CoChat

Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models

Open access
Qiu, Yuchi, Wei, Guo-Wei · 2023 · Briefings in Bioinformatics
Cited by 88

The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.

Abstract

Protein engineering is an emerging field in biotechnology that has the potential to revolutionize various areas, such as antibody design, drug discovery, food security, ecology, and more. However, the mutational space involved is too vast to be handled through experimental means alone. Leveraging accumulative protein databases, machine learning (ML) models, particularly those based on natural language processing (NLP), have considerably expedited protein engineering. Moreover, advances in topological data analysis (TDA) and artificial intelligence-based protein structure prediction, such as AlphaFold2, have made more powerful structure-based ML-assisted protein engineering strategies possible. This review aims to offer a comprehensive, systematic, and indispensable set of methodological components, including TDA and NLP, for protein engineering and to facilitate their future development.

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 · 10.1093/bib/bbad289

Cites

47 of 47 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 47 references

Research works printed but not linked: 105

  1. Narayanan, 2021, Machine learning for biologics: opportunities for protein engineering, developability, and formulation, Trends Pharmacol Sci, 42, 151, 10.1016/j.tips.2020.12.004 · DOI · Paper page
  2. Arnold, 1998, Design by directed evolution, Acc Chem Res, 31, 125, 10.1021/ar960017f · DOI · Paper page
  3. Karplus, 2005, Molecular dynamics and protein function, Proc Natl Acad Sci, 102, 6679, 10.1073/pnas.0408930102 · DOI · Paper page
  4. Boyken, 2016, De novo design of protein homo-oligomers with modular hydrogen-bond network–mediated specificity, Science, 352, 680, 10.1126/science.aad8865 · DOI · Paper page
  5. Romero, 2009, Exploring protein fitness landscapes by directed evolution, Nat Rev Mol Cell Biol, 10, 866, 10.1038/nrm2805 · DOI · Paper page
  6. Bhardwaj, 2016, Accurate de novo design of hyperstable constrained peptides, Nature, 538, 329, 10.1038/nature19791 · DOI · Paper page
  7. Pierce, 2002, Protein design is NP-hard, Protein Eng, 15, 779, 10.1093/protein/15.10.779 · DOI · Paper page
  8. Siedhoff, 2020, Machine learning-assisted enzyme engineering, Meth Enzymol, 643, 281, 10.1016/bs.mie.2020.05.005 · DOI
  9. Mazurenko, 2019, Machine learning in enzyme engineering, ACS Catal, 10, 1210, 10.1021/acscatal.9b04321 · DOI · Paper page
  10. Diaz, 2023, Using machine learning to predict the effects and consequences of mutations in proteins, Curr Opin Struct Biol, 78, 102518, 10.1016/j.sbi.2022.102518 · DOI · Paper page
  11. Wittmann, 2021, Advances in machine learning for directed evolution, Curr Opin Struct Biol, 69, 11, 10.1016/j.sbi.2021.01.008 · DOI · Paper page
  12. Yang, 2019, Machine-learning-guided directed evolution for protein engineering, Nat Methods, 16, 687, 10.1038/s41592-019-0496-6 · DOI · Paper page
  13. Berman, 2000, The protein data bank, Nucleic Acids Res, 28, 235, 10.1093/nar/28.1.235 · DOI · Paper page
  14. Leman, 2020, Macromolecular modeling and design in Rosetta: recent methods and frameworks, Nat Methods, 17, 665, 10.1038/s41592-020-0848-2 · DOI · Paper page
  15. Qiu, 2023, Persistent spectral theory-guided protein engineering, Nat Comput Sci, 3, 149, 10.1038/s43588-022-00394-y · doi:10.1038/s43588-022-00394-y
  16. Edelsbrunner, 2010, Computational Topology: An Introduction
  17. Nguyen, 2019, DG-GL: differential geometry-based geometric learning of molecular datasets, Int J Numer Methods Biomed Eng, 35, e3179, 10.1002/cnm.3179 · DOI
  18. Wee, 2021, Ollivier persistent Ricci curvature-based machine learning for the protein–ligand binding affinity prediction, J Chem Inf Model, 61, 1617, 10.1021/acs.jcim.0c01415 · DOI · Paper page
  19. Nguyen, 2019, AGL-Score: algebraic graph learning score for protein–ligand binding scoring, ranking, docking, and screening, J Chem Inf Model, 59, 3291, 10.1021/acs.jcim.9b00334 · DOI · Paper page
