scholarly journals Exploring Successful Parameter Region for Coarse-Grained Simulation of Biomolecules by Bayesian Optimization and Active Learning

Biomolecules ◽  
2020 ◽  
Vol 10 (3) ◽  
pp. 482
Author(s):  
Ryo Kanada ◽  
Atsushi Tokuhisa ◽  
Koji Tsuda ◽  
Yasushi Okuno ◽  
Kei Terayama
Keyword(s):  
Active Learning ◽  
Conformational Changes ◽  
Md Simulation ◽  
Md Simulations ◽  
Bayesian Optimization ◽  
Machine Learning Techniques ◽  
Coarse Grained ◽  
Environmental Sensitivity ◽  
Learning Techniques ◽  
And Behavior

Accompanied with an increase of revealed biomolecular structures owing to advancements in structural biology, the molecular dynamics (MD) approach, especially coarse-grained (CG) MD suitable for macromolecules, is becoming increasingly important for elucidating their dynamics and behavior. In fact, CG-MD simulation has succeeded in qualitatively reproducing numerous biological processes for various biomolecules such as conformational changes and protein folding with reasonable calculation costs. However, CG-MD simulations strongly depend on various parameters, and selecting an appropriate parameter set is necessary to reproduce a particular biological process. Because exhaustive examination of all candidate parameters is inefficient, it is important to identify successful parameters. Furthermore, the successful region, in which the desired process is reproducible, is essential for describing the detailed mechanics of functional processes and environmental sensitivity and robustness. We propose an efficient search method for identifying the successful region by using two machine learning techniques, Bayesian optimization and active learning. We evaluated its performance using F1-ATPase, a biological rotary motor, with CG-MD simulations. We successfully identified the successful region with lower computational costs (12.3% in the best case) without sacrificing accuracy compared to exhaustive search. This method can accelerate not only parameter search but also biological discussion of the detailed mechanics of functional processes and environmental sensitivity based on MD simulation studies.

scholarly journals Automation and control of laser wakefield accelerators using Bayesian optimization

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
R. J. Shalloo ◽  
S. J. D. Dann ◽  
J.-N. Gruse ◽  
C. I. D. Underwood ◽  
A. F. Antoine ◽  
...  
Keyword(s):  
Pulse Length ◽  
Bayesian Optimization ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Laser Wakefield ◽  
Accelerating Structure ◽  
Automation And Control ◽  
Laser Pulse Shape ◽  
And Control ◽  
Wakefield Accelerators

AbstractLaser wakefield accelerators promise to revolutionize many areas of accelerator science. However, one of the greatest challenges to their widespread adoption is the difficulty in control and optimization of the accelerator outputs due to coupling between input parameters and the dynamic evolution of the accelerating structure. Here, we use machine learning techniques to automate a 100 MeV-scale accelerator, which optimized its outputs by simultaneously varying up to six parameters including the spectral and spatial phase of the laser and the plasma density and length. Most notably, the model built by the algorithm enabled optimization of the laser evolution that might otherwise have been missed in single-variable scans. Subtle tuning of the laser pulse shape caused an 80% increase in electron beam charge, despite the pulse length changing by just 1%.

scholarly journals Predictive Model for Detection of Depression Based on Uncertainty Analysis Methods

Proceedings ◽  
2018 ◽  
Vol 2 (19) ◽  
pp. 551
Author(s):  
Alicia Martínez ◽  
Richard Benítez ◽  
Hugo Estrada ◽  
Yasmín Hernández
Keyword(s):  
Older Adults ◽  
Predictive Model ◽  
Smart Cities ◽  
Machine Learning Techniques ◽  
World Population ◽  
Novel Technologies ◽  
Learning Techniques ◽  
Problematic Situations ◽  
And Behavior ◽  
Important Disease

: Currently, advances in technology have permitted increases in the life expectancy of older adults. As a result, a large segment of the world population is 60’s years old, and over. Depression is an important disease in older adults is depression, which seriously affects the moods and behavior of elderly. Novel technologies for smart cities allow us to monitor people and prevent problematic situations related to this mental illness. In this paper, we propose a predictive model to automatically detect depression in older adults. The model is based on machine-learning techniques to analyze the data obtained by a sensor that monitores the daily activities of older adults. Also, the model was evaluated obtaining promising results.

