RESEARCH: PROTEIN-AI-MODELING
FOLDING PROJECT #19504 PROFILE
PROJECT TEAM
Manager(s): Andreas KrämerInstitution: Freie Universität Berlin
Project URL: View Project Website
WORK UNIT INFO
Atoms: 38,367Core: 0x22
Status: Public
Related Projects
TLDR; PROJECT SUMMARY AI BETA
This project uses AI to understand how proteins move and interact. This can help us predict how viruses change and design new medicines.
Note: This TLDR is a simplication and may not be 100% accurate.OFFICAL PROJECT DESCRIPTION
Summary The AI4Science Group at Freie Universität Berlin develops machine learning methods for physical sciences, with a focus on physics-constrained learning algorithms, complex dynamical systems analysis, efficient generative learning methods for statistical mechanics, and highly accurate machine learning methods for quantum mechanics.
They are an interdisciplinary team of mathematicians, chemists, physicists, and computer scientists. Details The primary objective of this project is to develop large-scale artificial intelligence (AI) models to efficiently sample protein dynamics and predict the stability of folded states and protein-protein interactions.
Being able to do this efficiently and accurately would be a game-changer for the prediction of virus mutants and the design of therapies for various diseases.
AI techniques have demonstrated exceptional performance on benchmark systems and have the potential to vastly speed up computations yet maintain comparable levels of accuracy as classical molecular dynamics simulations. The project aims to generate a comprehensive dataset of small protein systems that will provide the necessary information for creating the next generation of AI models for protein simulations.
We will collaborate with the Clementi Group at Freie Universität Berlin to achieve this goal.
RELATED TERMS GLOSSARY AI BETA
artificial intelligence
Simulating human intelligence processes in machines
Artificial intelligence (AI) is a field of computer science that aims to create systems capable of performing tasks that typically require human intelligence, such as learning, problem-solving, and decision-making. AI models are trained on vast datasets to recognize patterns and make predictions. Applications of AI include image recognition, natural language processing, and self-driving cars.
protein dynamics
The motion and flexibility of proteins over time
Protein dynamics refers to the constant movement and fluctuations in the shape and structure of protein molecules. These motions are essential for protein function, allowing them to interact with other molecules, carry out catalytic reactions, and transport substances. Studying protein dynamics helps us understand how proteins work at a molecular level and can provide insights into diseases caused by protein misfolding or dysfunction.
protein-protein interactions
The binding of two or more protein molecules together
Protein-protein interactions are crucial for various cellular processes, such as signal transduction, gene regulation, and metabolism. Proteins interact with each other through specific binding sites, forming complexes that carry out complex functions. Understanding protein-protein interactions is essential for developing new drugs and therapies.
virus mutants
Variants of a virus with genetic mutations that may alter its characteristics
Virus mutants are variants of a virus that have undergone genetic changes, leading to alterations in their properties. These mutations can affect the virus's infectivity, virulence, or resistance to antiviral drugs. The emergence of new virus mutants poses a significant challenge for public health, as it can lead to outbreaks of new diseases or increase the severity of existing ones.
therapies
Treatments for diseases or medical conditions
Therapies are interventions aimed at treating or managing diseases and improving patient health. They can involve medications, surgery, lifestyle changes, or a combination of approaches. The development of new therapies is a crucial aspect of healthcare research and innovation.
