scholarly journals DEEP picker is a deep neural network for accurate deconvolution of complex two-dimensional NMR spectra

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Da-Wei Li ◽  
Alexandar L. Hansen ◽  
Chunhua Yuan ◽  
Lei Bruschweiler-Li ◽  
Rafael Brüschweiler
Keyword(s):  
Neural Network ◽  
Nmr Spectra ◽  
Deep Neural Network ◽  
Intrinsically Disordered Proteins ◽  
Disordered Proteins ◽  
Two Dimensional ◽  
Molecular Systems ◽  
Intrinsically Disordered ◽  
Identification And Characterization

AbstractThe analysis of nuclear magnetic resonance (NMR) spectra for the comprehensive and unambiguous identification and characterization of peaks is a difficult, but critically important step in all NMR analyses of complex biological molecular systems. Here, we introduce DEEP Picker, a deep neural network (DNN)-based approach for peak picking and spectral deconvolution which semi-automates the analysis of two-dimensional NMR spectra. DEEP Picker includes 8 hidden convolutional layers and was trained on a large number of synthetic spectra of known composition with variable degrees of crowdedness. We show that our method is able to correctly identify overlapping peaks, including ones that are challenging for expert spectroscopists and existing computational methods alike. We demonstrate the utility of DEEP Picker on NMR spectra of folded and intrinsically disordered proteins as well as a complex metabolomics mixture, and show how it provides access to valuable NMR information. DEEP Picker should facilitate the semi-automation and standardization of protocols for better consistency and sharing of results within the scientific community.

Identifying short disorder-to-order binding regions in disordered proteins with a deep convolutional neural network method

2019 ◽  
Vol 17 (01) ◽  
pp. 1950004 ◽  
Author(s):  
Chun Fang ◽  
Yoshitaka Moriwaki ◽  
Aikui Tian ◽  
Caihong Li ◽  
Kentaro Shimizu
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Convolutional Neural Network ◽  
Intrinsically Disordered Proteins ◽  
Protein Sequences ◽  
Interaction Network ◽  
Deep Convolutional Neural Network ◽  
Disordered Proteins ◽  
Related Factors ◽  
Intrinsically Disordered

Molecular recognition features (MoRFs) are key functional regions of intrinsically disordered proteins (IDPs), which play important roles in the molecular interaction network of cells and are implicated in many serious human diseases. Identifying MoRFs is essential for both functional studies of IDPs and drug design. This study adopts the cutting-edge machine learning method of artificial intelligence to develop a powerful model for improving MoRFs prediction. We proposed a method, named as en_DCNNMoRF (ensemble deep convolutional neural network-based MoRF predictor). It combines the outcomes of two independent deep convolutional neural network (DCNN) classifiers that take advantage of different features. The first, DCNNMoRF1, employs position-specific scoring matrix (PSSM) and 22 types of amino acid-related factors to describe protein sequences. The second, DCNNMoRF2, employs PSSM and 13 types of amino acid indexes to describe protein sequences. For both single classifiers, DCNN with a novel two-dimensional attention mechanism was adopted, and an average strategy was added to further process the output probabilities of each DCNN model. Finally, en_DCNNMoRF combined the two models by averaging their final scores. When compared with other well-known tools applied to the same datasets, the accuracy of the novel proposed method was comparable with that of state-of-the-art methods. The related web server can be accessed freely via http://vivace.bi.a.u-tokyo.ac.jp:8008/fang/en_MoRFs.php .

scholarly journals NMR characterization of solvent accessibility and transient structure in intrinsically disordered proteins

2019 ◽  
Vol 73 (6-7) ◽  
pp. 305-317 ◽  
Author(s):  
Christoph Hartlmüller ◽  
Emil Spreitzer ◽  
Christoph Göbl ◽  
Fabio Falsone ◽  
Tobias Madl
Keyword(s):  
Intrinsically Disordered Proteins ◽  
Solvent Accessibility ◽  
Disordered Proteins ◽  
Intrinsically Disordered ◽  
Nmr Characterization ◽  
Transient Structure

scholarly journals NMR Characterization of Long-Range Order in Intrinsically Disordered Proteins

2010 ◽  
Vol 132 (24) ◽  
pp. 8407-8418 ◽  
Author(s):  
Loïc Salmon ◽  
Gabrielle Nodet ◽  
Valéry Ozenne ◽  
Guowei Yin ◽  
Malene Ringkjøbing Jensen ◽  
...  
Keyword(s):  
Long Range ◽  
Intrinsically Disordered Proteins ◽  
Range Order ◽  
Disordered Proteins ◽  
Long Range Order ◽  
Intrinsically Disordered ◽  
Nmr Characterization

scholarly journals Aptamers Selected for Recognizing Amyloid β-protein—A Case for Cautious Optimism

