Amagasa, T. | bioRxiv Science

bioRxiv2026

ConforFlux: Particle-Guided Trunk Repulsion for Diverse Protein Conformations

Deep-learning protein structure predictors achieve near-experimental accuracy on individual folds, yet their default inference samples concentrate around a single dominant conformation. We introduce ConforFlux, an inference-time procedure for Boltz-2 that couples multiple structure-prediction trajectories through a pair-wise C-RMSD repulsion gradient on the trunks single and pair embeddings. Because the trunk conditions every block of the diffusion module, this update propagates to every subsequent denoising step. On four conformational-change categories, ConforFlux improves the per-state success rate over default Boltz-2 by 3-17 percentage points. On twelve transporter pairs with at least one alternate-state reference released after the Boltz-2 cutoff, ConforFlux raises the 2[A] success rate from 33% to 75%. Under an extended bandwidth sweep, ConforFlux samples reach the inward, occluded, and outward states of the human dopamine transporter alternating-access cycle, while default samples cluster between them.

molecular biology↗

bioRxiv2026

Steering Conformational Sampling in Boltz-2 via Pair Representation Scaling

Deep learning has transformed protein structure prediction, yet most systems return a single dominant conformation with little control over alternative functional states. We introduce pair representation scaling, an inference-time method that biases conformational sampling in diffusion-based structure predictors by multiplying the latent pair representation by a single scalar before the Pairformer trunk, without retraining, an auxiliary model, or a second forward pass. On 86 two-state targets spanning domain motions and membrane transporters, scaling broadens the conformational ensembles of both AlphaFold 3 and Boltz-2 and recovers alternative states that default inference misses, most strongly in AlphaFold 3, where the gains extend even to targets deposited after the training cutoff. It approaches the alternative-state recovery of alignment-based sampling methods, and the benefit persists even without a multiple sequence alignment. The predicted distance distributions show that scaling shifts the encoded two-state distribution toward the experimentally observed alternative state, a directed modulation rather than arbitrary perturbation. Pair representation scaling is an interpretable, low-cost handle on the conformational ensembles of deep learning structure predictors. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=62 SRC="FIGDIR/small/701250v3_ufig1.gif" ALT="Figure 1"> View larger version (16K): org.highwire.dtl.DTLVardef@5e52dorg.highwire.dtl.DTLVardef@1090910org.highwire.dtl.DTLVardef@3218beorg.highwire.dtl.DTLVardef@f67068_HPS_FORMAT_FIGEXP M_FIG C_FIG Pair representation scalingA query sequence and its multiple sequence alignment enter the Pairformer trunk, where the latent pair representation z is rescaled by a single global scalar to (1 + {beta}) z and the diffusion module then generates a structure. The alignment and the trained weights are unchanged, and the same operation applies in AlphaFold 3 and Boltz-2. The scalar {beta} is a single explicit handle: sweeping it broadens the sampled ensemble toward alternative states, and its effect can be read out directly inside the network.

bioinformatics↗