Generative power of a protein language model trained on multiple sequence alignments

  1. Damiano Sgarbossa
  2. Umberto Lupo  Is a corresponding author
  3. Anne-Florence Bitbol  Is a corresponding author
  1. Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland

Abstract

Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families and learn constraints associated to protein structure and function. They thus open the possibility for generating novel sequences belonging to protein families. Protein language models trained on multiple sequence alignments, such as MSA Transformer, are highly attractive candidates to this end. We propose and test an iterative method that directly employs the masked language modeling objective to generate sequences using MSA Transformer. We demonstrate that the resulting sequences score as well as natural sequences, for homology, coevolution and structure-based measures. For large protein families, our synthetic sequences have similar or better properties compared to sequences generated by Potts models, including experimentally-validated ones. Moreover, for small protein families, our generation method based on MSA Transformer outperforms Potts models. Our method also more accurately reproduces the higher-order statistics and the distribution of sequences in sequence space of natural data than Potts models. MSA Transformer is thus a strong candidate for protein sequence generation and protein design.

Data availability

Python code for generating sequences using the iterative masking procedure is available in our GitHub repository: https://github.com/Bitbol-Lab/Iterative_masking.Raw data was collected from two public sources: 1) MSAs from the Pfam database (https://pfam.xfam.org/); 2) further MSAs from https://github.com/matteofigliuzzi/bmDCA. We generated sequences with bmDCA using code publicly available at https://github.com/ranganathanlab/bmDCA.

Article and author information

Author details

  1. Damiano Sgarbossa

    Institute of Bioengineering, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-7878-6061
  2. Umberto Lupo

    Institute of Bioengineering, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
    For correspondence
    umberto.lupo@epfl.ch
    Competing interests
    The authors declare that no competing interests exist.
  3. Anne-Florence Bitbol

    Institute of Bioengineering, Ecole Polytechnique Federale de Lausanne (EPFL), Lausanne, Switzerland
    For correspondence
    anne-florence.bitbol@epfl.ch
    Competing interests
    The authors declare that no competing interests exist.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-1020-494X

Funding

European Research Council (851173)

  • Damiano Sgarbossa
  • Umberto Lupo
  • Anne-Florence Bitbol

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Reviewing Editor

  1. Lucy J Colwell, Cambridge University, United Kingdom

Version history

  1. Preprint posted: April 15, 2022 (view preprint)
  2. Received: April 28, 2022
  3. Accepted: February 2, 2023
  4. Accepted Manuscript published: February 3, 2023 (version 1)
  5. Version of Record published: March 24, 2023 (version 2)

Copyright

© 2023, Sgarbossa et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 4,691
    views
  • 622
    downloads
  • 10
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Damiano Sgarbossa
  2. Umberto Lupo
  3. Anne-Florence Bitbol
(2023)
Generative power of a protein language model trained on multiple sequence alignments
eLife 12:e79854.
https://doi.org/10.7554/eLife.79854

Share this article

https://doi.org/10.7554/eLife.79854

Further reading

    1. Computational and Systems Biology
    2. Evolutionary Biology
    Ryan T Bell, Harutyun Sahakyan ... Eugene V Koonin
    Research Article

    A comprehensive census of McrBC systems, among the most common forms of prokaryotic Type IV restriction systems, followed by phylogenetic analysis, reveals their enormous abundance in diverse prokaryotes and a plethora of genomic associations. We focus on a previously uncharacterized branch, which we denote coiled-coil nuclease tandems (CoCoNuTs) for their salient features: the presence of extensive coiled-coil structures and tandem nucleases. The CoCoNuTs alone show extraordinary variety, with three distinct types and multiple subtypes. All CoCoNuTs contain domains predicted to interact with translation system components, such as OB-folds resembling the SmpB protein that binds bacterial transfer-messenger RNA (tmRNA), YTH-like domains that might recognize methylated tmRNA, tRNA, or rRNA, and RNA-binding Hsp70 chaperone homologs, along with RNases, such as HEPN domains, all suggesting that the CoCoNuTs target RNA. Many CoCoNuTs might additionally target DNA, via McrC nuclease homologs. Additional restriction systems, such as Type I RM, BREX, and Druantia Type III, are frequently encoded in the same predicted superoperons. In many of these superoperons, CoCoNuTs are likely regulated by cyclic nucleotides, possibly, RNA fragments with cyclic termini, that bind associated CARF (CRISPR-Associated Rossmann Fold) domains. We hypothesize that the CoCoNuTs, together with the ancillary restriction factors, employ an echeloned defense strategy analogous to that of Type III CRISPR-Cas systems, in which an immune response eliminating virus DNA and/or RNA is launched first, but then, if it fails, an abortive infection response leading to PCD/dormancy via host RNA cleavage takes over.

    1. Computational and Systems Biology
    Skander Kazdaghli, Iordanis Kerenidis ... Philip Teare
    Research Article

    Imputing data is a critical issue for machine learning practitioners, including in the life sciences domain, where missing clinical data is a typical situation and the reliability of the imputation is of great importance. Currently, there is no canonical approach for imputation of clinical data and widely used algorithms introduce variance in the downstream classification. Here we propose novel imputation methods based on determinantal point processes (DPP) that enhance popular techniques such as the multivariate imputation by chained equations and MissForest. Their advantages are twofold: improving the quality of the imputed data demonstrated by increased accuracy of the downstream classification and providing deterministic and reliable imputations that remove the variance from the classification results. We experimentally demonstrate the advantages of our methods by performing extensive imputations on synthetic and real clinical data. We also perform quantum hardware experiments by applying the quantum circuits for DPP sampling since such quantum algorithms provide a computational advantage with respect to classical ones. We demonstrate competitive results with up to 10 qubits for small-scale imputation tasks on a state-of-the-art IBM quantum processor. Our classical and quantum methods improve the effectiveness and robustness of clinical data prediction modeling by providing better and more reliable data imputations. These improvements can add significant value in settings demanding high precision, such as in pharmaceutical drug trials where our approach can provide higher confidence in the predictions made.