DOCSLIB.ORG

Simultaneous Identification of Specifically Interacting Paralogs and Interprotein Contacts by Direct Coupling Analysis

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Simultaneous Identification of Specifically Interacting Paralogs and Interprotein Contacts by Direct Coupling Analysis Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis Thomas Gueudréa,1, Carlo Baldassia,b,1, Marco Zamparoa, Martin Weigtc,2, and Andrea Pagnania,b,2 aDepartment of Applied Science and Technology, Politecnico di Torino, 10129 Torino, Italy; bHuman Genetics Foundation, Molecular Biotechnology Center, 10126 Torino, Italy; and cSorbonne Universités, UPMC Université Paris 06, CNRS, Biologie Computationnelle et Quantitative, Institut de Biologie Paris Seine, 75005 Paris, France Edited by Barry Honig, Howard Hughes Medical Institute, Columbia University, New York, NY, and approved September 16, 2016 (received for review May 12, 2016) Understanding protein−protein interactions is central to our under- unphysiological treatment needed for protein purification, enrich- standing of almost all complex biological processes. Computational ment, and crystallization. It is therefore tempting to use the ex- tools exploiting rapidly growing genomic databases to characterize ponentially increasing genomic databases to design in silico protein−protein interactions are urgently needed. Such methods techniques for identifying protein−protein interactions (cf. refs. 3 should connect multiple scales from evolutionary conserved interac- and 4). Prominent techniques, to date, include the search for tions between families of homologous proteins, over the identifica- colocalization of genes on the genome (e.g., operons in bacteria) tion of specifically interacting proteins in the case of multiple (5, 6), the Rosetta stone method (domains fused to a single protein paralogs inside a species, down to the prediction of residues being in some genome are expected to interact in other genomes) (7, 8), in physical contact across interaction interfaces. Statistical inference − and also coevolutionary techniques like phylogenetic profiling methods detecting residue residue coevolution have recently trig- (correlated presence or absence of interacting proteins in ge- gered considerable progress in using sequence data for quaternary nomes) (9) or similarities between phylogenetic trees of groups of protein structure prediction; they require, however, large joint align- orthologous proteins (compare the mirrortree method) (10, 11). ments of homologous protein pairs known to interact. The genera- tion of such alignments is a complex computational task on its own; Despite the success of all these methods, their sensitivity is limited application of coevolutionary modeling has, in turn, been restricted due to the use of relatively coarse global criteria (genomic location, to proteins without paralogs, or to bacterial systems with the corre- phylogenetic distance) instead of full amino acid sequences. sponding coding genes being colocalized in operons. Here we show The availability of thousands of sequenced genomes (12), that the direct coupling analysis of residue coevolution can be ex- thanks to next-generation sequencing techniques, enables the tended to connect the different scales, and simultaneously to match application of much finer-scale statistical modeling approaches, interacting paralogs, to identify interprotein residue−residue con- which take into account the full sequence (13). In this context, tacts and to discriminate interacting from noninteracting families in direct coupling analysis (DCA) (14) was developed to detect direct a multiprotein system. Our results extend the potential applications interprotein coevolution and, in turn, interprotein residue−residue of coevolutionary analysis far beyond cases treatable so far. Significance coevolution | protein−protein interaction networks | paralog matching | statistical inference | direct coupling analysis Most biological processes rely on specific interactions between proteins, but the experimental characterization of protein−pro- lmost all biological processes depend on interacting proteins. tein interactions is a labor-intensive task of frequently uncertain AUnderstanding protein−protein interactions is therefore key outcome. Computational methods based on exponentially grow- to our understanding of complex biological systems. In this con- ing genomic databases are urgently needed. It has recently been text, at least two questions are of interest: First, the question “who shown that coevolutionary methods are able to detect correlated with whom,” i.e., which proteins interact; this concerns the net- mutations between residues in different proteins, which are in works connecting specific proteins inside one organism, but also— contact across the interaction interface, thus enabling the struc- in the context of this article—the evolutionary perspective of ture prediction of protein complexes. Here we show that the protein−protein interactions, which are conserved across different applicability of coevolutionary methods is much broader, con- species. Their