RESEARCH: PROTEIN-DYNAMICS-DATASET
FOLDING PROJECT #17651 PROFILE
PROJECT TEAM
Manager(s): Sukrit SinghInstitution: Memorial Sloan-Kettering Cancer-Center
Project URL: View Project Website
WORK UNIT INFO
Atoms: 20,000Core: 0x26
Status: Public
Related Projects
TLDR; PROJECT SUMMARY AI BETA
The project aims to create a huge dataset of protein movements. This will help AI models like AlphaFold2 better understand how proteins work by showing them lots of different shapes and sizes. The dataset will include small, medium, and large proteins with varying numbers of atoms.
Note: This TLDR is a simplication and may not be 100% accurate.OFFICAL PROJECT DESCRIPTION
With the explosion of AI-based models and architectures, a ripe opportunity presents itself to use these statistical models to help us bridge the gap large scale simulations and functional insight.
In particular, with the explosion of methods like AlphaFold2, there is a clear potential for these models to potentially predict dynamics, or use them to predict different conformations of a system at extremely large scales for a diverse set of sequences. However, for folks to be able to generate those kinds of models, a broad set of training data is needed that captures dynamics across a variety of different protein topologies.
This project seeks to generate that dataset - capturing dynamics of systems across a variety of different protein sizes and topologies.
17651: Small proteins (20,000 atoms)
17652: medium sized proteins (40,000 atoms)
17653: Large sized proteins (70,000 atoms).
RELATED TERMS GLOSSARY AI BETA
AI
Artificial Intelligence
Artificial intelligence (AI) refers to the ability of computer systems to perform tasks that typically require human intelligence, such as learning, problem-solving, and decision-making.
Models
Mathematical representations of systems or processes
In the context of biotechnology, models are mathematical representations used to simulate biological systems and processes. They can be used to predict protein structures, drug interactions, and other biological phenomena.
AlphaFold2
Protein structure prediction algorithm
AlphaFold2 is a groundbreaking artificial intelligence system developed by DeepMind that can accurately predict the three-dimensional structures of proteins. This has revolutionized structural biology and drug discovery.
Dynamics
Movement and changes in a system over time
In the context of proteins, dynamics refer to their constant movement and flexibility. This movement is essential for protein function and interactions.
Conformations
Different shapes or arrangements of a molecule
Proteins can exist in different shapes or arrangements called conformations. These conformations are important for protein function and interactions.
Protein Topologies
The overall 3D arrangement of a protein's structure
Protein topology refers to the three-dimensional arrangement of amino acids within a protein. This arrangement is crucial for protein function and interactions.
Training Data
Dataset used to train machine learning models
Training data is a large dataset used to teach machine learning algorithms. In the context of biotechnology, training data can include protein sequences, structures, and functional information.
