Science · Coding
Machine learning and yeast variation
Katarina Aranguiz · A biochemistry student combined laboratory experience with computational work on diverse yeast species.
Project stage: During college
How it developed
College-stage lab work
Aranguiz joined Chris Todd Hittinger's genetics lab at UW–Madison.
Add a computational approach
She led efforts using machine learning to study phenotypic variation across yeast species.
2024 · Research support
The report identifies a Sophomore Research Fellowship and selection as a Goldwater Scholar.
Resources behind the work
Faculty mentoring, laboratory access and fellowship support accompanied the work. The source does not give a complete project budget.
What the evidence does not tell us
The report does not establish a commercial bioproduct or a model's accuracy. Earlier wet-lab experience is described without a full timeline.
Pathfind's starting point
Try a smaller version
Combining methods is useful when each method answers a clearly defined part of the question.
An original exercise inspired by the story, not the student's instructions or a promise of the same result.
- Find a licensed public table of organism traits and write one descriptive question it can answer.
- Make simple plots before trying prediction, keeping missing values visible.
- Compare one baseline model with your plots and explain errors and data limits in a teacher-reviewed report.
Includes the steps, source links and related groups. No signup needed.
Connect with the student or project
No published professional contact route is included in the sources we reviewed. You can still read the original account and explore related groups below.
Find people to build with
Groups with related interests. These links do not imply the student joined or endorses them.