The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Predicting improved protein conformations with a temporal deep recurrent neural network
Open accessPreprint — published as 10.1371/journal.pone.0202652 · Paper page
Abstract
Accurate protein structure prediction from amino acid sequence is still an unsolved problem. The most reliable methods centre on template based modelling. However, the accuracy of these models entirely depends on the availability of experimentally resolved homologous template structures. In order to generate more accurate models, extensive physics based molecular dynamics (MD) refinement simulations are performed to sample many different conformations to find improved conformational states. In this study, we propose a deep recurrent network model, called DeepTrajectory, that is able to identify these improved conformational states, with high precision, from a variety of different MD based sampling protocols. The proposed model learns the temporal patterns of features computed from the MD trajectory data in order to classify whether each recorded simulation snapshot is an improved conformational state, decreased conformational state or a none perceivable change in state with respect to the starting conformation. The model is trained and tested on 904 trajectories from 42 different protein systems with a cumulative number of more than 1.7 million snapshots. We show that our model outperforms other state of the art machine-learning algorithms that do not consider temporal dependencies. To our knowledge, DeepTrajectory is the first implementation of a time-dependent deep-learning protocol that is re-trainable and able to adapt to any new MD based sampling procedure, thereby demonstrating how a neural network can be used to learn the latter part of the protein folding funnel.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Markov state models of biomolecular conformational dynamics
Chodera, J. D., & Noé, F. (2014) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2014.04.002 · Cited by 776
Flagged first, then by citations
Research works printed but not linked: 51
- 10.1126/science.1065659 · DOI · Paper page
- 2014, Assessment of template-based protein structure predictions in CASP10Proteins: Structure, Function and Bioinfor-matics, 82, 43, 10.1002/prot.24488 · DOI
- 2015, The Phyre2 web portal for protein modelling, predic-tion, and analysis, Nature Protocols, 10, 845, 10.1038/nprot.2015.053 · DOI · Paper page
- 2014, Tramontano, A. Critical assessment of methods of protein structure prediction (CASP) - round XProteins, Struc-ture, Function and Bioinformatics, 82, 1, 10.1002/prot.24452 · DOI
- 2011, Assessment of template based protein structure predictions in CASP9Proteins: Structure, Function and Bioinformat-ics, 79, 37, 10.1002/prot.23177 · DOI
- 10.1093/bioinformatics/bth098 · DOI
- Lindorff-Larsen, K. , Piana, S. , Dror, R. O. & Shaw, D. E. How fast-folding proteins fold Science 334, 517–520 · DOI · Paper page
- J. Progress over the first decade of CASP experimentsProteins:, 2005, Structure, Function and Genetics, 61, 225
- 10.1016/j.sbi.2005.05.011 · DOI
- 2014, Physics-based protein structure refinement through multiple molecular dynamics trajectories and structure averagingProteins, Structure, Function and Bioinformatics, 82, 196, 10.1002/prot.24336 · DOI
- 2016, Local Protein Structure Refinement via Molecu-lar Dynamics Simulations with locPREFMD, Journal of Chemical Information and Modeling, 56, 1304, 10.1021/acs.jcim.6b00222 · DOI
- Hovan, 2017, Assessment of the model refinement cate-gory in CASP12Proteins, Structure, Function, and Bioin-formatics, 86, 152, 10.1002/prot.25409 · DOI
- 2017, Computational protein structure refinement: Al-most there, yet still so far to go, Wiley Interdisciplinary Re-views: Computational Molecular Science, 7, e1307
- 2016, Assessment of refinement of template-based models in CASP11Proteins, Structure, Function, and Bioinformatics, 84, 260, 10.1002/prot.25048 · DOI
- 2014, Evaluation of pre-dictions in the CASP10 model refinement categoryPro-teins, Structure, Function and Bioinformatics, 82, 98, 10.1002/prot.24377 · DOI
- ran, N. H. , Zhang, X. , Xin, L. , Shan, B. & Li, M. De novo peptide sequencing by deep learning Proceedings of the National Academy of Sciences 201705691 (2017).
