LINA logo

Laboratory for Integrative Neuroscience Analysis

AI Institute - Department of Computer Science and Engineering

The Laboratory for Integrative Neuroscience Analysis (LINA) was founded in 2022 by Christian O’Reilly, shortly after he moved to the University of South Carolina (UofSC), as a way to consolidate the identity of his research group and promote a model-driven approach to the study of neuroscience. It is located within the Artificial Intelligence Institute of South Carolina (AIISC).

Mission statement

The overarching research objective at LINA is to develop principled, model-driven approaches for multi-scale analysis of the brain to better understand this organ across spatial and temporal scales and address complex neurodevelopmental issues such as autism and other neurodevelopmental disorders. We believe in collaborative and open science and harness the highly expressive and powerfully featured Python ecosystem to deploy accessible and agile software. We use different methodological approaches, including analytical techniques (e.g., EEG source reconstruction, functional connectivity) and modeling (e.g., point neurons, morphologically-detailed neurons, neural masses), as well as the combination of these two approaches through Bayesian model-driven analyses. Computational neuroscience is a central element of our toolkit and we aim to contribute to the development of a critical mass of expertise in that area in South Carolina. Further, through our embedding within the AIISC and the Department of Computer Science and Engineering of the UofSC, we also seek to develop novel ways to empower the study of neuroscience through AI and to empower AI through biologically inspired neural networks.

Contact
 

 Lab Location
Storey Engineering and Innovation Center
550 Assembly St., Room 1209
Columbia, SC

 Email
christian.oreilly@sc.edu

 Phone
803-777-8923

Research Interests

By developing generative models of biological systems and the Bayesian inference of their parameters from experimental data, we aim to give researchers access to latent variables not directly observable.

We aim to develop a critical mass of expertise in computational neuroscience (i.e., the modeling and simulation of biological neural systems) at the University of South Carolina. Modeling is the foundation through which engineers can understand and predict the behavior of complex systems. A solid modeling approach to the study of the brain and neurodevelopmental disorders is essential to push the field forward.

Applications of artificial intelligence and machine learning have exploded recently. Yet, we still have a lot to learn from the brain to develop powerful learning machines that are energy efficient. By taking inspiration from the biology of neural systems, we aim to develop better learning machines.

By analyzing biosignals (EEG, ECG, eye-tracking) and neuroimaging (fMRI, fNIRS), we aim to understand how the brain works in health in disease. We currently have projects on autism and affective science.