scholarly journals Protocols for fast simulations of protein structure flexibility using CABS-flex and SURPASS

2019 ◽  
Author(s):  
Aleksandra Badaczewska-Dawid ◽  
Andrzej Kolinski ◽  
Sebastian Kmiecik
Keyword(s):  
Protein Function ◽  
Md Simulation ◽  
Protein Structures ◽  
Md Simulations ◽  
System Size ◽  
Coarse Grained ◽  
Simulation Tools ◽  
Speed Up ◽  
Structure Flexibility ◽  
Computational Resources

SummaryConformational flexibility of protein structures can play an important role in protein function. The flexibility is often studied using computational methods, since experimental characterization can be difficult. Depending on protein system size; computational tools may require large computational resources or significant simplifications in the modeled systems to speed-up calculations. In this work, we present the protocols for efficient simulations of flexibility of folded protein structures that use coarse-grained simulation tools of different resolutions: medium, represented by CABS-flex, and low, represented by SUPRASS. We test the protocols using a set of 140 globular proteins and compare the results with structure fluctuations observed in MD simulations, ENM modeling and NMR ensembles. As demonstrated, CABS-flex predictions show high correlation to experimental and MD simulation data, while SURPASS is less accurate but promising in terms of future developments.

scholarly journals Bias Free Multiobjective Active Learning for Materials Design and Discovery

2020 ◽  
Author(s):  
Kevin Maik Jablonka ◽  
Giriprasad Melpatti Jothiappan ◽  
Shefang Wang ◽  
Berend Smit ◽  
Brian Yoo
Keyword(s):  
Active Learning ◽  
De Novo ◽  
Learning Algorithm ◽  
Random Search ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Pareto Optimal ◽  
Design Rules ◽  
Learning Techniques ◽  
Screening Approaches

<div>The design rules for materials are clear for applications with a single objective. For most applications, however, there are often multiple, sometimes competing objectives where there is no single best material, and the design rules change to finding the set of Pareto optimal materials. </div><div>In this work, we introduce an active learning algorithm that directly uses the Pareto dominance relation to compute the set of Pareto optimal materials with desirable accuracy. <br></div><div>We apply our algorithm to de novo polymer design with a prohibitively large search space.</div><div>Using molecular simulations, we compute key descriptors for dispersant applications and reduce the number of materials that need to be evaluated to reconstruct the Pareto front with a desired confidence by over 98% compared to random search.</div><div>This work showcases how simulation and machine learning techniques can be coupled to discover materials within a design space that would be intractable using conventional screening approaches.</div>

scholarly journals Bias Free Multiobjective Active Learning for Materials Design and Discovery

2020 ◽  
Author(s):  
Kevin Maik Jablonka ◽  
Giriprasad Melpatti Jothiappan ◽  
Shefang Wang ◽  
Berend Smit ◽  
Brian Yoo
Keyword(s):  
Active Learning ◽  
De Novo ◽  
Learning Algorithm ◽  
Random Search ◽  
Search Space ◽  
Machine Learning Techniques ◽  
Pareto Optimal ◽  
Design Rules ◽  
Learning Techniques ◽  
Screening Approaches

<div>The design rules for materials are clear for applications with a single objective. For most applications, however, there are often multiple, sometimes competing objectives where there is no single best material, and the design rules change to finding the set of Pareto optimal materials. </div><div>In this work, we introduce an active learning algorithm that directly uses the Pareto dominance relation to compute the set of Pareto optimal materials with desirable accuracy. <br></div><div>We apply our algorithm to de novo polymer design with a prohibitively large search space.</div><div>Using molecular simulations, we compute key descriptors for dispersant applications and reduce the number of materials that need to be evaluated to reconstruct the Pareto front with a desired confidence by over 98% compared to random search.</div><div>This work showcases how simulation and machine learning techniques can be coupled to discover materials within a design space that would be intractable using conventional screening approaches.</div>

scholarly journals Using Machine Learning for Decreasing State Uncertainty in Planning

