DeepCV: A Deep Learning Framework for Blind Search of Collective Variables in Expanded Configurational Space

Ketkaew, Rangsiman; Luber, Sandra

doi:10.1021/acs.jcim.2c00883

Cited by 15 publications

(10 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TP sampling defines a set of CVs that capture the essential features or order parameters of the rare event of interest and generates a set of trajectories that connect the initial and final states of the transition and maximize the trajectory autocorrelation. Autoencoders, GNNs, and reinforcement-based actor-critic optimization of Doob dynamics may be employed − to choose the appropriate CV set, model the markovian trajectories, and perform symbolic regression for model interpretability. Once a TP has been found, the “syncategorematic” role , of bath gas or solvent composition in collisional dynamics needs to be addressed.…”

Section: Ann For Nanoscale Mixturesmentioning

confidence: 99%

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Nicolle,

Deng,

Ihme

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the ’recomposition’ of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure–Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

show abstract

Section: Ann For Nanoscale Mixturesmentioning

confidence: 99%

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Nicolle,

Deng,

Ihme

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Identifying CVs is challenging for complex systems and often involves resorting to physical or chemical intuition and trial-and-error approaches [47]. This motivated many theoretical and computational advances to construct CVs directly from simulation data, for example, using neural networks [48][49][50][51][52][53][54][55][56][57][58][59][60][61][62].…”

Section: Collective Variables (Cvs) and Target Mappingmentioning

confidence: 99%

Manifold learning in atomistic simulations: a conceptual review

Rydzewski

Chen

Valsson

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Analyzing large volumes of high-dimensional data requires dimensionality reduction: finding meaningful low-dimensional structures hidden in their high-dimensional observations. Such practice is needed in atomistic simulations of complex systems where even thousands of degrees of freedom are sampled. An abundance of such data makes gaining insight into a specific physical problem strenuous. Our primary aim in this review is to focus on unsupervised machine learning methods that can be used on simulation data to find a low-dimensional manifold providing a collective and informative characterization of the studied process. Such manifolds can be used for sampling long-timescale processes and free-energy estimation. We describe methods that can work on datasets from standard and enhanced sampling atomistic simulations. Unlike recent reviews on manifold learning for atomistic simulations, we consider only methods that construct low-dimensional manifolds based on Markov transition probabilities between high-dimensional samples. We discuss these techniques from a conceptual point of view, including their underlying theoretical frameworks and possible limitations.

show abstract

“…In addition to their interest in characterizing a molecular system, collective variables are used to enhance sampling in MD simulations. Identifying collective variables associated with slow or hard-to-model modes in an MD simulation is the focus of Molecular Enhanced Sampling with Autoencoders (MESA), FABULOUS (genetic algorithms and NN), COVAEM, and DeepCV (deep autoencoder NN). , To bypass the use of MD simulations for sampling, Atomistic Adversarial Attacks can generate molecular conformation and nonbonded configurations, which is achieved by combining uncertainty quantification, automatic differentiation, adversarial attacks, and active learning …”

Section: Computational Chemistry Toolsmentioning

confidence: 99%

Open-Source Machine Learning in Computational Chemistry

Hagg

2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The field of computational chemistry has seen a significant increase in the integration of machine learning concepts and algorithms. In this Perspective, we surveyed 179 open-source software projects, with corresponding peer-reviewed papers published within the last 5 years, to better understand the topics within the field being investigated by machine learning approaches. For each project, we provide a short description, the link to the code, the accompanying license type, and whether the training data and resulting models are made publicly available. Based on those deposited in GitHub repositories, the most popular employed Python libraries are identified. We hope that this survey will serve as a resource to learn about machine learning or specific architectures thereof by identifying accessible codes with accompanying papers on a topic basis. To this end, we also include computational chemistry open-source software for generating training data and fundamental Python libraries for machine learning. Based on our observations and considering the three pillars of collaborative machine learning work, open data, open source (code), and open models, we provide some suggestions to the community.

show abstract

DeepCV: A Deep Learning Framework for Blind Search of Collective Variables in Expanded Configurational Space

Cited by 15 publications

References 84 publications

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Manifold learning in atomistic simulations: a conceptual review

Open-Source Machine Learning in Computational Chemistry

Contact Info

Product

Resources

About