PROJECT FOLDING PPD AVERAGES BY GPU
Data as of Sunday, 26 April 2026 03:24:29|
Rank Project |
Model Name Folding@Home Identifier |
Make Brand |
GPU Model |
PPD Average |
Points WU Average |
WUs Day Average |
WU Time Average |
|---|---|---|---|---|---|---|---|
| 1 | TITAN V GV100 [TITAN V] M 12288 |
Nvidia | GV100 | 4,066,190 | 132,962 | 30.58 | 0 hrs 47 mins |
| 2 | GeForce RTX 2070 TU106 [GeForce RTX 2070] |
Nvidia | TU106 | 2,999,360 | 119,743 | 25.05 | 0 hrs 57 mins |
| 3 | GeForce RTX 2060 Super TU106 [GeForce RTX 2060 SUPER] |
Nvidia | TU106 | 2,203,521 | 109,302 | 20.16 | 1 hrs 11 mins |
| 4 | GeForce RTX 2070 Mobile TU106BM [GeForce RTX 2070 Mobile] |
Nvidia | TU106BM | 2,153,956 | 108,276 | 19.89 | 1 hrs 12 mins |
| 5 | GeForce RTX 2060 TU104 [GeForce RTX 2060] |
Nvidia | TU104 | 2,128,565 | 108,330 | 19.65 | 1 hrs 13 mins |
| 6 | GeForce GTX 1080 Ti GP102 [GeForce GTX 1080 Ti] 11380 |
Nvidia | GP102 | 2,019,072 | 91,086 | 22.17 | 1 hrs 5 mins |
| 7 | GeForce RTX 2070 Mobile / Max-Q Refresh TU106M [GeForce RTX 2070 Mobile / Max-Q Refresh] |
Nvidia | TU106M | 1,837,871 | 102,052 | 18.01 | 1 hrs 20 mins |
| 8 | Quadro RTX 5000 Mobile / Max-Q TU104GLM [Quadro RTX 5000 Mobile / Max-Q] |
Nvidia | TU104GLM | 1,796,914 | 102,128 | 17.59 | 1 hrs 22 mins |
| 9 | GeForce RTX 2060 TU106 [Geforce RTX 2060] |
Nvidia | TU106 | 1,707,940 | 100,589 | 16.98 | 1 hrs 25 mins |
| 10 | GeForce RTX 3060 Mobile / Max-Q GA106M [GeForce RTX 3060 Mobile / Max-Q] |
Nvidia | GA106M | 1,499,041 | 84,858 | 17.67 | 1 hrs 22 mins |
| 11 | GeForce GTX 1080 GP104 [GeForce GTX 1080] 8873 |
Nvidia | GP104 | 1,476,974 | 95,764 | 15.42 | 1 hrs 33 mins |
| 12 | GeForce GTX 1070 Ti GP104 [GeForce GTX 1070 Ti] 8186 |
Nvidia | GP104 | 1,410,000 | 94,470 | 14.93 | 1 hrs 36 mins |
| 13 | GeForce GTX 980 Ti GM200 [GeForce GTX 980 Ti] 5632 |
Nvidia | GM200 | 1,380,877 | 92,107 | 14.99 | 1 hrs 36 mins |
| 14 | GeForce GTX 1660 SUPER TU116 [GeForce GTX 1660 SUPER] |
Nvidia | TU116 | 1,367,525 | 92,166 | 14.84 | 1 hrs 37 mins |
| 15 | GeForce GTX 1660 Mobile TU116M [GeForce GTX 1660 Mobile] |
Nvidia | TU116M | 1,300,340 | 92,007 | 14.13 | 1 hrs 42 mins |
| 16 | GeForce GTX 1660 Ti TU116 [GeForce GTX 1660 Ti] |
Nvidia | TU116 | 1,216,392 | 89,492 | 13.59 | 1 hrs 46 mins |
| 17 | P104-100 GP104 [P104-100] |
Nvidia | GP104 | 1,202,938 | 89,216 | 13.48 | 1 hrs 47 mins |
| 18 | GeForce GTX 1070 GP104 [GeForce GTX 1070] 6463 |
Nvidia | GP104 | 1,092,703 | 85,295 | 12.81 | 1 hrs 52 mins |
| 19 | GeForce GTX 980 GM204 [GeForce GTX 980] 4612 |
Nvidia | GM204 | 950,382 | 82,569 | 11.51 | 2 hrs 5 mins |
|
|
|||||||
| 20 | GeForce GTX 1660 TU116 [GeForce GTX 1660] |
Nvidia | TU116 | 931,153 | 81,936 | 11.36 | 2 hrs 7 mins |
