ADVANCED TOPICS IN BIOINFORMATICS
Course: BBS741 - Advanced Topics in Bioinformatics
Semester Offered: Fall 2020, Fall 2022
Tuesdays, 9:00-11:00am
Professor:
Zhiping Weng, Zhiping.Weng@umassmed.edu
Course Topics:
- Introduction to machine learning
- Unsupervised learning: clustering
- Unsupervised learning: Principal component analysis
- Unsupervised learning: t-SNE and UMAP
- Project for unsupervised learning techniques
- Linear regression
- Classification
- Resampling methods
- Project for linear learning techniques
- Regularization
- Decision trees, bagging, and random forest
- Neural networks
- Deep Learning
- Project for nonlinear learning techniques
- Expectation Maximization
- Hidden Markov models
- Project for graphical learning techniques
- Project presentations
Course prerequisites:
This course is designed for graduate students who are interested in pursuing Bioinformatics and Computational Biology research. Previous programming experience, particularly in Python, is highly recommended. This course will cover a range of topics in the fields of statistical and machine learning so prior coursework in linear algebra or statistics is also recommended.
Course materials:
Students will be required to have a laptop computer with access to Python. Instructions for required package installation will be sent prior to each assignment
Lectures will draw from the following textbooks:
- Introduction to Statistical Learning with applications in R by James, Witten, Hastie, and Tibshirani
- Deep Learning by Goodfellow, Bengio and Courville
- Pattern Recognition and Machine Learning by Bishop
- Machine Learning: A Probabilistic Perspective by Murphy
Python resources:
https://www.pythonforbeginners.com/files/reading-and-writing-files-in-python
https://stackoverflow.com/questions/9039961/finding-the-average-of-a-list
https://stackoverflow.com/questions/35966940/finding-the-max-of-a-column-in-an-array
https://jakevdp.github.io/PythonDataScienceHandbook/02.04-computation-on-arrays-aggregates.html
Grading:
There will be one homework assignment, four projects and one final presentation for this course. Final grades will be calculated as follows