Timezone: »

3D Reconstruction of Protein Complex Structures Using Synthesized Multi-View AFM Images
Jaydeep Rade · Soumik Sarkar · Anwesha Sarkar · Adarsh Krishnamurthy

Recent developments in deep learning-based methods demonstrated its potential to predict the 3D protein structures using inputs such as protein sequences, Cryo-Electron microscopy (Cryo-EM) images of proteins, etc. However, these methods struggle to predict the protein complexes (PC), structures with more than one protein. In this work, we explore the atomic force microscope (AFM) assisted deep learning-based methods to predict the 3D structure of PCs. The images produced by AFM capture the protein structure in different and random orientations. These multi-view images can help train the neural network to predict the 3D structure of protein complexes. However, obtaining the dataset of actual AFM images is time-consuming and not a pragmatic task. We propose a virtual AFM imaging pipeline that takes a 'PDB' protein file and generates multi-view 2D virtual AFM images using volume rendering techniques. With this, we created a dataset of around 8K proteins. We train a neural network for 3D reconstruction called Pix2Vox++ using the synthesized multi-view 2D AFM images dataset. We compare the predicted structure obtained using a different number of views and get the intersection over union (IoU) value of 0.92 on the training dataset and 0.52 on the validation dataset. We believe this approach will lead to better prediction of the structure of protein complexes.

Author Information

Jaydeep Rade (Iowa State University)

I am Ph.D. student in Electrical Engineering department at Iowa State University, Ames, IA, USA. My research interests includes Deep Learning, Computer Vision, 3D Reconstruction. I am currently working on protein folding problem, where we are developing Deep Learning based 3D reconstruction algorithm to find 3D structure of protein complexes using Atomic Force Microscopy(AFM) microscope images. I worked as a Machine Learning Intern at ANSYS, Inc. Designed multiple neural networks model to perform end-to-end topology optimization consistent with SIMP algorithm using 3D CNNs. Implemented U-Net, U-SE-ResNet architectures for Topology Optimization using Keras and PyTorch deep learning frameworks.

Soumik Sarkar (Iowa State University)
Anwesha Sarkar (Iowa State University)
Adarsh Krishnamurthy (Iowa State University)

More from the Same Authors