Partnering with Macrocosmos to Accelerate Next-Generation NNP Development

May 1, 2025

Neural network potentials (NNPs) are revolutionizing molecular simulation. Starting today, Rowan is teaming up with Macrocosmos, an open-source AI research lab building on Bittensor, to accelerate the development of the next generation of NNPs through Subnet 25 - Mainframe.

From Macrocosmos' documentation on Subnet 25 - Mainframe:

Mainframe is a decentralised science subnet on Bittensor. It provides computing power and community talent to solve scientific problems.

Subnet 25 currently tackles decentalized protein folding using molecular dynamics (MD) a method for simulating the physical movements of atoms and molecules.

Our collaboration brings Bittensor closer to cutting-edge research in drug discovery and materials science. We look forward to working with the Macrocosmos team to add new capabilities to Mainframe.

In our newly released preprint "Egret-1: Pretrained Neural Network Potentials for Efficient and Accurate Bioorganic Simulation," we present a new family of open-source ML models for high-accuracy bioorganic simulations. One key insight from the paper is that the next generation of models will need a lot more high-quality data generated via density-functional theory (DFT). From the paper:

In particular, we anticipate that a combination of improved dataset scale and quality, more expressive architectures, and performance optimization will make it possible to achieve significantly improved accuracy, speed, and generality, which we expect to have a substantial impact on discovery across the chemical sciences.

Working with Macrocosmos and Mainframe will let us use the decentralized computing power of the Bittensor network to dynamically generate the data we need to train the next generation of NNPs.

Bittensor is an ideal partner for this ambitious scientific project. We're very excited to be working with Macrocosmos, Subnet 25 - Mainframe, and the community to combine our expertise and push the boundaries of ML-powered molecular simulation forward.

Banner background image

Ready to learn more?

Talk with a member of our team to learn how Rowan can accelerate your work. Security and compliance questions can go to security@rowansci.com, and our full security page covers current practices.

Contact us →

What to read next

LogP, API Key Budgets, and a User Survey

LogP, API Key Budgets, and a User Survey

the golden mean of logP; three approaches to predicting logP; API key budgets for low-trust delegation; a user survey and some blog posts
Aug 5, 2026 · Nick Casetti, Ari Wagen, Spencer Schneider, and Corin Wagen
How to Find Conformers

How to Find Conformers

A conceptual overview of conformer-generation and conformer-search methodology.
Aug 3, 2026 · Nicholas Casetti
Simulation Tools Improve Agent Problem-Solving

Simulation Tools Improve Agent Problem-Solving

External simulation tools do noticeably improve agent performance at 13C NMR structural elucidation.
Jul 31, 2026 · Corin Wagen
NMR Spectroscopy

NMR Spectroscopy

the importance of NMR spectroscopy; the languorousness typical of state-of-the-art methods; MagNET, a new model, and its Rowan workflow; testimonials and case studies; new agent benchmarks
Jul 23, 2026 · Corin Wagen and Eli Mann
Testing Rowan-Enabled Agents on DrugDiscoveryBench

Testing Rowan-Enabled Agents on DrugDiscoveryBench

How access to Rowan's computational tools affects scientific agents' performance on early-stage drug-discovery tasks.
Jul 21, 2026 · Eli Mann
Automating Transition-State Search

Automating Transition-State Search

strings and bands; interpolating between states; searching for transitions; confirmation; Vicena integration; recent blogs
Jul 20, 2026 · Jonathon Vandezande and Corin Wagen
Case Studies with Rowan's Hydration-Site Analysis

Case Studies with Rowan's Hydration-Site Analysis

Benchmarking Rowan's hydration-site detection on five documented protein–ligand complexes.
Jul 16, 2026 · Ishaan Ganti and Corin Wagen
What to Do with a Pose

What to Do with a Pose

A few helpful ideas for further analysis or calculations to run.
Jul 15, 2026 · Corin Wagen
Well-Prepared Proteins and How to Use Them

Well-Prepared Proteins and How to Use Them

better protein preparation through ML; Gnina & covalent docking; MM/GBSA refinement; fast MD and more trajectory analysis; synthetic RBFE intermediates; resubmitting FEP graphs without rerunning legs
Jul 9, 2026 · Ari Wagen, Nick Casetti, Zachary Fried, Corin Wagen, Ishaan Ganti, and Elias Mann
Symmetry, X-Ray Diffraction (XRD), Band Structures, and Elastic Tensors

Symmetry, X-Ray Diffraction (XRD), Band Structures, and Elastic Tensors

symmetry and asymmetry; reflections on X-rays; structure, both electronic and crystalline; stressing crystals
Jun 23, 2026 · Jonathon Vandezande and Raphael Stone