  20. Ryczko, 2019, Deep learning and density-functional theory, Phys Rev A, 100, 022512, 10.1103/PhysRevA.100.022512 · DOI
  21. Chen, 2021, MLIMC: machine learning-based implicit-solvent Monte Carlo, Chin J Chem Phys, 34, 683, 10.1063/1674-0068/cjcp2109150 · DOI
  22. Hsu, 2022, Learning protein fitness models from evolutionary and assay-labeled data, Nat Biotechnol, 40, 1114, 10.1038/s41587-021-01146-5 · DOI · Paper page
  23. Wittmann, 2021, Informed training set design enables efficient machine learning-assisted directed protein evolution, Cell Syst, 12, 1026, 10.1016/j.cels.2021.07.008 · DOI · Paper page
  24. Shihab, 2013, Predicting the functional, molecular, and phenotypic consequences of amino acid substitutions using hidden Markov models, Hum Mutat, 34, 57, 10.1002/humu.22225 · DOI · Paper page
  25. Rao, 2021, MSA transformer, 8844
  26. Meier, 2021, Language models enable zero-shot prediction of the effects of mutations on protein function, Adv Neural Inf Process Syst, 34
  27. Hsu, 2022, Learning inverse folding from millions of predicted structures, 8946
  28. Orengo, 1997, Cath–a hierarchic classification of protein domain structures, Structure, 5, 1093, 10.1016/S0969-2126(97)00260-8 · DOI · Paper page
  29. Madani, 2023, Large language models generate functional protein sequences across diverse families, Nat Biotechnol, 1
  30. Federhen, 2012, The NCBI Taxonomy database, Nucleic Acids Res, 40, D136, 10.1093/nar/gkr1178 · DOI · Paper page
  31. Hopf, 2019, The EVcouplings Python framework for coevolutionary sequence analysis, Bioinformatics, 35, 1582, 10.1093/bioinformatics/bty862 · DOI · Paper page
  32. Rabiner, 1989, A tutorial on hidden Markov models and selected applications in speech recognition, Proc IEEE, 77, 257, 10.1109/5.18626 · DOI · Paper page
  33. Livesey, 2020, Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations, Mol Syst Biol, 16, e9380, 10.15252/msb.20199380 · DOI · Paper page
  34. Kim, 2014, Convolutional neural networks for sentence classification, 1746, 10.3115/v1/D14-1181 · DOI · Paper page
  35. Vaswani, 2017, Attention is all you need, 5998
  36. Detlefsen, 2022, Learning meaningful representations of protein sequences, Nat Commun, 13, 1914, 10.1038/s41467-022-29443-w · DOI · Paper page
  37. Edelsbrunner, 2008, Persistent homology-a survey, Contemp Math, 453, 257, 10.1090/conm/453/08802 · DOI · Paper page
  38. Cang, 2020, Persistent cohomology for data with multicomponent heterogeneous information, SIAM J Math Data Sci, 2, 396, 10.1137/19M1272226 · DOI
  39. Chowdhury, 2018, Persistent path homology of directed networks, 1152
  40. Lütgehetmann, 2020, Computing persistent homology of directed flag complexes, Algorithms, 13, 19, 10.3390/a13010019 · DOI
  41. Cang, 2020, Evolutionary homology on coupled dynamical systems with applications to protein flexibility analysis, J Appl Comput Topol, 4, 481, 10.1007/s41468-020-00057-9 · DOI
  42. Meng, 2020, Weighted persistent homology for biomolecular data analysis, Sci Rep, 10, 2079, 10.1038/s41598-019-55660-3 · DOI
  43. Wang, 2020, Persistent spectral graph, Int J Numer Methods Biomed Eng, 36, e3376, 10.1002/cnm.3376 · DOI
  44. Mémoli, 2022, Persistent Laplacians: properties, algorithms and implications, SIAM J Math Data Sci, 4, 858, 10.1137/21M1435471 · DOI
  45. Chen, 2021, Evolutionary de Rham-Hodge method, Discrete Continuous Dyn Syst Ser B, 26, 3785, 10.3934/dcdsb.2020257 · DOI
  46. Wang, 2023, Persistent path Laplacian, Found Data Sci, 5, 26, 10.3934/fods.2022015 · DOI
  47. Liu, 2021, Persistent spectral hypergraph based machine learning (PSH-ML) for protein-ligand binding affinity prediction, Brief Bioinform, 22, bbab127, 10.1093/bib/bbab127 · DOI · Paper page
  48. Chen, 2023, Persistent hyperdigraph homology and persistent hyperdigraph Laplacians, 10.3934/fods.2023010 · DOI
  49. Kaczynski, 2004, Computational Homology, 10.1007/b97315 · DOI · Paper page
  50. Wasserman, 2018, Topological data analysis, Annu Rev Stat, 5, 501, 10.1146/annurev-statistics-031017-100045 · DOI · Paper page
  51. Bubenik, 2015, Statistical topological data analysis using persistence landscapes, J Mach Learn Res, 16, 77
  52. Adams, 2017, Persistence images: a stable vector representation of persistent homology, J Mach Learn Res, 18
  53. Clough, 2020, A topological loss function for deep-learning based image segmentation using persistent homology, IEEE Trans Pattern Anal Mach Intell, 44, 8766, 10.1109/TPAMI.2020.3013679 · DOI · Paper page
  54. Pun, 2018, Persistent-homology-based machine learning and its applications–a survey, 10.2139/ssrn.3275996 · DOI
  55. Stolz, 2017, Persistent homology of time-dependent functional networks constructed from coupled time series, Chaos, 27, 047410, 10.1063/1.4978997 · DOI
  56. Chen, 2022, Persistent Laplacian projected Omicron BA.4 and BA.5 to become new dominating variants, Comput Biol Med, 151, 106262, 10.1016/j.compbiomed.2022.106262 · DOI
  57. Meng, 2021, Persistent spectral–based machine learning (PerSpect ML) for protein-ligand binding affinity prediction, Sci Adv, 7, eabc5329, 10.1126/sciadv.abc5329 · DOI · Paper page
  58. Grigor’yan, 2020, Path complexes and their homologies, J Math Sci, 248, 564, 10.1007/s10958-020-04897-9 · DOI
  59. Hansen, 2019, Toward a spectral theory of cellular sheaves, J Appl Comput Topol, 3, 315, 10.1007/s41468-019-00038-7 · DOI
  60. You, 2020, Graph contrastive learning with augmentations, Adv Neural Inf Process Syst, 33, 5812
  61. Rong, 2020, Self-supervised graph transformer on large-scale molecular data, Adv Neural Inf Process Syst, 33, 12559
  62. Li, 2021, Structure-aware interactive graph neural networks for the prediction of protein-ligand binding affinity, 975, 10.1145/3447548.3467311 · DOI · Paper page
  63. Gligorijević, 2021, Structure-based protein function prediction using graph convolutional networks, Nat Commun, 12, 3168, 10.1038/s41467-021-23303-9 · DOI · Paper page
  64. Ingraham, 2019, Generative models for graph-based protein design, Adv Neural Inf Process Syst, 32
  65. Morris, 2019, Weisfeiler and Leman go neural: higher-order graph neural networks, 4602
  66. Wu, 2016, Adaptation in protein fitness landscapes is facilitated by indirect paths, Elife, 5, e16965, 10.7554/eLife.16965 · DOI · Paper page
  67. Podgornaia, 2015, Pervasive degeneracy and epistasis in a protein-protein interface, Science, 347, 673, 10.1126/science.1257360 · DOI · Paper page
  68. Zhang, 2023, Structural insights into the elevator-type transport mechanism of a bacterial ZIP metal transporter, Nat Commun, 14, 385, 10.1038/s41467-023-36048-4 · DOI
  69. Freschlin, 2022, Machine learning to navigate fitness landscapes for protein engineering, Curr Opin Biotechnol, 75, 102713, 10.1016/j.copbio.2022.102713 · DOI · Paper page
  70. Hie, 2022, Adaptive machine learning for protein engineering, Curr Opin Struct Biol, 72, 145, 10.1016/j.sbi.2021.11.002 · DOI · Paper page
  71. Tian, 2023, Sequence vs. structure: delving deep into data driven protein function prediction, bioRxiv
  72. Fox, 2007, Improving catalytic function by ProSAR-driven enzyme evolution, Nat Biotechnol, 25, 338, 10.1038/nbt1286 · DOI · Paper page
  73. Guo, 2008, Using support vector machine combined with auto covariance to predict protein–protein interactions from protein sequences, Nucleic Acids Res, 36, 3025, 10.1093/nar/gkn159 · DOI · Paper page
  74. Cang, 2017, Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology, Bioinformatics, 33, 3549
  75. Aghazadeh, 2021, Epistatic Net allows the sparse spectral regularization of deep neural networks for inferring fitness functions, Nat Commun, 12, 5225, 10.1038/s41467-021-25371-3 · DOI
  76. Dallago, 2021, FLIP: benchmark tasks in fitness landscape inference for proteins, bioRxiv
  77. Bryant, 2021, Deep diversification of an AAV capsid protein by machine learning, Nat Biotechnol, 39, 691, 10.1038/s41587-020-00793-4 · DOI · Paper page
  78. Qiu, 2021, Cluster learning-assisted directed evolution, Nat Comput Sci, 1, 809, 10.1038/s43588-021-00168-y · DOI · Paper page
  79. Qiu, 2022, CLADE 2.0: evolution-driven cluster learning-assisted directed evolution, J Chem Inf Model, 62, 4629, 10.1021/acs.jcim.2c01046 · DOI
  80. Thean, 2022, Machine learning-coupled combinatorial mutagenesis enables resource-efficient engineering of CRISPR-Cas9 genome editor activities, Nat Commun, 13, 2219, 10.1038/s41467-022-29874-5 · DOI
