To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
-
Updated
Oct 29, 2022 - Python
To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集
Optimizing AlphaFold Training and Inference on GPU Clusters
Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein folding
Implementation of Invariant Point Attention, used for coordinate refinement in the structure module of Alphafold2, as a standalone Pytorch module
Implementation of trRosetta and trDesign for Pytorch, made into a convenient package, for protein structure prediction and design
🧬 ManyFold: An efficient and flexible library for training and validating protein folding models
Singularity recipe for AlphaFold
Implementation of the Triangle Multiplicative module, used in Alphafold2 as an efficient way to mix rows or columns of a 2d feature map, as a standalone package for Pytorch
Deep learning for protein science
Infrastructure template and Jupyter notebooks for running RoseTTAFold on AWS Batch.
Python package for generating Markov state models
The largest open-source dataset for Protein Single Sequence Secondary Structure prediction.
Your open-source alternative to AlphaFold3🚀
A package for protein conformational ensemble analyses based on a differential geometry representation of protein backbones.
a package of Python modules and example scripts for experimenting with the two-dimensional HP lattice model of Dill and Chan.
We seek a classifier that will predict if a protein sequence (+3D coordinates) will fold.
ResNetQA: Improved protein model quality assessment by integrating sequential and pairwise features using deep learning
Lightning-Fast Template-free Protein Folding based on Predicted Residue Contacts and Secondary Structure
CA-2-HCOMB is a tool for simplifying single-chain protein structures from PDB files into manageable models like various honeycombs, retaining essential information for in-depth computations. It's efficient for large datasets and machine learning, and user-friendly for research and education.
Add a description, image, and links to the protein-folding topic page so that developers can more easily learn about it.
To associate your repository with the protein-folding topic, visit your repo's landing page and select "manage topics."