TorchCraft: Unified binder design by inverting an all-atom structure predictor

2026-09-17

AI Summary

TorchCraft通过冻结的全原子预测器优化序列logits，解决使用全原子结构预测器进行结合蛋白设计的难题。

Abstract

All-atom structure predictors model diverse molecular interactions, but using their learned structural priors for binder design remains challenging. Here we present TorchCraft, a unified binder-design framework that optimizes sequence logits through a frozen all-atom predictor. Implemented in TorchFold, TorchCraft combines confidence, contact, geometric, and sequence-prior objectives within a shared optimization procedure for minibinders, framework-conditioned VHHs, cyclic peptides, and ligand-binding proteins. Using pretrained AlphaFold 3 weights, TorchCraft generated representative minibinders and VHHs with experimentally measured binding across four targets in each format, without post hoc sequence redesign. Computational benchmarks further demonstrated the framework's applicability to cyclic peptides and ligand-conditioned pocket design. TorchCraft extends predictor inversion to multiple binder formats and molecular contexts, providing a common framework for reusing all-atom structural priors in design.

Problem

• all-atom structure predictor
• binder design
• structural priors

Innovation

• all-atom structure predictor
• binder design
• TorchFold
• AlphaFold 3
• sequence optimization