ADMET prediction
- ADMET Prediction Server Configuration
This document details the server configuration for running ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) prediction software. This guide is intended for newcomers to the server infrastructure and details the necessary hardware, software, and network considerations. Understanding these requirements is crucial for maintaining optimal performance and reliability of our ADMET prediction services.
Overview
ADMET prediction is a computationally intensive process, often involving complex molecular modeling and statistical analyses. Therefore, the server requires substantial resources to achieve reasonable turnaround times for predictions. This document outlines the recommended specifications and configuration steps for a dedicated ADMET prediction server. It will cover hardware, operating system, software dependencies, and networking aspects. We primarily use this server for supporting Drug Discovery, Molecular Modeling, and Pharmacokinetics projects.
Hardware Specifications
The following table details the recommended hardware specifications for the ADMET prediction server. These are minimum requirements and can be scaled based on the expected workload.
| Component | Specification |
|---|---|
| CPU | Dual Intel Xeon Gold 6248R (24 cores/48 threads per CPU) or AMD EPYC 7763 (64 cores/128 threads) |
| RAM | 256 GB DDR4 ECC Registered RAM (minimum), 512GB recommended for large datasets. |
| Storage | 2 x 1 TB NVMe SSD (RAID 1) for Operating System and Software. 4TB+ HDD for data storage. |
| Network Interface | Dual 10 Gigabit Ethernet (10GbE) network interface cards (NICs). |
| Power Supply | Redundant 1600W 80+ Platinum power supplies. |
| Motherboard | Server-grade motherboard supporting dual CPUs and ample RAM slots. |
It is important to note that the speed of the storage device significantly impacts the performance of ADMET predictions. NVMe SSDs are strongly recommended for the operating system and software installation to minimize I/O bottlenecks. See also Server Room Standards for physical security requirements.
Software Configuration
The ADMET prediction server runs a Linux-based operating system, specifically CentOS 7. The following software packages are essential:
- Operating System: CentOS 7 (or compatible Red Hat Enterprise Linux distribution)
- Programming Languages: Python 3.8+, R 4.0+
- ADMET Prediction Software: RDKit, Open Babel, SwissADME, pkCSM, ADMETlab 2.0
- Database: PostgreSQL 12 (for storing prediction results and metadata). See Database Management for details.
- Job Scheduler: Slurm Workload Manager (for managing and prioritizing prediction jobs). Refer to our Slurm Documentation.
The following table lists the key software packages and their versions.
| Software | Version | Purpose |
|---|---|---|
| CentOS | 7.9.2009 | Operating System |
| Python | 3.9.7 | Scripting and data analysis |
| R | 4.1.0 | Statistical computing and graphics |
| RDKit | 2021.09.1 | Cheminformatics toolkit |
| Open Babel | 3.1.1 | Chemical file format conversion |
| PostgreSQL | 12.7 | Database for storing prediction results |
| Slurm | 20.11.8 | Job scheduler |
All software should be installed using the appropriate package manager (e.g., `yum` for CentOS). Regular updates are crucial for security and stability. Consult the Software Update Policy for details.
Network Configuration
The ADMET prediction server requires a stable and high-bandwidth network connection. The server is connected to the internal network via dual 10GbE NICs, configured in a bonded mode for redundancy and increased throughput. The server's IP address is statically assigned and documented in the Network Inventory.
The server hosts a web interface for submitting and monitoring prediction jobs. This web interface is secured using HTTPS and accessed through a reverse proxy (NGINX Configuration). Access to the server is restricted to authorized personnel via SSH and is secured with key-based authentication. Firewall rules are configured to allow only necessary traffic (SSH, HTTPS, database connections). See the Firewall Policy for further information.
The following table summarizes the network settings:
| Setting | Value |
|---|---|
| Hostname | admet-server.example.com |
| IP Address | 192.168.1.100 |
| Subnet Mask | 255.255.255.0 |
| Gateway | 192.168.1.1 |
| DNS Servers | 8.8.8.8, 8.8.4.4 |
| Network Interfaces | bond0 (10GbE bonded) |
Monitoring and Maintenance
The server's performance is continuously monitored using Nagios. Metrics such as CPU usage, memory usage, disk I/O, and network traffic are tracked. Alerts are configured to notify administrators of any performance issues or failures. Regular backups of the database and critical configuration files are performed according to the Backup and Recovery Policy. Scheduled maintenance windows are used to apply software updates and perform system maintenance. Review System Logs regularly for anomalies.
Help Desk is the first point of contact for any issues.
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️