coevolution is at the basis of many modern com- necting multiple scales relevant in protein−protein interaction: putational techniques for characterizing protein−protein interac- the residue scale of interprotein contacts, the protein scale of tions. The second question is the question “how” proteins interact specific interactions between paralogous proteins, and the evo- with each other, in particular, which residues are involved in the lutionary scale of conserved interactions between homologous interaction interfaces, and which residues are in contact across the protein families. interfaces. Such knowledge may provide important mechanistic insight into questions related to interaction specificity or com- Author contributions: T.G., C.B., M.W., and A.P. designed research; T.G., C.B., M.Z., M.W., and A.P. performed research; T.G. and C.B. analyzed data; and M.W. and A.P. wrote petitive interaction with partially shared interfaces. the paper. − The experimental identification of protein protein interactions The authors declare no conflict of interest. is an arduous task (for reviews, cf. refs. 1 and 2): High-throughput This article is a PNAS Direct Submission. techniques that aim to identify protein−protein interactions in Data deposition: Julia package for paralog matching is available at https://github.com/ vivo or in vitro are well documented and include large-scale yeast Mirmu/ParalogMatching.jl. two-hybrid assays and protein affinity mass spectrometry assays. 1T.G. and C.B. contributed equally to this work. Such large-scale efforts have revealed useful information but are 2To whom correspondence may be addressed. Email: [email protected] or martin. hampered by high false positive and false negative error rates. [email protected]. Structural approaches based on protein cocrystallization are in- This article contains supporting information online at www.pnas.org/lookup/suppl/doi:10. trinsically low-throughput and of uncertain outcome due to the 1073/pnas.1607570113/-/DCSupplemental. 12186–12191 | PNAS | October 25, 2016 | vol. 113 | no. 43 www.pnas.org/cgi/doi/10.1073/pnas.1607570113 Downloaded by guest on September 23, 2021 contacts between bacterial signal transduction proteins, to help to ABC assemble protein complexes (15, 16) and shed light on interaction sort family by increasing generate 2k random specificity (17, 18). The applicability of DCA and related co- family 1 family 2 matching entropy matchings evolutionary approaches (19, 20) to protein−protein interactions far generate seed matching refine matchings by beyond the signaling system has been recently established (21, 22). gradient ascent However, these methods require a large joint multiple sequence calculate DCA model alignment (MSA) of at least about 1,000aminoacidsequencepairs merge pairs of matchings to work accurately. Each line of this MSA concatenates a pair of match new species interacting proteins. So far, the application of coevolutionary methods remains therefore restricted to those cases where such output matched MSA injective matching output matched MSA joint alignments could be constructed easily: (i) Each species has only a single copy of the family, i.e., no paralogs exist. Matching of Fig. 1. Paralog matching procedures. (A) The considered injective strategy to interacting proteins can be achieved by uniqueness in the genome. match paralogs. For each species (depicted by different colors), each paralog (ii) Even if paralogs exist, genes of interacting proteins are fre- from the species with the lower paralog number is matched to a distinct se- quently colocalized on the genome and can therefore be matched quence in the other species (injection). (B) The pipeline of the PPM algorithm. by chromosomal vicinity. This finding is true, in particular, in the Species are sorted by increasing matching entropy (a measure of the compu- tational complexity of the matching). Starting from a seed matching (gener- case of bacteria; functionally related proteins are frequently coded ated, in our case, by restricting the MSA to all genomes having a single in operons and consequently cotranscribed. sequence in both families), the algorithm calculates the DCA model, uses it to Colocalization is used extensively in the construction of joint add and match a new species, and iterates these two steps until all species are MSA for covariance analysis (22–25). However, the case of matched. (C) The IPM pipeline; 2k random matchings are generated, and each multiple paralogs with noncolocalized genes has remained out of one is independently refined using hill climbing of the likelihood. After re- reach for coevolutionary
Load more

Recommended publications
  • Inter-Residue, Inter-Protein and Inter-Family Coevolution: Bridging the Scales
