@mmoderwell
Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
Badges
Organizations
Teams
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
- Admin
Before the competition officially starts, I love to get some of the existing AI models out there on Ouro. Check out the APIs section (upside-down triangle) on the sidebar to see what's already been ad
Just added a protein visualization to Ouro. Right now it only supports .pdb files because .cif files would clash with the platform's crystal viewer. You can still upload any kind of file you want, but
Nipah virus attachment glycoprotein in complex with human cell surface receptor ephrinB2
Hey everyone, welcome to the #nipah-binder-competition team. You're in the right place if you're interested in applying AI to antibody/drug discovery. The purpose of this space if to:
This asset shows two plots for a CuNi crystal after a 10 picosecond melt equilibration at 1800 K. The left plot is the total radial distribution function (RDF) versus distance, with a strong first peak near 2 Å and several smaller peaks up to about 8–9 Å, suggesting some remaining order from the original lattice. The right plot shows the coordination number (CN) as a function of distance, which increases gradually and reaches around 350 by 10 Å. The note indicates that even at about 9 Å away, there is still a signal of another atom, meaning remnants of the supercell lattice persist in the melted state.
I'm excited to share a new page I've been building out this week. You may have already seen it, as it's the first page you be redirected to after sign in.
This post explores ideas about AI and how it might change human work and purpose. It mentions starting a small philosophy discussion group to talk about big questions like meaning, usefulness, and how technology affects society. The writer references the book Courage to Be Disliked and Adlerian psychology, noting a common claim that happiness comes from being useful to others. They also offer a personal take that this may not be the only source of happiness. The central question asks what could happen if people feel they are no longer useful to each other or cannot be. It’s a thoughtful look at consequences of automation and the search for meaning in a changing world. Keywords: AI, philosophy, Adlerian psychology, Courage to Be Disliked, usefulness, happiness, labor, future.
is a post about running molecular dynamics simulations to study how a Cu-Zr alloy forms a metallic glass. The author uses a 64% Cu and 36% Zr composition, an (10,10,10) supercell, and the orb-v3-direct-20-omat calculator to push speed and scale. The workflow includes equilibrating a melted alloy at high temperature, then rapid quenching from 2000 K to 300 K at various rates to compare glass formation versus crystallization. The write-up explains key concepts like what glass is in atomic terms, the difference between crystalline order and amorphous structure, and how RDF and coordination numbers help analyze results. It also notes the challenges of achieving crystallization in MD due to time scales and suggests exploring different cooling rates and compositions in future runs. The post includes example data and 3D visualization references to support the findings.
The Pareto frontier for a range of universal Machine Learning Interatomic Potentials. The 𝐾𝑆𝑅𝑀𝐸 metric assesses a model’s ability to predict thermal conductivity via the Wigner formulation of heat transport and requires accurate geometry optimizations as well as second and third order derivatives of the PES (computed via finite differences). The y-axis measure a model’s forward passes per second on a dense periodic system of 1000 atoms, disregarding graph construction time, measured on a NVIDIA H200. Point sizes represent max GPU memory usage. Y-axis jitter (+/- 5 steps/second) has been applied to allow visualization of overlapping points. Model families include a range of specific models with broadly the same architecture, but may be different sizes or trained on different datasets.
Meso-scale all-atom simulations with Orb-v3 open a new frontier in materials science and chemistry. This post discusses using ASE for molecular dynamics on GPUs (A100, H100, H200) via Modal, enabling larger, more affordable simulations than traditional DFT. It highlights metallic glass formation, crystallization, annealing, and emergent phenomena that arise from thousands of atoms. The focus is on a breakthrough in non-conservative architectures that balance memory use and speed, making complex systems feasible to study.
The authors introduce Orb-v3, the next generation of the Orb family of universal interatomic potentials. Models in this family expand the performance-speed-memory Pareto frontier, offering near SoTA performance across a range of evaluations with a ≥ 10× reduction in latency and ≥ 8× reduction in memory. Their experiments systematically traverse this frontier, charting the trade-off induced by roto-equivariance, conservatism and graph sparsity. Contrary to recent literature, they find that non-equivariant, non-conservative architectures can accurately model physical properties, including those which require higher-order derivatives of the potential energy surface.
Paper by Rich Sutton
A post about trying to use HamGNN with TB2J to forecast magnetocrystalline anisotropy energy, only to find the pre-trained model lacks the needed physics. The main gap is the absence of spin-polarization in H0, making the model better suited for SOC in non-magnetic materials, not for magnetic predictions. Potential outputs still relevant to SOC include band structure corrections, topological invariants, spin textures in k-space, orbital angular momentum, spin Hall conductivity, g-factors, effective masses, and optical properties. The use case focuses on non-magnetic materials and topological insulators without magnetism. Next steps involve exploring new Hamiltonian models like DeepH-pack and MACE-H, noting they lack pre-trained models. The plan is to gather consistent data, ensure SOC and spin-polarization, and align data sources from the same DFT software. Links: https://github.com/mzjb/DeepH-pack, https://github.com/maurergroup/MACE-H.