  81. Georgiev, 2009, Interpretable numerical descriptors of amino acid space, J Comput Biol, 16, 703, 10.1089/cmb.2008.0173 · DOI · Paper page
  82. Shen, SVSBI: sequence-based virtual screening of biomolecular interactions, 10.1038/s42003-023-04866-3 · DOI
  83. Luo, 2021, ECNet is an evolutionary context-integrated deep learning framework for protein engineering, Nat Commun, 12, 1, 10.1038/s41467-021-25976-8 · DOI · Paper page
  84. Greenman, 2022, Benchmarking uncertainty quantification for protein engineering
  85. Rasmussen, Carl Edward, 2003, Gaussian processes in machine learning, 63
  86. Bedbrook, 2019, Machine learning-guided channelrhodopsin engineering enables minimally invasive optogenetics, Nat Methods, 16, 1176, 10.1038/s41592-019-0583-8 · DOI · Paper page
  87. Bedbrook, 2017, Machine learning to design integral membrane channelrhodopsins for efficient eukaryotic expression and plasma membrane localization, PLoS Comput Biol, 13, e1005786, 10.1371/journal.pcbi.1005786 · DOI · Paper page
  88. Saito, 2018, Machine-learning-guided mutagenesis for directed evolution of fluorescent proteins, ACS Synth Biol, 7, 2014, 10.1021/acssynbio.8b00155 · DOI · Paper page
  89. Greenhalgh, 2021, Machine learning-guided acyl-ACP reductase engineering for improved in vivo fatty alcohol production, Nat Commun, 12, 5825, 10.1038/s41467-021-25831-w · DOI · Paper page
  90. Romero, 2013, Navigating the protein fitness landscape with gaussian processes, Proc Natl Acad Sci, 110, E193, 10.1073/pnas.1215251110 · DOI · Paper page
  91. Bubeck, 2011, X-armed bandits, J Mach Learn Res, 12
  92. Munos, 2011, Optimistic optimization of a deterministic function without the knowledge of its smoothness, Adv Neural Inf Process Syst, 24, 783
  93. Gupta, 2019, Feedback GAN for DNA optimizes protein functions, Nat Mach Intell, 1, 105, 10.1038/s42256-019-0017-4 · DOI · Paper page
  94. Bachas, 2022, Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness, bioRxiv
  95. Castro, 2022, Transformer-based protein generation with regularized latent space optimization, Nat Mach Intell, 4, 840, 10.1038/s42256-022-00532-1 · DOI
  96. Kandathil, 2023, Machine learning methods for predicting protein structure from single sequences, Curr Opin Struct Biol, 81, 102627, 10.1016/j.sbi.2023.102627 · DOI
  97. Wang, 2022, Single-sequence protein structure prediction using supervised transformer protein language models, Nat Comput Sci, 2, 804, 10.1038/s43588-022-00373-3 · DOI · Paper page
  98. Wu, 2022, High-resolution de novo structure prediction from primary sequence, bioRxiv
  99. Fang, 2022, HelixFold-Single: MSA-free protein structure prediction by using protein language model as an alternative, 10.21203/rs.3.rs-1969991/v1 · DOI · Paper page
  100. Barrett, 2022, So manyfolds, so little time: efficient protein structure prediction with pLMs and MSAs, bioRxiv
  101. Wu, 2022, tFold-Ab: fast and accurate antibody structure prediction without sequence homologs, bioRxiv
  102. Weissenow, 2022, Ultra-fast protein structure prediction to capture effects of sequence variation in mutation movies, bioRxiv
  103. Chidyausiku, 2022, De novo design of immunoglobulin-like domains, Nat Commun, 13, 5661, 10.1038/s41467-022-33004-6 · DOI · Paper page
  104. Keros, 2022, Dist2Cycle: a simplicial neural network for homology localization, 7133
  105. Schuster, 2008, Next-generation sequencing transforms today’s biology, Nat Methods, 5, 16, 10.1038/nmeth1156 · DOI · Paper page

Cited by

Metadata

Authors
Qiu, Y., & Wei, G.-W.
Venue
Briefings in Bioinformatics
Published
2023-08-14
Volume
24
Issue
5
ISSN
  • 1467-5463 (ISSN-L)
  • 1477-4054
OpenAlex
W4385373960
Cited by
88
References
47
FWCI
6.58
Type
journal article
Language
en
Open access
hybrid
Funders
  • National Institutes of Health (R01GM126189, R35GM148196, R01AI164266)
  • National Science Foundation (DMS-2052983, DMS-1761320, IIS-1900473)
  • National Aeronautics and Space Administration (80NSSC21M0023)
  • Michigan Economic Development Corporation
  • MSU Foundation
  • Bristol-Myers Squibb (65109)

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.