Generative power of a protein language model trained on multiple sequence alignments
- 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
Anne-Florence Bitbol
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
- Lucy J Colwell, Cambridge University, United Kingdom
Version history
- Preprint posted: April 15, 2022 (view preprint)
- Received: April 28, 2022
- Accepted: February 2, 2023
- Accepted Manuscript published: February 3, 2023 (version 1)
- 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
-
- 4,949
- views
-
- 650
- downloads
-
- 14
- 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)
Generative power of a protein language model trained on multiple sequence alignments
eLife 12:e79854.
https://doi.org/10.7554/eLife.79854
Further reading
-
- Computational and Systems Biology
- Medicine
Background:
Preterm birth is the leading cause of neonatal morbidity and mortality worldwide. Most cases of preterm birth occur spontaneously and result from preterm labor with intact (spontaneous preterm labor [sPTL]) or ruptured (preterm prelabor rupture of membranes [PPROM]) membranes. The prediction of spontaneous preterm birth (sPTB) remains underpowered due to its syndromic nature and the dearth of independent analyses of the vaginal host immune response. Thus, we conducted the largest longitudinal investigation targeting vaginal immune mediators, referred to herein as the immunoproteome, in a population at high risk for sPTB.
Methods:
Vaginal swabs were collected across gestation from pregnant women who ultimately underwent term birth, sPTL, or PPROM. Cytokines, chemokines, growth factors, and antimicrobial peptides in the samples were quantified via specific and sensitive immunoassays. Predictive models were constructed from immune mediator concentrations.
Results:
Throughout uncomplicated gestation, the vaginal immunoproteome harbors a cytokine network with a homeostatic profile. Yet, the vaginal immunoproteome is skewed toward a pro-inflammatory state in pregnant women who ultimately experience sPTL and PPROM. Such an inflammatory profile includes increased monocyte chemoattractants, cytokines indicative of macrophage and T-cell activation, and reduced antimicrobial proteins/peptides. The vaginal immunoproteome has improved predictive value over maternal characteristics alone for identifying women at risk for early (<34 weeks) sPTB.
Conclusions:
The vaginal immunoproteome undergoes homeostatic changes throughout gestation and deviations from this shift are associated with sPTB. Furthermore, the vaginal immunoproteome can be leveraged as a potential biomarker for early sPTB, a subset of sPTB associated with extremely adverse neonatal outcomes.
Funding:
This research was conducted by the Perinatology Research Branch, Division of Obstetrics and Maternal-Fetal Medicine, Division of Intramural Research, Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Institutes of Health, U.S. Department of Health and Human Services (NICHD/NIH/DHHS) under contract HHSN275201300006C. ALT, KRT, and NGL were supported by the Wayne State University Perinatal Initiative in Maternal, Perinatal and Child Health.
-
- Computational and Systems Biology
- Genetics and Genomics
Runs of homozygosity (ROH) segments, contiguous homozygous regions in a genome were traditionally linked to families and inbred populations. However, a growing literature suggests that ROHs are ubiquitous in outbred populations. Still, most existing genetic studies of ROH in populations are limited to aggregated ROH content across the genome, which does not offer the resolution for mapping causal loci. This limitation is mainly due to a lack of methods for the efficient identification of shared ROH diplotypes. Here, we present a new method, ROH-DICE, to find large ROH diplotype clusters, sufficiently long ROHs shared by a sufficient number of individuals, in large cohorts. ROH-DICE identified over 1 million ROH diplotypes that span over 100 SNPs and are shared by more than 100 UK Biobank participants. Moreover, we found significant associations of clustered ROH diplotypes across the genome with various self-reported diseases, with the strongest associations found between the extended HLA region and autoimmune disorders. We found an association between a diplotype covering the HFE gene and hemochromatosis, even though the well-known causal SNP was not directly genotyped or imputed. Using a genome-wide scan, we identified a putative association between carriers of an ROH diplotype in chromosome 4 and an increase in mortality among COVID-19 patients (P-value=1.82×10-11). In summary, our ROH-DICE method, by calling out large ROH diplotypes in a large outbred population, enables further population genetics into the demographic history of large populations. More importantly, our method enables a new genome-wide mapping approach for finding disease-causing loci with multi-marker recessive effects at a population scale.