PROJECT FOLDING PPD AVERAGES BY GPU
Data as of Sunday, 26 April 2026 00:37:30|
Rank Project |
Model Name Folding@Home Identifier |
Make Brand |
GPU Model |
PPD Average |
Points WU Average |
WUs Day Average |
WU Time Average |
|---|---|---|---|---|---|---|---|
| 1 | GeForce RTX 4080 AD103 [GeForce RTX 4080] |
Nvidia | AD103 | 10,944,483 | 15,678 | 698.08 | 0 hrs 2 mins |
| 2 | GeForce RTX 4060 Ti AD106 [GeForce RTX 4060 Ti] |
Nvidia | AD106 | 10,519,272 | 148,054 | 71.05 | 0 hrs 20 mins |
| 3 | GeForce RTX 4080 SUPER AD103 [GeForce RTX 4080 SUPER] |
Nvidia | AD103 | 10,128,463 | 9,486 | 1067.73 | 0 hrs 1 mins |
| 4 | GeForce RTX 4070 Ti AD104 [GeForce RTX 4070 Ti] |
Nvidia | AD104 | 9,399,627 | 35,595 | 264.07 | 0 hrs 5 mins |
| 5 | GeForce RTX 4090 AD102 [GeForce RTX 4090] |
Nvidia | AD102 | 9,064,921 | 27,981 | 323.97 | 0 hrs 4 mins |
| 6 | GeForce RTX 5090 GB202 [GeForce RTX 5090] |
Nvidia | GB202 | 8,732,214 | 3,850 | 2268.11 | 0 hrs 1 mins |
| 7 | GeForce RTX 4070 SUPER AD104 [GeForce RTX 4070 SUPER] |
Nvidia | AD104 | 8,722,789 | 20,238 | 431.01 | 0 hrs 3 mins |
| 8 | GeForce RTX 2060 TU104 [GeForce RTX 2060] |
Nvidia | TU104 | 7,063,563 | 181,786 | 38.86 | 0 hrs 37 mins |
| 9 | GeForce RTX 3080 Ti GA102 [GeForce RTX 3080 Ti] |
Nvidia | GA102 | 5,843,735 | 3,850 | 1517.85 | 0 hrs 1 mins |
| 10 | GeForce RTX 5080 GB203 [GeForce RTX 5080] |
Nvidia | GB203 | 5,319,960 | 3,850 | 1381.81 | 0 hrs 1 mins |
| 11 | GeForce RTX 3090 Ti GA102 [GeForce RTX 3090 Ti] |
Nvidia | GA102 | 5,168,903 | 64,150 | 80.58 | 0 hrs 18 mins |
| 12 | GeForce RTX 5070 Ti GB203 [GeForce RTX 5070 Ti] |
Nvidia | GB203 | 4,777,485 | 3,850 | 1240.91 | 0 hrs 1 mins |
| 13 | RTX 5000 Ada Generation Laptop GPU AD103GLM [RTX 5000 Ada Generation Laptop GPU] |
Nvidia | AD103GLM | 4,624,918 | 61,786 | 74.85 | 0 hrs 19 mins |
| 14 | GeForce RTX 3070 Ti GA104 [GeForce RTX 3070 Ti] |
Nvidia | GA104 | 4,494,727 | 3,850 | 1167.46 | 0 hrs 1 mins |
| 15 | GeForce RTX 3070 Lite Hash Rate GA104 [GeForce RTX 3070 Lite Hash Rate] |
Nvidia | GA104 | 4,438,016 | 61,885 | 71.71 | 0 hrs 20 mins |
| 16 | GeForce RTX 4070 AD104 [GeForce RTX 4070] |
Nvidia | AD104 | 4,234,852 | 3,850 | 1099.96 | 0 hrs 1 mins |
| 17 | GeForce RTX 3060 Ti Lite Hash Rate GA104 [GeForce RTX 3060 Ti Lite Hash Rate] |
Nvidia | GA104 | 4,214,992 | 3,850 | 1094.80 | 0 hrs 1 mins |
| 18 | GeForce RTX 3090 GA102 [GeForce RTX 3090] |
Nvidia | GA102 | 4,134,973 | 62,108 | 66.58 | 0 hrs 22 mins |
| 19 | GeForce RTX 3080 GA102 [GeForce RTX 3080] |
