Accurate prediction of protein structures and interactions using a three-track neural network

Baek, Minkyung; DiMaio, Frank; Anishchenko, Ivan; Dauparas, Justas; Ovchinnikov, Sergey; Lee, Gyu Rie; Wang, Jue; Cong, Qian; Kinch, Lisa N.; Schaeffer, R. Dustin; Millán, Claudia; Park, Hahnbeom; Adams, Carson; Glassman, Caleb R.; DeGiovanni, Andy; Pereira, Jose H.; Rodrigues, Andria V.; van Dijk, Alberdina A.; Ebrecht, Ana C.; Opperman, Diederik J.; Sagmeister, Theo; Buhlheller, Christoph; Pavkov-Keller, Tea; Rathinaswamy, Manoj K.; Dalwadi, Udit; Yip, Calvin K.; Burke, John E.; Garcia, K. Christopher; Grishin, Nick V.; Adams, Paul D.; Read, Randy J.; Baker, David

doi:10.1126/science.abj8754

Title: Accurate prediction of protein structures and interactions using a three-track neural network

Journal Article · 19 August 2021 · Science

DOI: https://doi.org/10.1126/science.abj8754 · OSTI ID:2470900

^[1];

^[2];

^[1];

^[3];

^[4];

^[1]; Adams, Carson ^[1];

^[5]; DeGiovanni, Andy ^[6];

^[6]; Rodrigues, Andria V. ^[6]; van Dijk, Alberdina A. ^[7];

^[7];

^[8] more »

University of Washington, Seattle, WA (United States)
Harvard University, Cambridge, MA (United States)
University of Texas Southwestern Medical Center, Dallas, TX (United States)
University of Cambridge (United Kingdom)
Stanford University School of Medicine, CA (United States)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
North-West University, Potchefstroom (South Africa)
University of the Free State, Bloemfontein (South Africa)
University of Graz (Austria)
University of Graz (Austria); Medical University of Graz (Austria)
University of Graz (Austria); BioTechMed-Graz (Austria)
University of Victoria, BC (Canada)
University of British Columbia, Vancouver, BC (Canada)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States)

DeepMind presented notably accurate predictions at the recent 14th Critical Assessment of Structure Prediction (CASP14) conference. We explored network architectures that incorporate related ideas and obtained the best performance with a three-track network in which information at the one-dimensional (1D) sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging x-ray crystallography and cryo–electron microscopy structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate protein-protein complex models from sequence information alone, short-circuiting traditional approaches that require modeling of individual subunits followed by docking. Here, we make the method available to the scientific community to speed biological research.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 2470900

Journal Information:: Science, Journal Name: Science Journal Issue: 6557 Vol. 373; ISSN 0036-8075

Publisher:: AAASCopyright Statement

Country of Publication:: United States

Language:: English

References (70)