Once again we're at a stopping point because of our inability to effectively predict MAE. Our AI discovery agents have discovered materials that have all the properties we can currently predict. This
A clear look at using LLMs for materials discovery. This post summarizes how Victor from Lila Sciences and the author compare their AI workflows, focusing on mutations in crystal structures, machine learning force fields (MLFF), and machine learning property predictors (MLPP). It explains why data limits push researchers toward direct reasoning with AI, the role of modification history and self-reflection, and how prompts influence performance. Key takeaways include constraints in rare-earth-free magnet design, the balance between control and relaxation, and the impact of self-reflection on speeding up convergence to target properties like band gap and formation energy. The notes also touch on challenges with crystal symmetry, CIF generation, and future work in MLIP/MLPP accuracy. A practical read for anyone exploring automated materials discovery and AI-driven design.
Discovering new materials can have significant scientific and technological implications but remains a challenging problem today due to the enormity of the chemical space. Recent advances in machine learning have enabled data-driven methods to rapidly screen or generate promising materials, but these methods still depend heavily on very large quantities of training data and often lack the flexibility and chemical understanding often desired in materials discovery. This paper introduces LLMatDesign, a novel language-based framework for interpretable materials design powered by large language models (LLMs).
Phase diagram of CrFe7; e_above_hull: 0.000000 eV/atom; predicted_stable: True
A phonon dispersion plot for a relaxed structure using a 2x2x2 supercell. The red lines show multiple phonon branches across high-symmetry paths labeled Gamma, X, Y, ZR2, U2, and V2. Frequencies range up to about 9 THz, with several bands crossing and bending as they move along the path. A blue dotted line marks zero frequency, and the data indicate no imaginary modes, though the lowest branch dips slightly below zero by about 0.07 THz. This image summarizes how vibrational modes vary with wavevector for the relaxed structure.
Cell + Ionic relaxation with Orb v3; 0.03 eV/Å threshold; final energy = -137.4990 eV; energy change = -0.2603 eV; symmetry: R3m → Im-3m
Standalone, embeddable HTML with MatterViz Trajectory viewer
Phase diagram of Fe8Co4N; e_above_hull: 0.093154 eV/atom; predicted_stable: False
Phonon band structure (supercell [2, 2, 2], Δ=0.01 Å); no imaginary modes; min freq = -0.02 THz
Phonon band structure (supercell [2, 2, 2], Δ=0.01 Å); no imaginary modes; min freq = -0.01 THz
Phase diagram of Fe8Co4N; e_above_hull: 0.093253 eV/atom; predicted_stable: False
Phase diagram of Fe8Co4N; e_above_hull: 0.173013 eV/atom; predicted_stable: False
Phonon band structure (supercell [2, 2, 2], Δ=0.01 Å); imaginary modes detected; min freq = -0.64 THz
Standalone, embeddable HTML with MatterViz Trajectory viewer
Phonon band structure (supercell [2, 2, 2], Δ=0.01 Å); no imaginary modes; min freq = -0.06 THz
Phase diagram of Fe2Co2N; e_above_hull: 0.142871 eV/atom; predicted_stable: False
Phase diagram of Fe2Co2N; e_above_hull: 0.100092 eV/atom; predicted_stable: False
Thinking about if view count should be number of unique users, or if it should be total number of viewport views. Total VPVs overcounts things a lot. Basically one person could just keep refreshing th
This post explores ideas for finding adjacent crystals in Matra-Genoa’s latent space to discover materials with targeted properties. The author describes challenges when mutating crystals, where small input changes can lead to large, different outputs after relaxation. Three approaches are considered: conditioned generation with token hints (fixing some inputs while mutating others), decoding from a modified latent space (using predictors and SHAP to steer latent directions before decoding), and a hybrid approach that combines fixed tokens with latent-space moves. The goal is faster exploration and smarter guidance from an AI research agent and a language model, reducing the cost of property evaluation. The notes also touch on fine-tuning and property-focused training to improve material design workflows. Keywords: adjacent crystals, latent space, Matra-Genoa, crystal generation, materials AI, property optimization.
Check out the paper here. It's a short read. I recommend checking it out. Although not very technical (just machine learning concepts that have been explored elsewhere), the creativity and simplicity
sorry for all the spam! I'll make the AI scientist make stuff private by default and only publish the really good stuff.
