AlphaFold3/GNINA workstation

They contacted us to ask about introducing a workstation to deepen their understanding of analysis using AlphaFold3 and GNINA and to utilize it in their research.
The budget is approximately 100 million yen.
The client is looking for a configuration that prioritizes GPU performance, such as an RTX A6000, while also considering future memory and storage expansion.

CPU	Intel Core Ultra 7 265K 3.90GHz(8C/8T)+3.30GHz(12C/12T)
memory	Total 64GB DDR5 6400 32GB x 2
Storage 1	1TB SSD M.2 NVMe Gen5
Storage 2	4TB SSD M.2 NVMe Gen4
Video	NVIDIA GeForce RTX5090 32GB
network	on board(2.5GBase-T x1) Wi-Fi, Bluetooth
Housing + power supply	Mid-tower case 1200W 80PLUS PLATINUM
OS	Ubuntu 24.04

GPU selection

AlphaFold3 is software that places importance on GPU performance, such as VRAM capacity.
To maximize AlphaFold3 computing performance within your budget, we chose the NVIDIA GeForce RTX5090 (32GB).
With its latest generation core performance, the RTX5090 delivers performance for many research applications.
Also, if VRAM capacity is important for large-scale models, you can select a GPU that prioritizes capacity.

CPU and memory configuration

The CPU is a Core Ultra 7 265K and the memory is 64GB (2 x 32GB).
The recommended memory capacity for AlphaFold3 is 64GB or more.
This configuration is equipped with 64GB of memory to ensure analysis stability.
Furthermore, by utilizing the available slot, the memory capacity can be expanded up to 128GB.

AlphaFold3 Related Information

Tegsys has released a version compatible with Ubuntu 24.04.AlphaFold3 installation instructionsis published.
We have posted specific commands from the preparation stage to starting AlphaFold3.
For more information, please see the link below.

For more details on proposed workstations for AlphaFold3 use, please see this article.

Reference: Case No. PC-TRNM253239 Machine learning and DFT calculation compatible workstation

For those who are active in these fields Computational Chemistry Structural biology Bioinformatics Molecular modeling Protein Engineering

Tegara's custom-made PC production service not only caters to initial use, but also supports system expansion in anticipation of future expansion of research scale.
We not only propose configurations that meet various software requirements, but also accept consultations regarding the construction of an entire research environment.
Please feel free to contact us and we will provide the best solution to suit your needs.

Keyword ・What is AlphaFold? AlphaFold is an innovative protein structure prediction AI developed by DeepMind. It is possible to predict three-dimensional structures with high accuracy from amino acid sequences, achieving overwhelming speed and cost-effectiveness compared to conventional experimental methods (X-ray crystallography and NMR). It is used in a wide range of fields, including structural biology, drug discovery, enzyme design, and disease research, and millions of structural information are made public through the AlphaFold Protein Structure Database. Reference: AlphaFold – DeepMind ・What is Gnina? Gnina is open source software that enables molecular docking and scoring using deep learning. It features a CNN (convolutional neural network) based scoring function and is integrated with the existing AutoDock Vina-based algorithm to improve the accuracy of ligand-protein interaction predictions. It is widely used in drug discovery calculations, molecular simulations, and structure-based drug design (SBDD). Reference: GitHub – gnina/gnina

■ Click here for details and inquiries about this PC case AlphaFold3/GNINA workstation * Please enter the name of the case or your desired conditions.