Machine Learning in Cancer class assignments. Various supervised and unsupervised machine learning methods are used. Jupyter notebooks of code available for Homework 3 and 4 (also many models are built in those assignments). Worked independently throughout.
Data Retrieval: Download and explore some RNA-seq data from the GDC. In this homework (Homework 1), you should become familiar with the GDC, some of its data, and become familiar how to access the data. Please download some RNA-seq data from the TCGA head and neck cancer project (TCGA-HNSC), explore the data, and create a histogram of the counts (from at least one) of the samples.
The goal of this lab is to cluster the TCGA-HNSC RNA-seq data from the GDC. In this lab, you should get some hands-on experience clustering RNA-seq data. Analyze and provide any biological interpretations of data.
The primary goal of this lab is to have you build one or more types of machine learning models for predicting drug response. We will use data from the GDSC. This data consists of drug response data from 265 drugs tested on ~1000 cell lines as discussed in class.
In this assignment we are going to work with both the Normal/Tumor datasets and the Cancer Type datasets discussed in class. The goal is to build some machine learning models using these datasets.
The goal of this assignment is to build a very simple model to model the relationship, if any, between the incidence level of colon and rectum cancer for each county and the income level for that county.