Towards Sub-Second Molecular Docking as a Structural Primitive: A Quantized Consistency Diffusion Framework

Agent-centered scientific discovery is turning scientific models into always-on computational infrastructure. In this paradigm, AI agents coordinate tools, interpret feedback, and drive high-frequency research loops, requiring domain models that are both accurate and callable in real time. Molecular docking exposes this bottleneck: it provides essential structural feedback for drug discovery, yet current high-fidelity docking and co-folding models remain limited by iterative generative refinement and heavy computation. We present a compute-efficient co-folding framework that turns molecular docking into a sub-second structural primitive. Because docking methods operate under different levels of structural prior, we report accuracy under information-level-matched protocols, comparing blind settings with blind generative methods and interface-informed settings with surface- or interface-informed baselines. Our framework combines two ideas. First, Progressive Consistency Regularization (PCR) compresses diffusion dynamics into reliable few-step inference through reconstruction-anchored consistency tuning. Second, Residual-Safe Quantization preserves high-fidelity residual streams and geometry-sensitive operations in BF16 while quantizing selected compute-intensive linear transformations. Our model achieves state-of-the-art docking accuracy under the matched interface-informed protocol, reports blind docking performance separately under the matched blind protocol, and generates five conformations for a representative 256-token complex in 0.17 seconds on a single NVIDIA H20 GPU, delivering a $>300\times$ speedup over AlphaFold3 under the benchmarked setting. Together, these results move molecular docking from an offline generative simulator toward a real-time structural primitive for agent-centered drug discovery.

Molecular docking predicts how a drug-like molecule binds to a protein, which is a key step in early drug discovery. Modern AI docking models can be accurate, but they are often too slow to be called repeatedly in large-scale screening or interactive scientific workflows. This work makes high-fidelity docking much faster by redesigning both the sampling process and the model deployment strategy. We reduce the number of repeated generation steps needed to produce a structure, while preserving the geometric accuracy required for protein--ligand binding. We also use a safer form of quantization that accelerates compute-heavy parts of the model without disturbing the precision-sensitive structural pathways. As a result, the model can generate multiple candidate binding poses in sub-second time on a single GPU, making docking closer to a real-time structural tool for drug discovery.