scholarly journals Explore Protein Conformational Space With Variational Autoencoder

2021 ◽  
Vol 8 ◽  
Author(s):  
Hao Tian ◽  
Xi Jiang ◽  
Francesco Trozzi ◽  
Sian Xiao ◽  
Eric C. Larson ◽  
...  
Keyword(s):  
Md Simulations ◽  
Conformational Space ◽  
Protein Conformations ◽  
Sampling Process ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Conformational Landscape ◽  
And Function ◽  
Computational Resources ◽  
Deep Learning Model

Molecular dynamics (MD) simulations have been actively used in the study of protein structure and function. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational autoencoders (VAEs), a type of deep learning model, can be employed to explore the conformational space of a protein through MD simulations. VAEs are shown to be superior to autoencoders (AEs) through a benchmark study, with low deviation between the training and decoded conformations. Moreover, we show that the learned latent space in the VAE can be used to generate unsampled protein conformations. Additional simulations starting from these generated conformations accelerated the sampling process and explored hidden spaces in the conformational landscape.

scholarly journals Explore protein conformational space with variational autoencoder

2021 ◽  
Author(s):  
Hao Tian ◽  
Xi Jiang ◽  
Francesco Trozzi ◽  
Sian Xiao ◽  
Eric Larson ◽  
...  
Keyword(s):  
Md Simulations ◽  
Conformational Space ◽  
Protein Conformations ◽  
Sampling Process ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Conformational Landscape ◽  
And Function ◽  
Computational Resources ◽  
Deep Learning Model

Molecular dynamic (MD) simulations have been actively used in the study of protein structure and function. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational autoencoders (VAEs), a type of deep learning model, can be employed to explore the conformational space of a protein through MD simulations. VAEs are shown to be superior to autoencoders (AEs) through a benchmark study, with low deviation between the training and decoded conformations. Moreover, we show that the learned latent space in the VAE can be used to generate unsampled protein conformations. Additional simulations starting from these generated conformations accelerated the sampling process and explored hidden spaces in the conformational landscape.

Pengaruh Citra Merek, Kualitas Produk Dan Harga Terhadap Kepuasan Konsumen Pada Bisnis Franchise Minuman

2017 ◽  
Vol 24 (2) ◽  
pp. 144-153
Author(s):  
Yunita Fitri Wahyuningtyas
Keyword(s):  
Regression Analysis ◽  
Marketing Strategy ◽  
Product Quality ◽  
Multiple Regression Analysis ◽  
Multiple Regression ◽  
Sampling Method ◽  
Sampling Technique ◽  
Sampling Process ◽  
And Function ◽  
Simultaneous Influence

This research is conducted upon the emergence of many companies producing the same product of the same kind and function. It leads to the urgency of proper and well planned marketing strategy. This research aims to investigate how far the influence of branding, product quality, and price toward consumer’s satisfaction in beverage franchise business. This research utilizes 5 likert scale questionnaire which is tested by using multiple regression analysis to reveal whether or not there is partial and simultaneous influence of branding, product quality, and price toward consumer’s satisfaction in beverage franchise business. Sampling method is accidental sampling technique, in which sample of particular population is taken based on the accessibility and availability of the sample during the sampling process. Sample used is 100 samples among consumers or customers of Mang Endy Milkshake. The result shows that branding, product quality, and price influence consumer’s satisfaction in beverage franchise business.

scholarly journals On the Use of the Discrete Constant pH Molecular Dynamics to Describe the Conformational Space of Peptides

Polymers ◽  
2020 ◽  
Vol 13 (1) ◽  
pp. 99
Author(s):  
Cristian Privat ◽  
Sergio Madurga ◽  
Francesc Mas ◽  
Jaime Rubio-Martínez
Keyword(s):  
Molecular Dynamics ◽  
Amino Acids ◽  
Md Simulations ◽  
Point Of View ◽  
Conformational Space ◽  
Conformational Sampling ◽  
Protonation State ◽  
Constant Ph ◽  
Biochemical Systems ◽  
Constant Ph Molecular Dynamics

