SBGrid Consortium homepage

RoseTTAFold2, extends the original three-track architecture of RoseTTAFold over the full network, incorporating the concepts of Frame-aligned point error, recycling during training, and the use of a distillation set from AlphaFold2.

a set of comprehensive facilities for Fourier processing of spectra in one to four dimensions, as well as a variety of facilities for spectral display and analysis. This is the official NMRScience version of NMRPipe.

a collection of cheminformatics and machine-learning software written in C++ and Python.

is the first flow-matching based protein folding model that uses only general purpose transformer layers, without relying on expensive modules like triangle attention or pair representation biases. The model scales to 3B parameters and is trained on over 8.6M distilled protein structures plus experimental PDB data, making it the largest scale folding model ever developed. SimpleFold achieves competitive performance on standard folding benchmarks and demonstrates strong ensemble prediction capabilities due to its generative training objective.

a tool that provides annotation and segmentation of cryo-ET data using convolutional neural networks.

a GPU accelerated python module to significantly improve the speed and sensitivity using template matching to detect macromolecules from tomograms.

a tool that improves the quality and interpretability of cryo-EM maps by local and non-local deep learning

a tool for scaling data analyses in cellular cryoET using comprehensive segmentation.

a package implemented in Python to manipulate Relion star files including counting, modifying, plotting, and sifting the data.

is a Python package for executing alchemical free energy calculations.