SEAStats

Stats and data science learning resources for researchers in the USDA ARS Southeast Area

View the Project on GitHub
USDA-REE-ARS/SEAStats

Contents:

Contents:

This project is maintained by USDA-REE-ARS

Minimalistic — Theme by vaibhavvikas

Little Rock May 2025 Workshop: Machine Learning and MultiOmics with R

All lessons will be delivered virtually via MS Teams. You should have an invitation to the Teams meeting in your email. All times on this agenda are Central Daylight Time.

Pre-workshop instructions

If you want to follow along with the code in this workshop, you will need to install the necessary software on your own machine.

  • First, install R and RStudio on your computer, following steps 1 and 2 of these instructions.
  • Next, install Git on your computer, choosing the appropriate version depending on whether you are on MacOS or Windows.
  • Restart your machine to allow changes in system configuration to take effect.
  • Then, you will need to open RStudio and run the code in the omics workshop setup script. Do this by opening the script file within RStudio and clicking the “Source” button at the top of the script.
  • Finally, you will need to download all the code worksheets and save them locally. We’ll be working off of those during the lessons. See the workshop materials section below.

If you need help with this, I strongly recommend you join the Teams meeting at 1:00-2:00 PM, Friday, May 30 for the software installation troubleshooting office hour! We may not have time during the workshop to troubleshoot any installation issues that may arise.

Workshop agenda and materials

You will need to bring your laptops, with software installed following the above instructions, to participate in the hands-on sessions. Before each lesson, you will need to open that lesson’s code worksheet in your RStudio session. Links to individual worksheets are found with the materials for each day, or you can download all worksheets at once as a .zip file.

.zip file with all worksheets

Day 1: Monday, June 2

Intro to R Programming and Machine Learning

Day 1 Agenda

  • 9:30 AM - 10:45 AM: R Boot Camp lesson 1 - The very basics of R
  • 10:45 AM - 11:00 AM: Break
  • 11:00 AM - 12:00 PM: R Boot Camp lesson 2 - Working with data frames in R
  • 12:00 PM - 1:00 PM: Lunch
  • 1:00 PM - 2:15 PM: Machine Learning Demystified
  • 2:15 PM - 2:30 PM: Break
  • 2:30 PM - 4:00 PM: Machine Learning Demystified, continued

Day 1 Materials

Full-text version Slides Worksheets Answers to Exercises
R Boot Camp Lesson 1: The very basics Slides Worksheet / Worksheet filled in Answers
R Boot Camp Lesson 2: Working with data frames Slides Worksheet / Worksheet filled in Answers
Machine Learning Demystified Slides Worksheet / (Worksheet filled in) Answers

Day 2: Tuesday, June 3

A Whirlwind Tour of Multiomics Analysis Techniques in R

Day 2 Agenda

  • 9:30 AM - 10:45 AM: MultiOmics introductory slides, code-along demo
  • 10:45 AM - 11:00 AM: Break
  • 11:00 AM - 12:00 PM: MultiOmics code-along demos continue
  • 12:00 PM - 1:00 PM: Lunch
  • 1:00 PM - 2:15 PM: MultiOmics code-along demos continue
  • 2:15 PM - 2:30 PM: Break
  • 2:30 PM - 4:00 PM: Optional office hours, where participants may ask about course materials, go over “homework” exercises, or bring their own data to consult about

Day 2 Materials

Full-text version Worksheets
Demo 1: Multiomics Factor Analysis (MOFA) mouse single-cell omics case study Worksheet / Worksheet filled in
Demo 2: MOFA chronic leukemia case study Worksheet / Worksheet filled in
Demo 3: mixOmics sPLS-DA small round blue cell tumors case study Worksheet / Worksheet filled in
Demo 4: DESeq2 differential expression analysis, Drosophila Pasilla RNAseq case study Worksheet / Worksheet filled in
Demo 5: mixOmics DIABLO breast cancer TCGA case study Worksheet / Worksheet filled in

Post-workshop survey

Please help me improve future trainings by taking a quick (<5 minute) survey telling me what you thought about the workshop!

MS Forms feedback survey

Page last updated 2025-05-23