IntFold：一款可控的基础模型，用于通用与专用生物分子结构预测

摘要

我们推出IntFold，一种可控的基础模型，适用于通用及特定生物分子结构预测。IntFold展现出与当前最先进的AlphaFold3相媲美的预测精度，同时采用了更优的定制注意力核。除标准结构预测外，IntFold通过使用独立适配器，可灵活预测变构状态、受限结构及结合亲和力。此外，我们引入了一种新颖的置信度头部来评估对接质量，为诸如抗体-抗原复合物等挑战性目标提供了更为细致的评估。最后，我们分享了在训练这一计算密集型模型过程中获得的洞见。

English

We introduce IntFold, a controllable foundation model for both general and specialized biomolecular structure prediction. IntFold demonstrates predictive accuracy comparable to the state-of-the-art AlphaFold3, while utilizing a superior customized attention kernel. Beyond standard structure prediction, IntFold can be adapted to predict allosteric states, constrained structures, and binding affinity through the use of individual adapters. Furthermore, we introduce a novel confidence head to estimate docking quality, offering a more nuanced assessment for challenging targets such as antibody-antigen complexes. Finally, we share insights gained during the training process of this computationally intensive model.

IntFold：一款可控的基础模型，用于通用与专用生物分子结构预测

IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction

摘要

Support