
Meta offers ESMFold
ESMFold is a protein structure prediction model developed by Meta AI that predicts 3D structures directly from protein sequences.
- Currently Offered

ESMFold is a protein structure prediction model developed by Meta AI that predicts 3D structures directly from protein sequences.
ESMFold is a deep learning model developed by Meta AI that predicts protein 3D structures directly from amino acid sequences using a language model approach. It powers the ESM Metagenomic Atlas, which has predicted structures for over 600 million metagenomic proteins.
ESMFold uses a transformer-based protein language model to generate structure predictions, offering a fast alternative to template-based methods and serving as a complementary tool in the protein structure prediction ecosystem alongside AlphaFold and RoseTTAFold.


AlphaFold is an AI system that predicts 3D protein structures from amino acid sequences, accelerating biological research and drug discovery.


Generative protein language model family that jointly reasons over protein sequence, structure, and function to design novel proteins.


Open database and exploration tool covering 6.8 billion proteins with over one billion predicted structures.
AlphaFold is an AI system that predicts 3D protein structures from amino acid sequences, accelerating biological research and drug discovery.

Generative protein language model family that jointly reasons over protein sequence, structure, and function to design novel proteins.

Open database and exploration tool covering 6.8 billion proteins with over one billion predicted structures.



Protein structure prediction model for biomolecular complexes spanning protein, DNA, RNA, and ligand inputs.


Protein language model family for representation learning, providing embeddings and zero-shot mutation analysis for proteins.


ProGen is Salesforce's open BSD-3 protein language-modeling suite for protein engineering and design.


AI platform for de novo antibody and protein design against challenging drug targets.
Protein structure prediction model for biomolecular complexes spanning protein, DNA, RNA, and ligand inputs.

Protein language model family for representation learning, providing embeddings and zero-shot mutation analysis for proteins.

ProGen is Salesforce's open BSD-3 protein language-modeling suite for protein engineering and design.

AI platform for de novo antibody and protein design against challenging drug targets.
