Learning protein constitutive motifs from sequence data
- École Normale Supérieure, France
Abstract
Statistical analysis of evolutionary-related protein sequences provides insights about their structure, function, and history. We show that Restricted Boltzmann Machines (RBM), designed to learn complex high-dimensional data and their statistical features, can efficiently model protein families from sequence information. We here apply RBM to twenty protein families, and present detailed results for two short protein domains, Kunitz and WW, one long chaperone protein, Hsp70, and synthetic lattice proteins for benchmarking. The features inferred by the RBM are biologically interpretable: they are related to structure (such as residue-residue tertiary contacts, extended secondary motifs (α-helix and β-sheet) and intrinsically disordered regions), to function (such as activity and ligand specificity), or to phylogenetic identity. In addition, we use RBM to design new protein sequences with putative properties by composing and turning up or down the different modes at will. Our work therefore shows that RBM are a versatile and practical tool to unveil and exploit the genotype-phenotype relationship for protein families.
Data availability
The Python 2.7 package for training and visualizing RBMs, used to obtained the results reported in this work, is available at https://github.com/jertubiana/ProteinMotifRBM. It can be readily used for any protein family. Moreover, all four multiple sequence alignments presented in the text, as well as the code for reproducing each panel are also included. Jupyter notebooks are provided for reproducing most figures of the article.
-
THE 1.2 ANGSTROM STRUCTURE OF KUNITZ TYPE DOMAIN C5Protein Data Bank, 2KNT.
-
Crystal Structure of the Nanog HomeodomainProtein Data Bank, 2VI6.
-
CRYSTAL STRUCTURE OF SH2 IN COMPLEX WITH RU82209Protein Data Bank, 1O47.
-
The crystal structure of Sod2 from Saccharomyces cerevisiaeProtein Data Bank, 3BFR.
-
Crystal Structure of domain 3 of human alpha polyC binding proteinProtein Data Bank, 1WVN.
-
Crystal Structure Analysis of human E-cadherin (1-213)Protein Data Bank, 2O72.
Article and author information
Author details
Funding
Centre National de la Recherche Scientifique
- Jérôme Tubiana
- Simona Cocco
- Rémi Monasson
Ecole Normale Supérieure (Allocation Specifique)
- Jérôme Tubiana
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
- Received: October 3, 2018
- Accepted: February 24, 2019
- Accepted Manuscript published: March 12, 2019 (version 1)
- Version of Record published: March 27, 2019 (version 2)
Copyright
© 2019, Tubiana 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
-
- 7,004
- views
-
- 1,212
- downloads
-
- 65
- 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)
Learning protein constitutive motifs from sequence data
eLife 8:e39397.
https://doi.org/10.7554/eLife.39397
Further reading
-
- Computational and Systems Biology
Revealing protein binding sites with other molecules, such as nucleic acids, peptides, or small ligands, sheds light on disease mechanism elucidation and novel drug design. With the explosive growth of proteins in sequence databases, how to accurately and efficiently identify these binding sites from sequences becomes essential. However, current methods mostly rely on expensive multiple sequence alignments or experimental protein structures, limiting their genome-scale applications. Besides, these methods haven’t fully explored the geometry of the protein structures. Here, we propose GPSite, a multi-task network for simultaneously predicting binding residues of DNA, RNA, peptide, protein, ATP, HEM, and metal ions on proteins. GPSite was trained on informative sequence embeddings and predicted structures from protein language models, while comprehensively extracting residual and relational geometric contexts in an end-to-end manner. Experiments demonstrate that GPSite substantially surpasses state-of-the-art sequence-based and structure-based approaches on various benchmark datasets, even when the structures are not well-predicted. The low computational cost of GPSite enables rapid genome-scale binding residue annotations for over 568,000 sequences, providing opportunities to unveil unexplored associations of binding sites with molecular functions, biological processes, and genetic variants. The GPSite webserver and annotation database can be freely accessed at https://bio-web1.nscc-gz.cn/app/GPSite.
-
- Cell Biology
- Computational and Systems Biology
Computer models of the human ventricular cardiomyocyte action potential (AP) have reached a level of detail and maturity that has led to an increasing number of applications in the pharmaceutical sector. However, interfacing the models with experimental data can become a significant computational burden. To mitigate the computational burden, the present study introduces a neural network (NN) that emulates the AP for given maximum conductances of selected ion channels, pumps, and exchangers. Its applicability in pharmacological studies was tested on synthetic and experimental data. The NN emulator potentially enables massive speed-ups compared to regular simulations and the forward problem (find drugged AP for pharmacological parameters defined as scaling factors of control maximum conductances) on synthetic data could be solved with average root-mean-square errors (RMSE) of 0.47 mV in normal APs and of 14.5 mV in abnormal APs exhibiting early afterdepolarizations (72.5% of the emulated APs were alining with the abnormality, and the substantial majority of the remaining APs demonstrated pronounced proximity). This demonstrates not only very fast and mostly very accurate AP emulations but also the capability of accounting for discontinuities, a major advantage over existing emulation strategies. Furthermore, the inverse problem (find pharmacological parameters for control and drugged APs through optimization) on synthetic data could be solved with high accuracy shown by a maximum RMSE of 0.22 in the estimated pharmacological parameters. However, notable mismatches were observed between pharmacological parameters estimated from experimental data and distributions obtained from the Comprehensive in vitro Proarrhythmia Assay initiative. This reveals larger inaccuracies which can be attributed particularly to the fact that small tissue preparations were studied while the emulator was trained on single cardiomyocyte data. Overall, our study highlights the potential of NN emulators as powerful tool for an increased efficiency in future quantitative systems pharmacology studies.