Nvidia | GA102 | 4,102,257 | 61,015 | 67.23 | 0 hrs 21 mins |
|
|
|||||||
| 20 | GeForce RTX 3070 GA104 [GeForce RTX 3070] |
Nvidia | GA104 | 3,421,081 | 55,916 | 61.18 | 0 hrs 24 mins |
| 21 | Radeon RX 7700XT/7800XT Navi 32 [Radeon RX 7700XT/7800XT] |
AMD | Navi 32 | 3,366,299 | 3,850 | 874.36 | 0 hrs 2 mins |
| 22 | TITAN V GV100 [TITAN V] M 12288 |
Nvidia | GV100 | 3,348,516 | 3,850 | 869.74 | 0 hrs 2 mins |
| 23 | GeForce RTX 5070 GB205 [GeForce RTX 5070] |
Nvidia | GB205 | 3,318,752 | 3,850 | 862.01 | 0 hrs 2 mins |
| 24 | GeForce RTX 3060 Lite Hash Rate GA106 [GeForce RTX 3060 Lite Hash Rate] |
Nvidia | GA106 | 2,921,998 | 53,514 | 54.60 | 0 hrs 26 mins |
| 25 | Radeon RX 7900XT/XTX/GRE Navi 31 [Radeon RX 7900XT/XTX/GRE] |
AMD | Navi 31 | 2,793,744 | 3,850 | 725.65 | 0 hrs 2 mins |
| 26 | Radeon RX 6800/6800XT/6900XT Navi 21 [Radeon RX 6800/6800XT/6900XT] |
AMD | Navi 21 | 2,390,811 | 3,850 | 620.99 | 0 hrs 2 mins |
| 27 | GeForce RTX 3060 Mobile / Max-Q GA106M [GeForce RTX 3060 Mobile / Max-Q] |
Nvidia | GA106M | 2,227,521 | 23,232 | 95.88 | 0 hrs 15 mins |
| 28 | GeForce RTX 2060 Super TU106 [GeForce RTX 2060 SUPER] |
Nvidia | TU106 | 2,186,060 | 41,390 | 52.82 | 0 hrs 27 mins |
| 29 | GeForce RTX 2060 TU106 [Geforce RTX 2060] |
Nvidia | TU106 | 2,126,718 | 36,159 | 58.82 | 0 hrs 24 mins |
| 30 | GeForce RTX 3050 8GB GA107 [GeForce RTX 3050 8GB] |
Nvidia | GA107 | 2,114,856 | 49,002 | 43.16 | 0 hrs 33 mins |
| 31 | GeForce GTX 1080 GP104 [GeForce GTX 1080] 8873 |
Nvidia | GP104 | 1,931,222 | 3,850 | 501.62 | 0 hrs 3 mins |
| 32 | GeForce GTX 980 Ti GM200 [GeForce GTX 980 Ti] 5632 |
Nvidia | GM200 | 1,735,973 | 3,850 | 450.90 | 0 hrs 3 mins |
| 33 | GeForce RTX 2070 Mobile / Max-Q Refresh TU106M [GeForce RTX 2070 Mobile / Max-Q Refresh] |
Nvidia | TU106M | 1,541,765 | 43,926 | 35.10 | 0 hrs 41 mins |
| 34 | GeForce GTX 1660 TU116 [GeForce GTX 1660] |
Nvidia | TU116 | 1,323,626 | 41,496 | 31.90 | 0 hrs 45 mins |
| 35 | GeForce GTX 1070 GP104 [GeForce GTX 1070] 6463 |
Nvidia | GP104 | 1,279,924 | 37,350 | 34.27 | 0 hrs 42 mins |
| 36 | Tesla P4 GP104GL [Tesla P4] 5704 |
Nvidia | GP104GL | 1,135,330 | 39,629 | 28.65 | 0 hrs 50 mins |
| 37 | GeForce GTX 1660 Mobile TU116M [GeForce GTX 1660 Mobile] |
Nvidia | TU116M | 1,007,934 | 36,042 | 27.97 | 0 hrs 51 mins |
| 38 | GeForce GTX 1060 6GB GP106 [GeForce GTX 1060 6GB] 4372 |
Nvidia | GP106 | 993,161 | 3,850 | 257.96 | 0 hrs 6 mins |
| 39 | GeForce GTX 970 GM204 [GeForce GTX 970] 3494 |
