scholarly journals MemBlob database and server for identifying transmembrane regions using cryo-EM maps

2019 ◽  
Vol 36 (8) ◽  
pp. 2595-2598 ◽  
Author(s):  
Bianka Farkas ◽  
Georgina Csizmadia ◽  
Eszter Katona ◽  
Gábor E Tusnády ◽  
Tamás Hegedűs
Keyword(s):  
Protein Structures ◽  
Transmembrane Proteins ◽  
Bulk Water ◽  
Supplementary Information ◽  
Hydrophobic Core ◽  
Transmembrane Helices ◽  
Cryo Electron Microscopy ◽  
Density Maps ◽  
Transmembrane Regions ◽  
Atomistic Structure

Abstract Summary The identification of transmembrane helices in transmembrane proteins is crucial, not only to understand their mechanism of action but also to develop new therapies. While experimental data on the boundaries of membrane-embedded regions are sparse, this information is present in cryo-electron microscopy (cryo-EM) density maps and it has not been utilized yet for determining membrane regions. We developed a computational pipeline, where the inputs of a cryo-EM map, the corresponding atomistic structure, and the potential bilayer orientation determined by TMDET algorithm of a given protein result in an output defining the residues assigned to the bulk water phase, lipid interface and the lipid hydrophobic core. Based on this method, we built a database involving published cryo-EM protein structures and a server to be able to compute this data for newly obtained structures. Availability and implementation http://memblob.hegelab.org. Supplementary information Supplementary data are available at Bioinformatics online.

Inter-residue interactions in alpha-helical transmembrane proteins

2018 ◽  
Vol 35 (15) ◽  
pp. 2578-2584 ◽  
Author(s):  
Eduardo Mayol ◽  
Mercedes Campillo ◽  
Arnau Cordomí ◽  
Mireia Olivella
Keyword(s):  
Membrane Proteins ◽  
Present Report ◽  
Protein Structures ◽  
Transmembrane Proteins ◽  
Globular Proteins ◽  
Supplementary Information ◽  
Backbone Carbonyl ◽  
Composition Characteristic ◽  
Almost All ◽  
Residue Composition

Abstract Motivation The number of available membrane protein structures has markedly increased in the last years and, in parallel, the reliability of the methods to detect transmembrane (TM) segments. In the present report, we characterized inter-residue interactions in α-helical membrane proteins using a dataset of 3462 TM helices from 430 proteins. This is by far the largest analysis published to date. Results Our analysis of residue–residue interactions in TM segments of membrane proteins shows that almost all interactions involve aliphatic residues and Phe. There is lack of polar–polar, polar–charged and charged–charged interactions except for those between Thr or Ser sidechains and the backbone carbonyl of aliphatic and Phe residues. The results are discussed in the context of the preferences of amino acids to be in the protein core or exposed to the lipid bilayer and to occupy specific positions along the TM segment. Comparison to datasets of β-barrel membrane proteins and of α-helical globular proteins unveils the specific patterns of interactions and residue composition characteristic of α-helical membrane proteins that are the clue to understanding their structure. Availability and implementation Results data and datasets used are available at http://lmc.uab.cat/TMalphaDB/interactions.php. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals DeepSymmetry: using 3D convolutional networks for identification of tandem repeats and internal symmetries in protein structures

2019 ◽  
Vol 35 (24) ◽  
pp. 5113-5120 ◽  
Author(s):  
Guillaume Pagès ◽  
Sergei Grudinin
Keyword(s):  
Tandem Repeat ◽  
Tandem Repeats ◽  
Protein Structures ◽  
Molecular Structures ◽  
Supplementary Information ◽  
Convolutional Networks ◽  
Repeat Proteins ◽  
Density Maps ◽  
Tandem Repeat Proteins ◽  
Internal Symmetries

