Deep Learning to Predict Protein Backbone Structure from High-Resolution Cryo-EM Density Maps

Abstract

cryo-electron microscopy (cryo-eM) has become a leading technology for determining protein structures. Recent advances in this field have allowed for atomic resolution. However, predicting the backbone trace of a protein has remained a challenge on all but the most pristine density maps (<2.5 Å resolution). Here we introduce a deep learning model that uses a set of cascaded convolutional neural networks (CNNs) to predict Cα atoms along a protein's backbone structure. the cascaded-cnn (c-cnn) is a novel deep learning architecture comprised of multiple CNNs, each predicting a specific aspect of a protein's structure. this model predicts secondary structure elements (SSes), backbone structure, and cα atoms, combining the results of each to produce a complete prediction map. the cascaded-cnn is a semantic segmentation image classifier and was trained using thousands of simulated density maps. this method is largely automatic and only requires a recommended threshold value for each protein density map. A specialized tabu-search path walking algorithm was used to produce an initial backbone trace with Cα placements. A helix-refinement algorithm made further improvements to the α-helix SSes of the backbone trace. finally, a novel quality assessment-based combinatorial algorithm was used to effectively map protein sequences onto Cα traces to obtain full-atom protein structures. This method was tested on 50 experimental maps between 2.6 Å and 4.4 Å resolution. It outperformed several state-of-the-art prediction methods including Rosetta de-novo, MAinMASt, and a phenix based method by producing the most complete predicted protein structures, as measured by percentage of found cα atoms. This method accurately predicted 88.9% (mean) of the Cα atoms within 3 Å of a protein's backbone structure surpassing the 66.8% mark achieved by the leading alternate method (phenix based fully automatic method) on the same set of density maps. the c-cnn also achieved an average root-mean-square deviation (RMSD) of 1.24 Å on a set of 50 experimental density maps which was tested by the Phenix based fully automatic method. The source code and demo of this research has been published at https://github.com/DrDongSi/ca-Backbone-prediction.Proteins perform a vast array of functions within organisms. From molecule transportation, to mechanical cellular support, to immune protection, proteins are the central building blocks of life in the universe 1 . Despite each protein being composed from a combination of the same 20 naturally occurring amino acids, a protein's functionality is mainly derived from its unique three-dimensional (3D) shape. Therefore, learning the details of a protein's 3D structure is a prerequisite to understanding its biological function. cryo electron Microscopy (cryo-eM). Currently, one of the leading techniques for determining the atomic structure of proteins is cryo-electron microscopy (cryo-EM) 2-4 . Briefly, samples are fast frozen in liquid-nitrogen cooled liquid ethane and imaged in an electron microscope at cryogenic te...

DeepTracer: Fast Cryo-EM Protein Structure Modeling and Special Studies on CoV-related Complexes

“…Before training the U-Net model, we have to collect a training dataset. Previous projects, such as [17], used simulated density maps to train their neural networks. However, for the network to learn common noise patterns in cryo-EM density maps, we decided to use experimental maps.…”

“…Therefore, there is a tremendous demand for a method that automatically determines the molecular structure from a cryo-EM density map. Unfortunately, existing tools [14,15,16,17,18] such as Rosetta, MAINMAST, and Phenix determine only fragments of a protein complex, or require extensive manual processing steps. Due to the ability of cryo-EM to capture multiple large proteins in the course of a single study [19,20], a fully automated, e cient tool to determine complex structures would be crucial to increase the throughput of the technology and speed up the development of medicines.…”

DeepEMhancer: a deep learning solution for cryo-EM volume post-processing

“…Deep learning has revolutionized the field of Artificial Intelligence and its impact has been felt in many others including cryo-EM. Deep learning in cryo-EM was firstly applied for the problem of particle picking (Wagner et al, 2019;Wang et al, 2016;Zhu et al, 2017) and since then, it has evolved to deal with other questions such as map reconstruction (Gupta et al, 2020;Zhong et al, 2019), map segmentation (Maddhuri Venkata Subramaniya et al, 2019;Si et al, 2020) or local resolution determination (Avramov et al, 2019;Ramírez-Aportela et al, 2019). As in most of those methods, our approach relies on a convolutional neural network (CNN) that is trained on massive quantities of data.…”

Early Diagnosis of Hepatocellular Carcinoma Using Machine Learning Method

“…Machine learning method is a good choice to uncover underlying patterns (Stephenson et al, 2019). It has been widely employed in bioinformatics (Cao et al, 2017;Bao et al, 2019;Conover et al, 2019;Moritz et al, 2019;Stephenson et al, 2019;Zou and Ma, 2019;Sun et al, 2020). The current work aims to develop a machine learning based method to diagnose HCC within-sample REOs.…”