Cross-species representation learning aligns mouse and human neural dynamics and tracks clinical drug efficacy
作者: Marko Tvrdic, Justin Richmond Domingo, Jae Ann Buenaluz, Jydell Ashley Palomo Penollar, Edmayelle Villavicencio Alforja, Jobi Fallaeria Subosa, Gabriel Ocana-Santero
分类: q-bio.QM, cs.LG, q-bio.NC
发布日期: 2026-10-08
备注: 33 pages, 5 figures; supplementary material included (2 supplementary figures, 3 supplementary tables)
💡 一句话要点
提出跨物种神经表征学习以解决药物临床效果预测问题
🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)
关键词: 跨物种学习 神经动态 药物疗效 对比学习 电生理数据 神经系统疾病 临床前模型
📋 核心要点
- 现有的临床前模型在预测人类药物疗效方面存在显著不足，尤其是在神经系统疾病的研究中。
- 本文提出了一种双规则对比学习框架，旨在通过生物状态而非物种来对齐小鼠和人类的神经动态。
- 实验结果显示，该框架能够有效追踪药物治疗的临床效果，并识别不同物种间的共享疾病相关神经动态。
📝 摘要（中文）
现有的临床前模型在预测人类药物疗效方面表现不佳，尤其是在神经系统疾病中。神经活动作为一种独特的信息源，能够捕捉到动物与人类神经系统功能的高维变化。本文提出了一种双规则对比学习框架，通过生物状态而非物种来组织神经动态，从而识别共享的神经动态。该框架在癫痫模型中揭示了小鼠模型与异质人类患者群体之间的关系，并能够追踪十种模型-药物组合的临床疗效。研究结果表明，跨物种神经表征学习具有将人类疾病映射到可实验处理的临床前状态的潜力。
🔬 方法详解
问题定义：本文旨在解决临床前模型在预测人类药物疗效时的不足，尤其是在神经系统疾病领域。现有方法难以区分由物种、记录方式和实验背景引起的变异与保守的疾病相关特征。
核心思路：论文提出的双规则对比学习框架通过生物状态对齐小鼠和人类的神经动态，旨在保留不同表型之间的分离性，从而识别共享的神经动态。
技术框架：该框架包括数据预处理、特征提取、对比学习和结果分析等主要模块。通过对电生理数据进行处理，提取出与生物状态相关的特征，并进行对比学习以实现跨物种对齐。
关键创新：最重要的创新在于通过生物状态而非物种来组织神经动态，这一方法能够有效地恢复跨物种的感官反应结构，并揭示不同小鼠模型与人类患者之间的关系。
关键设计：在框架中，采用了特定的损失函数来优化对比学习过程，确保不同表型之间的分离性，同时保持共享特征的识别。网络结构设计上，使用了深度学习模型以处理高维电生理数据。
🖼️ 关键图片
📊 实验亮点
实验结果表明，该框架能够有效追踪药物治疗的临床效果，成功识别了十种模型-药物组合的已知临床疗效，并在癫痫模型中揭示了小鼠与人类患者之间的共享神经动态，显示出显著的临床相关性。
🎯 应用场景
该研究的潜在应用领域包括药物开发、神经科学研究和临床前模型评估。通过跨物种神经表征学习，研究人员能够更好地理解人类疾病的机制，并评估药物干预的有效性，从而推动新疗法的开发与应用。
📄 摘要（原文）
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.