SimpleFold2: Efficient Biomolecular Co-folding with Transformers

Biomolecular co-folding models jointly predict the 3D atomic structure of systems where a protein interacts with other proteins, ligands, and nucleic acids. Most modern co-folding models build on the AlphaFold lineage, which designed bespoke architectures like pair representations, triangle updates, and deep MSA encodings. In this work, we ask if co-folding models require these domain specific designs or could instead be framed as general purpose generative models from the ground up. We introduce SimpleFold2, a flow matching model for co-folding built exclusively using general purpose transformers. Similar to text-to-image models, we use pre-trained protein language models (pLMs) to embed sequence information, and we do not incorporate triangle updates, template stacks, recycling, or equivariant modules. Because every layer in SimpleFold2 is ordinary attention or an MLP, it inherits the favorable behavior of modern transformers. We scale SimpleFold2 to 3B parameters and demonstrate strong performance on protein-ligand co-folding and competitive performance on monomers. We then show how the efficiency of SimpleFold2 leads to strong test-time scaling behavior. Overall, SimpleFold2's architecture ensures it is highly efficient on modern hardware: it uses $\approx 0.3\times$ the memory of AlphaFold-style models, runs $10\times$ faster for $1700$-residue complexes, and can even fold a $4960$-residue complex on a single NVIDIA H100 GPU in 39s using only 62 GB of memory, a task well beyond most comparable methods.