The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Generating functional protein variants with variational autoencoders
Open accessPublished version of a preprint
Abstract
The vast expansion of protein sequence databases provides an opportunity for new protein design approaches which seek to learn the sequence-function relationship directly from natural sequence variation. Deep generative models trained on protein sequence data have been shown to learn biologically meaningful representations helpful for a variety of downstream tasks, but their potential for direct use in the design of novel proteins remains largely unexplored. Here we show that variational autoencoders trained on a dataset of almost 70000 luciferase-like oxidoreductases can be used to generate novel, functional variants of the luxA bacterial luciferase. We propose separate VAE models to work with aligned sequence input (MSA VAE) and raw sequence input (AR-VAE), and offer evidence that while both are able to reproduce patterns of amino acid usage characteristic of the family, the MSA VAE is better able to capture long-distance dependencies reflecting the influence of 3D structure. To confirm the practical utility of the models, we used them to generate variants of luxA whose luminescence activity was validated experimentally. We further showed that conditional variants of both models could be used to increase the solubility of luxA without disrupting function. Altogether 6/12 of the variants generated using the unconditional AR-VAE and 9/11 generated using the unconditional MSA VAE retained measurable luminescence, together with all 23 of the less distant variants generated by conditional versions of the models; the most distant functional variant contained 35 differences relative to the nearest training set sequence. These results demonstrate the feasibility of using deep generative models to explore the space of possible protein sequences and generate useful variants, providing a method complementary to rational design and directed evolution approaches.
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
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911
MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets
Steinegger, M., & Söding, J. (2017) · Nature Biotechnology · doi:10.1038/nbt.3988 · Cited by 4,840
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016239118 · Cited by 3,286
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2019) · doi:10.1101/622803 · Cited by 3,280 · cited 3×
“76 Deep sequence models such as LSTMs and transformers trained on datasets spanning the entire 77 range of known sequences have been shown to learn representations which distill structural and 78 functional information from the sequence [30, 31].”
BackgroundAutomatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
Gómez-Bombarelli, R., Wei, J. N., Duvenaud, D., Hernández-Lobato, J. M., Sánchez-Lengeling, B., Sheberla, D., Aguilera-Iparraguirre, J., Hirzel, T. D., Adams, R. P., & Aspuru-Guzik, A. (2018) · ACS Central Science · doi:10.1021/acscentsci.7b00572 · Cited by 3,106
Generating Sentences from a Continuous Space
Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R., & Bengio, S. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1002 · Cited by 2,061
The coming of age of de novo protein design
Huang, P.-S., Boyken, S. E., & Baker, D. (2016) · Nature · doi:10.1038/nature19946 · Cited by 1,478
Protein 3D Structure Computed from Evolutionary Sequence Variation
Marks, D. S., Colwell, L. J., Sheridan, R., Hopf, T. A., Pagnani, A., Zecchina, R., & Sander, C. (2011) · PLoS ONE · doi:10.1371/journal.pone.0028766 · Cited by 1,144
Unified rational protein engineering with sequence-based deep representation learning
Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M., & Church, G. M. (2019) · Nature Methods · doi:10.1038/s41592-019-0598-1 · Cited by 1,131
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
Wang, S., Sun, S., Li, Z., Zhang, R., & Xu, J. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005324 · Cited by 931
Research works printed but not linked: 52
- MS Packer, 2015, Methods for the directed evolution of proteins, Nature Reviews Genetics, 16, 379, 10.1038/nrg3927 · DOI · Paper page
- FH Arnold, 2018, Directed Evolution: Bringing New Chemistry to Life, Angewandte Chemie International Edition, 57, 4143, 10.1002/anie.201708408 · DOI · Paper page
- GJ Rocklin, 2017, Global analysis of protein folding using massively parallel design, synthesis, and testing, Science, 357, 168, 10.1126/science.aan0693 · DOI · Paper page
- BI Dahiyat, 1997, De Novo Protein Design: Fully Automated Sequence Selection, Science, 278, 82, 10.1126/science.278.5335.82 · DOI · Paper page
- CM Kraemer-Pecore, 2003, A de novo redesign of the WW domain, Protein Science, 12, 2194, 10.1110/ps.03190903 · DOI
- WP Russ, 2005, Natural-like function in artificial WW domains, Nature, 437, 579, 10.1038/nature03990 · DOI · Paper page
- PB Harbury, 1998, High-Resolution Protein Design with Backbone Freedom, Science, 282, 1462, 10.1126/science.282.5393.1462 · DOI · Paper page
- B Kuhlman, 2003, Design of a Novel Globular Protein Fold with Atomic-Level Accuracy, Science, 302, 1364, 10.1126/science.1089427 · DOI · Paper page
- IJ Goodfellow, 2017, NIPS 2016 Tutorial: Generative Adversarial Networks, CoRR
- Kingma DP, Welling M. Auto-Encoding Variational Bayes. In: Bengio Y, LeCun Y, editors. 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings; 2014. Available from: http://arxiv.org/abs/1312.6114. · arXiv
- Rezende DJ, Mohamed S, Wierstra D. Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In: ICML. vol. 32 of JMLR Workshop and Conference Proceedings. JMLR.org; 2014. p. 1278–1286. Available from: http://proceedings.mlr.press/v32/rezende14.html.
- Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative Adversarial Nets. In: Ghahramani Z, Welling M, Cortes C, Lawrence ND, Weinberger KQ, editors. Advances in Neural Information Processing Systems 27. Curran Associates, Inc.; 2014. p. 2672–2680. Available from: http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf.
- Y Bengio, 2003, A Neural Probabilistic Language Model, Journal of Machine Learning Research, 3, 1137
- Oord Avd, Kalchbrenner N, Kavukcuoglu K. Pixel Recurrent Neural Networks. In: Balcan MF, Weinberger KQ, editors. Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016. vol. 48 of JMLR Workshop and Conference Proceedings. JMLR.org; 2016. p. 1747–1756. Available from: http://proceedings.mlr.press/v48/oord16.html.
- M Spencer, 2015, A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 12, 103, 10.1109/TCBB.2014.2343960 · DOI · Paper page
- S Wang, 2016, Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields, Scientific Reports, 6, 18962, 10.1038/srep18962 · DOI · Paper page
- AJ Riesselman, 2018, Deep generative models of genetic variation capture the effects of mutations, Nature Methods, 15, 816, 10.1038/s41592-018-0138-4 · DOI · Paper page
- J Tubiana, 2019, Learning protein constitutive motifs from sequence data, eLife, 8, e39397, 10.7554/eLife.39397 · DOI
- Das P, Wadhawan K, Chang O, Sercu T, Santos CD, Riemer M, et al. PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences. arXiv:181007743 [cs, q-bio, stat]. 2018;.
- JG Greener, 2018, Design of metalloproteins and novel protein folds using variational autoencoders, Scientific Reports, 8, 16189, 10.1038/s41598-018-34533-1 · DOI
- J Ingraham, 2019, Advances in Neural Information Processing Systems, 15820
- A Riesselman, 2019, Accelerating Protein Design Using Autoregressive Generative Models, bioRxiv, 757252
- A Madani, 2020, ProGen: Language Modeling for Protein Generation, bioRxiv
- A Strokach, 2020, Fast and Flexible Protein Design Using Deep Graph Neural Networks, Cell Systems, 11, 402, 10.1016/j.cels.2020.08.016 · DOI · Paper page
- S Cocco, 2018, Inverse Statistical Physics of Protein Sequences: A Key Issues Review, Reports on Progress in Physics, 81, 032601, 10.1088/1361-6633/aa9965 · DOI · Paper page
- M Lehmann, 2000, From DNA sequence to improved functionality: using protein sequence comparisons to rapidly design a thermostable consensus phytase, Protein Engineering, Design and Selection, 13, 49, 10.1093/protein/13.1.49 · DOI · Paper page
- M Socolich, 2005, Evolutionary information for specifying a protein fold, Nature, 437, 512, 10.1038/nature03991 · DOI · Paper page
- F Sievers, 2018, Clustal Omega for making accurate alignments of many protein sequences, Protein Science, 27, 135, 10.1002/pro.3290 · DOI · Paper page
- Brookes D, Park H, Listgarten J. Conditioning by adaptive sampling for robust design. In: ICML; 2019. p. 773–782. Available from: http://proceedings.mlr.press/v97/brookes19a.html.
- S Hunter, 2009, InterPro: the integrative protein signature database, Nucleic Acids Research, 37, D211, 10.1093/nar/gkn785 · DOI · Paper page
- Sinai S, Kelsic E, Church GM, Nowak MA. Variational auto-encoding of protein sequences. arXiv:171203346 [cs, q-bio]. 2018;.
- RD Finn, 2014, Pfam: the protein families database, Nucleic Acids Research, 42, D222, 10.1093/nar/gkt1223 · DOI · Paper page
- Gulrajani I, Kumar K, Ahmed F, Taïga AA, Visin F, Vázquez D, et al. PixelVAE: A Latent Variable Model for Natural Images. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net; 2017. Available from: https://openreview.net/forum?id=BJKYvt5lg.
