Video Gamers Beat Scientists and Computers in Protein Folding Competition

Researchers from the University of Michigan (U-M) have discovered that video gamers can be as good or better than professionally trained crystallographers and computer algorithms at identifying the shape of a protein, a finding that has the potential to bolster citizen science initiatives and classroom gamification.

The researchers held a competition "to interpret biochemical data in order to discover the protein's structure," according to a news release. Participants included 469 gamers, two trained crystallographers, 61 University of Michigan undergraduate students with computer modeling training, and two separate computer algorithms.

The video gamers were playing Foldit, a computer-based videogame that challenges players to use their puzzle-solving skills to fold 3-D graphical representations of proteins and consequently contribute to crowdsourced scientific research into diseases such as HIV, cancer and Alzheimer's. In the end, the video gamers outperformed all other groups in the competition.

Analysis of the competition results "uncovered a new family of proteins that appears to be involved in preventing plaque formation, which is implicated in diseases like Alzheimer's," stated the news release.

One major difference between the winning gamers and the other groups is that the video gamers worked collaboratively, while the crystallographers, computer modeling students and computer algorithms worked independently. The researchers concluded that collaboration may improve results in this type of research.

"We think this is a big deal because interpreting an electron-density map can be a labor-intensive, error-prone process — and we show that crowd-sourced Foldit players can do it as well as, or better than, professionally trained crystallographers," said Brian Koepnick in a prepared statement. Koepnick  is a graduate student from the University of Washington Institute for Protein Design, and a member of the team that designed the contest and analyzed its results.

Through this competition, the researchers picked up some tips and tricks from the gamers and plan to incorporate those findings into the software scientists use when modeling protein structures.

Scott Horowitz, a postdoctoral fellow at U-M and co-author of the study, said he plans to start using Foldit in his classes. "I've seen how much players learn about proteins from playing this game,"he told Michigan News. "We spend weeks and weeks trying to jam this into students' brains and Foldit players learn it naturally because it's fun."

The study was led by U-M researchers in collaboration with the University of Washington, University of Massachusetts-Dartmouth and Northeastern University, according to Michigan News. The study has been published in Nature Communications.

About the Author

Leila Meyer is a technology writer based in British Columbia. She can be reached at [email protected].

Featured

  • The AI Show

    Register for Free to Attend the World's Greatest Show for All Things AI in EDU

    The AI Show @ ASU+GSV, held April 5–7, 2025, at the San Diego Convention Center, is a free event designed to help educators, students, and parents navigate AI's role in education. Featuring hands-on workshops, AI-powered networking, live demos from 125+ EdTech exhibitors, and keynote speakers like Colin Kaepernick and Stevie Van Zandt, the event offers practical insights into AI-driven teaching, learning, and career opportunities. Attendees will gain actionable strategies to integrate AI into classrooms while exploring innovations that promote equity, accessibility, and student success.

  • cloud, database stack, computer screen, binary code, and flowcharts interconnected by lines and arrows

    Salesforce to Acquire Data Management Firm Informatica

    Salesforce has announced plans to acquire data management company Informatica for $8 billion. The deal is aimed at strengthening Salesforce's AI foundation and expanding its enterprise data capabilities.

  • stylized AI code and a neural network symbol, paired with glitching code and a red warning triangle

    New Anthropic AI Models Demonstrate Coding Prowess, Behavior Risks

    Anthropic has released Claude Opus 4 and Claude Sonnet 4, its most advanced artificial intelligence models to date, boasting a significant leap in autonomous coding capabilities while simultaneously revealing troubling tendencies toward self-preservation that include attempted blackmail.

  • NVIDIA DGX line

    NVIDIA Intros Personal AI Supercomputers

    NVIDIA has introduced a new lineup of AI-powered computing solutions designed to accelerate enterprise workloads.