Applications and Discovery on Brain Networks - REVISED
You may be wondering what happens after all of the time and money is spent on creating a connectome. In this assignment, we’ll walk you through analyzing some brain graphs by creating a program that will learn the difference between graphs of different phenotypes (attributes of an organism). So for example, you could learn which brain networks are likely to belong to a male or female subject.
Please create a 1-2 page submission that covers each of the following 6 criteria. You should also include any code that you use to generate your results with your submission (e.g., a copy of your colab notebook.
Criteria 0 (20 points) Scienceinthe.cloud is not being actively maintained. That’s a bummer for reproducible science. Instead we’ll investigate another very successful reproducible neuroscience project. Visit http://thunder-project.org/ and run the live demo. This should launch a live jupyter notebook in your browser using binder. Exe- cute the tutorials and report on what you’ve learned (how did it go, was it reproducible, easy to follow). Make at least 3 suggestions for improvement and 3 things that worked well. Please also read their paper (Open source tools for large-scale neuroscience) for context here: https://www.ncbi.nlm.nih.gov/pubmed/25982977)
Criteria 1 (25 points) compute and visualize mean connectomes for all of the data
Criteria 2 (25 points) compute and visualize class conditional connectomes (e.g., male and female subpopulations)
Criteria 3 (30 points) compute 5 different covariates related to graphs
Criteria 4 (20 points) interpret meaning of covariates, with some hypothesis connect- ing to neuroscience
Criteria 5 (30 points) build classifier and obtain classification score at 70% or higher
Total 150 points
Instructions for Analysis Environment
To greatly simplify this assignment, we’ve created a Jupyter notebook in Google Colab with detailed instructions; the original instructions requested you to set up a Docker-backed python environment on your local computer. This will instead run self-contained browser. If you are interested in learning more, please get in touch! Go here to get started:
Click on the colab link to launch a copy of the notebook in your own space.
The ready solutions purchased from Library are already used solutions. Please do not submit them directly as it may lead to plagiarism. Once paid, the solution file download link will be sent to your provided email. Please either use them for learning purpose or re-write them in your own language. In case if you haven't get the email, do let us know via chat support.
Get Free Quote!
269 Experts Online