IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v13y2022i1d10.1038_s41467-022-29443-w.html
   My bibliography  Save this article

Learning meaningful representations of protein sequences

Author

Listed:
  • Nicki Skafte Detlefsen

    (Technical University of Denmark)

  • Søren Hauberg

    (Technical University of Denmark)

  • Wouter Boomsma

    (University of Copenhagen)

Abstract

How we choose to represent our data has a fundamental impact on our ability to subsequently extract information from them. Machine learning promises to automatically determine efficient representations from large unstructured datasets, such as those arising in biology. However, empirical evidence suggests that seemingly minor changes to these machine learning models yield drastically different data representations that result in different biological interpretations of data. This begs the question of what even constitutes the most meaningful representation. Here, we approach this question for representations of protein sequences, which have received considerable attention in the recent literature. We explore two key contexts in which representations naturally arise: transfer learning and interpretable learning. In the first context, we demonstrate that several contemporary practices yield suboptimal performance, and in the latter we demonstrate that taking representation geometry into account significantly improves interpretability and lets the models reveal biological information that is otherwise obscured.

Suggested Citation

  • Nicki Skafte Detlefsen & Søren Hauberg & Wouter Boomsma, 2022. "Learning meaningful representations of protein sequences," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
  • Handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-29443-w
    DOI: 10.1038/s41467-022-29443-w
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-022-29443-w
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-022-29443-w?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Jonathan Frazer & Pascal Notin & Mafalda Dias & Aidan Gomez & Joseph K. Min & Kelly Brock & Yarin Gal & Debora S. Marks, 2021. "Disease variant prediction with deep generative models of evolutionary data," Nature, Nature, vol. 599(7883), pages 91-95, November.
    2. Jung-Eun Shin & Adam J. Riesselman & Aaron W. Kollasch & Conor McMahon & Elana Simon & Chris Sander & Aashish Manglik & Andrew C. Kruse & Debora S. Marks, 2021. "Protein design and variant prediction using autoregressive generative models," Nature Communications, Nature, vol. 12(1), pages 1-11, December.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Allen Y. Leary & Darius Scott & Namita T. Gupta & Janelle C. Waite & Dimitris Skokos & Gurinder S. Atwal & Peter G. Hawkins, 2024. "Designing meaningful continuous representations of T cell receptor sequences with deep generative models," Nature Communications, Nature, vol. 15(1), pages 1-14, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Fatma-Elzahraa Eid & Albert T. Chen & Ken Y. Chan & Qin Huang & Qingxia Zheng & Isabelle G. Tobey & Simon Pacouret & Pamela P. Brauer & Casey Keyes & Megan Powell & Jencilin Johnston & Binhui Zhao & K, 2024. "Systematic multi-trait AAV capsid engineering for efficient gene delivery," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    2. Wenkai Han & Ningning Chen & Xinzhou Xu & Adil Sahil & Juexiao Zhou & Zhongxiao Li & Huawen Zhong & Elva Gao & Ruochi Zhang & Yu Wang & Shiwei Sun & Peter Pak-Hang Cheung & Xin Gao, 2023. "Predicting the antigenic evolution of SARS-COV-2 with deep learning," Nature Communications, Nature, vol. 14(1), pages 1-14, December.
    3. Guoling Li & Xue Dong & Jiamin Luo & Tanglong Yuan & Tong Li & Guoli Zhao & Hainan Zhang & Jingxing Zhou & Zhenhai Zeng & Shuna Cui & Haoqiang Wang & Yin Wang & Yuyang Yu & Yuan Yuan & Erwei Zuo & Chu, 2024. "Engineering TadA ortholog-derived cytosine base editor without motif preference and adenosine activity limitation," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    4. Mireia Seuma & Ben Lehner & Benedetta Bolognesi, 2022. "An atlas of amyloid aggregation: the impact of substitutions, insertions, deletions and truncations on amyloid beta fibril nucleation," Nature Communications, Nature, vol. 13(1), pages 1-13, December.