Nvidia | GM204 | 976,317 | 3,850 | 253.59 | 0 hrs 6 mins |
|
|
|||||||
| 40 | RX 5600 OEM/5600XT/5700/5700XT Navi 10 [RX 5600 OEM/5600XT/5700/5700XT] |
AMD | Navi 10 | 918,581 | 23,284 | 39.45 | 0 hrs 37 mins |
| 41 | GeForce GTX 980 GM204 [GeForce GTX 980] 4612 |
Nvidia | GM204 | 835,860 | 3,850 | 217.11 | 0 hrs 7 mins |
| 42 | P106-100 GP106 [P106-100] |
Nvidia | GP106 | 750,525 | 12,480 | 60.14 | 0 hrs 24 mins |
| 43 | GeForce GTX 1080 Ti GP102 [GeForce GTX 1080 Ti] 11380 |
Nvidia | GP102 | 515,010 | 30,189 | 17.06 | 1 hrs 24 mins |
| 44 | GeForce GTX 1060 3GB GP106 [GeForce GTX 1060 3GB] 3935 |
Nvidia | GP106 | 463,977 | 3,850 | 120.51 | 0 hrs 12 mins |
| 45 | RX 470/480/570/580/590 Ellesmere XT [RX 470/480/570/580/590] |
AMD | Ellesmere XT | 402,977 | 25,405 | 15.86 | 1 hrs 31 mins |
| 46 | GeForce GTX Titan X GM200 [GeForce GTX Titan X] 6144 |
Nvidia | GM200 | 387,201 | 3,850 | 100.57 | 0 hrs 14 mins |
| 47 | Radeon RX Vega 56/64 Vega 10 XL/XT [Radeon RX Vega 56/64] |
AMD | Vega 10 XL/XT | 380,954 | 3,850 | 98.95 | 0 hrs 15 mins |
| 48 | GeForce GTX 750 Ti GM107 [GeForce GTX 750 Ti] 1389 |
Nvidia | GM107 | 275,388 | 3,850 | 71.53 | 0 hrs 20 mins |
| 49 | R9 Fury X/NANO Fiji XT [R9 Fury X/NANO] |
AMD | Fiji XT | 255,222 | 3,850 | 66.29 | 0 hrs 22 mins |
| 50 | RX Vega M GL Polaris 22 XL [RX Vega M GL] |
AMD | Polaris 22 XL | 173,633 | 3,850 | 45.10 | 0 hrs 32 mins |
| 51 | Quadro K1200 GM107GL [Quadro K1200] |
Nvidia | GM107GL | 135,526 | 19,571 | 6.92 | 3 hrs 28 mins |
| 52 | Radeon RX 460/560D Baffin [Radeon RX 460/560D] |
AMD | Baffin | 131,057 | 3,850 | 34.04 | 0 hrs 42 mins |
| 53 | Vega Mobile 5000 series APU Cezanne [Vega Mobile 5000 series APU] |
AMD | Cezanne | 104,894 | 11,738 | 8.94 | 2 hrs 41 mins |
| 54 | Ryzen 7000 Series iGPU Raphael [Ryzen 7000 Series iGPU] |
AMD | Raphael | 51,329 | 12,429 | 4.13 | 5 hrs 49 mins |
| 55 | RX Vega 10 Mobile Picasso APU [RX Vega 10 Mobile] |
AMD | Picasso APU | 33,527 | 3,850 | 8.71 | 2 hrs 45 mins |
| 56 | Vega Mobile APU Lucienne [Vega Mobile APU] |
AMD | Lucienne | 23,408 | 10,962 | 2.14 | 11 hrs 14 mins |
| 57 | Ryzen 4900HS mobile Renoir [Ryzen 4900HS mobile] |
AMD | Renoir | 18,936 | 6,976 | 2.71 | 8 hrs 50 mins |
| 58 | R7 240/340/520/HD8570 Hawaii [R7 240/340/520/HD8570] |
AMD | Hawaii | 16,288 | 9,671 | 1.68 | 14 hrs 15 mins |
PROJECT FOLDING PPD AVERAGES BY CPU BETA
Data as of Sunday, 26 April 2026 00:37:30|
Rank Project |
CPU Model |
Logical Processors (LP) |
PPD-PLP AVG PPD per 1 LP |
ALL LP-PPD (Estimated) |
Make |
|---|