    Inter-residue, inter-protein and inter-family coevolution: bridging the scales Hendrik Szurmant1+, Martin Weigt2+ Affiliations: 1. Department of Basic Medical Sciences, College of Osteopathic Medicine of the Pacific, Western University of Health Sciences, Pomona CA 91766, USA 2. Sorbonne Universités, UPMC Université Paris 06, CNRS, Biologie Computationnelle et Quantitative - Institut de Biologie Paris Seine, 75005 Paris, France + to whom correspondence might be addressed Corresponding authors: Hendrik Szurmant: 309 E. 2nd Street, Pomona, CA 91766-1854, USA, tel. +1-909-706-3938, email: [email protected] Martin Weigt: LCQB UMR7238, 4 place Jussieu 75005 Paris, France, tel. +33 1 44 27 73 68, email: [email protected] Short title: Coevolutionary modeling of interacting proteins Abstract Interacting proteins coevolve at multiple but interconnected scales, from the residue-residue over the protein-protein up to the family-family level. The recent accumulation of enormous amounts of sequence data allows for the development of novel, data-driven computational approaches. Notably, these approaches can bridge scales within a single statistical framework. While being currently applied mostly to isolated problems on single scales, their immense potential for an evolutionary informed, structural systems biology is steadily emerging. Highlights • Coevolutionary modeling has an immense potential in structural systems biology. • Interaction between two protein families can be detected. • Specific interaction partners inside families can be deduced. • Contact residues between interacting proteins can be predicted. • Predicted inter-protein contacts can guide in silico protein-complex assembly. Introduction The importance of protein-protein interactions (PPI) in living systems is unquestioned. However, concerning PPI, different research communities are interested in differing aspects.
    [Show full text]
  • 1 Codon-Level Information Improves Predictions of Inter-Residue Contacts in Proteins 2 by Correlated Mutation Analysis 3
    1 Codon-level information improves predictions of inter-residue contacts in proteins 2 by correlated mutation analysis 3 4 5 6 7 8 Etai Jacob1,2, Ron Unger1,* and Amnon Horovitz2,* 9 10 11 1The Mina & Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat- 12 Gan, 52900, 2Department of Structural Biology 13 Weizmann Institute of Science, Rehovot 7610001, Israel 14 15 16 *To whom correspondence should be addressed: 17 Amnon Horovitz ([email protected]) 18 Ron Unger ([email protected]) 19 1 20 Abstract 21 Methods for analysing correlated mutations in proteins are becoming an increasingly 22 powerful tool for predicting contacts within and between proteins. Nevertheless, 23 limitations remain due to the requirement for large multiple sequence alignments (MSA) 24 and the fact that, in general, only the relatively small number of top-ranking predictions 25 are reliable. To date, methods for analysing correlated mutations have relied exclusively 26 on amino acid MSAs as inputs. Here, we describe a new approach for analysing 27 correlated mutations that is based on combined analysis of amino acid and codon MSAs. 28 We show that a direct contact is more likely to be present when the correlation between 29 the positions is strong at the amino acid level but weak at the codon level. The 30 performance of different methods for analysing correlated mutations in predicting 31 contacts is shown to be enhanced significantly when amino acid and codon data are 32 combined. 33 2 34 The effects of mutations that disrupt protein structure and/or function at one site are often 35 suppressed by mutations that occur at other sites either in the same protein or in other 36 proteins.
    [Show full text]
  • Assessing the Utility of Residue-Residue Contact Information in a Sequence and Structure Rich Era
    Supplementary Information: Assessing the utility of residue-residue contact information in a sequence and structure rich era Hetunandan Kamisetty, Sergey Ovchinnikov, David Baker Learning The basis of methods that predict contact information from Multiple Sequence Alignments is that pro- teins with statistically significant sequence similarity have similar structure and that this common structural constraint affects their compositional variability. Thus, a statistical model of the constraints on the composi- tional variability might recover structural constraints (contacts). Historically, these methods were based on Mutual information (MI) and its variations and tended to suffer from the problem of conflating direct and indirect statistical coupling: if positions (A,B) and (B,C) have a high MI; so do (A,C). Thus, even if only spatially proximal positions co-evolve in composition, non-adjacent positions can display a high MI due to transitivity. More recent methods use a global statistical model as described in Eq. 2. The use of a global statistical model allows disentangling direct interactions versus indirect transitive effects. Here, we briefly review alternate approaches to learning this model. Maximum Likelihood Estimation A common approach to learning statistical models from data is the maximum likelihood procedure [1] which for the case of the model in Eq. 2 having parameters Θ =(v,w) is v^; w^ = arg max ll(v; wjD) − R(v; w) v;w PN n where ll(v; wjD) = n=1 log P (x jv; w) is the log likelihood of the model given a set of protein se- quences D = [x1; x2::xN ] and R(v; w) is an optional penalty term added to prevent over-fitting, especially in high-dimensions.