Impairment of ceramide synthesis causes a novel progressive myoclonus epilepsy Vanni, Nicola; Fruscione, Floriana; Ferlazzo, Edoardo Annals of Neurology, Vol. 76, Issue 2 https://doi.org/10.1002/ana.24170	journal	May 2014
Protein Sequence Analysis Using the MPI Bioinformatics Toolkit Gabler, Felix; Nam, Seung‐Zin; Till, Sebastian Current Protocols in Bioinformatics, Vol. 72, Issue 1 https://doi.org/10.1002/cpbi.108	journal	December 2020
Mammalian ceramide synthases Levy, Michal; Futerman, Anthony H. IUBMB Life https://doi.org/10.1002/iub.319	journal	January 2010
The phenotype associated with variants in TANGO2 may be explained by a dual role of the protein in ER‐to‐Golgi transport and at the mitochondria Milev, Miroslav P.; Saint‐Dic, Djenann; Zardoui, Khashayar Journal of Inherited Metabolic Disease, Vol. 44, Issue 2 https://doi.org/10.1002/jimd.12312	journal	September 2020
Relaxation of backbone bond geometry improves protein energy landscape modeling: Relaxation of Backbone Bond Geometry Conway, Patrick; Tyka, Michael D.; DiMaio, Frank Protein Science, Vol. 23, Issue 1 https://doi.org/10.1002/pro.2389	journal	November 2013
MolProbity: More and better reference data for improved all-atom structure validation: PROTEIN SCIENCE.ORG Williams, Christopher J.; Headd, Jeffrey J.; Moriarty, Nigel W. Protein Science, Vol. 27, Issue 1 https://doi.org/10.1002/pro.3330	journal	November 2017
UCSF ChimeraX : Structure visualization for researchers, educators, and developers Pettersen, Eric F.; Goddard, Thomas D.; Huang, Conrad C. Protein Science, Vol. 30, Issue 1 https://doi.org/10.1002/pro.3943	journal	October 2020
Scoring function for automated assessment of protein structure template quality Zhang, Yang; Skolnick, Jeffrey Proteins: Structure, Function, and Bioinformatics, Vol. 57, Issue 4 https://doi.org/10.1002/prot.20264	journal	January 2004
Toward optimal fragment generations for ab initio protein structure assembly: Ab Initio Fragment Generation Xu, Dong; Zhang, Yang Proteins: Structure, Function, and Bioinformatics, Vol. 81, Issue 2 https://doi.org/10.1002/prot.24179	journal	October 2012
Assessment of protein assembly prediction in CASP12 Lafita, Aleix; Bliven, Spencer; Kryshtafovych, Andriy Proteins: Structure, Function, and Bioinformatics, Vol. 86 https://doi.org/10.1002/prot.25408	journal	November 2017
Continuous Automated Model EvaluatiOn (CAMEO) complementing the critical assessment of structure prediction in CASP12 Haas, Jürgen; Barbato, Alessandro; Behringer, Dario Proteins: Structure, Function, and Bioinformatics, Vol. 86 https://doi.org/10.1002/prot.25431	journal	December 2017
Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO) Haas, Juergen; Gumienny, Rafal; Barbato, Alessandro Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12 https://doi.org/10.1002/prot.25815	journal	August 2019
Using Dali for Protein Structure Comparison Holm, Liisa Methods in Molecular Biology https://doi.org/10.1007/978-1-0716-0270-6_3	book	January 2020
The lipocalin protein family: structural and sequence overview Flower, Darren R.; North, Anthony C. T.; Sansom, Clare E. Biochimica et Biophysica Acta (BBA) - Protein Structure and Molecular Enzymology, Vol. 1482, Issue 1-2 https://doi.org/10.1016/S0167-4838(00)00148-5	journal	October 2000
TRAM, LAG1 and CLN8: members of a novel family of lipid-sensing domains? Winter, Eitan; Ponting, Chris P. Trends in Biochemical Sciences, Vol. 27, Issue 8 https://doi.org/10.1016/S0968-0004(02)02154-0	journal	August 2002
Recurrent Muscle Weakness with Rhabdomyolysis, Metabolic Crises, and Cardiac Arrhythmia Due to Bi-allelic TANGO2 Mutations Lalani, Seema R.; Liu, Pengfei; Rosenfeld, Jill A. The American Journal of Human Genetics, Vol. 98, Issue 2 https://doi.org/10.1016/j.ajhg.2015.12.008	journal	February 2016
Bi-allelic Truncating Mutations in TANGO2 Cause Infancy-Onset Recurrent Metabolic Crises with Encephalocardiomyopathy Kremer, Laura S.; Distelmaier, Felix; Alhaddad, Bader The American Journal of Human Genetics, Vol. 98, Issue 2 https://doi.org/10.1016/j.ajhg.2015.12.009	journal	February 2016