Solvent pH is an important property that defines the protonation state of the amino acids and, therefore, modulates the interactions and the conformational space of the biochemical systems. Generally, this thermodynamic variable is poorly considered in Molecular Dynamics (MD) simulations. Fortunately, this lack has been overcome by means of the Constant pH Molecular Dynamics (CPHMD) methods in the recent decades. Several studies have reported promising results from these approaches that include pH in simulations but focus on the prediction of the effective pKa of the amino acids. In this work, we want to shed some light on the CPHMD method and its implementation in the AMBER suitcase from a conformational point of view. To achieve this goal, we performed CPHMD and conventional MD (CMD) simulations of six protonatable amino acids in a blocked tripeptide structure to compare the conformational sampling and energy distributions of both methods. The results reveal strengths and weaknesses of the CPHMD method in the implementation of AMBER18 version. The change of the protonation state according to the chemical environment is presumably an improvement in the accuracy of the simulations. However, the simulations of the deprotonated forms are not consistent, which is related to an inaccurate assignment of the partial charges of the backbone atoms in the CPHMD residues. Therefore, we recommend the CPHMD methods of AMBER program but pointing out the need to compare structural properties with experimental data to bring reliability to the conformational sampling of the simulations.

scholarly journals Conformational Ensembles by NMR and MD Simulations in Model Heptapeptides with Select Tri-Peptide Motifs

2021 ◽  
Vol 22 (3) ◽  
pp. 1364
Author(s):  
V. V. Krishnan ◽  
Timothy Bentley ◽  
Alina Xiong ◽  
Kalyani Maitra
Keyword(s):  
Principal Component ◽  
Md Simulations ◽  
Conformational Space ◽  
Random Coil ◽  
Radius Of Gyration ◽  
Small Peptides ◽  
Conformational Ensembles ◽  
Solution State ◽  
Peptide Motifs ◽  
Explicit Solvent

Both nuclear magnetic resonance (NMR) and molecular dynamics (MD) simulations are routinely used in understanding the conformational space sampled by peptides in the solution state. To investigate the role of single-residue change in the ensemble of conformations sampled by a set of heptapeptides, AEVXEVG with X = L, F, A, or G, comprehensive NMR, and MD simulations were performed. The rationale for selecting the particular model peptides is based on the high variability in the occurrence of tri-peptide E*L between the transmembrane β-barrel (TMB) than in globular proteins. The ensemble of conformations sampled by E*L was compared between the three sets of ensembles derived from NMR spectroscopy, MD simulations with explicit solvent, and the random coil conformations. In addition to the estimation of global determinants such as the radius of gyration of a large sample of structures, the ensembles were analyzed using principal component analysis (PCA). In general, the results suggest that the -EVL- peptide indeed adopts a conformational preference that is distinctly different not only from a random distribution but also from other peptides studied here. The relatively straightforward approach presented herein could help understand the conformational preferences of small peptides in the solution state.

scholarly journals High-resolution mining of the SARS-CoV-2 main protease conformational space: supercomputer-driven unsupervised adaptive sampling

2021 ◽  
Author(s):  
Théo Jaffrelot Inizan ◽  
Frédéric Célerse ◽  
Olivier Adjoua ◽  
Dina El Ahdab ◽  
Luc-Henri Jolly ◽  
...  
Keyword(s):  
Molecular Dynamics ◽  
High Resolution ◽  
Adaptive Sampling ◽  
Force Fields ◽  
Sampling Strategy ◽  
Md Simulations ◽  
Conformational Space ◽  
Many Body ◽  
Polarizable Force Fields ◽  
Main Protease

We provide an unsupervised adaptive sampling strategy capable of producing μs-timescale molecular dynamics (MD) simulations of large biosystems using many-body polarizable force fields (PFFs).

