Find open-source science resources

Fully open-source (Apache 2.0) biomolecular structure prediction reproducing AlphaFold3

protein binder design with test-time optimization, SOTA on binder

protein design platform via Google Colab integrating AlphaFold2, RoseTTAFold, and ProteinMPNN

Neural network-based cryo-EM heterogeneous reconstruction, modeling continuous 3D

protein design using diffusion modeling, equivariant graph neural networks, and conditional

proteins, nucleic acids, small molecules, ions, and post-translational modifications

proteins, nucleic acids, and small molecules in drug discovery; ranked

protein-protein interaction screening with AlphaFold-Multimer and AlphaFold 3, supporting

protein design framework integrating Boltz, AlphaFold2, OpenFold3, ProteinMPNN, and ESM via JAX-based

protein sequence, structure, and biochemical properties to predict class-I immunogenicity

Trainable PyTorch reproduction of AlphaFold 3

proteins, nucleic acids, and complexes, featuring a public web server

protein equilibrium conformations 100,000× faster than MD simulations, predicting

protein folding model using only general-purpose transformer layers, scaled

Democratizing AlphaFold3: PyTorch reimplementation to accelerate protein structure prediction research

proteins, nucleic acids, small molecules, and cyclic peptides with fine

proteins, small molecules, DNA, RNA, glycans) achieving SOTA across benchmarks

Cross-platform system optimizations for accelerating AlphaFold3 training with 1.73

Learning the language of protein-protein interactions

protein structure determination from electron density with high accuracy (3DEM/EMBL

proteins via backpropagation through compositional design constraints parameterized by structure

First fully open-source model achieving AlphaFold3-level accuracy with

protein-nucleic acid-small molecule-metal ion complexes, enabling accurate

protein design framework enabling DNA-encoding of chemistry for programmable

protein design achieving state-of-the-art performance on unconditional

Semi-flexible molecular diffusion model for structure-based drug design

Protein structure prediction

proteins, nucleic acids, ligands, ions, and post-translational modifications within

protein conformational ensembles, covering both experimental PDB states and molecular

protein language model using 3D structural vocabulary (Foldseek) for joint

protein backbone generation, 37× faster than RFDiffusion with 0.972 designability

proteins with noncanonical amino acids, enabling AI-powered modeling of synthetic

protein sequence design over evolutionary-scale databases, supporting unconditional generation

protein binders based on the Protenix foundation model, achieving 17-82% nanomolar

protein structure prediction and design pipelines (Columbia AlQuraishi Lab & OpenFold

protein-ligand conformational ensemble prediction and docking, generating diverse solutions

protein language models via sparse autoencoders, enabling mechanistic understanding of PLM representations

protein's amino acid sequence and full atomistic structure, including

Protein Data Bank integrating dynamic behaviors and physical properties into

protein language models demonstrating versatile generative and predictive capabilities for protein

protein backbone generator utilizing hierarchical fold class labels for conditioning

protein language model family, including PMC-15B supporting sequence- and structure

protein binding pocket, enabling scaffold hopping and linker design workflows

protein activities, enabling rapid protein engineering with minimal experimental data

Universal 3D molecular pretraining framework with 209M conformations, scaling to

Diffusion-based molecular docking achieving SOTA blind docking performance, treating

protein sequence design in the context of small-molecule ligands

Large-scale biomolecular instruction dataset for chemistry/biology LLMs (ICLR2024)

protein structure design with multi-motif scaffolding capabilities, achieving state