| 21 | GeForce GTX 1060 Mobile GP106M [GeForce GTX 1060 Mobile] |
Nvidia | GP106M | 831,826 | 79,136 | 10.51 | 2 hrs 17 mins |
| 22 | P106-100 GP106 [P106-100] |
Nvidia | GP106 | 828,639 | 78,803 | 10.52 | 2 hrs 17 mins |
| 23 | GeForce GTX 1060 3GB GP106 [GeForce GTX 1060 3GB] 3935 |
Nvidia | GP106 | 800,797 | 77,887 | 10.28 | 2 hrs 20 mins |
| 24 | GeForce GTX 1060 6GB GP104 [GeForce GTX 1060 6GB] |
Nvidia | GP104 | 794,483 | 77,719 | 10.22 | 2 hrs 21 mins |
| 25 | Tesla P4 GP104GL [Tesla P4] 5704 |
Nvidia | GP104GL | 748,439 | 76,471 | 9.79 | 2 hrs 27 mins |
| 26 | GeForce GTX 1060 6GB GP106 [GeForce GTX 1060 6GB] 4372 |
Nvidia | GP106 | 725,153 | 75,529 | 9.60 | 2 hrs 30 mins |
| 27 | GeForce GTX 1650 SUPER TU116 [GeForce GTX 1650 SUPER] |
Nvidia | TU116 | 677,668 | 74,425 | 9.11 | 2 hrs 38 mins |
| 28 | Quadro P2200 GP106GL [Quadro P2200] |
Nvidia | GP106GL | 673,672 | 73,794 | 9.13 | 2 hrs 38 mins |
| 29 | GeForce GTX 970 GM204 [GeForce GTX 970] 3494 |
Nvidia | GM204 | 648,723 | 71,401 | 9.09 | 2 hrs 38 mins |
| 30 | GeForce GTX 1650 TU116 [GeForce GTX 1650] 3091 |
Nvidia | TU116 | 612,485 | 71,279 | 8.59 | 2 hrs 48 mins |
| 31 | GeForce GTX 1650 TU117 [GeForce GTX 1650] |
Nvidia | TU117 | 510,608 | 67,021 | 7.62 | 3 hrs 9 mins |
| 32 | Quadro T1000 Mobile TU117GLM [Quadro T1000 Mobile] |
Nvidia | TU117GLM | 454,540 | 64,547 | 7.04 | 3 hrs 24 mins |
| 33 | GeForce GTX 1050 Ti GP107 [GeForce GTX 1050 Ti] 2138 |
Nvidia | GP107 | 400,374 | 60,501 | 6.62 | 3 hrs 38 mins |
| 34 | GeForce GTX 960 GM206 [GeForce GTX 960] 2308 |
Nvidia | GM206 | 313,710 | 56,585 | 5.54 | 4 hrs 20 mins |
| 35 | GeForce GTX 950 GM206 [GeForce GTX 950] 1572 |
Nvidia | GM206 | 294,764 | 55,929 | 5.27 | 4 hrs 33 mins |
| 36 | GeForce GTX 1050 LP GP107 [GeForce GTX 1050 LP] 1862 |
Nvidia | GP107 | 261,009 | 51,639 | 5.05 | 4 hrs 45 mins |
| 37 | Quadro P620 GP107GL [Quadro P620] |
Nvidia | GP107GL | 180,816 | 47,584 | 3.80 | 6 hrs 19 mins |
| 38 | GeForce GTX 750 Ti GM107 [GeForce GTX 750 Ti] 1389 |
Nvidia | GM107 | 177,747 | 47,330 | 3.76 | 6 hrs 23 mins |
| 39 | Quadro K1200 GM107GL [Quadro K1200] |
Nvidia | GM107GL | 107,668 | 40,086 | 2.69 | 8 hrs 56 mins |
|
|
|||||||
| 40 | R7 370/R9 270/370 OEM Curacao Pro [R7 370/R9 270/370 OEM] |
AMD | Curacao Pro | 80,094 | 36,156 | 2.22 | 10 hrs 50 mins |
| 41 | R7 370/R9 270X/370X Curacao XT/Trinidad XT [R7 370/R9 270X/370X] |
AMD | Curacao XT/Trinidad XT | 68,620 | 34,376 | 2.00 | 12 hrs 1 mins |
| 42 | GeForce GT 1030 GP108 [GeForce GT 1030] |
Nvidia | GP108 | 41,410 | 29,140 | 1.42 | 16 hrs 53 mins |
PROJECT FOLDING PPD AVERAGES BY CPU BETA
Data as of Sunday, 26 April 2026 03:24:29|
Rank Project |
CPU Model |
Logical Processors (LP) |
PPD-PLP AVG PPD per 1 LP |
ALL LP-PPD (Estimated) |
Make |
|---|