    [Show full text]
  • Ensembling Multiple Raw Coevolutionary Features with Deep Residual Neural Networks for Contact‐Map Prediction in CASP13
    Received: 17 April 2019 Revised: 20 July 2019 Accepted: 8 August 2019 DOI: 10.1002/prot.25798 RESEARCH ARTICLE Ensembling multiple raw coevolutionary features with deep residual neural networks for contact-map prediction in CASP13 Yang Li1,2 | Chengxin Zhang2 | Eric W. Bell2 | Dong-Jun Yu1,2 | Yang Zhang2 1School of Computer Science and Engineering, Nanjing University of Science and Technology, Abstract Nanjing, China We report the results of residue-residue contact prediction of a new pipeline built 2 Department of Computational Medicine and purely on the learning of coevolutionary features in the CASP13 experiment. For a Bioinformatics, University of Michigan, Ann Arbor, Michigan, USA query sequence, the pipeline starts with the collection of multiple sequence alignments (MSAs) from multiple genome and metagenome sequence databases using two comple- Correspondence Yang Zhang, Department of Computational mentary Hidden Markov Model (HMM)-based searching tools. Three profile matrices, Medicine and Bioinformatics, University of built on covariance, precision, and pseudolikelihood maximization respectively, are then Michigan, Ann Arbor, MI 48109. Email: [email protected] created from the MSAs, which are used as the input features of a deep residual con- volutional neural network architecture for contact-map training and prediction. Two Dong-Jun Yu, School of Computer Science and Engineering, Nanjing University of Science and ensembling strategies have been proposed to integrate the matrix features through Technology, Xiaolingwei 200, Nanjing
    [Show full text]
  • Direct Information Reweighted by Contact Templates: Improved RNA Contact Prediction by Combining Structural Features
    Direct Information Reweighted by Contact Templates: Improved RNA Contact Prediction by Combining Structural Features Yiren Jian2, Chen Zeng2*, Yunjie Zhao1* Author affiliation: 1Institute of Biophysics and Department of Physics, Central China Normal University, Wuhan 430079, China 2Department of Physics, The George Washington University, Washington, DC 20052, USA *Corresponding author Chen Zeng Email: [email protected] Yunjie Zhao Email: [email protected] Abstract It is acknowledged that co-evolutionary nucleotide-nucleotide interactions are essential for RNA structures and functions. Currently, direct coupling analysis (DCA) infers nucleotide contacts in a sequence from its homologous sequence alignment across different species. DCA and similar approaches that use sequence information alone usually yield a low accuracy, especially when the available homologous sequences are limited. Here we present a new method that incorporates a Restricted Boltzmann Machine (RBM) to augment the information on sequence co-variations with structural patterns in contact inference. We thus name our method DIRECT that stands for Direct Information REweighted by Contact Templates. Benchmark tests demonstrate that DIRECT produces a substantial enhancement of 13% in accuracy on average for contact prediction in comparison to the traditional DCA. These results suggest that DIRECT could be used for improving predictions of RNA tertiary structures and functions. The source codes and dataset of DIRECT are available at http:// http://zhao.phy.ccnu.edu.cn:8122/DIRECT/index.html. Introduction RNA molecules play critical roles in various biological processes (1-8). There remain various challenges in determination of RNA structure through experiments to get a comprehensive understanding of structure-function relation for RNAs (9).
