What is Neuroinformatics?
The NI group uses the term neuroinformatics in a broad and inclusive way.
Neuroinformatics refers to the application of a cluster of powerful quantitative modeling techniques to the analysis and interpretation of complex data sets representing a broad spectrum of brain, neural, and mental health research problems. Such applications are often associated with advances in Artificial Intelligence, machine learning, computational modeling, data science, and multi-omics technologies.
These analytic approaches are flexible and can accommodate multiple modalities of data. They can operate within—but also integrate across—research projects that feature:
- Data-driven or hypothesis-guided designs,
- Big data (variables, persons, dimensional) or selective data sets,
- Both dynamic (longitudinal) and static data structures.
Research Applications: NI members are engaged in research spanning a wide and fertile range of complementary topics, including: neuroimaging, genomics, epigenetics, cognition, neurodevelopment, neurodegeneration, neurochemistry, mental health, psychiatric, electrophysiological, synapses/signaling, sensory-motor systems, protein misfolding, spinal cord, and neural injury/repair. Our researchers operate at multiple levels of research (cellular, molecular, neural, cognitive, behavioral) and include both animal models and human participants. Within the NI group, neuroinformatics approaches are helping members link:
- Preclinical with clinical research,
- Big data analytics with precision health application,
- Mechanistic insights with intervention and prevention aspirations.
Training Initiatives: Trainees at all levels are involved directly or indirectly in NI research activities.
As the NI group matures, we will enhance opportunities for NMHI trainees to learn, practice, share, and apply advanced computational tools in their own and collaborative research projects. An educational culture that supports the testing of new and integrative neuroscience research questions with optimal research tools, providing a foundation for further professional development in a broad range of neuroscience-related careers (academic, industry, clinical, public health) will be developed.
Our informal curriculum will include offerings in the form of seminars, webinars, workshops, guest lectures, internships, hackathons, panel discussions, lab visits, and student presentations. Specific topics for learning opportunities include:
- Identifying and accessing big data archives
- Data wrangling and data mining
- Typical challenges (small n, unbalanced data, power, missing data)
- Neuroinformatics for precision analyses in multimodal data
- Machine and deep learning (e.g., classifier algorithms)
- R or Python for data analysis
- Computational cognition, memory, neuroscience, psychiatry
- Person-centered analytics
- Structural equation modeling
- Longitudinal analytics
- Data visualization
- Science dissemination and communication
- NI in an open science era