    5. Ziyi Zhou & Liang Zhang & Yuanxi Yu & Banghao Wu & Mingchen Li & Liang Hong & Pan Tan, 2024. "Enhancing efficiency of protein language models with minimal wet-lab data through few-shot learning," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    6. Lasse M. Blaabjerg & Nicolas Jonsson & Wouter Boomsma & Amelie Stein & Kresten Lindorff-Larsen, 2024. "SSEmb: A joint embedding of protein sequence and structure enables robust variant effect predictions," Nature Communications, Nature, vol. 15(1), pages 1-9, December.
    7. Yaan J. Jang & Qi-Qi Qin & Si-Yu Huang & Arun T. John Peter & Xue-Ming Ding & Benoît Kornmann, 2024. "Accurate prediction of protein function using statistics-informed graph networks," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    8. Christian M. Boßelmann & Costin Leu & Tobias Brünger & Lucas Hoffmann & Sara Baldassari & Mathilde Chipaux & Roland Coras & Katja Kobow & Hajo Hamer & Daniel Delev & Karl Rössler & Christian G. Bien &, 2024. "Analysis of 1386 epileptogenic brain lesions reveals association with DYRK1A and EGFR," Nature Communications, Nature, vol. 15(1), pages 1-10, December.
    9. Kevin E. Wu & Kevin K. Yang & Rianne Berg & Sarah Alamdari & James Y. Zou & Alex X. Lu & Ava P. Amini, 2024. "Protein structure generation via folding diffusion," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    10. Han Meng & Nengxiong Xu & Yunfu Zhu & Gang Mei, 2024. "Generating Stochastic Structural Planes Using Statistical Models and Generative Deep Learning Models: A Comparative Investigation," Mathematics, MDPI, vol. 12(16), pages 1-37, August.
    11. Jeffrey A. Ruffolo & Lee-Shin Chu & Sai Pooja Mahajan & Jeffrey J. Gray, 2023. "Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    12. Lin Li & Esther Gupta & John Spaeth & Leslie Shing & Rafael Jaimes & Emily Engelhart & Randolph Lopez & Rajmonda S. Caceres & Tristan Bepler & Matthew E. Walsh, 2023. "Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    13. Ertunc Erdil & Anton S. Becker & Moritz Schwyzer & Borja Martinez-Tellez & Jonatan R. Ruiz & Thomas Sartoretti & H. Alberto Vargas & A. Irene Burger & Alin Chirindel & Damian Wild & Nicola Zamboni & B, 2024. "Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    14. Evgenii Lobzaev & Michael A. Herrera & Martyna Kasprzyk & Giovanni Stracquadanio, 2024. "Protein engineering using variational free energy approximation," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    15. Evgenii Lobzaev & Giovanni Stracquadanio, 2024. "Dirichlet latent modelling enables effective learning and sampling of the functional protein design space," Nature Communications, Nature, vol. 15(1), pages 1-11, December.
    16. Mischan Vali-Pour & Solip Park & Jose Espinosa-Carrasco & Daniel Ortiz-Martínez & Ben Lehner & Fran Supek, 2022. "The impact of rare germline variants on human somatic mutation processes," Nature Communications, Nature, vol. 13(1), pages 1-21, December.
    17. Daniel J. Diaz & Chengyue Gong & Jeffrey Ouyang-Zhang & James M. Loy & Jordan Wells & David Yang & Andrew D. Ellington & Alexandros G. Dimakis & Adam R. Klivans, 2024. "Stability Oracle: a structure-based graph-transformer framework for identifying stabilizing mutations," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    18. Henry Webel & Lili Niu & Annelaura Bach Nielsen & Marie Locard-Paulet & Matthias Mann & Lars Juhl Jensen & Simon Rasmussen, 2024. "Imputation of label-free quantitative mass spectrometry-based proteomics data using self-supervised deep learning," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    19. Kian Hong Kock & Patrick K. Kimes & Stephen S. Gisselbrecht & Sachi Inukai & Sabrina K. Phanor & James T. Anderson & Gayatri Ramakrishnan & Colin H. Lipper & Dongyuan Song & Jesse V. Kurland & Julia M, 2024. "DNA binding analysis of rare variants in homeodomains reveals homeodomain specificity-determining residues," Nature Communications, Nature, vol. 15(1), pages 1-19, December.
    20. Karol Buda & Charlotte M. Miton & Nobuhiko Tokuriki, 2023. "Pervasive epistasis exposes intramolecular networks in adaptive enzyme evolution," Nature Communications, Nature, vol. 14(1), pages 1-12, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:13:y:2022:i:1:d:10.1038_s41467-022-29443-w. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.