    [Show full text]
  • DIRECT: RNA Contact Predictions by Integrating Structural Patterns
    Jian et al. BMC Bioinformatics (2019) 20:497 https://doi.org/10.1186/s12859-019-3099-4 RESEARCH ARTICLE Open Access DIRECT: RNA contact predictions by integrating structural patterns Yiren Jian1,2†, Xiaonan Wang1†, Jaidi Qiu1, Huiwen Wang1, Zhichao Liu2, Yunjie Zhao1* and Chen Zeng2* Abstract Background: It is widely believed that tertiary nucleotide-nucleotide interactions are essential in determining RNA structure and function. Currently, direct coupling analysis (DCA) infers nucleotide contacts in a sequence from its homologous sequence alignment across different species. DCA and similar approaches that use sequence information alone typically yield a low accuracy, especially when the available homologous sequences are limited. Therefore, new methods for RNA structural contact inference are desirable because even a single correctly predicted tertiary contact can potentially make the difference between a correct and incorrectly predicted structure. Here we present a new method DIRECT (Direct Information REweighted by Contact Templates) that incorporates a Restricted Boltzmann Machine (RBM) to augment the information on sequence co-variations with structural features in contact inference. Results: Benchmark tests demonstrate that DIRECT achieves better overall performance than DCA approaches. Compared to mfDCA and plmDCA, DIRECT produces a substantial increase of 41 and 18%, respectively, in accuracy on average for contact prediction. DIRECT improves predictions for long-range contacts and captures more tertiary structural features. Conclusions:
    [Show full text]
  • Understanding and Improving Statistical Models of Protein Sequences, November 2018
    THÈSE DE DOCTORAT DE L’UNIVERSITÉ PIERRE ET MARIE CURIE Spécialité : Informatique École doctorale no130: Informatique, Télécommunications et électronique (Paris) réalisée au Laboratoire de biologie computationnelle et quantitative sous la direction de Martin WEIGT présentée par Pierre BARRAT-CHARLAIX pour obtenir le grade de : DOCTEUR DE L’UNIVERSITÉ PIERRE ET MARIE CURIE Sujet de la thèse : Comprendre et améliorer les modèles statistiques de séquences de protéines soutenue le 9 novembre 2018 devant le jury composé de : M. Alessandro LAIO Rapporteur M. Clément NIZAK Rapporteur M. Guillaume ACHAZ Examinateur Mme Aleksandra WALCZAK Examinatrice M. Martin WEIGT Directeur de thèse Pierre Barrat-Charlaix: Understanding and improving statistical models of protein sequences, November 2018 Tchouang-tseu et Houei-tsu se promenaient sur le pont enjambant la rivière Hao. Tchouang-tseu dit : – Regarde les vairons, qui nagent et bondissent tout leur soûl. C’est ça qui rend les poissons heureux. Houei-tseu dit : –Tu n’es pas un poisson, alors comment sais-tu ce qui rend les poissons heureux ? Tchouang-tseu dit : – Tu n’es pas moi, alors comment sais-tu que je ne sais pas ce qui rend les poissons heureux ? Houei tseu dit : – C’est vrai, je ne suis pas toi, je n’ai donc, c’est certain, aucune idée de ce que tu sais. D’un autre côté, tu n’es pas un poisson, c’est certain, et cela prouve simplement que tu ne peux pas savoir ce qui rend les poissons heureux. Tchouang-tseu dit : – Revenons à ta question initiale. Tu as dit : "Comment sais-tu ce qui rend les poissons heureux ?" Donc lorsque tu as posé cette question, tu savais que je le savais.