A Disintegrin and Metalloproteinase (ADAM) and ADAM with thrombospondin motifs (ADAMTS) family in vascular biology and disease Zhong, Sheng; Khalil, Raouf A. Biochemical Pharmacology, Vol. 164 https://doi.org/10.1016/j.bcp.2019.03.033	journal	June 2019
Structural basis for IL-12 and IL-23 receptor sharing reveals a gateway for shaping actions on T versus NK cells Glassman, Caleb R.; Mathiharan, Yamuna Kalyani; Jude, Kevin M. Cell, Vol. 184, Issue 4 https://doi.org/10.1016/j.cell.2021.01.018	journal	February 2021
Ceramide synthases: Reflections on the impact of Dr. Lina M. Obeid Kim, Jiyoon L.; Mestre, Beatriz; Shin, Sun-Hye Cellular Signalling, Vol. 82 https://doi.org/10.1016/j.cellsig.2021.109958	journal	June 2021
SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning Hanson, Jack; Paliwal, Kuldip K.; Litfin, Thomas Genomics, Proteomics & Bioinformatics, Vol. 17, Issue 6 https://doi.org/10.1016/j.gpb.2019.01.004	journal	December 2019
Crystal Structure of the Catalytic Domain of Human ADAM33 Orth, Peter; Reichert, Paul; Wang, Wenyan Journal of Molecular Biology, Vol. 335, Issue 1 https://doi.org/10.1016/j.jmb.2003.10.037	journal	January 2004
A Completely Reimplemented MPI Bioinformatics Toolkit with a New HHpred Server at its Core Zimmermann, Lukas; Stephens, Andrew; Nam, Seung-Zin Journal of Molecular Biology, Vol. 430, Issue 15 https://doi.org/10.1016/j.jmb.2017.12.007	journal	July 2018
The DBSAV Database: Predicting Deleteriousness of Single Amino Acid Variations in the Human Proteome Pei, Jimin; Grishin, Nick V. Journal of Molecular Biology, Vol. 433, Issue 11 https://doi.org/10.1016/j.jmb.2021.166915	journal	May 2021
Local Error Estimates Dramatically Improve the Utility of Homology Models for Solving Crystal Structures by Molecular Replacement Bunkóczi, Gábor; Wallner, Björn; Read, Randy J. Structure, Vol. 23, Issue 2 https://doi.org/10.1016/j.str.2014.11.020	journal	February 2015
Active Metalloproteases of the A Disintegrin And Metalloprotease (ADAM) Family: Biological Function and Structure Klein, Theo; Bischoff, Rainer Journal of Proteome Research, Vol. 10, Issue 1 https://doi.org/10.1021/pr100556z	journal	January 2011
Improved protein structure refinement guided by deep learning based accuracy estimation Hiranuma, Naozumi; Park, Hahnbeom; Baek, Minkyung Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-21511-x	journal	February 2021
CopulaNet: Learning residue co-evolution directly from multiple sequence alignment for protein structure prediction Ju, Fusong; Zhu, Jianwei; Shao, Bin Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-22869-8	journal	May 2021
Improved protein structure prediction using potentials from deep learning Senior, Andrew W.; Evans, Richard; Jumper, John Nature, Vol. 577, Issue 7792 https://doi.org/10.1038/s41586-019-1923-7	journal	January 2020
Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold Steinegger, Martin; Mirdita, Milot; Söding, Johannes Nature Methods, Vol. 16, Issue 7 https://doi.org/10.1038/s41592-019-0437-4	journal	June 2019
Improved protein structure prediction by deep learning irrespective of co-evolution information Xu, Jinbo; McPartlon, Matthew; Li, Jin Nature Machine Intelligence, Vol. 3, Issue 7 https://doi.org/10.1038/s42256-021-00348-5	journal	May 2021
Crystal structures of VAP1 reveal ADAMs' MDC domain architecture and its unique C-shaped scaffold Takeda, Soichi; Igarashi, Tomoko; Mori, Hidezo The EMBO Journal, Vol. 25, Issue 11 https://doi.org/10.1038/sj.emboj.7601131	journal	May 2006
Ab initio solution of macromolecular crystal structures without direct methods McCoy, Airlie J.; Oeffner, Robert D.; Wrobel, Antoni G. Proceedings of the National Academy of Sciences, Vol. 114, Issue 14 https://doi.org/10.1073/pnas.1701640114	journal	March 2017
Improved protein structure prediction using predicted interresidue orientations Yang, Jianyi; Anishchenko, Ivan; Park, Hahnbeom Proceedings of the National Academy of Sciences, Vol. 117, Issue 3 https://doi.org/10.1073/pnas.1914677117	journal	January 2020
