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

What to Read Next

Modeling Thia-Michael Reactions

Modeling Thia-Michael Reactions

In which the addition of a thiolate to an enone proves to be unexpectedly difficult to model.
Jul 25, 2025 · Corin Wagen
API v2, New BDE Methods, MCP, And More

API v2, New BDE Methods, MCP, And More

new API philosophy; streamlined interfaces for workflows; using NNPs and g-xTB to predict bond strength; an MCP server; .sdf files; benchmarking protein–ligand interactions; Diels–Alder visualizations
Jul 21, 2025 · Spencer Schneider, Corin Wagen, Ari Wagen, Jonathon Vandezande, Ishaan Ganti, and Isaiah Sippel
ExpBDE54: A Slim Experimental Benchmark for Exploring the Pareto Frontier of Bond-Dissociation-Enthalpy-Prediction Methods

ExpBDE54: A Slim Experimental Benchmark for Exploring the Pareto Frontier of Bond-Dissociation-Enthalpy-Prediction Methods

ExpBDE54 is a benchmark dataset of experimental homolytic bond-dissociation enthalpies (BDEs) for 54 small molecules, used for benchmarking DFT, semiempirical methods, and NNPs.
Jul 17, 2025 · Jonathon E. Vandezande, Corin C. Wagen
Benchmarking Protein–Ligand Interaction Energy

Benchmarking Protein–Ligand Interaction Energy

How new low-cost computational methods perform on the PLA15 benchmark.
Jul 11, 2025 · Ishaan Ganti
Efficient Black-Box Prediction of Hydrogen-Bond-Donor and Acceptor Strength

Efficient Black-Box Prediction of Hydrogen-Bond-Donor and Acceptor Strength

Here, we report a robust black-box workflow for predicting site-specific hydrogen-bond basicity and acidity in organic molecules with minimal computational cost.
Jul 1, 2025 · Corin C. Wagen
Tracking Boltz-2 Benchmarks

Tracking Boltz-2 Benchmarks

Tracking the community's response to the new Boltz-2 model, plus some notes about Chai-2.
Jul 1, 2025 · Corin Wagen
g-xTB, Credit Usage, & More

g-xTB, Credit Usage, & More

the new g-xTB model from Grimme and co-workers; an easy visual overview of credit usage; better credit handling for organizations; bulk PDB download; a new collapsible JSON viewer
Jun 27, 2025 · Jonathon Vandezande, Ari Wagen, Spencer Schneider, and Corin Wagen
Representing Local Protein Environments With Atomistic Foundation Models

Representing Local Protein Environments With Atomistic Foundation Models

A guest post about how to use NNP embeddings for other prediction tasks.
Jun 20, 2025 · Meital Bojan and Sanketh Vedula
Co-Folding Updates

Co-Folding Updates

Boltz-2 FAQ and launch event recap; new visuals for co-folding workflows; new submission options; PDB bugfixes; new credit-management tools
Jun 12, 2025 · Ari Wagen, Spencer Schneider, and Corin Wagen
The Boltz-2 FAQ

The Boltz-2 FAQ

Questions and answers about the Boltz-2 biomolecular foundation model.
Jun 9, 2025 · Corin Wagen and Ari Wagen