AlphaFold 2, developed by Google DeepMind, predicts the 3D structure of a protein from its amino acid sequence at atomic-level accuracy — a problem that had challenged structural biologists for 50 years. It's freely available for both academic and commercial use under the Apache 2.0 license, making it a great choice for teams that need reliable, reproducible structure predictions at scale.

In Benchling, you can run AlphaFold 2 directly from your sequence records, submit batch jobs across hundreds of proteins, and have predicted structures written back to the experimental record automatically.

Key capabilities:

• Monomer and multimer structure prediction from sequence alone

• Per-residue confidence scoring (pLDDT) and predicted aligned error (PAE)

• Multiple Sequence Alignment (MSA) support for evolutionary context

• Apache 2.0 licensed — fully available for commercial research