2018 ◽  
Author(s):  
Farid Rahimi
Keyword(s):  
Intrinsically Disordered Proteins ◽  
Scientific Evidence ◽  
Protein A ◽  
Intrinsically Disordered Protein ◽  
Disordered Proteins ◽  
Full Potential ◽  
Amyloid Beta Protein ◽  
Intrinsically Disordered ◽  
Metastable Structures

Aptamers are versatile oligonucleotide ligands used for molecular recognition of diverse targets. However, application of aptamers to the field of amyloid β-protein (Aβ) has been limited so far. Aβ is an intrinsically disordered protein that exists in a dynamic conformational equilibrium, presenting time-dependent ensembles of short-lived, metastable structures and assemblies that have been generally difficult to isolate and characterize. Moreover, despite understanding of potential physiological roles of Aβ, this peptide has been linked to the pathogenesis of Alzheimer disease, and its pathogenic roles remain controversial. Accumulated scientific evidence thus far highlights undesirable or nonspecific interactions between selected aptamers and different Aβ assemblies likely due to metastable nature of Aβ or inherent affinity of RNA oligonucleotides to β-sheet-rich fibrillar structures of amyloidogenic proteins. Accordingly, lessons drawn from Aβ–aptamer studies emphasize that purity and uniformity of the protein target and rigorous characterization of aptamers’ specificity are important for realizing and garnering the full potential of aptamers selected for recongizing Aβ or other intrinsically disordered proteins. This review summarizes studies of aptamers selected for recognizing different Aβ assemblies and highlights controversies, difficulties, and limitations of such studies.

scholarly journals Folding Free Energy Landscape of Ordered and Intrinsically Disordered Proteins

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Song-Ho Chong ◽  
Sihyun Ham
Keyword(s):  
Free Energy ◽  
Intrinsically Disordered Proteins ◽  
Energy Landscape ◽  
Disordered Proteins ◽  
Free Energy Landscape ◽  
Ww Domain ◽  
Intrinsically Disordered ◽  
Ca 50 ◽  
Folding Free Energy

Abstract Folding funnel is the essential concept of the free energy landscape for ordered proteins. How does this concept apply to intrinsically disordered proteins (IDPs)? Here, we address this fundamental question through the explicit characterization of the free energy landscapes of the representative α-helical (HP-35) and β-sheet (WW domain) proteins and of an IDP (pKID) that folds upon binding to its partner (KIX). We demonstrate that HP-35 and WW domain indeed exhibit the steep folding funnel: the landscape slope for these proteins is ca. −50 kcal/mol, meaning that the free energy decreases by ~5 kcal/mol upon the formation of 10% native contacts. On the other hand, the landscape of pKID is funneled but considerably shallower (slope of −24 kcal/mol), which explains why pKID is disordered in free environments. Upon binding to KIX, the landscape of pKID now becomes significantly steep (slope of −54 kcal/mol), which enables otherwise disordered pKID to fold. We also show that it is the pKID–KIX intermolecular interactions originating from hydrophobic residues that mainly confer the steep folding funnel. The present work not only provides the quantitative characterization of the protein folding free energy landscape, but also establishes the usefulness of the folding funnel concept to IDPs.

scholarly journals Characterization of partially ordered states in the intrinsically disordered N-terminal domain of p53 using millisecond molecular dynamics simulations

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Pablo Herrera-Nieto ◽  
Adrià Pérez ◽  
Gianni De Fabritiis
Keyword(s):  
Molecular Dynamics ◽  
Molecular Dynamics Simulations ◽  
Intrinsically Disordered Proteins ◽  
Dynamical Behavior ◽  
Disordered Proteins ◽  
Partially Ordered ◽  
Intrinsically Disordered ◽  
State Models ◽  
Dynamics Simulations

Abstract The exploration of intrinsically disordered proteins in isolation is a crucial step to understand their complex dynamical behavior. In particular, the emergence of partially ordered states has not been explored in depth. The experimental characterization of such partially ordered states remains elusive due to their transient nature. Molecular dynamics mitigates this limitation thanks to its capability to explore biologically relevant timescales while retaining atomistic resolution. Here, millisecond unbiased molecular dynamics simulations were performed in the exemplar N-terminal region of p53. In combination with state-of-the-art Markov state models, simulations revealed the existence of several partially ordered states accounting for $$\sim $$ ∼ 40% of the equilibrium population. Some of the most relevant states feature helical conformations similar to the bound structure of p53 to Mdm2, as well as novel $$\beta $$ β -sheet elements. This highlights the potential complexity underlying the energy surface of intrinsically disordered proteins.

Sign in / Sign up

Export Citation Format

Share Document