scholarly journals Dynamical Behavior and Conformational Selection Mechanism of the Intrinsically Disordered Sic1 Kinase-Inhibitor Domain

Life ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. 110 ◽  
Author(s):  
Davide Sala ◽  
Ugo Cosentino ◽  
Anna Ranaudo ◽  
Claudio Greco ◽  
Giorgio Moro
Keyword(s):  
Kinase Inhibitor ◽  
Dynamical Behavior ◽  
Md Simulations ◽  
Molecular Shape ◽  
Conformational Space ◽  
Coarse Grained ◽  
Conformational Ensemble ◽  
Selection Mechanism ◽  
Conformational Selection ◽  
Intrinsically Disordered

Intrinsically Disordered Peptides and Proteins (IDPs) in solution can span a broad range of conformations that often are hard to characterize by both experimental and computational methods. However, obtaining a significant representation of the conformational space is important to understand mechanisms underlying protein functions such as partner recognition. In this work, we investigated the behavior of the Sic1 Kinase-Inhibitor Domain (KID) in solution by Molecular Dynamics (MD) simulations. Our results point out that application of common descriptors of molecular shape such as Solvent Accessible Surface (SAS) area can lead to misleading outcomes. Instead, more appropriate molecular descriptors can be used to define 3D structures. In particular, we exploited Weighted Holistic Invariant Molecular (WHIM) descriptors to get a coarse-grained but accurate definition of the variegated Sic1 KID conformational ensemble. We found that Sic1 is able to form a variable amount of folded structures even in absence of partners. Among them, there were some conformations very close to the structure that Sic1 is supposed to assume in the binding with its physiological complexes. Therefore, our results support the hypothesis that this protein relies on the conformational selection mechanism to recognize the correct molecular partners.

scholarly journals Mapping the glycosyltransferase fold landscape using interpretable deep learning

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Rahil Taujale ◽  
Zhongliang Zhou ◽  
Wayland Yeung ◽  
Kelley W. Moremen ◽  
Sheng Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Secondary Structure ◽  
Structural Features ◽  
Functional Diversification ◽  
Sequence Structure ◽  
Cellular Processes ◽  
And Function ◽  
Deep Learning Model ◽  
Fold Prediction ◽  
Primary Sequence Alignment

AbstractGlycosyltransferases (GTs) play fundamental roles in nearly all cellular processes through the biosynthesis of complex carbohydrates and glycosylation of diverse protein and small molecule substrates. The extensive structural and functional diversification of GTs presents a major challenge in mapping the relationships connecting sequence, structure, fold and function using traditional bioinformatics approaches. Here, we present a convolutional neural network with attention (CNN-attention) based deep learning model that leverages simple secondary structure representations generated from primary sequences to provide GT fold prediction with high accuracy. The model learns distinguishing secondary structure features free of primary sequence alignment constraints and is highly interpretable. It delineates sequence and structural features characteristic of individual fold types, while classifying them into distinct clusters that group evolutionarily divergent families based on shared secondary structural features. We further extend our model to classify GT families of unknown folds and variants of known folds. By identifying families that are likely to adopt novel folds such as GT91, GT96 and GT97, our studies expand the GT fold landscape and prioritize targets for future structural studies.

scholarly journals Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic

2021 ◽  
Author(s):  
Yuen Ler Chow ◽  
Shantanu Singh ◽  
Anne E Carpenter ◽  
Gregory P. Way
Keyword(s):  
Gene Expression ◽  
Cell Morphology ◽  
Learning Algorithm ◽  
Simulated Data ◽  
Biomedical Data ◽  
Data Types ◽  
Generative Capacity ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Target Effects