The cysteine switch: a principle of regulation of metalloproteinase activity with potential applicability to the entire matrix metalloproteinase gene family. Van Wart, H. E.; Birkedal-Hansen, H. Proceedings of the National Academy of Sciences, Vol. 87, Issue 14 https://doi.org/10.1073/pnas.87.14.5578	journal	July 1990
Necessary Role for the Lag1p Motif in (Dihydro)ceramide Synthase Activity Spassieva, Stefka; Seo, Jae-Gu; Jiang, James C. Journal of Biological Chemistry, Vol. 281, Issue 45 https://doi.org/10.1074/jbc.M608092200	journal	November 2006
ADAM, a novel family of membrane proteins containing A Disintegrin And Metalloprotease domain: multipotential functions in cell-cell and cell-matrix interactions. Wolfsberg, T. G.; Primakoff, P.; Myles, D. G. The Journal of cell biology, Vol. 131, Issue 2 https://doi.org/10.1083/jcb.131.2.275	journal	October 1995
AL2CO: calculation of positional conservation in a protein sequence alignment Pei, J.; Grishin, N. V. Bioinformatics, Vol. 17, Issue 8 https://doi.org/10.1093/bioinformatics/17.8.700	journal	August 2001
Clustal W and Clustal X version 2.0 Larkin, M. A.; Blackshields, G.; Brown, N. P. Bioinformatics, Vol. 23, Issue 21, p. 2947-2948 https://doi.org/10.1093/bioinformatics/btm404	journal	September 2007
PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta Chaudhury, S.; Lyskov, S.; Gray, J. J. Bioinformatics, Vol. 26, Issue 5, p. 689-691 https://doi.org/10.1093/bioinformatics/btq007	journal	January 2010
Toward the estimation of the absolute quality of individual protein structure models Benkert, Pascal; Biasini, Marco; Schwede, Torsten Bioinformatics, Vol. 27, Issue 3 https://doi.org/10.1093/bioinformatics/btq662	journal	December 2010
lDDT: a local superposition-free score for comparing protein structures and models using distance difference tests Mariani, Valerio; Biasini, Marco; Barbato, Alessandro Bioinformatics, Vol. 29, Issue 21 https://doi.org/10.1093/bioinformatics/btt473	journal	August 2013
MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability Katoh, K.; Standley, D. M. Molecular Biology and Evolution, Vol. 30, Issue 4 https://doi.org/10.1093/molbev/mst010	journal	January 2013
OMA orthology in 2021: website overhaul, conserved isoforms, ancestral gene order and more Altenhoff, Adrian M.; Train, Clément-Marie; Gilbert, Kimberly J. Nucleic Acids Research, Vol. 49, Issue D1 https://doi.org/10.1093/nar/gkaa1007	journal	November 2020
GPCRdb in 2021: integrating GPCR sequence, structure and function Kooistra, Albert J.; Mordalski, Stefan; Pándy-Szekeres, Gáspár Nucleic Acids Research, Vol. 49, Issue D1 https://doi.org/10.1093/nar/gkaa1080	journal	December 2020
I-TASSER server: new development for protein structure and function predictions Yang, Jianyi; Zhang, Yang Nucleic Acids Research, Vol. 43, Issue W1 https://doi.org/10.1093/nar/gkv342	journal	April 2015
Uniclust databases of clustered and deeply annotated protein sequences and alignments Mirdita, Milot; von den Driesch, Lars; Galiez, Clovis Nucleic Acids Research, Vol. 45, Issue D1 https://doi.org/10.1093/nar/gkw1081	journal	November 2016
UniProt: the universal protein knowledgebase Nucleic Acids Research, Vol. 45, Issue D1, p. D158-D169 https://doi.org/10.1093/nar/gkw1099	journal	November 2016
The SWISS-MODEL Repository—new features and functionality Bienert, Stefan; Waterhouse, Andrew; de Beer, Tjaart A. P. Nucleic Acids Research, Vol. 45, Issue D1 https://doi.org/10.1093/nar/gkw1132	journal	November 2016
I-TASSER-MR: automated molecular replacement for distant-homology proteins using iterative fragment assembly and progressive sequence truncation Wang, Yan; Virtanen, Jouko; Xue, Zhidong Nucleic Acids Research, Vol. 45, Issue W1 https://doi.org/10.1093/nar/gkx349	journal	May 2017
IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding Mészáros, Bálint; Erdős, Gábor; Dosztányi, Zsuzsanna Nucleic Acids Research, Vol. 46, Issue W1 https://doi.org/10.1093/nar/gky384	journal	June 2018
SWISS-MODEL: homology modelling of protein structures and complexes Waterhouse, Andrew; Bertoni, Martino; Bienert, Stefan Nucleic Acids Research, Vol. 46, Issue W1 https://doi.org/10.1093/nar/gky427	journal	May 2018
