UWMadisonMLM25

Repository for UW-Madison Machine Learning Marathon 2025

Project Kanban Board

To Do

In Progress

• Get ESM running on Platform R - Zach
  • Show group how to do - Zach
• Read MaveDB paper: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1845-6
  • Mike
  • Zach
  • Sean
  • Brendan
• Read Kaggle website (https://www.kaggle.com/competitions/mave-db-amino-acid-substitution-prediction/data)
  • Mike
  • Zach
  • Sean
  • Brendan

Done

• Download Data
  • Mike
  • Zach
  • Sean
  • Brendan
• Code to generate protein sequences and variants - Brendan
• EDA Slides due 9/30
  • Create slide deck - Mike 9/22 (https://docs.google.com/presentation/d/1bbqywkXwJe28KgNbH5wtFZf6BR64EssxS5nZa9J39Ks/edit?usp=sharing)
  • Explanation of problem - Mike 9/22
  • First fit of a model results - Mike 9/29
  • Key technologies used
    • Figure for ESM - Zach or Brendan
    • Explanation of getting downloading proteins embeddings - Zach or Brendan
  • Initial EDA explanation
    • Best figure for showing proteins in embedding space- Zach
    • Best figure for showing distribution of variants - Sean
  • Next steps
    • Update with at least one bullet point for next steps
      • Mike 9/29
      • Zach
      • Sean
      • Brendan