Software & Data Resources
Open source software and data accessibility is a critical part of the DMREF program. Below are some examples of publicly accessible software and databases that have been developed by DMREF teams.

AQUAMI

AQUAMI is an open source Python package and GUI which can automatically analyze micrographs and extract quantitative information to characterize microstructure features. (Also see related paper on this software tool.)

Building a Materials Data Infrastructure: Opening New Pathways to Discovery and Innovation in Science and Engineering

The availability of increasingly sophisticated experimental and computational tools provides scientists and engineers with new opportunities, but harnessing the vast amounts of data generated from these new approaches presents a challenge. Building a Materials Data Infrastructure, funded by the DMREF program, identifies and prioritizes these challenges, while also providing actionable recommendations for addressing them.
 

Chemoresponsive Liquid Crystal Research Database

This website presents key results of the joint efforts of Cornell University, Kent State University, and the University of Wisconsin-Madison to accelerate the design of chemoresponsive liquid crystalline systems that respond to targeted analytes, such as organophosphonates (e.g. DMMP), O3, Cl2, and formaldehyde.

Learn more

DeepFRI

DeepFRI is a structure-based protein function prediction (and functional residue identification) method using Graph Convolutional Networks with Language Model features. DeepFRI is a product of the Computationally Driven-Genetically Engineered Materials (CD-GEM) project.

HybriD³ Materials Database

The HybriD³ materials database provides a comprehensive collection of experimental and computational materials data for crystalline organic-inorganic compounds, predominantly based on the perovskite paradigm.

Learn more

Magnetic Materials Database

Magnetic Materials Database provides a large array of datasets for magnetic compounds as well as magnetic clusters, with focus on rare-earth-free magnets. An Iowa State University effort, this database is specifically designed for data sciences and machine learning modelings.

MASTML_Metallic_Glass_Bulk_Modulus

A scikit-learn Gradient Boosted Trees model predicting metallic glass bulk modulus values from accessible elemental feature inputs is shared on the DLHub hosting site. The model is callable with the DLHub API.

 

Learn more

MASTML_Metallic_Glass_Debye_T

A scikit-learn Random Forest model predicting metallic glass debye temperature values from accessible elemental feature inputs is shared on the DLHub hosting site. The model is callable with the DLHub API.

 

Learn more

MASTML_Metallic_Glass_Density

A scikit-learn Linear Regression model predicting metallic glass density values from accessible elemental feature inputs is shared on the DLHub hosting site. The model is callable with the DLHub API.

 

Learn more

MASTML_Metallic_Glass_Poissons_Ratio

A scikit-learn Random Forest model predicting metallic glass poisson’s ratio values from accessible elemental feature inputs is shared on the DLHub hosting site. The model is callable with the DLHub API.

 

Learn more

Showing 1 to 10 of 21