Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy
Abstract
Preclinical models poorly predict human drug efficacy, particularly in neurological disorders. Neural activity offers a uniquely rich source of translational information because it captures high-dimensional variation in nervous-system function that can be measured in both animals and humans. However, its high dimensionality makes it difficult to distinguish conserved disease-related features from variation arising from species, recording modality and experimental context. Here, we test whether shared neural dynamics can be identified directly from electrophysiology data by learning representations organized by biological state rather than species. We develop a dual-rule contrastive learning framework that aligns corresponding mouse and human states while preserving separation between distinct phenotypes. This framework recovered conserved sensory-response structure across species and, in epilepsy, resolved distinct relationships between three mouse models and heterogeneous human patient populations. When treated animals were projected into a frozen cross-species representation, drug-induced movement towards the human-aligned healthy state retrospectively tracked known clinical efficacy across ten model-drug combinations including a disease-specific detrimental effect. The framework also identified shared disease-associated neural dynamics between Fmr1-knockout mice and human 16p11.2 copy-number variant carriers despite differences in genetic aetiology and recording modality. Together, these findings show the potential of cross-species neural representation learning to map heterogeneous human disease onto experimentally tractable preclinical states and assess whether interventions restore human-relevant circuit function.
Related
- Graph-based representation learning of neuronal dynamics and behavior
- Enhancing Clinical Classifier Robustness with Deep Representation Learning Based OOD Detection on DNA Methylation Data
- Comparing the efficacy of LORETA neurofeedback versus cognitive rehabilitation on working memory in children with learning disorders: A double-blind clinical trial.
- Toward a Transferable Representation of Protein Dynamics for Functional Prediction and Mechanistic Discovery
- High-dimensional hippocampus representation facilitates learning of low-dimensional abstract representation and supports generalization
BibTeX
@misc{tvrdic2026crossspecies,
title = {{Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy}},
author = {Marko Tvrdic and Justin Richmond Domingo and Jae Ann Buenaluz and Jydell Ashley Palomo Penollar and Edmayelle Villavicencio Alforja and Jobi Fallaeria Subosa and Gabriel Ocana-Santero},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11222},
eprint = {2610.11222},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11222},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy
AU - Marko Tvrdic
AU - Justin Richmond Domingo
AU - Jae Ann Buenaluz
AU - Jydell Ashley Palomo Penollar
AU - Edmayelle Villavicencio Alforja
AU - Jobi Fallaeria Subosa
AU - Gabriel Ocana-Santero
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11222
UR - https://arxiv.org/abs/2610.11222
AB - Preclinical models poorly predict human drug efficacy, particularly in neurological disorders. Neural activity offers a uniquely rich source of translational information because it captures high-dimensional variation in nervous-system function that can be measured in both animals and humans. However, its high dimensionality makes it difficult to distinguish conserved disease-related features from variation arising from species, recording modality and experimental context. Here, we test whether shared neural dynamics can be identified directly from electrophysiology data by learning representations organized by biological state rather than species. We develop a dual-rule contrastive learning framework that aligns corresponding mouse and human states while preserving separation between distinct phenotypes. This framework recovered conserved sensory-response structure across species and, in epilepsy, resolved distinct relationships between three mouse models and heterogeneous human patient populations. When treated animals were projected into a frozen cross-species representation, drug-induced movement towards the human-aligned healthy state retrospectively tracked known clinical efficacy across ten model-drug combinations including a disease-specific detrimental effect. The framework also identified shared disease-associated neural dynamics between Fmr1-knockout mice and human 16p11.2 copy-number variant carriers despite differences in genetic aetiology and recording modality. Together, these findings show the potential of cross-species neural representation learning to map heterogeneous human disease onto experimentally tractable preclinical states and assess whether interventions restore human-relevant circuit function.
ER -