2020 ◽  
Vol 69 ◽  
pp. 765-806
Author(s):  
Senka Krivic ◽  
Michael Cashmore ◽  
Daniele Magazzeni ◽  
Sandor Szedmak ◽  
Justus Piater
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Learning Process ◽  
The State ◽  
Machine Learning Techniques ◽  
Planning Problem ◽  
Planning Techniques ◽  
Novel Approach ◽  
Learning Techniques ◽  
State Uncertainty

We present a novel approach for decreasing state uncertainty in planning prior to solving the planning problem. This is done by making predictions about the state based on currently known information, using machine learning techniques. For domains where uncertainty is high, we define an active learning process for identifying which information, once sensed, will best improve the accuracy of predictions. We demonstrate that an agent is able to solve problems with uncertainties in the state with less planning effort compared to standard planning techniques. Moreover, agents can solve problems for which they could not find valid plans without using predictions. Experimental results also demonstrate that using our active learning process for identifying information to be sensed leads to gathering information that improves the prediction process.

scholarly journals Solution structure of multi-domain protein ER-60 studied by aggregation-free SAXS and coarse-grained-MD simulation

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Aya Okuda ◽  
Masahiro Shimizu ◽  
Ken Morishima ◽  
Rintaro Inoue ◽  
Nobuhiro Sato ◽  
...  
Keyword(s):  
Conformational Changes ◽  
Solution Structure ◽  
Md Simulation ◽  
Redox State ◽  
Dynamics Simulation ◽  
Coarse Grained ◽  
X Ray ◽  
Physiological Conditions ◽  
X Ray Scattering ◽  
Active Centres

AbstractMulti-domain proteins (MDPs) show a variety of domain conformations under physiological conditions, regulating their functions through such conformational changes. One of the typical MDPs, ER-60 which is a protein folding enzyme, has a U-shape with four domains and is thought to have different domain conformations in solution depending on the redox state at the active centres of the edge domains. In this work, an aggregation-free small-angle X-ray scattering revealed that the structures of oxidized and reduced ER-60 in solution are different from each other and are also different from those in the crystal. Furthermore, structural modelling with coarse-grained molecular dynamics simulation indicated that the distance between the two edge domains of oxidized ER-60 is longer than that of reduced ER-60. In addition, one of the edge domains has a more flexible conformation than the other.

scholarly journals A combined coarse-grained and all-atom simulation of TRPV1 channel gating and heat activation

2015 ◽  
Vol 145 (5) ◽  
pp. 443-456 ◽  
Author(s):  
Wenjun Zheng ◽  
Feng Qin
Keyword(s):  
Conformational Changes ◽  
Md Simulation ◽  
Molecular Mechanisms ◽  
Transient Receptor Potential ◽  
Trp Channels ◽  
Normal Mode Analysis ◽  
Coarse Grained ◽  
Mode Analysis ◽  
Structural Dynamic ◽  
Heat Activation

The transient receptor potential (TRP) channels act as key sensors of various chemical and physical stimuli in eukaryotic cells. Despite years of study, the molecular mechanisms of TRP channel activation remain unclear. To elucidate the structural, dynamic, and energetic basis of gating in TRPV1 (a founding member of the TRPV subfamily), we performed coarse-grained modeling and all-atom molecular dynamics (MD) simulation based on the recently solved high resolution structures of the open and closed form of TRPV1. Our coarse-grained normal mode analysis captures two key modes of collective motions involved in the TRPV1 gating transition, featuring a quaternary twist motion of the transmembrane domains (TMDs) relative to the intracellular domains (ICDs). Our transition pathway modeling predicts a sequence of structural movements that propagate from the ICDs to the TMDs via key interface domains (including the membrane proximal domain and the C-terminal domain), leading to sequential opening of the selectivity filter followed by the lower gate in the channel pore (confirmed by modeling conformational changes induced by the activation of ICDs). The above findings of coarse-grained modeling are robust to perturbation by lipids. Finally, our MD simulation of the ICD identifies key residues that contribute differently to the nonpolar energy of the open and closed state, and these residues are predicted to control the temperature sensitivity of TRPV1 gating. These computational predictions offer new insights to the mechanism for heat activation of TRPV1 gating, and will guide our future electrophysiology and mutagenesis studies.

Sign in / Sign up

Export Citation Format

Share Document