The paper proposes a cheap, differentiable predictor that estimates AlphaFold 3’s confidence metrics (ipSAE, ipTM) and structural consistency directly from the trunk during early recycling. This predictor can be used as a decision signal to allocate recycling budget efficiently during screening and as an objective in hallucination‑based binder design. Both uses improve performance while significantly reducing computational cost.
arXiv:2602. 24007v3 Announce Type: replace-cross Abstract: Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles that match experimental data.
TorchCraft is a unified binder‑design framework that optimizes sequence logits using a frozen all‑atom structure predictor. It integrates confidence, contact, geometric, and sequence‑prior objectives within TorchFold to design minibinders, framework‑conditioned VHHs, cyclic peptides, and ligand‑binding proteins. Using pretrained AlphaFold 3 weights, TorchCraft produced experimentally validated binders across four targets without post‑hoc redesign, and computational tests confirmed its applicability to cyclic peptides and ligand‑conditioned pocket design.
The paper introduces two closed‑form projection operators that enforce physical validity in biomolecular diffusion models during inference. One operator resolves inter‑chain van der Waals clashes, while the other restores ligand geometry, including bond lengths, angles, planarity, and chirality. These lightweight, model‑agnostic corrections preserve structural accuracy and ligand placement across multiple benchmarks without adding runtime or memory overhead.
CODesign is a co-design framework that jointly generates protein sequences and structures to improve consistency between them. It introduces a large consistency‑distilled dataset of about 105,000 dimers and employs a multimodal joint flow model with a consistency‑aware resampling strategy to iteratively refine sequences and side chains. The approach achieves state‑of‑the‑art in silico success rates for protein‑ and ligand‑target binder design, with ablation studies showing a 70.9% performance boost from the distilled dataset and further gains from the resampling mechanism.
Blitz is a few‑step distillation framework that accelerates diffusion‑based protein structure prediction models by reducing denoising steps from 200 to eight. It employs a geometric noise schedule, multistep consistency training, physical steering, and target‑free candidate selection to maintain high structural accuracy. Applied to AlphaFold 3 and Boltz‑2, Blitz matches teacher‑level accuracy and outperforms other few‑step baselines across multiple evaluation metrics.
The paper introduces MCTH (Monte Carlo Tree Hallucination), an inference-only framework that performs all‑atom biomolecular sequence‑structure co‑design by treating pretrained folding and inverse‑folding models as black‑box operators. MCTH uses Monte Carlo Tree Search to allocate a fixed inference budget across competing design trajectories, incorporating model confidence, uncertainty, and cross‑expert consensus. Experiments across protein‑RNA, protein‑DNA, protein‑protein, and protein‑ligand design show that adaptive search outperforms simpler sampling strategies, and evaluations with AlphaFold3 and Chai‑1 demonstrate transferability beyond the search‑time oracle.
arXiv:2608. 16094v1 Announce Type: new Abstract: Accurate protein structure prediction is fundamental to structural biology because protein structure underlies molecular function and provides a basis for mechanistic interpretation.
SymFold introduces a symmetric dual‑path architecture that combines protein language models (PLMs) and multimodal protein language models (MPLMs) to iteratively guide protein sequence generation for inverse folding. By leveraging pretrained sequence evolution knowledge from PLMs and structural knowledge from MPLMs, the method improves upon the traditional serial pipeline where structure encoders produce coarse sequences refined by PLMs. Experiments on standard inverse‑folding benchmarks show state‑of‑the‑art performance, and ablation studies confirm the effectiveness of the symmetric design.
The paper introduces Prompteina, an all‑atom protein structure generation model that accepts natural‑language descriptions of desired structural and functional properties, similar to text‑to‑image systems. It is trained on a large paired dataset of 1.8 million protein structures and over 50 million captions, and fine‑tuned from the Proteina‑Complexa model to align residues with textual cues. Prompteina outperforms existing baselines on most structural metrics, improves binder design performance, and experimentally validates nine new binders for the GM2A target.
arXiv:2607. 19237v1 Announce Type: new Abstract: Designing small molecule ligands that bind with high affinity to specific protein pockets is a fundamental goal in drug discovery, as small molecules constitute a major fraction of approved therapeutics.
NEAT-POCKET is a pocket‑conditioned extension of the autoregressive NEAT model that generates 3D molecules atom by atom within protein binding pockets, maintaining atom permutation invariance and explicitly modeling hydrogen atoms. It outperforms existing baselines on the CrossDocked and SPINDR datasets, achieving competitive structure‑based generation performance while sampling significantly faster. The model also supports pocket‑conditioned fragment completion, a capability directly useful for lead optimization and scaffold elaboration in drug design.
AtomSteer is a test‑time inference framework that steers pretrained atomistic generative models to satisfy structural constraints such as crystallographic symmetry, geometry, and stereochemistry. It applies bounded local projections, graph‑rigid stereochemical transformations, and periodic symmetry projections during sampling, accepting updates that improve constraint satisfaction while preserving the rest of the structure. The method is demonstrated on three backbones—FlowMM, ET‑Flow, and Boltz‑2—across tasks including de novo crystal generation, crystal structure prediction, molecular conformer generation, and protein‑ligand complex prediction, yielding improvements in space‑group coverage, stereochemical accuracy, and ligand E/Z error rates.