- Semeniuta S, Severyn A, Barth E. A Hybrid Convolutional Variational Autoencoder for Text Generation. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark: Association for Computational Linguistics; 2017. p. 627–637. Available from: https://www.aclweb.org/anthology/D17-1066. · DOI · Paper page
- WR Taylor, 1986, The classification of amino acid conservation, Journal of Theoretical Biology, 119, 205, 10.1016/S0022-5193(86)80075-3 · DOI · Paper page
- R Durbin, 1998, Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids, 10.1017/CBO9780511790492 · DOI · Paper page
- DT Jones, 2012, PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments, Bioinformatics, 28, 184, 10.1093/bioinformatics/btr638 · DOI · Paper page
- S Seemayer, 2014, CCMpred–fast and precise prediction of protein residue-residue contacts from correlated mutations, Bioinformatics (Oxford, England), 30, 3128, 10.1093/bioinformatics/btu500 · DOI · Paper page
- M Figliuzzi, 2018, How Pairwise Coevolutionary Models Capture the Collective Residue Variability in Proteins?, Molecular Biology and Evolution, 35, 1018, 10.1093/molbev/msy007 · DOI
- ZT Campbell, 2009, Crystal structure of the bacterial luciferase/flavin complex provides insight into the function of the beta subunit, Biochemistry, 48, 6085, 10.1021/bi900003t · DOI
- W Wang, 1999, Instability, stabilization, and formulation of liquid protein pharmaceuticals, International Journal of Pharmaceutics, 185, 129, 10.1016/S0378-5173(99)00152-0 · DOI · Paper page
- JD Pédelacq, 2002, Engineering soluble proteins for structural genomics, Nature Biotechnology, 20, 927, 10.1038/nbt732 · DOI · Paper page
- M Hebditch, 2017, Protein–Sol: a web tool for predicting protein solubility from sequence, Bioinformatics, 33, 3098, 10.1093/bioinformatics/btx345 · DOI · Paper page
- M Figliuzzi, 2016, Coevolutionary Landscape Inference and the Context-Dependence of Mutations in Beta-Lactamase TEM-1, Molecular Biology and Evolution, 33, 268, 10.1093/molbev/msv211 · DOI · Paper page
- S Vorberg, 2018, Synthetic protein alignments by CCMgen quantify noise in residue-residue contact prediction, PLOS Computational Biology, 14, e1006526, 10.1371/journal.pcbi.1006526 · DOI
- Elnaggar A, Heinzinger M, Dallago C, Rihawi G, Wang Y, Jones L, et al. ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing. arXiv:200706225 [cs, stat]. 2020;. · DOI · Paper page
- KK Yang, 2019, Machine-learning-guided directed evolution for protein engineering, Nature Methods, 16, 687, 10.1038/s41592-019-0496-6 · DOI · Paper page
- Kingma DP, Mohamed S, Jimenez Rezende D, Welling M. Semi-supervised Learning with Deep Generative Models. In: Advances in Neural Information Processing Systems. vol. 27; 2014. p. 3581–3589. Available from: https://proceedings.neurips.cc/paper/2014/hash/d523773c6b194f37b938d340d5d02232-Abstract.html.
- TA Hopf, 2019, The EVcouplings Python framework for coevolutionary sequence analysis, Bioinformatics, 35, 1582, 10.1093/bioinformatics/bty862 · DOI · Paper page
- A Chastanet, 2003, Comparative genomics reveal novel heat shock regulatory mechanisms in Staphylococcus aureus and other Gram-positive bacteria, Molecular Microbiology, 47, 1061, 10.1046/j.1365-2958.2003.03355.x · DOI
- DG Gibson, 2009, Enzymatic assembly of DNA molecules up to several hundred kilobases, Nature Methods, 6, 343, 10.1038/nmeth.1318 · DOI · Paper page
- KJ Rhee, 2011, Determination of spatial and temporal colonization of enteropathogenic E. coli and enterohemorrhagic E. coli in mice using bioluminescent in vivo imaging, Gut Microbes, 2, 34, 10.4161/gmic.2.1.14882 · DOI
Cited by
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2016239118 · Cited by 3,286
De novo protein design by deep network hallucination
Anishchenko, I., Chidyausiku, T. M., Ovchinnikov, S., Pellock, S. J., & Baker, D. (2020) · doi:10.1101/2020.07.22.211482 · Cited by 629
Rives, A., Meier, J., Sercu, T., Goyal, S., Lin, Z., Liu, J., Guo, D., Ott, M., Zitnick, C. L., Ma, J., et al. (2019) · doi:10.1101/622803 · Cited by 3,280
Utilizing graph machine learning within drug discovery and development
Gaudelet, T., Day, B., Jamasb, A. R., Soman, J., Regep, C., Liu, G., Hayter, J. B. R., Vickers, R., Roberts, C., Tang, J., et al. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab159 · Cited by 313
Machine learning for functional protein design
Notin, P., Rollins, N., Gal, Y., Sander, C., & Marks, D. (2024) · Nature Biotechnology · doi:10.1038/s41587-024-02127-0 · Cited by 270
Metadata
- Authors
- Hawkins-Hooker, A., Depardieu, F., Baur, S., Couairon, G., Chen, A., & Bikard, D.
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2021-02-26
- Volume
- 17
- Issue
- 2
- Pages
- e1008736
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- OpenAlex
- W3132323068
- Cited by
- 209
- References
- 17
- FWCI
- 9.39
- Type
- journal article
- Language
- en
- Update notices
- new_version (2021-03-10)
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Generating functional protein variants with variational autoencoders. https://app.cochat.ai/papers/10.1371/journal.pcbi.1008736
- The paper
- Hawkins-Hooker, A., Depardieu, F., Baur, S., Couairon, G., Chen, A., & Bikard, D. (2021). Generating functional protein variants with variational autoencoders. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1008736
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.