FADiff: Floating Anchor Diffusion Model for Multi-motif Scaffolding

* Ke Liu 1, * Shuaike Shen 1, * Weian Mao2, Xiaoran jiao1, Zheng Sun3, † Hao Chen 1, †Chunhua Shen1,4
1Zhejiang University, 2The University of Adelaide, 3Swansea University, 4Ant Group
*Equal Contribution
†Corresponding Author
Paper arXiv Code

Abstract

Motif scaffolding seeks to design scaffold structures for constructing proteins with functions derived from the desired motif, which is crucial for the design of vaccines and enzymes. Previous works approach the problem by inpainting or conditional generation. Both of them can only scaffold motifs with fixed positions, and the conditional generation cannot guarantee the presence of motifs. However, prior knowledge of the relative positions of motifs in a protein is not readily available, and constructing a protein with multiple functions in one protein is more general and significant because of the synergies between functions. We propose a Floating Anchor Diffusion (FADiff) model. FADiff allows motifs to float rigidly and independently in the process of diffusion, which guarantees the presence of motifs and the automatic motif position design. Our experiments demonstrate the efficacy of FADiff with high successful design rates and designable scaffolds. To the best of our knowledge, FADiff is the first work to tackle the challenge of scaffolding multiple motifs with flexible locations in one protein.

Two motifs Sampling

Process of sampling two independent motifs.

Three motifs Sampling

Process of sampling three independent motifs.

Pipeline

Sampling & Preprocess

We treat each motif as independent rigid body, which can rotate and translate freely. And we TSP algorithm to find the optimal order of motifs.


Evaluation

We use ProteinMPNN to acquire the predicted sequences corresponding to the designed structures with multiple motifs. Subsequently, we use ESMFold to fold the sequences into structures and align them with the designed structures to calculate the scTM, which is a metric to evaluate the designability.

BibTeX

@inproceedings{
          anonymous2024floating,
          title={Floating Anchor Diffusion Model for Multi-motif Scaffolding},
          author={Ke, Liu and Shuaike, Shen and Weian, Mao and Xiaoran, Jiao and Zheng, Sun and Hao, Chen and Chunhua, Shen},
          booktitle={Forty-first International Conference on Machine Learning},
          year={2024},
          url={https://openreview.net/forum?id=CtgJUQxmEo}
}