A variational autoencoder (VAE) is a machine learning algorithm, useful for generating a compressed and interpretable latent space. These representations have been generated from various biomedical data types and can be used to produce realistic-looking simulated data. However, standard vanilla VAEs suffer from entangled and uninformative latent spaces, which can be mitigated using other types of VAEs such as β-VAE and MMD-VAE. In this project, we evaluated the ability of VAEs to learn cell morphology characteristics derived from cell images. We trained and evaluated these three VAE variants-Vanilla VAE, β-VAE, and MMD-VAE-on cell morphology readouts and explored the generative capacity of each model to predict compound polypharmacology (the interactions of a drug with more than one target) using an approach called latent space arithmetic (LSA). To test the generalizability of the strategy, we also trained these VAEs using gene expression data of the same compound perturbations and found that gene expression provides complementary information. We found that the β-VAE and MMD-VAE disentangle morphology signals and reveal a more interpretable latent space. We reliably simulated morphology and gene expression readouts from certain compounds thereby predicting cell states perturbed with compounds of known polypharmacology. Inferring cell state for specific drug mechanisms could aid researchers in developing and identifying targeted therapeutics and categorizing off-target effects in the future.

scholarly journals Conformational and functional characterization of artificially conjugated non-canonical ubiquitin dimers

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Tobias Schneider ◽  
Andrej Berg ◽  
Zeynel Ulusoy ◽  
Martin Gamerdinger ◽  
Christine Peter ◽  
...  
Keyword(s):  
Experimental Data ◽  
Functional Characterization ◽  
Isotopic Labeling ◽  
Md Simulations ◽  
Conformational Space ◽  
Coarse Grained ◽  
Covalent Attachment ◽  
Binding Studies ◽  
Polyubiquitin Chains ◽  
Polypeptide Chains

AbstractUbiquitylation is an eminent posttranslational modification referring to the covalent attachment of single ubiquitin molecules or polyubiquitin chains to a target protein dictating the fate of such labeled polypeptide chains. Here, we have biochemically produced artificially Lys11-, and Lys27-, and Lys63-linked ubiquitin dimers based on click-chemistry generating milligram quantities in high purity. We show that the artificial linkage used for the conjugation of two ubiquitin moieties represents a fully reliable surrogate of the natural isopeptide bond by acquiring highly resolved nuclear magnetic resonance (NMR) spectroscopic data including ligand binding studies. Extensive coarse grained and atomistic molecular dynamics (MD) simulations allow to extract structures representing the ensemble of domain-domain conformations used to verify the experimental data. Advantageously, this methodology does not require individual isotopic labeling of both ubiquitin moieties as NMR data have been acquired on the isotopically labeled proximal moiety and complementary MD simulations have been used to fully interpret the experimental data in terms of domain-domain conformation. This combined approach intertwining NMR spectroscopy with MD simulations makes it possible to describe the conformational space non-canonically Lys11-, and Lys27-linked ubiquitin dimers occupy in a solution averaged ensemble by taking atomically resolved information representing all residues in ubiquitin dimers into account.

Framing constructicography

2019 ◽  
Vol 35 (1) ◽  
pp. 41-85 ◽  
Author(s):  
Hans C. Boas ◽  
Benjamin Lyngfelt ◽  
Tiago Timponi Torrent
Keyword(s):  
Construction Grammar ◽  
Frame Semantics ◽  
Comprehensive Overview ◽  
Form And Function ◽  
And Function ◽  
Computational Resources

Abstract Constructicography can be defined as a blend between Construction Grammar and Practical Lexicography, which aims at developing constructicons: repositories of form and function pairings in a language. In this paper, we present a comprehensive overview of this emerging field by (i) tracking the origins of both Frame Semantics and Construction Grammar and the repercussions of their intertwined developments to Computational Lexicography and Constructicography; (ii) comparing the impacts of the different degrees of interconnection between constructicons and framenets and (iii) discussing the possible applications of these resources. Also, we argue that Constructicography, while obviously building on the accumulated knowledge compiled by numerous Construction Grammar approaches to language, also contributes to its mother theory, since the effort to build coherent formalized computational resources forces constructionist analysis to go beyond describing families of constructions into the enterprise of describing a coherent construction grammar of a language.

Sign in / Sign up

Export Citation Format

Share Document