ConforNets: Latents-Based Conformational Control in OpenFold3

TL;DR

ConforNets introduces a latent perturbation method in AlphaFold3 that enables efficient, controllable generation of biologically relevant protein conformations, outperforming previous approaches on multiple benchmarks.

Contribution

The paper presents ConforNets, a novel global latent modulation technique for AlphaFold3 that enables reliable conformational control across proteins.

Findings

Achieves state-of-the-art success in multi-state benchmarks.

Enables conformational transfer across protein families.

Outperforms previous methods in generating alternate protein states.

Abstract

Models from the AlphaFold (AF) family reliably predict one dominant conformation for most well-ordered proteins but struggle to capture biologically relevant alternate states. Several efforts have focused on eliciting greater conformational variability through ad hoc inference-time perturbations of AF models or their inputs. Despite their progress, these approaches remain inefficient and fail to consistently recover major conformational modes. Here, we investigate both the optimal location and manner-of-operation for perturbing latent representations in the AF3 architecture. We distill our findings in ConforNets: channel-wise affine transforms of the pre-Pairformer pair latents. Unlike previous methods, ConforNets globally modulate AF3 representations, making them reusable across proteins. On unsupervised generation of alternate states, ConforNets achieve state-of-the-art success rates on all existing multi-state benchmarks. On the novel supervised task of conformational transfer, ConforNets trained on one source protein can induce a conserved conformational change across a protein family. Collectively, these results introduce a mechanism for conformational control in AF3-based models.