“A Neural Data Science: How and Why” published March 26, 2018 by Mark Humphries. You can read it here.
At the core of the field of Neuroscience lies the question: how does the brain work? The human brain is comprised of billions of neurons that communicate by sending electrical and chemical signals to one another. The vast amount of data collected from neural recordings has led to an emerging field: neural data science. Using machine learning techniques, neural data can be explored to answer crucial questions regarding the collaboration and inter-connectedness of neurons in the brain.
Imagine you have n amount of neurons that you compile into a matrix with n columns and rows for every time-point at which data was collected. Using machine learning, this data can be modeled to answer specific systems-Neuroscience questions such as what is the structure of neural spikes? What causes the spikes? What are the inputs and outputs of these spikes?
Applications of Machine Learning for Systems Neuroscience
Through use of machine learning approaches and data science tools, Neuroscience big data has become incredibly accessible and promising for those interested in further studying the underlying principles of neural circuitry.
Many Neuroscience-oriented research labs across the country are taking a data-science approach to further the understanding of how the brain works.
This lab, headed by Eva L. Dyer, PhD., centers its research on the analyzing and interpretation of “complex neuroscience datasets” through machine learning.
Image source: A. Balwani+, J. Miano+, R. Liu, L. Kitchell, J.A. Prasad, E.C. Johnson, W. Gray-Roncal, E.L. Dyer, Multi-scale modeling of neural structure in X-ray imagery, to appear at the IEEE International Conf. on Image Processing (ICIP), 2021
Recent Papers:
A. Balwani+, J. Miano+, R. Liu, L. Kitchell, J.A. Prasad, E.C. Johnson, W. Gray-Roncal, E.L. Dyer, Multi-scale modeling of neural structure in X-ray imagery, to appear at the IEEE International Conf. on Image Processing (ICIP), 2021 (Paper)
C-H. Lin, M. Azabou, E.L. Dyer, Making transport more robust and interpretable by moving data through a small number of anchor points, to appear at the International Conference on Machine Learning (ICML), 2021
This lab is led PI Kristofer Bouchard and develops data science tools to explore how neural circuits lead to behaviors and perception.
Image source: Sparse coding of ECoG signals identifies interpretable components for speech control in human sensorimotor cortex. Bouchard, K.E.*, Bujan, A.F., Chang, E.F., Sommer, F.T.; IEEE, EMBC, Aug., 2017.
Recent Papers
Improved inference in coupling, encoding, and decoding models and its consequence for neuroscientific interpretation. Sachdeva, P.S., Livezey, J.A., Dougherty, M.E., Gu, B.M., Berke, J.D., Bouchard, K.E., J. Neuroscience Mthds, 2021
Deep-learning as a data analysis tool for systems neuroscience. Livezey, J., Bouchard, K.E.\(, Chang, E.F.\); PLoS Computational Biology, 15(9): e1007091. Sept, 2019.
As a Neuroscience major and Data Science minor, I am fascinated by the implications that neural data science has for the field of Neuroscience at large. The largely computational nature of the brain poses an interesting opportunity for the use of programming and machine learning in exploration. I think that models of neural signaling, such as those described by Humphries, may be the future of understanding many neurological disorders such as epilepsy.
“The Core Computational Priciples of a Neuron” is an article in The Spike written by Viacheslav Osaulenko on Janurary 7, 2021. You can read it here.
This article is educational for those wanting to learn more about how the brain can be analyzed using computational techniques. It discusses the binary nature of neurons, how neurons integrate information, and survival methods used by neurons.
“Why Neuroscience Needs Data Scientists” is an article by the Simons Foundation written by Emily Singer and published November 19, 2018. You can read it here.
This article contains interview questions and responses by a reporter and Dr. Liam Paninski, a professor of statistics and Neuroscience at Columbia University. In the article, Dr. Paninski details how statistical Neuroscience is a growing field with a need for skilled data scientists.