Smart de novo Macromolecular Structure Modeling from Cryo-EM Maps |
| |
Affiliation: | Division of Computing and Software Systems, University of Washington Bothell, Bothell, WA 98011, United States |
| |
Abstract: | The study of macromolecular structures has expanded our understanding of the amazing cell machinery and such knowledge has changed how the pharmaceutical industry develops new vaccines in recent years. Traditionally, X-ray crystallography has been the main method for structure determination, however, cryogenic electron microscopy (cryo-EM) has increasingly become more popular due to recent advancements in hardware and software. The number of cryo-EM maps deposited in the EMDataResource (formerly EMDatabase) since 2002 has been dramatically increasing and it continues to do so. De novo macromolecular complex modeling is a labor-intensive process, therefore, it is highly desirable to develop software that can automate this process. Here we discuss our automated, data-driven, and artificial intelligence approaches including map processing, feature extraction, modeling building, and target identification. Recently, we have enabled DNA/RNA modeling in our deep learning-based prediction tool, DeepTracer. We have also developed DeepTracer-ID, a tool that can identify proteins solely based on the cryo-EM map. In this paper, we will present our accumulated experiences in developing deep learning-based methods surrounding macromolecule modeling applications. |
| |
Keywords: | cryogenic electron microscopy (cryo-EM) structural biology macromolecular modeling deep learning AA" },{" #name" :" keyword" ," $" :{" id" :" k0035" }," $$" :[{" #name" :" text" ," _" :" Amino Acid Ab" },{" #name" :" keyword" ," $" :{" id" :" k0045" }," $$" :[{" #name" :" text" ," _" :" Antibody Ag" },{" #name" :" keyword" ," $" :{" id" :" k0055" }," $$" :[{" #name" :" text" ," _" :" Antigen ANN" },{" #name" :" keyword" ," $" :{" id" :" k0065" }," $$" :[{" #name" :" text" ," _" :" Artificial Neural Network CAE" },{" #name" :" keyword" ," $" :{" id" :" k0075" }," $$" :[{" #name" :" text" ," _" :" Convolutional Autoencoder CCD" },{" #name" :" keyword" ," $" :{" id" :" k0085" }," $$" :[{" #name" :" text" ," _" :" Charge Coupled Device C-CNN" },{" #name" :" keyword" ," $" :{" id" :" k0095" }," $$" :[{" #name" :" text" ," _" :" Cascaded Convolutional Neural Network CNN" },{" #name" :" keyword" ," $" :{" id" :" k0105" }," $$" :[{" #name" :" text" ," _" :" Convolutional Neural Network Cryo-EM" },{" #name" :" keyword" ," $" :{" id" :" k0115" }," $$" :[{" #name" :" text" ," _" :" Cryogenic Electron Microscopy CV" },{" #name" :" keyword" ," $" :{" id" :" k0125" }," $$" :[{" #name" :" text" ," _" :" Computer Vision DED" },{" #name" :" keyword" ," $" :{" id" :" k0135" }," $$" :[{" #name" :" text" ," _" :" Directed Electron Detector DNA" },{" #name" :" keyword" ," $" :{" id" :" k0145" }," $$" :[{" #name" :" text" ," _" :" Deoxyribonucleic Acid DNN" },{" #name" :" keyword" ," $" :{" id" :" k0155" }," $$" :[{" #name" :" text" ," _" :" Dense Neural Network DP" },{" #name" :" keyword" ," $" :{" id" :" k0165" }," $$" :[{" #name" :" text" ," _" :" Dynamic Programming EMDB" },{" #name" :" keyword" ," $" :{" id" :" k0175" }," $$" :[{" #name" :" text" ," _" :" EMDataResource FSC" },{" #name" :" keyword" ," $" :{" id" :" k0185" }," $$" :[{" #name" :" text" ," _" :" Fourier Shell Correlation GPU" },{" #name" :" keyword" ," $" :{" id" :" k0195" }," $$" :[{" #name" :" text" ," _" :" Graphics Processing Unit kNN" },{" #name" :" keyword" ," $" :{" id" :" k0205" }," $$" :[{" #name" :" text" ," _" :" k-Nearest Neighbor LSTM" },{" #name" :" keyword" ," $" :{" id" :" k0215" }," $$" :[{" #name" :" text" ," _" :" Long Short-Term Memory ML" },{" #name" :" keyword" ," $" :{" id" :" k0225" }," $$" :[{" #name" :" text" ," _" :" Machine Learning MSA" },{" #name" :" keyword" ," $" :{" id" :" k0235" }," $$" :[{" #name" :" text" ," _" :" Multiple Sequence Alignment NLP" },{" #name" :" keyword" ," $" :{" id" :" k0245" }," $$" :[{" #name" :" text" ," _" :" Natural Language Processing RMSD" },{" #name" :" keyword" ," $" :{" id" :" k0255" }," $$" :[{" #name" :" text" ," _" :" Root-Mean-Square Deviation RNA" },{" #name" :" keyword" ," $" :{" id" :" k0265" }," $$" :[{" #name" :" text" ," _" :" Ribonucleic Acid RNN" },{" #name" :" keyword" ," $" :{" id" :" k0275" }," $$" :[{" #name" :" text" ," _" :" Residual Neural Network SNR" },{" #name" :" keyword" ," $" :{" id" :" k0285" }," $$" :[{" #name" :" text" ," _" :" Signal-to-Noise Ratio SPA" },{" #name" :" keyword" ," $" :{" id" :" k0295" }," $$" :[{" #name" :" text" ," _" :" Single-Particle Analysis SSE" },{" #name" :" keyword" ," $" :{" id" :" k0305" }," $$" :[{" #name" :" text" ," _" :" Secondary Structure Element SVM" },{" #name" :" keyword" ," $" :{" id" :" k0315" }," $$" :[{" #name" :" text" ," _" :" Support Vector Machine TSP" },{" #name" :" keyword" ," $" :{" id" :" k0325" }," $$" :[{" #name" :" text" ," _" :" Traveling Salesman Problem |
本文献已被 ScienceDirect 等数据库收录! |
|