Abstract Motivation Thanks to the recent advances in structural biology, nowadays 3D structures of various proteins are solved on a routine basis. A large portion of these structures contain structural repetitions or internal symmetries. To understand the evolution mechanisms of these proteins and how structural repetitions affect the protein function, we need to be able to detect such proteins very robustly. As deep learning is particularly suited to deal with spatially organized data, we applied it to the detection of proteins with structural repetitions. Results We present DeepSymmetry, a versatile method based on 3D convolutional networks that detects structural repetitions in proteins and their density maps. Our method is designed to identify tandem repeat proteins, proteins with internal symmetries, symmetries in the raw density maps, their symmetry order and also the corresponding symmetry axes. Detection of symmetry axes is based on learning 6D Veronese mappings of 3D vectors, and the median angular error of axis determination is less than one degree. We demonstrate the capabilities of our method on benchmarks with tandem-repeated proteins and also with symmetrical assemblies. For example, we have discovered about 7800 putative tandem repeat proteins in the PDB. Availability and implementation The method is available at https://team.inria.fr/nano-d/software/deepsymmetry. It consists of a C++ executable that transforms molecular structures into volumetric density maps, and a Python code based on the TensorFlow framework for applying the DeepSymmetry model to these maps. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Automatic local resolution-based sharpening of cryo-EM maps

2019 ◽  
Author(s):  
Erney Ramírez-Aportela ◽  
Jose Luis Vilas ◽  
Alisa Glukhova ◽  
Roberto Melero ◽  
Pablo Conesa ◽  
...  
Keyword(s):  
Point Of View ◽  
Supplementary Information ◽  
Cryo Electron Microscopy ◽  
Technological Advances ◽  
Density Maps ◽  
Local Quality ◽  
Local Filters ◽  
High Flexibility ◽  
Starting Model

Abstract Motivation Recent technological advances and computational developments have allowed the reconstruction of Cryo-Electron Microscopy (cryo-EM) maps at near-atomic resolution. On a typical workflow and once the cryo-EM map has been calculated, a sharpening process is usually performed to enhance map visualization, a step that has proven very important in the key task of structural modeling. However, sharpening approaches, in general, neglects the local quality of the map, which is clearly suboptimal. Results Here, a new method for local sharpening of cryo-EM density maps is proposed. The algorithm, named LocalDeblur, is based on a local resolution-guided Wiener restoration approach of the original map. The method is fully automatic and, from the user point of view, virtually parameter-free, without requiring either a starting model or introducing any additional structure factor correction or boosting. Results clearly show a significant impact on map interpretability, greatly helping modeling. In particular, this local sharpening approach is especially suitable for maps that present a broad resolution range, as is often the case for membrane proteins or macromolecules with high flexibility, all of them otherwise very suitable and interesting specimens for cryo-EM. To our knowledge, and leaving out the use of local filters, it represents the first application of local resolution in cryo-EM sharpening. Availability and implementation The source code (LocalDeblur) can be found at https://github.com/I2PC/xmipp and can be run using Scipion (http://scipion.cnb.csic.es) (release numbers greater than or equal 1.2.1). Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Deep Learning for Validating and Estimating Resolution of Cryo-Electron Microscopy Density Maps †

Molecules ◽  
2019 ◽  
Vol 24 (6) ◽  
pp. 1181 ◽  
Author(s):  
Todor Avramov ◽  
Dan Vyenielo ◽  
Josue Gomez-Blanco ◽  
Swathi Adinarayanan ◽  
Javier Vargas ◽  
...  
Keyword(s):  
Neural Network ◽  
Electron Microscopy ◽  
Deep Learning ◽  
Protein Structures ◽  
Imaging Method ◽  
Classification Models ◽  
Cryo Electron Microscopy ◽  
Density Maps ◽  
Density Map ◽  
3D Cnn

