RESUMO
Keypoint tracking algorithms can flexibly quantify animal movement from videos obtained in a wide variety of settings. However, it remains unclear how to parse continuous keypoint data into discrete actions. This challenge is particularly acute because keypoint data are susceptible to high-frequency jitter that clustering algorithms can mistake for transitions between actions. Here we present keypoint-MoSeq, a machine learning-based platform for identifying behavioral modules ('syllables') from keypoint data without human supervision. Keypoint-MoSeq uses a generative model to distinguish keypoint noise from behavior, enabling it to identify syllables whose boundaries correspond to natural sub-second discontinuities in pose dynamics. Keypoint-MoSeq outperforms commonly used alternative clustering methods at identifying these transitions, at capturing correlations between neural activity and behavior and at classifying either solitary or social behaviors in accordance with human annotations. Keypoint-MoSeq also works in multiple species and generalizes beyond the syllable timescale, identifying fast sniff-aligned movements in mice and a spectrum of oscillatory behaviors in fruit flies. Keypoint-MoSeq, therefore, renders accessible the modular structure of behavior through standard video recordings.
Assuntos
Algoritmos , Comportamento Animal , Aprendizado de Máquina , Gravação em Vídeo , Animais , Camundongos , Comportamento Animal/fisiologia , Gravação em Vídeo/métodos , Movimento/fisiologia , Drosophila melanogaster/fisiologia , Humanos , MasculinoRESUMO
Rostro-caudal patterning of vertebrates depends on the temporally progressive activation of HOX genes within axial stem cells that fuel axial embryo elongation. Whether the pace of sequential activation of HOX genes, the 'HOX clock', is controlled by intrinsic chromatin-based timing mechanisms or by temporal changes in extrinsic cues remains unclear. Here, we studied HOX clock pacing in human pluripotent stem cell-derived axial progenitors differentiating into diverse spinal cord motor neuron subtypes. We show that the progressive activation of caudal HOX genes is controlled by a dynamic increase in FGF signaling. Blocking the FGF pathway stalled induction of HOX genes, while a precocious increase of FGF, alone or with GDF11 ligand, accelerated the HOX clock. Cells differentiated under accelerated HOX induction generated appropriate posterior motor neuron subtypes found along the human embryonic spinal cord. The pacing of the HOX clock is thus dynamically regulated by exposure to secreted cues. Its manipulation by extrinsic factors provides synchronized access to multiple human neuronal subtypes of distinct rostro-caudal identities for basic and translational applications.This article has an associated 'The people behind the papers' interview.
Assuntos
Relógios Circadianos , Proteínas de Homeodomínio/metabolismo , Neurônios Motores/metabolismo , Células-Tronco Pluripotentes/metabolismo , Benzamidas/farmacologia , Proteínas Morfogenéticas Ósseas/genética , Proteínas Morfogenéticas Ósseas/metabolismo , Proteínas Morfogenéticas Ósseas/farmacologia , Diferenciação Celular , Relógios Circadianos/efeitos dos fármacos , Difenilamina/análogos & derivados , Difenilamina/farmacologia , Embrião de Mamíferos/citologia , Embrião de Mamíferos/metabolismo , Desenvolvimento Embrionário , Fatores de Crescimento de Fibroblastos/antagonistas & inibidores , Fatores de Crescimento de Fibroblastos/metabolismo , Fatores de Crescimento de Fibroblastos/farmacologia , Regulação da Expressão Gênica no Desenvolvimento , Fatores de Diferenciação de Crescimento/genética , Fatores de Diferenciação de Crescimento/metabolismo , Fatores de Diferenciação de Crescimento/farmacologia , Proteínas de Homeodomínio/genética , Humanos , Neurônios Motores/citologia , Células-Tronco Pluripotentes/citologia , Pirimidinas/farmacologia , Transdução de Sinais/efeitos dos fármacos , Medula Espinal/metabolismoRESUMO
Studying the intricacies of individual subjects' moods and cognitive processing over extended periods of time presents a formidable challenge in medicine. While much of systems neuroscience appropriately focuses on the link between neural circuit functions and well-constrained behaviors over short timescales (e.g., trials, hours), many mental health conditions involve complex interactions of mood and cognition that are non-stationary across behavioral contexts and evolve over extended timescales. Here, we discuss opportunities, challenges, and possible future directions in computational psychiatry to quantify non-stationary continuously monitored behaviors. We suggest that this exploratory effort may contribute to a more precision-based approach to treating mental disorders and facilitate a more robust reverse translation across animal species. We conclude with ethical considerations for any field that aims to bridge artificial intelligence and patient monitoring.
Assuntos
Psiquiatria , Humanos , Animais , Psiquiatria/métodos , Psiquiatria/tendências , Etologia/métodos , Transtornos Mentais/terapia , Inteligência ArtificialRESUMO
Spatially modulated neurons known as grid cells are thought to play an important role in spatial cognition. A new study has found that units with grid-cell-like properties can emerge within artificial neural networks trained to path integrate, and developed a unifying theory explaining the formation of these cells which shows what circuit constraints are necessary and how learned systems carry out path integration.
Assuntos
Córtex Entorrinal , Redes Neurais de Computação , Córtex Entorrinal/fisiologia , Neurônios/fisiologia , Cognição , Aprendizagem , Modelos Neurológicos , Percepção Espacial/fisiologia , Potenciais de Ação/fisiologiaRESUMO
We propose centralized brain observatories for large-scale recordings of neural activity in mice and non-human primates coupled with cloud-based data analysis and sharing. Such observatories will advance reproducible systems neuroscience and democratize access to the most advanced tools and data.
Assuntos
Encéfalo , Neurociências , Animais , CamundongosRESUMO
Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological understanding, but are limited by current processing approaches which inefficiently distill data into relevant information. We argue that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge. Incorporating machine learning into ecological workflows could improve inputs for ecological models and lead to integrated hybrid modeling tools. This approach will require close interdisciplinary collaboration to ensure the quality of novel approaches and train a new generation of data scientists in ecology and conservation.
Assuntos
Animais Selvagens , Conservação dos Recursos Naturais , Ecologia , Aprendizado de Máquina , Animais , Automação , Ecossistema , Conhecimento , Modelos TeóricosRESUMO
Recent work is revealing neural correlates of a leading theory of motor control. By linking an elegant series of behavioral experiments with neural inactivation in macaques with computational models, a new study shows that premotor and parietal areas can be mapped onto a model for optimal feedback control.
Assuntos
RetroalimentaçãoRESUMO
The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data. The field of movement science already elegantly incorporates theory and engineering principles to guide experimental work, and in this review we discuss the growing use of machine learning: from pose estimation, kinematic analyses, dimensionality reduction, and closed-loop feedback, to its use in understanding neural correlates and untangling sensorimotor systems. We also give our perspective on new avenues, where markerless motion capture combined with biomechanical modeling and neural networks could be a new platform for hypothesis-driven research.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Fenômenos Biomecânicos , Movimento (Física) , MovimentoRESUMO
The ability to control a behavioral task or stimulate neural activity based on animal behavior in real-time is an important tool for experimental neuroscientists. Ideally, such tools are noninvasive, low-latency, and provide interfaces to trigger external hardware based on posture. Recent advances in pose estimation with deep learning allows researchers to train deep neural networks to accurately quantify a wide variety of animal behaviors. Here, we provide a new