DCFold: Efficient Protein Structure Generation with Single Forward Pass
cs.LG, cs.AI, q-bio.QM
Submitted: 2026-05-18
Updated: 2026-09-26
Comments: ICLR 2026 Oral
License: http://creativecommons.org/licenses/by/4.0/
The gist: AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy.
Terminology
Abstract
AlphaFold3 introduces a diffusion-based architecture that elevates protein structure prediction to all-atom resolution with improved accuracy. This state-of-the-art performance has established AlphaFold3 as a foundation model for diverse generation and design tasks. However, its iterative design substantially increases inference time, limiting practical deployment in downstream settings such as virtual screening and protein design. We propose DCFold, a single-step generative model that attains AlphaFold3-level accuracy. Our Dual Consistency training framework, which incorporates a novel Temporal Geodesic Matching (TGM) scheduler, enables DCFold to achieve a 15x acceleration in inference while maintaining predictive fidelity. We validate its effectiveness across both structure prediction and binder design benchmarks.
Sources
- FastFold: Reducing AlphaFold Training Time from 11 Days to 67 Hours
- HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative
- Consistency Models Made Easy
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
- Progressive Distillation for Fast Sampling of Diffusion Models
- Denoising Diffusion Implicit Models
- Improved Techniques for Training Consistency Models
- Consistency Models
- Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks