CoChat

Markov State Models to Study the Functional Dynamics of Proteins in the Wake of Machine Learning

Open access
Konovalov, Kirill A., Unarta, Ilona Christy, Cao, Siqin, Goonetilleke, Eshani C., Huang, Xuhui · 2021 · JACS Au
Cited by 120

The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.

Abstract

Markov state models (MSMs) based on molecular dynamics (MD) simulations are routinely employed to study protein folding, however, their application to functional conformational changes of biomolecules is still limited. In the past few years, the field of computational chemistry has experienced a surge of advancements stemming from machine learning algorithms, and MSMs have not been left out. Unlike global processes, such as protein folding, the application of MSMs to functional conformational changes is challenging because they mostly consist of localized structural transitions. Therefore, it is critical to properly select a subset of structural features that can describe the slowest dynamics of these functional conformational changes. To address this challenge, we recommend several automatic feature selection methods such as Spectral-OASIS. To identify states in MSMs, the chosen features can be subject to dimensionality reduction methods such as TICA or deep learning based VAMPNets to project MD conformations onto a few collective variables for subsequent clustering. Another challenge for the application of MSMs to the study of functional conformational changes is the ability to comprehend their biophysical mechanisms, as MSMs built for these processes often require a large number of states. We recommend the recently developed quasi-MSMs (qMSMs) to address this issue. Compared to MSMs, qMSMs encode the non-Markovian dynamics via the generalized master equation and can significantly reduce the number of states. As a result, qMSMs can be built with a handful of states to facilitate the interpretation of functional conformational changes. In the wake of machine learning, we believe that the rapid advancement in the MSM methodology will lead to their wider application in studying functional conformational changes of biomolecules.