    [Show full text]
  • Optimal Alignment of Coevolutionary Models for Protein Sequences
    bioRxiv preprint doi: https://doi.org/10.1101/2020.06.12.147702; this version posted June 12, 2020. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made available under aCC-BY 4.0 International license. ComPotts: Optimal alignment of coevolutionary models for protein sequences Hugo Talibart1 and Fran¸cois Coste1 Univ Rennes, Inria, CNRS, IRISA, Campus de Beaulieu, 35042, Rennes, France Corresponding author: [email protected] Abstract To assign structural and functional annotations to the ever increasing amount of sequenced proteins, the main approach relies on sequence-based homology search meth- ods, e.g. BLAST or the current state-of-the-art methods based on profile Hidden Markov Models (pHMMs), which rely on significant alignments of query sequences to annotated proteins or protein families. While powerful, these approaches do not take coevolution between residues into account. Taking advantage of recent advances in the field of con- tact prediction, we propose here to represent proteins by Potts models, which model direct couplings between positions in addition to positional composition. Due to the presence of non-local dependencies, aligning two Potts models is computationally hard. To tackle this task, we introduce an Integer Linear Programming formulation of the problem and present ComPotts, an implementation able to compute the optimal alignment of two Potts models representing proteins in tractable time. A first experimentation on 59 low sequence identity pairwise alignments, extracted from 3 reference alignments from sisyphus and BaliBase3 databases, shows that ComPotts finds better alignments than the other tested methods in the majority of these cases.
    [Show full text]
  • Assessing the Accuracy of Direct-Coupling Analysis for RNA Contact Prediction
    Downloaded from rnajournal.cshlp.org on October 1, 2021 - Published by Cold Spring Harbor Laboratory Press Assessing the accuracy of direct-coupling analysis for RNA contact prediction FRANCESCA CUTURELLO,1 GUIDO TIANA,2 and GIOVANNI BUSSI1 1Scuola Internazionale Superiore di Studi Avanzati, International School for Advanced Studies, 34136 Trieste, Italy 2Center for Complexity and Biosystems and Department of Physics, Università degli Studi di Milano and INFN, 20133 Milano, Italy ABSTRACT Many noncoding RNAs are known to play a role in the cell directly linked to their structure. Structure prediction based on the sole sequence is, however, a challenging task. On the other hand, thanks to the low cost of sequencing technologies, a very large number of homologous sequences are becoming available for many RNA families. In the protein community, the idea of exploiting the covariance of mutations within a family to predict the protein structure using the direct-coupling- analysis (DCA) method has emerged in the last decade. The application of DCA to RNA systems has been limited so far. We here perform an assessment of the DCA method on 17 riboswitch families, comparing it with the commonly used mu- tual information analysis and with state-of-the-art R-scape covariance method. We also compare different flavors of DCA, including mean-field, pseudolikelihood, and a proposed stochastic procedure (Boltzmann learning) for solving exactly the DCA inverse problem. Boltzmann learning outperforms the other methods in predicting contacts observed in high-reso- lution crystal structures. Keywords: DCA; RNA; coevolution INTRODUCTION accumulation of a vast number of sequence data for many homologous RNA families (Nawrocki et al.
    [Show full text]
  • Arxiv:2105.01428V1 [Q-Bio.PE] 4 May 2021
    Statistical Genetics and Direct Coupling Analysis beyond Quasi-Linkage Equilibrium Vito Dichioa,b,c, Hong-Li Zenge and Erik Aurelld a Inria, Aramis project-team, Paris, France b Institut du Cerveau et de la Moelle ´epini`ere,ICM, Paris, France c Sorbonne Universit´e,Paris, France d Department of Computational Science and Technology, AlbaNova University Center, SE-106 91 Stockholm, Sweden; e School of Science, Nanjing University of Posts and Telecommunications, New Energy Technology Engineering Laboratory of Jiangsu Province, Nanjing, 210023, China ARTICLE HISTORY Compiled May 5, 2021 ABSTRACT This work is about statistical genetics, an interdisciplinary topic between Statistical Physics and Population Biology. Our focus is on the phase of Quasi-Linkage Equi- librium (QLE) which has many similarities to equilibrium statistical mechanics, and how the stability of that phase is lost. The QLE phenomenon was discovered by Mo- too Kimura in the mid-1960ies for a two-locus two-allele model, and was extended and generalized to the global genome scale by Neher & Shraiman (2011). What we will refer to as the Kimura-Neher-Shraiman (KNS) theory describes a population evolving due to the mutations, recombination, genetic drift, natural selection (pair- wise epistatic fitness). The main conclusion of KNS is that QLE phase exists at sufficiently high recombination rate (r) with respect to the variability in selection strength (fitness). Combining the results of the KNS theory with the techniques of the Direct Coupling Analysis (DCA), developed for applications in Statistical Physics and Computational Biology, we show that in QLE epistatic fitness can be inferred from the knowledge of the (dynamical) distribution of genotypes in a pop- ulation.
