TorchDrug

Boltz-1 — open-source deep learning model for predicting biomolecular 3D structures and interactions, approaching AlphaFold3-level accuracy. Supports protein, DNA, RNA, and small-molecule ligand struc

2 shared topics • 3 shared operations

Gnina — deep learning molecular docking program built on AutoDock Vina. Uses convolutional neural networks (CNNs) to rescore protein-ligand poses for improved binding pose prediction and virtual scree

2 shared topics • 3 shared operations

ProteinMPNN — deep learning-based protein sequence design from backbone structures. Uses message passing neural networks to predict amino acid sequences that fold into a given 3D backbone. Supports fi

2 shared topics • 3 shared operations

RoseTTAFold — deep learning-based protein structure prediction using a three-track neural network architecture for simultaneous processing of 1D sequence, 2D distance maps, and 3D coordinates. Predict

2 shared topics • 3 shared operations

Infernal — RNA covariance model (CM) toolkit for homology search and structural alignment of RNA sequences. Builds profile CMs from Stockholm alignments (cmbuild), calibrates E-values (cmcalibrate), s

2 shared topics • 2 shared operations