AI-discovered magnetic material: Mn2CrFe4Co4N (performance score: 0.740) | Space group: 1 (resolved from structure) | Key properties: Tc: 612K, Ms: 0.14T, Cost: $13/kg, E_hull: 0.235eV/atom, Dynamically stable | Discovered in 20 AI iterations | - The combination of Mn, Cr, Fe, Co, and N in this stoichiometry yields a high Curie temperature and magnetic density. - The material is dynamically stable, which supports its structural integrity. - The energy above hull suggests that the material is metastable or unstable thermodynamically. - Cost is low, indicating practical feasibility from an economic standpoint.
AI-discovered magnetic material: Fe11CoSiGeAsP (performance score: 0.597) | Space group: 8 (resolved from structure) | Key properties: Tc: 687K, Ms: 0.13T, Cost: $82/kg, E_hull: 0.161eV/atom, Dynamically stable | Discovered in 10 AI iterations | - Strong ferromagnetism with high Tc arises naturally from the Fe/Co sublattice; this is retained despite chemical complexity. - Dynamic stability indicates the structure is at least locally stable; the main risk is competition with lower-energy phases (slightly positive e_hull). - The metastability is small enough that slight stoichiometric shifts (e.g., favoring smaller/more covalent anions like P over As, or Si over Ge) or controlled disorder could stabilize the phase thermodynamically. - Magnetic density is adequate but not exceptionally high; maintaining or modestly enhancing it while reducing e_hull should be feasible by delicate tuning of Co content or anion ratios.
AI-discovered magnetic material: Fe4Mn3B4 (performance score: 0.728) | Space group: 1 (resolved from structure) | AI-generated from scratch using crystal structure prediction | Key properties: Tc: 536K, Ms: 0.09T, Cost: $1/kg, E_hull: 0.230eV/atom, Dynamically stable | Discovered in 2 AI iterations | The Fe4Mn3B4 compound shows promising magnetic ordering temperature and dynamic stability, suggesting good intrinsic magnetic behavior and structural robustness. The main challenge is its thermodynamic stability, as indicated by the high energy above hull. The magnetic density is close but slightly below the target, suggesting that minor compositional or structural modifications might improve it. The low cost and atom count within limits make it a practical candidate if stability can be enhanced.
AI-discovered magnetic material: MnFe4(CoB2)2 (performance score: 0.731) | Space group: 38 (resolved from structure) | Key properties: Tc: 518K, Ms: 0.12T, Cost: $10/kg, E_hull: 0.164eV/atom, Dynamically stable | Discovered in 2 AI iterations | The material MnFe4(CoB2)2 demonstrates promising magnetic properties with a Curie temperature above 500 K and magnetic density above 0.1, confirming its potential as a high-performance magnetic material. Its low cost and dynamic stability are additional advantages. The slight excess in energy above hull indicates that minor compositional or structural tuning might be needed to improve thermodynamic stability. This suggests that the compound is close to being stable and could be optimized further.
Sometime soon (Late summer / fall '25) I want to host a hackathon-type event for the technical creators in Chicago. I just moved back here and have already met some amazing builders. But the community
I got rid of the collected feed recently. Instead of seeing all of the content from your teams together, you now have to choose a team to see the feed of content. To make catching up easier, I added u
Welcome
Interactive trajectory explorer with MatterViz
Interactive browser visualizations for materials science, by @janosh
Welcome
Relax a crystal structure and create a post
Get a detailed description of a crystal structure
Generate CIF file from crystal structure description
Get space groups compatible with a given chemical formula
Root
Generate a crystal structure using GGen
Random bulk crystal generation with PyXtal and Orb v3
Relax a crystal structure with animation
Create interstitially doped structure
Generate a crystal structure with MatterGen
Generate a crystal structure with Chemeleon
Generate crystal structures with magnetic density and HHI score conditioning
Calculate phonon dispersion and return band structure plot
Generate crystal structures for target compositions
Generate crystal structures from text descriptions
Welcome
This dataset has a set of 34,000 ferro/ferrimagnetic materials from Materials Project, their formula, if they include rare earth elements, magnetic moment, volume, magnetic density, a predicted Curie temperature, and cosine distances to some known permanent magnets like NdFeB. Distances are based on a 256 dimension embedding from Orb v2 latent space.
A collection of 5020 magnetic materials from Materials Project, with estimated magnetic density and predicted Curie temperatures.
This is a first draft of a compiled Curie temperature dataset mapping crystal structure (from Materials Project) to Curie temperature. Builds on the work of https://github.com/Songyosk/CurieML. Dataset includes ~6,800 unique materials representing 3,284 unique chemical families.
Evaluation results for the MatterGen fine-tuned model candidates, with new superconducting families labeled.
3DSC dataset grouped by chemical composition, with Tc as our target. For use with MatterGen and the chemical system sampling.