The Pfam protein families database in 2019 El-Gebali, Sara; Mistry, Jaina; Bateman, Alex Nucleic Acids Research, Vol. 47, Issue D1 https://doi.org/10.1093/nar/gky995	journal	October 2018
IntFOLD: an integrated web resource for high performance protein structure and function prediction McGuffin, Liam J.; Adiyaman, Recep; Maghrabi, Ali H. A. Nucleic Acids Research, Vol. 47, Issue W1 https://doi.org/10.1093/nar/gkz322	journal	May 2019
MSA Transformer Rao, Roshan; Liu, Jason; Verkuil, Robert bioRxiv https://doi.org/10.1101/2021.02.12.430858	preprint	August 2021
Phaser crystallographic software McCoy, Airlie J.; Grosse-Kunstleve, Ralf W.; Adams, Paul D. Journal of Applied Crystallography, Vol. 40, Issue 4 https://doi.org/10.1107/S0021889807021206	journal	July 2007
Maximum-likelihood density modification Terwilliger, Thomas C. Acta Crystallographica Section D Biological Crystallography, Vol. 56, Issue 8 https://doi.org/10.1107/S0907444900005072	journal	August 2000
Iterative model building, structure refinement and density modification with the PHENIX AutoBuild wizard Terwilliger, Thomas C.; Grosse-Kunstleve, Ralf W.; Afonine, Pavel V. Acta Crystallographica Section D Biological Crystallography, Vol. 64, Issue 1 https://doi.org/10.1107/S090744490705024X	journal	December 2007
Features and development of Coot Emsley, P.; Lohkamp, B.; Scott, W. G. Acta Crystallographica Section D Biological Crystallography, Vol. 66, Issue 4 https://doi.org/10.1107/S0907444910007493	journal	March 2010
Improvement of molecular-replacement models with Sculptor Bunkóczi, Gábor; Read, Randy J. Acta Crystallographica Section D Biological Crystallography, Vol. 67, Issue 4 https://doi.org/10.1107/S0907444910051218	journal	March 2011
Using SAD data in Phaser Read, Randy J.; McCoy, Airlie J. Acta Crystallographica Section D Biological Crystallography, Vol. 67, Issue 4 https://doi.org/10.1107/S0907444910051371	journal	March 2011
Towards automated crystallographic structure refinement with phenix.refine Afonine, Pavel V.; Grosse-Kunstleve, Ralf W.; Echols, Nathaniel Acta Crystallographica Section D Biological Crystallography, Vol. 68, Issue 4 https://doi.org/10.1107/S0907444912001308	journal	March 2012
Macromolecular structure determination using X-rays, neutrons and electrons: recent developments in Phenix Liebschner, Dorothee; Afonine, Pavel V.; Baker, Matthew L. Acta Crystallographica Section D Structural Biology, Vol. 75, Issue 10 https://doi.org/10.1107/S2059798319011471	journal	October 2019
Protein interaction networks revealed by proteome coevolution Cong, Qian; Anishchenko, Ivan; Ovchinnikov, Sergey Science, Vol. 365, Issue 6449 https://doi.org/10.1126/science.aaw6718	journal	July 2019
Hidden Markov model speed heuristic and iterative HMM search procedure Johnson, L. Steven; Eddy, Sean R.; Portugaly, Elon BMC Bioinformatics, Vol. 11, Issue 1 https://doi.org/10.1186/1471-2105-11-431	journal	August 2010
HH-suite3 for fast remote homology detection and deep protein annotation Steinegger, Martin; Meier, Markus; Mirdita, Milot BMC Bioinformatics, Vol. 20, Issue 1 https://doi.org/10.1186/s12859-019-3019-7	journal	September 2019
ECOD: An Evolutionary Classification of Protein Domains Cheng, Hua; Schaeffer, R. Dustin; Liao, Yuxing PLoS Computational Biology, Vol. 10, Issue 12 https://doi.org/10.1371/journal.pcbi.1003926	journal	December 2014
Improving homology modeling from low-sequence identity templates in Rosetta: A case study in GPCRs Bender, Brian Joseph; Marlow, Brennica; Meiler, Jens PLOS Computational Biology, Vol. 16, Issue 10 https://doi.org/10.1371/journal.pcbi.1007597	journal	October 2020
RUPEE: A fast and accurate purely geometric protein structure search Ayoub, Ronald; Lee, Yugyung PLOS ONE, Vol. 14, Issue 3 https://doi.org/10.1371/journal.pone.0213712	journal	March 2019
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification Shi, Yunsheng; Huang, Zhengjie; Feng, Shikun Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence https://doi.org/10.24963/ijcai.2021/214	conference	August 2021

