Graph Analysis
Applications and Discovery on Brain Networks - REVISED
Introduction
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.
Assignment
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:
github.com/wrgr/graph-explorer/blob/master/graph_explorer_2020.ipynb
Click on the colab link to launch a copy of the notebook in your own space.
DescriptionIn this final assignment, the students will demonstrate their ability to apply two ma
Path finding involves finding a path from A to B. Typically we want the path to have certain properties,such as being the shortest or to avoid going t
Develop a program to emulate a purchase transaction at a retail store. Thisprogram will have two classes, a LineItem class and a Transaction class. Th
1 Project 1 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of
1 Project 2 Introduction - the SeaPort Project series For this set of projects for the course, we wish to simulate some of the aspects of a number of