Using machine learning to improve protein modeling education
Official title: Harnessing Machine Learning & Object Detection for Automated Evaluation of Student-folded Protein Models
Funded at 3d Molecular Designs · NIH-10918783 · Data updated 2026-11-12
This study is all about making learning about proteins more fun and effective for students by using cool digital tools that give instant feedback on their protein models, helping them see and fix mistakes right away.
Quick facts
| Grant type | Sbir 1 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | 3d Molecular Designs NIH-funded |
| Lab location | 1 site (Milwaukee, United States) |
| Project start | August 1, 2024 |
| Project end | January 31, 2026 |
| Funding year | 2024 |
| Award (this year) | $295,921 |
| NIH project number | 1R43GM154526-01 |
| Project ID | NIH-10918783 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal candidates for this research are students and educators involved in bioscience education, particularly those using modeling tools to learn about protein structures.
✕Less likely to help
Patients who are not engaged in bioscience education or do not utilize protein modeling tools may not benefit from this research.
What this research studies
This research focuses on enhancing bioscience education by developing digital applications that provide immediate feedback on student-created protein models. By utilizing machine learning and object detection, the project aims to evaluate the accuracy of models made with mini-toobers, a popular educational tool for representing protein structures. The applications will include augmented reality features to help students understand their modeling mistakes in real-time, thereby improving their learning experience. This innovative approach seeks to address the challenges educators face in assessing student models effectively.
Why it matters
Potential benefit: If successful, this research could significantly enhance the quality of bioscience education by providing students with immediate feedback on their protein modeling efforts.
How similar studies have gone: While the application of machine learning in educational tools is gaining traction, this specific approach to protein modeling feedback is relatively novel and untested.
Where this research is happening
-
3d Molecular Designs
Milwaukee, United States Active
Researchers
- Principal investigator: Ryan, Heather — 3d Molecular Designs
- Study coordinator: Ryan, Heather
Related research
Other NIH-funded projects on the same topics.
-
Automated feedback for student-made protein models using phones and AI
A smartphone app uses AI to give students and teachers immediate feedback on their student-made protein models created with flexible foam tools.
-
Preparing teachers for future pandemics through hands-on science education
This study is all about helping high school science teachers learn more about infectious diseases and new technologies, so they can teach their students better using fun, hands-on tools like 3D-printed protein models.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.