Cited By (4)

Additional file 2 of Systemic evolutionary chemical space exploration for drug discovery Lu, Chong; Liu, Shien; Shi, Weihua figshare https://doi.org/10.6084/m9.figshare.19498417.v1	dataset	January 2022
Additional file 3 of Systemic evolutionary chemical space exploration for drug discovery Lu, Chong; Liu, Shien; Shi, Weihua figshare https://doi.org/10.6084/m9.figshare.19498420.v1	dataset	January 2022
Additional file 4 of Systemic evolutionary chemical space exploration for drug discovery Lu, Chong; Liu, Shien; Shi, Weihua figshare https://doi.org/10.6084/m9.figshare.19498423.v1	dataset	January 2022
Additional file 2 of Purifying selection leads to low protein diversity of the mitochondrial cyt b gene in avian malaria parasites Wang, Xinyi; Bensch, Staffan; Huang, Xi figshare https://doi.org/10.6084/m9.figshare.24116530.v1	dataset	January 2023

Similar Records

Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps

Journal Article · 2022 · BMC Bioinformatics · OSTI ID:1876657

Mahmud, Sajid; Guo, Zhiye; Quadir, Farhan; +2 more

Improving deep learning-based protein distance prediction in CASP14

Journal Article · 2021 · Bioinformatics · OSTI ID:1826198

Guo, Zhiye; Wu, Tianqi; Liu, Jian; +3 more

Improving AlphaFold2-based protein tertiary structure prediction with MULTICOM in CASP15

Journal Article · 2023 · Communications Chemistry · OSTI ID:2278950

Liu, Jian; Guo, Zhiye; Wu, Tianqi; +3 more

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
Science & Technology - Other Topics

Title: Accurate prediction of protein structures and interactions using a three-track neural network

Citation Formats

References (70)

Cited By (4)

Similar Records

Related Subjects