ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916957002924032 |
|---|---|
| author | Rade, Jaydeep Hasib, Md Hasibul Hasan Ozturk, Meric Faal, Baboucarr Yang, Sheng Sashital, Dipali G. Venditti, Vincenzo Chen, Baoyu Sarkar, Soumik Krishnamurthy, Adarsh Sarkar, Anwesha |
| author_facet | Rade, Jaydeep Hasib, Md Hasibul Hasan Ozturk, Meric Faal, Baboucarr Yang, Sheng Sashital, Dipali G. Venditti, Vincenzo Chen, Baoyu Sarkar, Soumik Krishnamurthy, Adarsh Sarkar, Anwesha |
| contents | AI-based in silico methods have improved protein structure prediction but often struggle with large protein complexes (PCs) involving multiple interacting proteins due to missing 3D spatial cues. Experimental techniques like Cryo-EM are accurate but costly and time-consuming. We present ProFusion, a hybrid framework that integrates a deep learning model with Atomic Force Microscopy (AFM), which provides high-resolution height maps from random orientations, naturally yielding multi-view data for 3D reconstruction. However, generating a large-scale AFM imaging data set sufficient to train deep learning models is impractical. Therefore, we developed a virtual AFM framework that simulates the imaging process and generated a dataset of ~542,000 proteins with multi-view synthetic AFM images. We train a conditional diffusion model to synthesize novel views from unposed inputs and an instance-specific Neural Radiance Field (NeRF) model to reconstruct 3D structures. Our reconstructed 3D protein structures achieve an average Chamfer Distance within the AFM imaging resolution, reflecting high structural fidelity. Our method is extensively validated on experimental AFM images of various PCs, demonstrating strong potential for accurate, cost-effective protein complex structure prediction and rapid iterative validation using AFM experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15242 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images Rade, Jaydeep Hasib, Md Hasibul Hasan Ozturk, Meric Faal, Baboucarr Yang, Sheng Sashital, Dipali G. Venditti, Vincenzo Chen, Baoyu Sarkar, Soumik Krishnamurthy, Adarsh Sarkar, Anwesha Computer Vision and Pattern Recognition AI-based in silico methods have improved protein structure prediction but often struggle with large protein complexes (PCs) involving multiple interacting proteins due to missing 3D spatial cues. Experimental techniques like Cryo-EM are accurate but costly and time-consuming. We present ProFusion, a hybrid framework that integrates a deep learning model with Atomic Force Microscopy (AFM), which provides high-resolution height maps from random orientations, naturally yielding multi-view data for 3D reconstruction. However, generating a large-scale AFM imaging data set sufficient to train deep learning models is impractical. Therefore, we developed a virtual AFM framework that simulates the imaging process and generated a dataset of ~542,000 proteins with multi-view synthetic AFM images. We train a conditional diffusion model to synthesize novel views from unposed inputs and an instance-specific Neural Radiance Field (NeRF) model to reconstruct 3D structures. Our reconstructed 3D protein structures achieve an average Chamfer Distance within the AFM imaging resolution, reflecting high structural fidelity. Our method is extensively validated on experimental AFM images of various PCs, demonstrating strong potential for accurate, cost-effective protein complex structure prediction and rapid iterative validation using AFM experiments. |
| title | ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.15242 |