Convergence: RAISE Integrating machine learning and biological neural networks

融合：RAISE 集成机器学习和生物神经网络

• 批准号: 1848029
• 负责人: Xue Han
• 金额: $ 100万
• 依托单位: Trustees of Boston University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1848029&HistoricalAwards=false
• 关键词: Convergence; RAISE; Integrating; machine; learning

The field of neuroscience is undergoing a rapid transformation, and within the next decade, it may become possible to capture data from millions of individual neurons at the same time. Such a technological advancement would allow scientists to record and analyze a significant fraction of the brain's neural network at unprecedented spatial and time resolutions. The goal of this research project is to advance our understanding of brain activity through the integration of bioengineering, systems neuroscience and data science and their application to the study of networks of neurons. The research team will engineer new sensors designed to image the activity of individual neurons within a large network and then apply this method to the study of functioning neural systems. The team will also develop computational methods to extract information from the resulting, extremely large datasets. This research will have broader impact through training STEM students in a convergent science area and through deepening our understanding of the science underlying neurological disease and thereby improving mental health treatment.This research project aims to create novel protein sensors to acquire single-neuron-resolution imaging data. This methodology could serve as the basis for ultra-large-scale neural network imaging. The researchers will establish the architectural principles and fundamental limits for fluorescence imaging systems and inference algorithms that extract underlying neural activity. They will then develop machine learning techniques to extract network-level phenomena from high-dimensional neural data. Finally, the researchers will study large networks of neurons during behavior and learning via carefully-designed experiments and machine learning techniques. The technologies developed in this work, to acquire and to analyze, single-neuron-resolution imaging data, will facilitate the understanding of brain's neural network computation at an ultra-large scale, directly confronting challenging societal problems related to the human brain. The project participants will also educate the next generation of engineers and scientists in the convergent area of neuroscience with data science.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

神经科学领域正在经历快速的变革，在未来十年内，可能会同时捕获数百万个神经元的数据。 这样的技术进步将使科学家能够以前所未有的空间和时间分辨率记录和分析大脑神经网络的重要部分。 该研究项目的目标是通过整合生物工程，系统神经科学和数据科学及其在神经元网络研究中的应用，促进我们对大脑活动的理解。 该研究小组将设计新的传感器，用于对大型网络中单个神经元的活动进行成像，然后将这种方法应用于功能神经系统的研究。 该团队还将开发计算方法，从由此产生的超大数据集中提取信息。 本研究将通过在融合科学领域培养STEM学生，加深我们对神经系统疾病的科学基础的理解，从而改善心理健康治疗，从而产生更广泛的影响。本研究项目旨在创建新型蛋白质传感器，以获取单神经元分辨率的成像数据。 这种方法可以作为超大规模神经网络成像的基础。 研究人员将建立荧光成像系统的架构原理和基本限制，以及提取潜在神经活动的推理算法。 然后，他们将开发机器学习技术，从高维神经数据中提取网络级现象。 最后，研究人员将通过精心设计的实验和机器学习技术研究行为和学习过程中的大型神经元网络。 在这项工作中开发的技术，以获取和分析，单神经元分辨率成像数据，将有助于在超大规模的大脑神经网络计算的理解，直接面对与人类大脑相关的具有挑战性的社会问题。 该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

CaMKIIα-Positive Interneurons Identified via a microRNA-Based Viral Gene Targeting Strategy

• DOI: 10.1523/jneurosci.2570-19.2020
• 发表时间: 2020-12-09
• 期刊: JOURNAL OF NEUROSCIENCE
• 影响因子: 5.3
• 作者: Keaveney, Marianna K.;Rahsepar, Bahar;Han, Xue
• 通讯作者: Han, Xue

Large-scale voltage imaging in the brain using targeted illumination

• DOI: 10.1101/2021.04.05.438451
• 发表时间: 2021-04
• 期刊: bioRxiv
• 作者: Sheng Xiao;E. Lowet;H. Gritton;Pierre Fabris;Yangyang Wang;J. Sherman;Rebecca A. Mount;Hua-an Tseng;H. Man;J. Mertz;Xue Han

Population imaging of neural activity in awake behaving mice

• DOI: 10.1038/s41586-019-1641-1
• 发表时间: 2019-10-17
• 期刊: NATURE
• 影响因子: 64.8
• 作者: Piatkevich, Kiryl D.;Bensussen, Seth;Han, Xue
• 通讯作者: Han, Xue

A Teensy microcontroller-based interface for optical imaging camera control during behavioral experiments

• DOI: 10.1016/j.jneumeth.2019.03.019
• 发表时间: 2019-05-15
• 期刊: JOURNAL OF NEUROSCIENCE METHODS
• 影响因子: 3
• 作者: Romano, Michael;Bucklin, Mark;Han, Xue
• 通讯作者: Han, Xue

Precision Calcium Imaging of Dense Neural Populations via a Cell-Body-Targeted Calcium Indicator

• DOI: 10.1016/j.neuron.2020.05.029
• 发表时间: 2020-08-05
• 期刊: NEURON
• 影响因子: 16.2
• 作者: Shemesh, Or A.;Linghu, Changyang;Boyden, Edward S.
• 通讯作者: Boyden, Edward S.