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

How to Simulate Materials with DFT

How to Simulate Materials with DFT

An introduction to plane-wave DFT for chemists: pseudopotentials, energy cutoffs, k-points, smearing, and what to watch out for.
May 28, 2026 · Raphael Stone
Fast and Efficient Butina Splitting of Chemical Data with Chalcedon

Fast and Efficient Butina Splitting of Chemical Data with Chalcedon

A fast, memory-efficient, minimal-dependency Python package for Butina clustering and splitting chemical data.
May 27, 2026 · Eli Mann
Improving Rowan's Performance on the OpenBind EV-A71 Release

Improving Rowan's Performance on the OpenBind EV-A71 Release

How we recovered useful RBFE accuracy on a challenging real-world dataset.
May 20, 2026 · Corin Wagen
New Protein Visualizations

New Protein Visualizations

distilling insight from complexity; two-dimensional protein–ligand interaction diagrams; protein blob surfaces; space-filling molecule representations
May 19, 2026 · Ari Wagen
Notes on Rowan Engineering; Or How to Vibe-Refactor a Codebase

Notes on Rowan Engineering; Or How to Vibe-Refactor a Codebase

stuck in Rowan's dependency slough of despond; fleeing the complexity of microservices & partial refactors; multiplying packages to reduce complexity; using agents to vibe-refactor our whole codebase
May 13, 2026 · Jonathon Vandezande
Testing Rowan on the OpenBind EV-A71 Release

Testing Rowan on the OpenBind EV-A71 Release

How Rowan's analogue-docking and RBFE workflows fare on this dataset.
May 6, 2026 · Corin Wagen
Benchmarking Membrane-Permeability Predictors

Benchmarking Membrane-Permeability Predictors

Testing GNN-MTL and PyPermm on datasets of small molecules, macrocycles, and PROTACs
Apr 28, 2026 · Ari Wagen
Smarter Analogue Docking, Pocket Detection, and g-xTB Analytical Gradients

Smarter Analogue Docking, Pocket Detection, and g-xTB Analytical Gradients

more robust MCS detection; conformer sampling with torsional Monte Carlo; better alignment and RBFE results; a new pocket-detection workflow; analytical gradients now available for g-xTB
Apr 23, 2026 · Zachary Fried, Corin Wagen, Ari Wagen, and Jonathon Vandezande
g-xTB pKa and Website Redesign

g-xTB pKa and Website Redesign

the flaws with Rowan's AIMNet2-based pKa method; our new g-xTB-based approach; benchmarking and availability; a logo and new website for Rowan
Apr 15, 2026 · Corin Wagen and Ari Wagen
Easter Updates to Rowan

Easter Updates to Rowan

webhooks, draft workflows, and usage estimates for Rowan's Python API; tautomers in non-aqueous solvents; COSMO-based descriptors; overage-based billing; an FEP speed test; welcome Zach
Apr 9, 2026 · Eli Mann, Ari Wagen, Spencer Schneider, Jonathon Vandezande, and Corin Wagen