Exciting applications are coming soon, with experimental validation in the next version!

📄paper: www.biorxiv.org/content/10.1...
💻code: github.com/yehlincho/Pr...

Protein Hunter enables multimer binder design, multi-motif scaffolding, partial redesign, and nucleic acid binder design — offering a general pipeline for protein design that can be applied to any AF3-style models, existing or in development.

Additionally, Protein Hunter supports all-atom molecular binder design. We show in silico success rates for four small molecules, where iterative cycles of Boltz2 and LigandMPNN achieve the highest AF3 success rates.

We also demonstrate the success of the pipeline on cyclic peptides, exemplified with the MDM2 target.
Macrocyclic peptide design can be achieved through cyclic positional encodings.

However, diffusion-based models favor α-helical topologies (reflecting training bias), reducing structural diversity. To enhance β-sheet content, we applied a negative helix bias to Pairformer pair features before diffusion, increasing sheet-rich samples.

Repeating this process significantly improves the in silico success rates of AlphaFold3 and the designability of both unconditional and conditional (binder) design tasks.

Protein Hunter: Starting from an all "X" sequence, we find that diffusion-based structure prediction models can hallucinate reasonable looking structures, which can be further improved through iterative sequence design and structure prediction, similar to AF2Cycler and LASErMPNN.

And they do it remarkably well with an all-“X” sequence. ❌😮
AF3-style models treat unknown PDB residues as X tokens and explicitly handle non-canonical amino acids and ligands, enabling folding of undefined sequences while minimizing bias from amino acid specific features.

It actually folds into a structure and binds near the target!

We found that AF3-like structure prediction models (Boltz, Chai, AF3) can hallucinate proteins within their diffusion modules.

Have you ever wondered what AF3-like structure prediction models would produce when given a random protein sequence and a target of your choice?

Would it form a completely disordered structure that wraps around the target, or would it still fold and bind to it?

5. BoltzDesign1 can be used to design sequences and structures that AlphaFold3 predicts to bind to metal ions, nucleic acids, and other biomolecules

4. We achieved the best results by setting the Pairformer recycling step to 0 and fixing the initial BoltzDesign1 sequence at the interface while redesigning the remaining surface regions using LigandMPNN.

3. By utilizing only the Pairformer and Confidence module, our method generates highly diverse binders, with high AlphaFold3 success rates, strong cross-model and self-consistency, as demonstrated by benchmarks on four small-molecule targets from the RFDiffusionAA benchmark set.

2. Instead of optimizing single structures, we optimize directly on the distogram, shaping the probability distributions of atomic distances. We show that the distogram effectively captures interactions between proteins and their targets, serving as a proxy for confidence scores

1. We introduce BoltzDesign1, which inverts the Boltz-1 model—an open-source reproduction of AlphaFold3—to enable the design of protein binders for diverse molecular targets without requiring model fine-tuning.

www.biorxiv.org/content/10.1...