- 2016, Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, ArXiv e-prints, 1
- Lee, B. , Baek, J. & Yoon, S. deepTarget: End-to-end Learn-ing Framework for microRNA Target Prediction using Deep Recurrent Neural Networks ArXiv e-prints (2016). · DOI
- 10.1016/j.neunet.2014.09.003 · DOI · Paper page
- 2009, Evaluation of template-based models in CASP8 with standard measures Proteins, Structure, Function and Bioinformatics, 77, 18, 10.1002/prot.22561 · DOI
- 2001, Processing and evaluation of predictions in CASP4 Proteins, Struc-ture, Function and Genetics, 45, 13
- 10.1023/A:1010933404324. · DOI · Paper page
- 2006, Pattern recognition and machine learning, 4, 0-387
- 2008). 1307.1662, Visualizing Data using t-SNE, Journal of Machine Learning Research 1, 620, 267
- 2017, A machine learning approach for ranking clusters of docked protein-protein complexes by pairwise cluster com-parison Proteins, Structure, Function and Bioinformatics, 85, 528, 10.1002/prot.25218 · DOI
- 10.1093/bioinformatics/btm287 · DOI
- 2011, Characterization and rapid sampling of protein folding Markov state model topologies, Journal of Chemical Theory and Computation, 7, 3405, 10.1021/ct2004484 · DOI
- 10.1016/j.sbi.2010.02.001 · DOI
- 2007, Flexible relax-ation of rigid-body docking solutions, Proteins: nStructure, Function and Genetics, 68, 159, 10.1002/prot.21391 · DOI
- 10.1093/bioinformatics/btu594 · DOI
- Vangone, A. & Bonvin, A. M. Contacts-based prediction of binding affinity in proteinâĂŞprotein complexes eLife 4 (2015). · DOI
- 10.1016/j.drudis.2013.10.027 · DOI
- Brunk, E et al. Systems biology of the structural proteome BMC Systems Biology 10 (2016). · DOI
- 2016, TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- 2014, Adam: nA Method for Stochastic Optimization
- 2004, A physical ref-erence state unifies the structure-derived potential of mean force for protein folding and binding Proteins, Structure, Function, and Bioinformatics, 56, 93, 10.1002/prot.20019 · DOI · Paper page
- 2006, Statistical potential for assessment and prediction of protein structures Protein, Science, 15, 2507
- 2015, Optimized distance-dependent atom-pair-based potential DOOP for protein structure prediction Proteins, Structure, Function and Bioinformatics, 83, 881, 10.1002/prot.24782 · DOI
- 10.1371/journal.pone.0015386 · DOI
- 10.1016/j.bpj.2011.09.012 · DOI
- 2008, Protein Structure Modeling with MODELLER, In Protein Structure Prediction, 145
- 2006, New Algorithms for Efficient High-Dimensional Nonparametric Classifica-tion, Journal of Machine Learning Research, 7, 1135
- 10.1145/361002.361007 · DOI
- 2011, Scikit-learn: Machine learning in Python, Journal of Machine Learning Research, 12, 2825
- 10.1021/ct700301q · DOI
- 10.1007/s00249-011-0700-9 · DOI
- 10.1063/1.445869 · DOI
- 2007, Canonical sampling through velocity rescaling, Journal of Chemical Physics, 126
- 10.1063/1.448118 · DOI
- 10.1063/1.464397 · DOI
- 10.1016/j.cpc.2013.09.018 · DOI
Metadata
- Authors
- Pfeiffenberger, E., & Bates, P. A.
- Affiliations
- The Francis Crick Institute (GB)
- Corresponding author
- Pfeiffenberger, Erik
- Bates, Paul A.
- Venue
- PLoS ONE
- Publisher
- openRxiv
- Published
- 2018-03-03
- Volume
- 13
- Issue
- 9
- Pages
- e0202652-e0202652
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC6122789
- OpenAlex
- W2949122381
- Cited by
- 21
- References
- 1
- Citations by year
- 2025: 3 · 2024: 2 · 2023: 1 · 2022: 4 · 2021: 3 · 2020: 4 · 2019: 2 · 2018: 2
- FWCI
- 0.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- PLoS ONE (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- Nvidia
- Wellcome Trust (FC001003)
- Francis Crick Institute (10743, 10316, FC001003, 10681)
- Cancer Research UK (10748, FC001003)
- Medical Research Council (FC001003)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Keywords
- protein structure prediction, protein conformational states, molecular dynamics trajectories, deep recurrent neural networks, conformational sampling
- MeSH terms
- Deep Learning, Algorithms, Amino Acid Sequence, Protein Conformation, Software, Neural Networks, Computer, Protein Folding, Sequence Analysis, Protein, Molecular Dynamics Simulation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
