VAMPnets for deep learning of molecular kinetics

Mardt, Andreas; Pasquali, Luca; Wu, Hao; Noé, Frank

doi:10.1038/s41467-017-02388-1

Cited by 474 publications

(735 citation statements)

References 82 publications

(128 reference statements)

Supporting

Mentioning

700

Contrasting

Unclassified

Order By: Relevance

“…In the last few years, the deep learning, a particular variant of machine learning approach, is emerging as an e cient approach for identification of linear and/or nonlinear reaction coordinates to perform biased sampling [57][58][59][60] . In future, it would be interesting to compare the behavior (i.e.…”

Section: Resultsmentioning

confidence: 99%

Assessment and Optimization of Collective Variables for Protein Conformational Landscape: GB1 β-hairpin as a Case Study

Ahalawat

Mondal

2018

Preprint

View full text Add to dashboard Cite

Collective variables (CV), when chosen judiciously, can play an important role in recognizing rate-limiting processes and rare events in any biomolecular systems. However, high dimensionality and inherent complexities associated with such biochemical systems render the identification of an optimal CV a challenging task, which in turn precludes the elucidation of underlying conformational landscape in su cient details. In this context, a relevant model system is presented by 16-residue -hairpin of GB1 protein. Despite being the target of numerous theoretical and computational studies for understanding the protein folding, the set of CVs optimally characterizing the conformational landscape of -hairpin of GB1 protein has remained elusive, resulting in a lack of consensus on its folding mechanism. Here we address this by proposing a pair of optimal CVs which can resolve the underlying free energy landscape of GB1 hairpin quite e ciently. Expressed as a linear combination of a number of traditional CVs, the optimal CV for this system is derived by employing recently introduced Time-structured Independent Component Analysis (TICA) approach on a large number of independent unbiased simulations. By projecting the replica-exchange simulated trajectories along these pair of optimized CVs, the resulting free energy landscape of this system are able to resolve four distinct well-separated metastable states encompassing the extensive ensembles of folded,unfolded and molten globule states. Importantly, the optimized CVs were found to be capable of automatically recovering a novel partial helical state of this protein, without needing to explicitly invoke helicity as a constituent CV. Furthermore, a quantitative sensitivity analysis of each constituent in the optimized CV provided key insights on the relative contributions of the constituent CVs in the overall free energy landscapes. Finally, the kinetic pathways connecting these metastable states, constructed using a Markov State Model, provide an optimum description of underlying folding mechanism of the peptide. Taken together, this work o↵ers a quantitatively robust approach towards comprehensive mapping of the underlying folding landscape of a quintessential model system along its optimized collective variables.

show abstract

Section: Resultsmentioning

confidence: 99%

Assessment and Optimization of Collective Variables for Protein Conformational Landscape: GB1 β-hairpin as a Case Study

Ahalawat

Mondal

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…The neural network applied here was inspired by deep rank-reduction architectures, recently used for characterization and interpretation of numerical solutions of large non-linear dynamical systems [46,47]. dFI increases exponentially with age and is associated with remaining lifespan.…”

Section: Discussionmentioning

confidence: 99%

Identification of a blood test-based biomarker of aging through deep learning of aging trajectories in large phenotypic datasets of mice

Avchaciov

Antoch

Andrianova³

et al. 2020

Preprint

View full text Add to dashboard Cite

We proposed and characterized a novel biomarker of aging and frailty in mice trained from the large set of the most conventional, easily measured blood parameters such as Complete Blood Counts (CBC) from the open-access Mouse Phenome Database (MPD). Instead of postulating the existence of an aging clock associated with any particular subsystem of an aging organism, we assumed that aging arises cooperatively from positive feedback loops spanning across physiological compartments and leading to an organism-level instability of the underlying regulatory network. To analyze the data, we employed a deep artificial neural network including auto-encoder (AE) and auto-regression (AR) components. The AE was used for dimensionality reduction and denoising the data. The AR was used to describe the dynamics of an individual mouse's health state by means of stochastic evolution of a single organism state variable, the "dynamic frailty index" (dFI), that is the linear combination of the latent AE features and has the meaning of the total number of regulatory abnormalities developed up to the point of the measurement or, more formally, the order parameter associated with the instability. We used neither the chronological age nor the remaining lifespan of the animals while training the model. Nevertheless, dFI fully described aging on the organism level, that is it increased exponentially with age and predicted remaining lifespan. Notably, dFI correlated strongly with multiple hallmarks of aging such as physiological frailty index, indications of physical decline, molecular markers of inflammation and accumulation of senescent cells. The dynamic nature of dFI was demonstrated in mice subjected to aging acceleration by placement on a high-fat diet and aging deceleration by treatment with rapamycin.

show abstract

“…Recently, machine learning has been successfully applied to the fast and accurate prediction of molecular properties across chemical compound space [4][5][6][7][8][9][10] and molecular dynamics simulations [11][12][13][14][15] as well as for studying properties of quantum-mechanical densities [16,17]. An indispensable ingredient to most machine learning models are molecular descriptors, which are constructed to provide an invariant, unique and efficient representation as input to machine learning models [18][19][20][21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning

et al. 2018

View full text Add to dashboard Cite

Abstract. Machine learning has been successfully applied to the prediction of chemical properties of small organic molecules such as energies or polarizabilities. Compared to these properties, the electronic excitation energies pose a much more challenging learning problem. Here, we examine the applicability of two existing machine learning methodologies to the prediction of excitation energies from time-dependent density functional theory. To this end, we systematically study the performance of various 2-and 3-body descriptors as well as the deep neural network SchNet to predict extensive as well as intensive properties such as the transition energies from the ground state to the first and second excited state. As perhaps expected current state-of-the-art machine learning techniques are more suited to predict extensive as opposed to intensive quantities. We speculate on the need to develop global descriptors that can describe both extensive and intensive properties on equal footing.

show abstract

VAMPnets for deep learning of molecular kinetics

Cited by 474 publications

References 82 publications

Assessment and Optimization of Collective Variables for Protein Conformational Landscape: GB1 β-hairpin as a Case Study

Assessment and Optimization of Collective Variables for Protein Conformational Landscape: GB1 β-hairpin as a Case Study

Identification of a blood test-based biomarker of aging through deep learning of aging trajectories in large phenotypic datasets of mice

Capturing intensive and extensive DFT/TDDFT molecular properties with machine learning

Contact Info

Product

Resources

About