Leveraging deep learning for fully automated NMR protein structure determination

01/28/2022
by   Piotr Klukowski, et al.
0

Nuclear Magnetic Resonance (NMR) spectroscopy is one of the major techniques in structural biology with over 11800 protein structures deposited in the Protein Data Bank. NMR can elucidate structures and dynamics of small and medium size proteins in solution, living cells, and solids, but has been limited by the tedious data analysis process. It typically requires weeks or months of manual work of trained expert to turn NMR measurements into a protein structure. Automation of this process is an open problem, formulated in the field over 30 years ago. Here, we present the first approach that addresses this challenge. Our method, ARTINA, uses as input only NMR spectra and the protein sequence, delivering a structure strictly without any human intervention. Tested on a 100-protein benchmark (1329 2D/3D/4D NMR spectra), ARTINA demonstrated its ability to solve structures with 1.44 Å median RMSD to the PDB reference and 91.36 be used by non-experts, reducing the effort for a protein structure determination by NMR essentially to the preparation of the sample and the spectra measurements.

READ FULL TEXT

page 17

page 19

page 20

page 21

page 24

page 25

page 32

page 33

research
07/31/2018

Towards fully automated protein structure elucidation with NMR spectroscopy

Nuclear magnetic resonance (NMR) spectroscopy is one of the leading tech...
research
10/01/1997

Analysis of Three-Dimensional Protein Images

A fundamental goal of research in molecular biology is to understand pro...
research
08/09/2020

NMR Assignment through Linear Programming

Nuclear Magnetic Resonance (NMR) Spectroscopy is the second most used te...
research
03/18/2021

Structure Calculation and Reconstruction of Discrete State Dynamics from Residual Dipolar Couplings using REDCRAFT

Residual Dipolar Couplings (RDCs) acquired by Nuclear Magnetic Resonance...
research
06/18/2015

Automated Assignment of Backbone NMR Data using Artificial Intelligence

Nuclear magnetic resonance (NMR) spectroscopy is a powerful method for t...
research
11/19/2019

Improvements of the REDCRAFT Software Package

Traditional approaches to elucidation of protein structures by NMR spect...
research
10/20/2022

Removing grid structure in angle-resolved photoemission spectra via deep learning method

Spectroscopic data may often contain unwanted extrinsic signals. For exa...

Please sign up or login with your details

Forgot password? Click here to reset