The Catalophore platform, running on your desk.
An NVIDIA DGX Spark, delivered with Catalophore Platform Pro, Catalophore Studio, LigForge and Catalophore Intelligence installed and ready to use. Target discovery, off-target validation, enzyme discovery and generative ligand design run on the system itself, AI features included. Connect by WiFi, office network or screen and start within minutes. Your structures, sequences and ligands stay inside your building, with or without an internet connection.
Launch offer: USD 9,900 including the hardware and a six-month full license for all modules.
From the box to the first binding site in three steps.
The system arrives installed, configured and tested. There is no software to deploy, no cluster to book and no cloud account to open.
Connect power
All services start by themselves. Catalophore Studio and Platform Pro are available after about three minutes, the AI features a few minutes later.
Join the system
Connect your laptop to the built-in WiFi of the system, plug the system into your office network, or attach a screen, keyboard and mouse.
Open your browser
A welcome page links to Studio, Platform Pro and the system dashboard. One user account gives access to all of them.
Three ways to connect, one interface.
Both applications run in the browser. Every scientist in the room can work on the same system from their own laptop.
- Built-in WiFi access point. The system provides its own protected wireless network. Laptops receive an address automatically and the welcome page opens by itself.
- Office network. Connected by Ethernet, the system takes an address from your DHCP server and serves your team on the existing network.
- Stand-alone workstation. With screen, keyboard and mouse attached, the system is a complete desktop with all tools linked from the dock.
- System dashboard. One page for live system metrics, network status, WiFi control, updates and support. A watchdog restarts services automatically if one stops responding.
The protein cavity workbench
Point-cloud cavity detection with more than 30 property fields, structure-aware AI interpretation, ligand preparation and docking in one interactive tool.
The molecular intelligence platform
Structures, sequences, cavities, ligands and experiments in one library, with cavity matching by shape and physico-chemical property and statistically scored results.
What your team can do with the system.
Catalophore describes every binding site as a three-dimensional point cloud of physico-chemical properties. Comparing sites by these properties reveals relationships that sequence and fold comparison cannot detect.
Target discovery
Detect and characterise the binding sites of a target, assess druggability and derive a ligand strategy from geometry, electrostatics and hydrophobicity of the pocket.
Off-target validation
Compare the binding site of your target with distinct panels such as kinases, nuclear receptors and GPCRs, or with the whole human proteome. The result is a ranked list with the structural evidence for every match.
Enzyme discovery
Search for enzymes whose active sites match the geometry and chemistry a reaction requires, including candidates from protein folds that a sequence search would never return.
Binding site interpretation
Every pocket is annotated with more than 30 property fields. Catalophore Intelligence reads this point cloud and returns functional zones, the probable mechanism and a druggability assessment, each with a stated confidence.
Generative ligand design and docking
LigForge generates new ligands directly inside the selected cavity, guided by its physico-chemical properties. Dock the candidates and let Catalophore Intelligence evaluate each pose against the landscape of the pocket.
Modelling and variants
Build structural models, introduce mutations in silico and compare the resulting cavities before the first variant is expressed in the laboratory.
Designed for air-gapped operation.
Unpublished structures, lead series and engineered variants are among the most valuable assets of a research organisation. On this system they are stored, processed and analysed in one place: the device in front of you.
Nothing leaves the system
Cavity detection, matching, docking and AI analysis run on the system. The language model behind the AI features is served locally on its GPU.
Signed updates by USB stick
Innophore delivers each update as a single file. The system verifies the cryptographic signature before anything is unpacked, installs the update and writes a report back to the stick.
Remote support under your control
The encrypted support connection is switched off by default. You open it in the dashboard when you want assistance and close it when the session is finished.
What an on-premise system changes in practice.
Full control over intellectual property
No upload, no third-party storage, no data processing agreement for a cloud provider. This simplifies internal security reviews.
Dedicated compute, no queue
The system belongs to your team. Interactive analyses respond immediately and longer experiments run overnight without competing for shared resources.
Predictable budget
One fixed price covers the hardware and the first six months with all modules. There are no usage fees per structure, per job or per GPU hour.
Productive on the first day
Installation, configuration and validation are completed before shipping. Your scientists start with the science.
Fits on a desk
The system is compact, runs from a standard power outlet and needs no server room.
Every module, six months
The full license lets your team test all modules on real projects and decide on evidence which ones to continue.
An NVIDIA DGX Spark, yours to use.
The system is built on NVIDIA DGX Spark with the NVIDIA GB10 Grace Blackwell chip and 128 GB of unified memory. Beyond Catalophore it remains a complete AI workstation for your team. All workloads share the memory of the system with the Catalophore services.
Large models, locally
According to NVIDIA, the DGX Spark runs AI models with up to 200 billion parameters at the desk.
Models adapted to your data
NVIDIA specifies fine-tuning of models with up to 70 billion parameters on a single system.
Analytics and machine learning
The NVIDIA AI software stack is preinstalled and supports data analytics and machine learning workflows.
Your own tools and agents
The local language model offers an OpenAI-compatible interface for your scripts, pipelines and AI agents.
One price, hardware and all modules.
The price includes the NVIDIA DGX Spark hardware and the complete software for the first six months. Afterwards you license the modules your projects need.
Hardware included, with a six-month full license for all modules of Catalophore Platform Pro and Catalophore Studio.
Request a quote →Included
- NVIDIA DGX Spark hardware, installed and configured
- Catalophore Platform Pro, all modules
- Catalophore Studio, all modules
- LigForge and Catalophore Intelligence
- Local AI features
- Signed software updates by USB stick
- Remote support on request
After six months
Licensing continues per module. The hardware is yours, you keep the modules you use and your data remains on your system.
Bring the platform to your site.
Tell us about your targets and your IT requirements. We will configure the system for your programs.
Order a system
Receive a quote with delivery time and the module overview for the period after the first six months.
Request a quote →See it first
Send us a PDB ID, a UniProt ID or a sequence. We will show you the analysis on a live system.
Book a demo →Questions? Write to customer@innophore.com · Built and maintained by Innophore, Graz, Austria.