    [Show full text]
  • And Contact-Based Protein Structure Prediction
    International Journal of Molecular Sciences Review Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction Donghyuk Suh 1 , Jai Woo Lee 1 , Sun Choi 1 and Yoonji Lee 2,* 1 Global AI Drug Discovery Center, School of Pharmaceutical Sciences, College of Pharmacy and Graduate, Ewha Womans University, Seoul 03760, Korea; [email protected] (D.S.); [email protected] (J.W.L.); [email protected] (S.C.) 2 College of Pharmacy, Chung-Ang University, Seoul 06974, Korea * Correspondence: [email protected] Abstract: The new advances in deep learning methods have influenced many aspects of scientific research, including the study of the protein system. The prediction of proteins’ 3D structural compo- nents is now heavily dependent on machine learning techniques that interpret how protein sequences and their homology govern the inter-residue contacts and structural organization. Especially, meth- ods employing deep neural networks have had a significant impact on recent CASP13 and CASP14 competition. Here, we explore the recent applications of deep learning methods in the protein structure prediction area. We also look at the potential opportunities for deep learning methods to identify unknown protein structures and functions to be discovered and help guide drug–target interactions. Although significant problems still need to be addressed, we expect these techniques in the near future to play crucial roles in protein structural bioinformatics as well as in drug discovery. Keywords: structural bioinformatics; deep learning; protein sequence homology; 3D structure of Citation: Suh, D.; Lee, J.W.; Choi, S.; Lee, Y. Recent Applications of Deep proteins; drug discovery Learning Methods on Evolution- and Contact-Based Protein Structure Prediction.
    [Show full text]
  • Towards a Genome-Scale Coevolutionary Analysis Giancarlo Croce
    Towards a genome-scale coevolutionary analysis Giancarlo Croce To cite this version: Giancarlo Croce. Towards a genome-scale coevolutionary analysis. Bioinformatics [q-bio.QM]. Sor- bonne Université, 2019. English. tel-02912097v2 HAL Id: tel-02912097 https://tel.archives-ouvertes.fr/tel-02912097v2 Submitted on 11 Apr 2021 HAL is a multi-disciplinary open access L’archive ouverte pluridisciplinaire HAL, est archive for the deposit and dissemination of sci- destinée au dépôt et à la diffusion de documents entific research documents, whether they are pub- scientifiques de niveau recherche, publiés ou non, lished or not. The documents may come from émanant des établissements d’enseignement et de teaching and research institutions in France or recherche français ou étrangers, des laboratoires abroad, or from public or private research centers. publics ou privés. THÈSEDEDOCTORAT DESORBONNEUNIVERSITÉ Spécialité : Informatique École doctorale n. 130 : Informatique, Télécommunications et électronique (Paris) réalisée au Laboratoire de Biologie Computationnelle et Quantitative sous la direction de Martin WEIGT et la co-direction de Olivier TENAILLON présentée par Giancarlo CROCE Sujet de la thèse : Towards a genome-scale coevolutionary analysis Présentée et soutenue publiquement le 22 Novembre 2019 devant un jury composé de : M. Erik AURELL Rapporteur M. Paolo DE LOS RIOS Rapporteur Mme Alessandra CARBONE Examinatrice M. Philippe LOPEZ Examinateur M. Martin WEIGT Directeur de thèse M. Olivier TENAILLON Co-directeur de thèse Giancarlo Croce: Towards a genome-scale coevolutionary analysis, November 2019 ABSTRACT Advances in sequencing technologies have revolutionized the life sciences. The explosion of genomic sequence data has prompted the development of a wide variety of methods, at the interface between bioinformatics, machine learning, and physics, which aim at gaining a deeper understanding of biological systems from such data.
    [Show full text]