Unsupervised Learning Methods for Molecular Simulation Data

Glielmo, Aldo; Husic, Brooke E.; Rodríguez, Álex; Clementi, Cecilia; Noé, Frank; Laio, Alessandro

doi:10.1021/acs.chemrev.0c01195

Cited by 243 publications

(263 citation statements)

References 380 publications

(736 reference statements)

Supporting

Mentioning

244

Contrasting

Order By: Relevance

“…The conventional machine learning estimators for dimension reduction supported by deeptime are detailed below. For more thorough introductions to available methods and overviews of their relationships, we refer the reader to [11,67,68]. Most of the following methods seek a matrix K ∈ R m×m , a finite-dimensional approximation of a transfer operator that should fulfill…”

Section: Conventional Dimension Reduction and Decompositionmentioning

confidence: 99%

Deeptime: a Python library for machine learning dynamical models from time series data

Hoffmann

Scherer

Hempel

et al. 2021

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables, dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software. Deeptime can be found under https://deeptime-ml.github.io/.

show abstract

Section: Conventional Dimension Reduction and Decompositionmentioning

confidence: 99%

Deeptime: a Python library for machine learning dynamical models from time series data

Hoffmann

Scherer

Hempel

et al. 2021

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Two main groups of clustering approaches can be distinguished, namely partitional and hierarchical, both of which can be carried out in the bottom-up agglomerative way or using a top-down divisive approach ( Kaufman and Rousseeuw, 1990 ). Another group of data grouping methods are density-based schemes, in which the clusters refer to the peaks of the probability distribution (or free energy minima) from which the data are collected ( Sander, 2011 ; Glielmo et al, 2021 ). In MD simulations, such probability peaks typically correspond to metastable states of the system.…”

Section: Clustering and Reduction Of Data Dimensionalitymentioning

confidence: 99%

From Data to Knowledge: Systematic Review of Tools for Automatic Analysis of Molecular Dynamics Output

Baltrukevich

Podlewska

2022

Front. Pharmacol.

View full text Add to dashboard Cite

An increasing number of crystal structures available on one side, and the boost of computational power available for computer-aided drug design tasks on the other, have caused that the structure-based drug design tools are intensively used in the drug development pipelines. Docking and molecular dynamics simulations, key representatives of the structure-based approaches, provide detailed information about the potential interaction of a ligand with a target receptor. However, at the same time, they require a three-dimensional structure of a protein and a relatively high amount of computational resources. Nowadays, as both docking and molecular dynamics are much more extensively used, the amount of data output from these procedures is also growing. Therefore, there are also more and more approaches that facilitate the analysis and interpretation of the results of structure-based tools. In this review, we will comprehensively summarize approaches for handling molecular dynamics simulations output. It will cover both statistical and machine-learning-based tools, as well as various forms of depiction of molecular dynamics output.

show abstract

“…In the following we apply to the set of inferred interactions {J} two general methods usually applied to the analysis of correlation matrices, i.e. HC and PCA [13,14]. Fig.…”

Section: The Inferred Interactions Networkmentioning

confidence: 99%

“…In order to assess the consistency of the inferred interactions and to apply to them cluster-ization methods, their properties have been contrasted with the ones of RMCs [10][11][12]. Finally, we apply to the inferred interactions set algorithms usually exploited in the analysis of cross-correlations matrices, Hierarchical Clustering (HC) and Principal Component Analysis (PCA) [13,14]. We obtain a division in clusters of different countries based on their interactions profile with all the other countries.…”

Section: Introductionmentioning

confidence: 99%

Worldwide bilateral geopolitical interactions network inferred from national disciplinary profiles

Izzo¹,

Daraio²,

Leuzzi³

et al. 2022

Preprint

View full text Add to dashboard Cite

A disciplinary profile of a country is defined as the versor whose components are the numbers of articles produced in a given discipline divided the overall production of the country. Starting from the Essential Science Indicators (ESI) schema of classification of subject area, we obtained the yearly disciplinary profiles of a worldwide graph, where on each node sits a country, in the two time intervals [1980 − 1988] and [1992 − 2017], the fall of the Berlin Wall being the watershed. We analyse the empirical pairwise cross-correlation matrices of the time series of disciplinary profiles. The contrast with random matrix theory proves that, beyond measurement noise, the empirical cross-correlation matrices bring genuine information. Arising from the Shannon theorem as the least-structured model consistent with the measured pairwise correlations, the stationary probability distribution of disciplinary profiles can be described by a Boltzmann distribution related to a generalized n ddimensional Heisenberg model. The set of network interactions of the Heisenberg model have been inferred and to it they have been applied two clusterization methods, hierarchical clustering and principal component analysis. On a geopolitical plane this allow to obtain a characterization of the worldwide bilateral interactions based on physical modeling. A simple geopolitical analysis reveals the consistency of the results obtained and gives a boost to deeper historical analysis. In order to obtain the optimal set of pairwise interactions we used a Pseudo-Likelihood approach. We analytically computed the Pseudo-Likelihood and its gradient. The analytical computations deserve interest in whatever inference Bayesian problem involving a n d -dimensional Heisenberg model.

show abstract

Unsupervised Learning Methods for Molecular Simulation Data

Cited by 243 publications

References 380 publications

Deeptime: a Python library for machine learning dynamical models from time series data

Deeptime: a Python library for machine learning dynamical models from time series data

From Data to Knowledge: Systematic Review of Tools for Automatic Analysis of Molecular Dynamics Output

Worldwide bilateral geopolitical interactions network inferred from national disciplinary profiles

Contact Info

Product

Resources

About