CoChat

Chasing Collective Variables Using Autoencoders and Biased Trajectories

Open access
Belkacemi, Zineb, Gkeka, Paraskevi, Lelièvre, Tony, Stoltz, Gabriel · 2022 · Journal of Chemical Theory and Computation
Cited by 85

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Free energy biasing methods have proven to be powerful tools to accelerate the simulation of important conformational changes of molecules by modifying the sampling measure. However, most of these methods rely on the prior knowledge of low-dimensional slow degrees of freedom, i.e., collective variables (CVs). Alternatively, such CVs can be identified using machine learning (ML) and dimensionality reduction algorithms. In this context, approaches where the CVs are learned in an iterative way using adaptive biasing have been proposed: at each iteration, the learned CV is used to perform free energy adaptive biasing to generate new data and learn a new CV. In this paper, we introduce a new iterative method involving CV learning with autoencoders: Free Energy Biasing and Iterative Learning with AutoEncoders (FEBILAE). Our method includes a reweighting scheme to ensure that the learning model optimizes the same loss at each iteration and achieves CV convergence. Using the alanine dipeptide system and the solvated chignolin mini-protein system as examples, we present results of our algorithm using the extended adaptive biasing force as the free energy adaptive biasing method.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acs.jctc.1c00415

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 14 references

Research works printed but not linked: 60

  1. 10.1016/j.neuron.2018.08.011 · DOI · Paper page
  2. 10.1063/1.4830403 · DOI · Paper page
  3. 10.3390/e16010163 · DOI · Paper page
  4. 10.1209/0295-5075/19/6/002 · DOI · Paper page
  5. 10.1103/PhysRevLett.57.2607 · DOI · Paper page
  6. 10.1016/S0006-3495(03)74897-8 · DOI · Paper page
  7. 10.1021/jp962142e · DOI · Paper page
  8. 10.1063/1.481576 · DOI · Paper page
  9. 10.1103/PhysRevLett.86.2050 · DOI · Paper page
  10. 10.1002/wcms.66 · DOI · Paper page
  11. 10.1021/jp506633n · DOI · Paper page
  12. 10.1063/1.1773132 · DOI · Paper page
  13. 10.1063/1.1410978 · DOI · Paper page
  14. 10.1002/jcc.25589 · DOI
  15. 10.1021/acs.jctc.0c00355 · DOI
  16. 10.1021/acs.chemrev.0c01195 · DOI · Paper page
  17. 10.1080/00268976.2020.1737742 · DOI · Paper page
  18. 10.1007/s00332-017-9437-7 · DOI · Paper page
  19. 10.1063/1.4979344 · DOI · Paper page
  20. 10.1137/070696325 · DOI · Paper page
  21. 10.1016/j.acha.2005.07.004 · DOI · Paper page
  22. 10.1021/jacs.7b12191 · DOI · Paper page
  23. 10.1038/s41467-017-02388-1 · DOI · Paper page
  24. 10.1063/1.5092521 · DOI · Paper page
  25. 10.1063/1.5029972 · DOI · Paper page
  26. 10.1021/ct500353m · DOI · Paper page
  27. 10.1103/PhysRevLett.123.245701 · DOI
  28. 10.1021/acs.jpclett.0c00535 · DOI · Paper page
  29. 10.1016/0098-1354(92)80051-A · DOI · Paper page
  30. 10.1063/1.5011399 · DOI · Paper page
  31. 10.1063/1.5058063 · DOI
  32. Kingma D., 2013, arXiv, 1312.6114 · arXiv
  33. 10.1103/PhysRevE.97.062412 · DOI · Paper page
  34. 10.1088/2632-2153/ab80b7 · DOI
  35. 10.1063/5.0058639 · DOI
  36. Felsberger L., 2018, arXiv,, 1802.03824 · arXiv
  37. 10.1039/C9ME00115H · DOI · Paper page
  38. 10.1002/jcc.25520 · DOI · Paper page
  39. 10.1063/1.5023804 · DOI · Paper page
  40. 10.1063/1.5025487 · DOI · Paper page
  41. 10.1038/s41467-019-11405-4 · DOI · Paper page
  42. Plaut E., 2018, arXiv, 1804.10253 · arXiv
  43. 10.1007/BF00332918 · DOI · Paper page
  44. 10.1063/1.1570396 · DOI
  45. 10.1063/1.2711185 · DOI · Paper page
  46. 10.5802/smai-jcm.4 · DOI
  47. 10.1021/acs.jpcb.6b10055 · DOI · Paper page
  48. 10.1038/s41592-019-0506-8 · DOI · Paper page
  49. 10.1016/j.cpc.2013.09.018 · DOI · Paper page
  50. 10.1021/acs.jcim.8b00115 · DOI
  51. 10.1107/S0567739478001680 · DOI · Paper page
  52. Kingma, D.; Ba, J. Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations, 2014.
  53. Morgan, N.; Bourlard, H. In Adv. Neural Inf. Process. Syst. 2; Touretzky, D. S., Ed. Morgan-Kaufmann, 1990; pp 630–637.
  54. 10.1002/prot.21123 · DOI · Paper page
  55. 10.1016/j.febslet.2006.05.015 · DOI
  56. 10.1002/prot.22711 · DOI · Paper page
  57. 10.1063/1.445869 · DOI · Paper page
  58. 10.1002/(SICI)1096-987X(199709)18:12<1463::AID-JCC4>3.0.CO;2-H · DOI · Paper page
  59. 10.1063/1.4906425 · DOI
  60. 10.1016/j.str.2004.05.022 · DOI · Paper page

Cited by

Metadata

Authors
Belkacemi, Z., Gkeka, P., Lelièvre, T., & Stoltz, G.
Venue
Journal of Chemical Theory and Computation
Published
2021-12-29
Volume
18
Issue
1
Pages
59-78
ISSN
  • 1549-9618 (ISSN-L)
  • 1549-9626
OpenAlex
W3154850927
Cited by
85
References
14
FWCI
3.76
Type
journal article
Language
en
Open access
green
Funders
  • Centre National de la Recherche Scientifique
  • University of Illinois at Urbana-Champaign
  • H2020 European Research Council (810367)

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

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.