Cryo-electron microscopy (cryo-EM) is becoming the imaging method of choice for determining protein structures. Many atomic structures have been resolved based on an exponentially growing number of published three-dimensional (3D) high resolution cryo-EM density maps. However, the resolution value claimed for the reconstructed 3D density map has been the topic of scientific debate for many years. The Fourier Shell Correlation (FSC) is the currently accepted cryo-EM resolution measure, but it can be subjective, manipulated, and has its own limitations. In this study, we first propose supervised deep learning methods to extract representative 3D features at high, medium and low resolutions from simulated protein density maps and build classification models that objectively validate resolutions of experimental 3D cryo-EM maps. Specifically, we build classification models based on dense artificial neural network (DNN) and 3D convolutional neural network (3D CNN) architectures. The trained models can classify a given 3D cryo-EM density map into one of three resolution levels: high, medium, low. The preliminary DNN and 3D CNN models achieved 92.73% accuracy and 99.75% accuracy on simulated test maps, respectively. Applying the DNN and 3D CNN models to thirty experimental cryo-EM maps achieved an agreement of 60.0% and 56.7%, respectively, with the author published resolution value of the density maps. We further augment these previous techniques and present preliminary results of a 3D U-Net model for local resolution classification. The model was trained to perform voxel-wise classification of 3D cryo-EM density maps into one of ten resolution classes, instead of a single global resolution value. The U-Net model achieved 88.3% and 94.7% accuracy when evaluated on experimental maps with local resolutions determined by MonoRes and ResMap methods, respectively. Our results suggest deep learning can potentially improve the resolution evaluation process of experimental cryo-EM maps.

SIR2004: an improved tool for crystal structure determination and refinement

2005 ◽  
Vol 38 (2) ◽  
pp. 381-388 ◽  
Author(s):  
Maria C. Burla ◽  
Rocco Caliandro ◽  
Mercedes Camalli ◽  
Benedetta Carrozzini ◽  
Giovanni L. Cascarano ◽  
...  
Keyword(s):  
Crystal Structure ◽  
Ab Initio ◽  
Structure Determination ◽  
Protein Structures ◽  
Medium Size ◽  
Graphical Interface ◽  
Asymmetric Unit ◽  
Density Maps ◽  
Data Resolution ◽  
User Friendly

SIR2004is the evolution of theSIR2002program [Burla, Camalli, Carrozzini, Cascarano, Giacovazzo, Polidori & Spagna (2003).J. Appl. Cryst.36, 1103]. It is devoted to the solution of crystal structures by direct and Patterson methods. Several new features implemented inSIR2004make this program efficient: it is able to solveab initioboth small/medium-size structures as well as macromolecules (up to 2000 atoms in the asymmetric unit). In favourable circumstances, the program is also able to solve protein structures with data resolution up to 1.4–1.5 Å, and to provide interpretable electron density maps. A powerful user-friendly graphical interface is provided.

scholarly journals Influence of assignment on the prediction of transmembrane helices in protein structures

Amino Acids ◽  
2010 ◽  
Vol 39 (5) ◽  
pp. 1241-1254 ◽  
Author(s):  
Jean Pylouster ◽  
Aurélie Bornot ◽  
Catherine Etchebest ◽  
Alexandre G. de Brevern
Keyword(s):  
Protein Structures ◽  
Transmembrane Helices

scholarly journals Sequence alignment using machine learning for accurate template-based protein structure prediction

2019 ◽  
Vol 36 (1) ◽  
pp. 104-111
Author(s):  
Shuichiro Makigaki ◽  
Takashi Ishida
Keyword(s):  
Machine Learning ◽  
Structure Prediction ◽  
Tertiary Structure ◽  
Structural Alignment ◽  
Protein Structures ◽  
Substitution Matrix ◽  
Detection Methods ◽  
Supplementary Information ◽  
Homology Detection ◽  
Sequence Alignments

