LigandMPNN With Multi-state?

Mar 28, 2025ligandmpnn is a deep-learning-based protein sequence design method that can explicitly model all nonprotein components of biomolecular systems. Mar 29, 2025our latest deep-learning model, ligandmpnn, excels at creating proteins that interact with other diverse molecules, including small molecules, nucleic acids, and metals. Apr 28, 2025this page provides detailed examples and step-by-step tutorials for common usage scenarios of the ligandmpnn system.

Ligandmpnn - colab atomic context-conditioned protein sequence design using ligandmpnn - paper this colab notebook provides inference code for ligandmpnn & proteinmpnn models.. Ligandmpnn is an inverse folding model that is capable of not only predicting the amino acids of a protein structure, but also certain chains, and complexes. Here, we describe a deep learning-based protein sequence design method called ligandmpnn that explicitly models all non-protein components of biomolecular systems.

Dec 2, 2024the ligandmpnn data is inflated because these calls also include the sc.py file which allows for side-cahin packing. Ligandmpnn is an inverse folding model that explicitly accounts for non-protein atoms in protein sequence design. Sep 10, 2025the ligandmpnn api provides an interface to the ligandmpnn protein design tool.