Deep clustering of protein folding simulations

Background We examine the problem of clustering biomolecular simulations using deep learning techniques. Since biomolecular simulation datasets are inherently high dimensional, it is often necessary to build low dimensional representations that can be used to extract quantitative insights into the a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	BMC bioinformatics Jg. 19; H. Suppl 18; S. 484 - 58
Hauptverfasser:	Bhowmik, Debsindhu, Gao, Shang, Young, Michael T., Ramanathan, Arvind
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	London BioMed Central 21.12.2018 BioMed Central Ltd Springer Nature B.V BMC
Schlagworte:	Algorithms Artificial intelligence Artificial neural networks BASIC BIOLOGICAL SCIENCES Bioinformatics Biological activity Biological effects Biomedical and Life Sciences Cluster Analysis Clustering Computational Biology/Bioinformatics Computer Appl. in Life Sciences Computer simulation Conformational substates Datasets Deep learning Folding Information processing International conferences Learning Life Sciences Ligands Machine learning Microarrays Molecular Dynamics Simulation Molecular rotation Peptides Principal components analysis Protein Folding Proteins Sampling Simulation Trajectories Variational autoencoder Deep learning Variational autoencoder Conformational substates Protein folding
ISSN:	1471-2105, 1471-2105
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Background We examine the problem of clustering biomolecular simulations using deep learning techniques. Since biomolecular simulation datasets are inherently high dimensional, it is often necessary to build low dimensional representations that can be used to extract quantitative insights into the atomistic mechanisms that underlie complex biological processes. Results We use a convolutional variational autoencoder (CVAE) to learn low dimensional, biophysically relevant latent features from long time-scale protein folding simulations in an unsupervised manner. We demonstrate our approach on three model protein folding systems, namely Fs-peptide (14 μ s aggregate sampling), villin head piece (single trajectory of 125 μ s) and β - β - α (BBA) protein (223 + 102 μ s sampling across two independent trajectories). In these systems, we show that the CVAE latent features learned correspond to distinct conformational substates along the protein folding pathways. The CVAE model predicts, on average, nearly 89% of all contacts within the folding trajectories correctly, while being able to extract folded, unfolded and potentially misfolded states in an unsupervised manner. Further, the CVAE model can be used to learn latent features of protein folding that can be applied to other independent trajectories, making it particularly attractive for identifying intrinsic features that correspond to conformational substates that share similar structural features. Conclusions Together, we show that the CVAE model can quantitatively describe complex biophysical processes such as protein folding.
Bibliographie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 AC02-06-CH11357; AC52-07NA27344; AC5206NA25396; AC05-00OR22725 USDOE Office of Science (SC)
ISSN:	1471-2105 1471-2105
DOI:	10.1186/s12859-018-2507-5