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/jacsau.1c00254

Cites

22 of 22 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

Research works printed but not linked: 80

  1. 10.1038/s41557-021-00707-0 · DOI · Paper page
  2. 10.1073/pnas.1315751111 · DOI · Paper page
  3. 10.1371/journal.pcbi.1000047 · DOI · Paper page
  4. 10.1021/ct501156t · DOI
  5. 10.1146/annurev-physchem-052516-050843 · DOI · Paper page
  6. 10.1016/j.sbi.2012.10.008 · DOI · Paper page
  7. 10.1073/pnas.1411798111 · DOI · Paper page
  8. 10.1021/jacs.7b12191 · DOI · Paper page
  9. 10.1021/ct5002363 · DOI · Paper page
  10. Bowman G. R., 2014, Advances in Experimental Medicine and Biology
  11. 10.1063/1.2714538 · DOI · Paper page
  12. 10.1063/1.2959573 · DOI · Paper page
  13. 10.1371/journal.pcbi.1001015 · DOI · Paper page
  14. 10.1073/pnas.0909088106 · DOI · Paper page
  15. 10.1016/j.sbi.2010.10.006 · DOI · Paper page
  16. 10.1371/journal.pcbi.1002054 · DOI · Paper page
  17. 10.1063/1.2714539 · DOI · Paper page
  18. 10.1021/ct900620b · DOI · Paper page
  19. 10.1007/s00332-019-09567-y · DOI · Paper page
  20. 10.1021/jacs.0c09343 · DOI
  21. 10.1039/C7CP06181A · DOI
  22. 10.1021/acs.jpcb.6b02015 · doi:10.1021/acs.jpcb.6b02015
  23. 10.1021/ja9090353 · DOI · Paper page
  24. 10.1021/ja207470h · DOI · Paper page
  25. 10.1002/wcms.1343 · DOI · Paper page
  26. 10.1016/j.sbi.2020.10.005 · DOI
  27. 10.1021/acs.jctc.8b00089 · DOI
  28. 10.1021/acs.jpclett.8b00759 · DOI · Paper page
  29. 10.1038/s41467-017-02388-1 · DOI · Paper page
  30. 10.1063/1.5092521 · DOI · Paper page
  31. 10.1063/5.0010787 · DOI
  32. 10.1038/ncomms11244 · DOI
  33. 10.1038/ncomms8588 · DOI · Paper page
  34. 10.1038/ncomms8283 · DOI · Paper page
  35. 10.1371/journal.pcbi.1004404 · DOI
  36. 10.1021/ja210656k · DOI · Paper page
  37. 10.1016/0263-7855(94)80072-3 · DOI · Paper page
  38. 10.1038/ncomms15443 · DOI
  39. 10.1016/j.jmb.2008.10.064 · DOI · Paper page
  40. 10.1073/pnas.0604375103 · DOI · Paper page
  41. 10.1021/acs.accounts.5b00338 · DOI · Paper page
  42. 10.1021/jp0777059 · DOI · Paper page
  43. 10.1063/1.5082633 · DOI
  44. 10.1039/C9ME00115H · DOI · Paper page
  45. 10.1016/0304-3975(85)90224-5 · DOI · Paper page
  46. 10.1002/jcc.24664 · DOI
  47. 10.1142/9789814295291_0025 · DOI · Paper page
  48. 10.1063/1.4916292 · DOI · Paper page
  49. 10.1021/acs.jctc.8b00500 · DOI · Paper page
  50. 10.1021/acs.jctc.6b00049 · DOI · Paper page
  51. 10.1021/ct500827g · DOI
  52. 10.1021/acs.jctc.5b00737 · DOI · Paper page
  53. 10.1093/nar/gkaa1252 · DOI
  54. 10.1016/j.str.2021.03.014 · DOI
  55. 10.1016/S0024-3795(00)00095-1 · DOI · Paper page
  56. 10.1007/s11634-013-0134-6 · DOI · Paper page
  57. 10.1063/1.5027001 · DOI
  58. 10.1103/PhysRevX.7.031060 · DOI
  59. 10.1038/nchem.2785 · DOI · Paper page
  60. 10.1021/acs.accounts.5b00536 · DOI
  61. 10.1073/pnas.1707922114 · DOI
  62. 10.1093/nar/gky386 · DOI
  63. 10.1063/1.4885338 · DOI · Paper page
  64. 10.1063/1.4974306 · DOI
  65. 10.1021/acs.jpcb.9b05578 · DOI · Paper page
  66. 10.1016/j.bpj.2017.11.359 · DOI
  67. 10.7554/eLife.38805 · DOI
  68. 10.1039/D0SC05053A · DOI · Paper page
  69. 10.1073/pnas.2002971117 · DOI
  70. Mardt, A.; Pasquali, L.; Noé, F.; Wu, H. Deep learning Markov and Koopman models with physical constraints. In Proceedings of The First Mathematical and Scientific Machine Learning Conference; Jianfeng, L., Rachel, W., Eds. PMLR: Proceedings of Machine Learning Research, 2020; Vol. 107, pp 451–475.
  71. 10.1073/pnas.2024324118 · DOI
  72. 10.1038/s41467-020-18959-8 · DOI · Paper page
  73. Vaswani A., 2017, Adv. Neur. In, 30, 6000
  74. 10.1063/1.5049637 · DOI · Paper page
  75. 10.1021/acs.chemrev.0c01195 · DOI · Paper page
  76. 10.1063/1674-0068/31/cjcp1806147 · DOI
  77. 10.1063/1.5099194 · DOI
  78. 10.1063/1.4828816 · DOI · Paper page
  79. 10.1021/acs.jctc.5b00743 · DOI · Paper page
  80. 10.1063/1.4965440 · DOI

Cited by

See all 120

Metadata

Authors
Konovalov, K. A., Unarta, I. C., Cao, S., Goonetilleke, E. C., & Huang, X.
Venue
JACS Au
Published
2021-08-04
Volume
1
Issue
9
Pages
1330-1341
ISSN
2691-3704 (ISSN-L)
OpenAlex
W3189465577
Cited by
120
References
22
FWCI
4.96
Type
journal article
Language
en
Open access
gold
Funders
Research Grants Council, University Grants Committee (16303919, 16307718, AoE/P-705/16, N_HKUST635/20, PF16-06144)

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.