v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06031-6"},{"key":"2026100606100799000_2026.09.26.754562v1.35","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"2026100606100799000_2026.09.26.754562v1.36","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"2026100606100799000_2026.09.26.754562v1.37","first-page":"124297","article-title":"Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential","volume":"38","year":"2026","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026100606100799000_2026.09.26.754562v1.38","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.78362"},{"key":"2026100606100799000_2026.09.26.754562v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2021.09.002"},{"key":"2026100606100799000_2026.09.26.754562v1.40","unstructured":"Guo, C. , Pleiss, G. , Sun, Y. & Weinberger, K. Q . On calibration of modern neural networks. In International conference on machine learning, 1321\u20131330 (PMLR, 2017)."},{"key":"2026100606100799000_2026.09.26.754562v1.41","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00680.2018"},{"key":"2026100606100799000_2026.09.26.754562v1.42","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.67490"},{"key":"2026100606100799000_2026.09.26.754562v1.43","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.61834"},{"key":"2026100606100799000_2026.09.26.754562v1.44","doi-asserted-by":"crossref","unstructured":"Li, Y. et al. Triple-N dataset: large-scale fMRI-guided dense recordings of nonhuman primate neural responses to natural scenes. Nature Neuroscience 1\u201313 (2026).","DOI":"10.1038\/s41593-026-02322-z"},{"key":"2026100606100799000_2026.09.26.754562v1.45","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"key":"2026100606100799000_2026.09.26.754562v1.46","unstructured":"Hamilton, W. , Ying, Z. & Leskovec, J . Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017)."},{"key":"2026100606100799000_2026.09.26.754562v1.47","doi-asserted-by":"crossref","first-page":"5241","DOI":"10.1038\/s41467-026-71331-0","article-title":"A multimodal approach for visualizing and identifying electrophysiological cell types in vivo","volume":"17","year":"2026","journal-title":"Nat. Commun"},{"key":"2026100606100799000_2026.09.26.754562v1.48","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.67490"},{"key":"2026100606100799000_2026.09.26.754562v1.49","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.61834"},{"key":"2026100606100799000_2026.09.26.754562v1.50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2021.09.002"},{"key":"2026100606100799000_2026.09.26.754562v1.51","first-page":"42271","article-title":"Towards robust and generalizable representations of extracellular data using contrastive learning","volume":"36","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"2026100606100799000_2026.09.26.754562v1.52","doi-asserted-by":"crossref","first-page":"2218","DOI":"10.1016\/j.cell.2025.01.041","article-title":"A deep learning strategy to identify cell types across species from high-density extracellular recordings","volume":"188","year":"2025","journal-title":"Cell"},{"key":"2026100606100799000_2026.09.26.754562v1.53","first-page":"99472","article-title":"Know thyself by knowing others: Learning neuron identity from population context","volume":"38","year":"2026","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2026100606100799000_2026.09.26.754562v1.54","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06031-6"},{"key":"2026100606100799000_2026.09.26.754562v1.55","doi-asserted-by":"crossref","first-page":"RP101506","DOI":"10.7554\/eLife.101506","article-title":"Neurons throughout the brain embed robust signatures of their anatomical location into spike trains","volume":"13","year":"2025","journal-title":"Elife"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.26.754562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T13:10:20Z","timestamp":1791292220000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.26.754562"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":55,"URL":"https:\/\/doi.org\/10.64898\/2026.09.26.754562","relation":{},"subject":[],"published":{"date-parts":[[2026,10,1]]},"subtype":"preprint"}}