Abstract Motivation Template-based modeling, the process of predicting the tertiary structure of a protein by using homologous protein structures, is useful if good templates can be found. Although modern homology detection methods can find remote homologs with high sensitivity, the accuracy of template-based models generated from homology-detection-based alignments is often lower than that from ideal alignments. Results In this study, we propose a new method that generates pairwise sequence alignments for more accurate template-based modeling. The proposed method trains a machine learning model using the structural alignment of known homologs. It is difficult to directly predict sequence alignments using machine learning. Thus, when calculating sequence alignments, instead of a fixed substitution matrix, this method dynamically predicts a substitution score from the trained model. We evaluate our method by carefully splitting the training and test datasets and comparing the predicted structure’s accuracy with that of state-of-the-art methods. Our method generates more accurate tertiary structure models than those produced from alignments obtained by other methods. Availability and implementation https://github.com/shuichiro-makigaki/exmachina. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals BionoiNet: ligand-binding site classification with off-the-shelf deep neural network

2020 ◽  
Vol 36 (10) ◽  
pp. 3077-3083
Author(s):  
Wentao Shi ◽  
Jeffrey M Lemoine ◽  
Abd-El-Monsif A Shawky ◽  
Manali Singha ◽  
Limeng Pu ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Ligand Binding ◽  
Binding Sites ◽  
Protein Structures ◽  
Supplementary Information ◽  
Heme Binding ◽  
Unseen Data ◽  
Ligand Binding Sites ◽  
Binding Pockets

Abstract Motivation Fast and accurate classification of ligand-binding sites in proteins with respect to the class of binding molecules is invaluable not only to the automatic functional annotation of large datasets of protein structures but also to projects in protein evolution, protein engineering and drug development. Deep learning techniques, which have already been successfully applied to address challenging problems across various fields, are inherently suitable to classify ligand-binding pockets. Our goal is to demonstrate that off-the-shelf deep learning models can be employed with minimum development effort to recognize nucleotide- and heme-binding sites with a comparable accuracy to highly specialized, voxel-based methods. Results We developed BionoiNet, a new deep learning-based framework implementing a popular ResNet model for image classification. BionoiNet first transforms the molecular structures of ligand-binding sites to 2D Voronoi diagrams, which are then used as the input to a pretrained convolutional neural network classifier. The ResNet model generalizes well to unseen data achieving the accuracy of 85.6% for nucleotide- and 91.3% for heme-binding pockets. BionoiNet also computes significance scores of pocket atoms, called BionoiScores, to provide meaningful insights into their interactions with ligand molecules. BionoiNet is a lightweight alternative to computationally expensive 3D architectures. Availability and implementation BionoiNet is implemented in Python with the source code freely available at: https://github.com/CSBG-LSU/BionoiNet. Supplementary information Supplementary data are available at Bioinformatics online.

KORP: knowledge-based 6D potential for fast protein and loop modeling

2019 ◽  
Vol 35 (17) ◽  
pp. 3013-3019 ◽  
Author(s):  
José Ramón López-Blanco ◽  
Pablo Chacón
Keyword(s):  
Structure Prediction ◽  
Protein Structures ◽  
Joint Probability ◽  
Protein Modeling ◽  
Supplementary Information ◽  
Joint Probability Distribution ◽  
Loop Modeling ◽  
Statistical Potentials ◽  
Knowledge Based ◽  
Backbone Atoms

Abstract Motivation Knowledge-based statistical potentials constitute a simpler and easier alternative to physics-based potentials in many applications, including folding, docking and protein modeling. Here, to improve the effectiveness of the current approximations, we attempt to capture the six-dimensional nature of residue–residue interactions from known protein structures using a simple backbone-based representation. Results We have developed KORP, a knowledge-based pairwise potential for proteins that depends on the relative position and orientation between residues. Using a minimalist representation of only three backbone atoms per residue, KORP utilizes a six-dimensional joint probability distribution to outperform state-of-the-art statistical potentials for native structure recognition and best model selection in recent critical assessment of protein structure prediction and loop-modeling benchmarks. Compared with the existing methods, our side-chain independent potential has a lower complexity and better efficiency. The superior accuracy and robustness of KORP represent a promising advance for protein modeling and refinement applications that require a fast but highly discriminative energy function. Availability and implementation http://chaconlab.org/modeling/korp. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document