Somnotate: A probabilistic sleep stage classifier for studying vigilance state transitions.
Somnotate: A probabilistic sleep stage classifier for studying vigilance state transitions.
复制标题
DOI：
10.1371/journal.pcbi.1011793
复制
发表时间：
2024-01
影响因子：
4.3
通讯作者：
Akerman CJ
中科院分区：
文献类型：
--
作者：
Brodersen PJN;Alfonsa H;Krone LB;Blanco-Duque C;Fisk AS;Flaherty SJ;Guillaumin MCC;Huang YG;Kahn MC;McKillop LE;Milinski L;Taylor L;Thomas CW;Yamagata T;Foster RG;Vyazovskiy VV;Akerman CJ
自由行为动物的电生理记录是睡眠研究中广泛而有力的调查模式。这些记录产生了大量需要睡眠阶段注释（多导睡眠图）的数据，其中数据根据三种警惕状态进行分组：清醒、快速眼动（REM）睡眠和非REM（NREM）睡眠。手动和当前的计算注释方法忽略了中间状态，因为分类特征变得模糊不清，即使中间状态包含关于警惕状态动态的重要信息。为了解决这个问题，我们开发了“Somnotate”-一种基于线性判别分析（LDA）与隐马尔可夫模型（HMM）相结合的概率分类器。首先，我们证明了Somnotate在多导睡眠图中设定了新的标准，在小鼠电生理数据上表现出超过人类专家的注释准确性，对训练数据中的错误具有显着的鲁棒性，与不同记录配置的兼容性，以及在实验干预期间保持高准确性的能力。然而，Somnotate的关键特征是它量化并报告了其注释的确定性。我们利用这一功能，揭示了许多中间警惕状态集群周围的状态转换，而其他人对应于失败的尝试过渡。这使我们能够第一次表明，不同类型的过渡的成功率受到实验操作的不同影响，并可以解释以前观察到的睡眠模式。Somnotate是开源的，有可能促进睡眠阶段转换的研究，并为睡眠-觉醒动力学的潜在机制提供新的见解。通常情况下，三种不同的警觉状态-清醒，快速眼动睡眠和非快速眼动睡眠-表现出明显的特征，很容易识别的电生理记录。然而，特别是在警戒状态转换周围，时期通常表现出来自多个状态的特征。这些中间警戒状态对现有的手动和自动分类方法构成了挑战，因此经常被忽视。在这里，我们介绍了“Somnotate”-一个开源的，高度准确和强大的睡眠阶段分类器，它支持对小鼠中间状态和睡眠阶段动态的研究。Somnotate量化并报告其注释的确定性，使实验者能够以原则性的方式识别异常时期。我们使用此功能来识别中间状态，并检测不成功的尝试之间切换警惕状态。这有可能为警惕状态转变机制提供新的见解，并为未来的实验创造新的机会。
Electrophysiological recordings from freely behaving animals are a widespread and powerful mode of investigation in sleep research. These recordings generate large amounts of data that require sleep stage annotation (polysomnography), in which the data is parcellated according to three vigilance states: awake, rapid eye movement (REM) sleep, and non-REM (NREM) sleep. Manual and current computational annotation methods ignore intermediate states because the classification features become ambiguous, even though intermediate states contain important information regarding vigilance state dynamics. To address this problem, we have developed "Somnotate"—a probabilistic classifier based on a combination of linear discriminant analysis (LDA) with a hidden Markov model (HMM). First we demonstrate that Somnotate sets new standards in polysomnography, exhibiting annotation accuracies that exceed human experts on mouse electrophysiological data, remarkable robustness to errors in the training data, compatibility with different recording configurations, and an ability to maintain high accuracy during experimental interventions. However, the key feature of Somnotate is that it quantifies and reports the certainty of its annotations. We leverage this feature to reveal that many intermediate vigilance states cluster around state transitions, whereas others correspond to failed attempts to transition. This enables us to show for the first time that the success rates of different types of transition are differentially affected by experimental manipulations and can explain previously observed sleep patterns. Somnotate is open-source and has the potential to both facilitate the study of sleep stage transitions and offer new insights into the mechanisms underlying sleep-wake dynamics. Typically, the three different vigilance states–awake, REM sleep, and non-REM sleep–exhibit distinct features that are readily recognised in electrophysiological recordings. However, particularly around vigilance state transitions, epochs often exhibit features from more than one state. These intermediate vigilance states pose challenges for existing manual and automated classification methods, and are hence often ignored. Here, we present ‘Somnotate’—an open-source, highly accurate and robust sleep stage classifier, which supports research into intermediate states and sleep stage dynamics in mice. Somnotate quantifies and reports the certainty of its annotations, enabling the experimenter to identify abnormal epochs in a principled manner. We use this feature to identify intermediate states and to detect unsuccessful attempts to switch between vigilance states. This has the potential to provide new insights into the mechanisms of vigilance state transitions, and creates new opportunities for future experiments.
登录
查看更多内容
根据2014年AASM标准，美国和中国睡眠中心之间的评估者协议
影响因子：
2.5
作者：
Deng, Shujian;Zhang, Xin;Xu, Yan
通讯作者：
Xu, Yan
影响因子：
3
作者：
Zeng, Tao;Mott, Christopher;Mollicone, Daniel;Sanford, Larry D.
通讯作者：
Sanford, Larry D.
影响因子：
5.6
作者：
通讯作者：
--
影响因子：
9.8
作者：
Bagur S;Lacroix MM;de Lavilléon G;Lefort JM;Geoffroy H;Benchenane K
通讯作者：
Benchenane K
影响因子：
2.9
作者：
Brankack, Jurij;Kukushka, Valeriy I.;Draguhn, Andreas
通讯作者：
Draguhn, Andreas