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

2026 Intern Reflections

2026 Intern Reflections

Takeaways and other thoughts from each of our summer interns.
Aug 26, 2026 · Isaiah Sippel, Ishaan Ganti, Nick Casetti, and Raphael Stone
Excited States and UV-Vis with TDDFT

Excited States and UV-Vis with TDDFT

an extension of density-functional theory; modeling absorbance and fluorescence; excited-state optimization
Aug 25, 2026 · Jonathon Vandezande, Isaiah Sippel, and Ari Wagen
Predicting UV-Vis Spectra with TDDFT

Predicting UV-Vis Spectra with TDDFT

Comparing the experimental and predicted UV-Vis spectra of azo dyes and other compounds.
Aug 25, 2026 · Isaiah Sippel
Tricky Cases in Protein Preparation

Tricky Cases in Protein Preparation

How we're using Boltz-2 inpainting to improve protein preparation.
Aug 20, 2026 · Ari Wagen
Running a Full FEP Campaign in Python with Rowan

Running a Full FEP Campaign in Python with Rowan

Learn how to run an iterative FEP campaign programmatically with Rowan's Python SDK.
Aug 19, 2026 · Eli Mann
Phonons

Phonons

band structures and density of states; material waves; sound, light, and heat
Aug 18, 2026 · Raphael Stone and Jonathon Vandezande
Binder Optimization with LLMs and Specialized Models

Binder Optimization with LLMs and Specialized Models

Testing LLMs and specialized models on generating strongly binding ligands.
Aug 17, 2026 · Ishaan Ganti
Performance Optimization

Performance Optimization

or, how to get more Rowan for your dollar
Aug 10, 2026 · Corin Wagen and Eli Mann
Hits From a Hackathon

Hits From a Hackathon

How certain schemes to identify TBXT-binding compounds have succeeded.
Aug 7, 2026 · Kat Yenko, Corin Wagen, Ari Wagen, and Derek Alia
Testing Different Pose-Ranking Methods for RBFE Calculations

Testing Different Pose-Ranking Methods for RBFE Calculations

Benchmarking how well Rowan's analogue-docking pose scoring picks the best starting structure for RBFE, and how much a ranking miss actually matters downstream.
Aug 6, 2026 · Zachary Fried