A General Framework to Learn Tertiary Structure for Protein Sequence Characterization

Gao, Mu; Skolnick, Jeffrey

doi:10.3389/fbinf.2021.689960

A General Framework to Learn Tertiary Structure for Protein Sequence Characterization

Journal Article · Fri May 21 00:00:00 EDT 2021 · Frontiers in Bioinformatics

DOI:https://doi.org/10.3389/fbinf.2021.689960· OSTI ID:1831097

Gao, Mu ^[1]; Skolnick, Jeffrey ^[2]

Georgia Institute of Technology, Atlanta, GA (United States); Georgia Institute of Technology
Georgia Institute of Technology, Atlanta, GA (United States)

During the past five years, deep-learning algorithms have enabled ground-breaking progress towards the prediction of tertiary structure from a protein sequence. Very recently, we developed SAdLSA, a new computational algorithm for protein sequence comparison via deep-learning of protein structural alignments. SAdLSA shows significant improvement over established sequence alignment methods. In this contribution, we show that SAdLSA provides a general machine-learning framework for structurally characterizing protein sequences. By aligning a protein sequence against itself, SAdLSA generates a fold distogram for the input sequence, including challenging cases whose structural folds were not present in the training set. About 70% of the predicted distograms are statistically significant. Although at present the accuracy of the intra-sequence distogram predicted by SAdLSA self-alignment is not as good as deep-learning algorithms specifically trained for distogram prediction, it is remarkable that the prediction of single protein structures is encoded by an algorithm that learns ensembles of pairwise structural comparisons, without being explicitly trained to recognize individual structural folds. As such, SAdLSA can not only predict protein folds for individual sequences, but also detects subtle, yet significant, structural relationships between multiple protein sequences using the same deep-learning neural network. The former reduces to a special case in this general framework for protein sequence annotation.

View Accepted Manuscript (DOE)

Research Organization:: Georgia Institute of Technology, Atlanta, GA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Biological and Environmental Research (BER); National Institutes of Health (NIH)

Grant/Contract Number:: SC0021303

OSTI ID:: 1831097

Journal Information:: Frontiers in Bioinformatics, Journal Name: Frontiers in Bioinformatics Vol. 1; ISSN 2673-7647

Publisher:: Frontiers Media S.A.Copyright Statement

Country of Publication:: United States

Language:: English

References (34)

Proteopedia: Rossmann fold: A beta-alpha-beta fold at dinucleotide binding sites: Rossmann Fold in FAD, NAD and NADP Binding Domains Hanukoglu, Israel Biochemistry and Molecular Biology Education, Vol. 43, Issue 3 https://doi.org/10.1002/bmb.20849	journal	February 2015
On the Role of Physics and Evolution in Dictating Protein Structure and Function Skolnick, Jeffrey; Gao, Mu; Zhou, Hongyi Israel Journal of Chemistry, Vol. 54, Issue 8-9 https://doi.org/10.1002/ijch.201400013	journal	July 2014
The relation between the divergence of sequence and structure in proteins. Chothia, C.; Lesk, A. M. The EMBO Journal, Vol. 5, Issue 4 https://doi.org/10.1002/j.1460-2075.1986.tb04288.x	journal	April 1986
Development and large scale benchmark testing of the PROSPECTOR_3 threading algorithm Skolnick, Jeffrey; Kihara, Daisuke; Zhang, Yang Proteins: Structure, Function, and Bioinformatics, Vol. 56, Issue 3 https://doi.org/10.1002/prot.20106	journal	April 2004
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
SPARKS 2 and SP3 servers in CASP6 Zhou, Hongyi; Zhou, Yaoqi Proteins: Structure, Function, and Bioinformatics, Vol. 61, Issue S7 https://doi.org/10.1002/prot.20732	journal	January 2005
Fast and accurate automatic structure prediction with HHpred Hildebrand, Andrea; Remmert, Michael; Biegert, Andreas Proteins: Structure, Function, and Bioinformatics, Vol. 77, Issue S9 https://doi.org/10.1002/prot.22499	journal	January 2009
Assessment of contact predictions in CASP12: Co-evolution and deep learning coming of age Schaarschmidt, Joerg; Monastyrskyy, Bohdan; Kryshtafovych, Andriy Proteins: Structure, Function, and Bioinformatics, Vol. 86 https://doi.org/10.1002/prot.25407	journal	November 2017
Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13 Hou, Jie; Wu, Tianqi; Cao, Renzhi Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12 https://doi.org/10.1002/prot.25697	journal	April 2019
A further leap of improvement in tertiary structure prediction in CASP13 prompts new routes for future assessments Abriata, Luciano A.; Tamò, Giorgio E.; Dal Peraro, Matteo Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12 https://doi.org/10.1002/prot.25787	journal	August 2019
Deep‐learning contact‐map guided protein structure prediction in CASP13 Zheng, Wei; Li, Yang; Zhang, Chengxin Proteins: Structure, Function, and Bioinformatics, Vol. 87, Issue 12 https://doi.org/10.1002/prot.25792	journal	August 2019
GenTHREADER: an efficient and reliable protein fold recognition method for genomic sequences Jones, David T. Journal of Molecular Biology, Vol. 287, Issue 4 https://doi.org/10.1006/jmbi.1999.2583	journal	April 1999
Identification of common molecular subsequences Smith, T. F.; Waterman, M. S. Journal of Molecular Biology, Vol. 147, Issue 1, p. 195-197 https://doi.org/10.1016/0022-2836(81)90087-5	journal	March 1981
Progress and challenges in protein structure prediction Zhang, Yang Current Opinion in Structural Biology, Vol. 18, Issue 3 https://doi.org/10.1016/j.sbi.2008.02.004	journal	June 2008
Protein sequence comparison and fold recognition: progress and good-practice benchmarking Söding, Johannes; Remmert, Michael Current Opinion in Structural Biology, Vol. 21, Issue 3 https://doi.org/10.1016/j.sbi.2011.03.005	journal	June 2011
The role of local versus nonlocal physicochemical restraints in determining protein native structure Skolnick, Jeffrey; Gao, Mu Current Opinion in Structural Biology, Vol. 68 https://doi.org/10.1016/j.sbi.2020.10.008	journal	June 2021
How far divergent evolution goes in proteins Murzin, Alexey G. Current Opinion in Structural Biology, Vol. 8, Issue 3 https://doi.org/10.1016/s0959-440x(98)80073-0	journal	June 1998
The Hemophore HasA from Yersinia pestis (HasA _yp ) Coordinates Hemin with a Single Residue, Tyr75, and with Minimal Conformational Change Kumar, Ritesh; Lovell, Scott; Matsumura, Hirotoshi Biochemistry, Vol. 52, Issue 16 https://doi.org/10.1021/bi400280z	journal	April 2013
HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment Remmert, Michael; Biegert, Andreas; Hauser, Andreas Nature Methods, Vol. 9, Issue 2 https://doi.org/10.1038/nmeth.1818	journal	December 2011
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
DESTINI: A deep-learning approach to contact-driven protein structure prediction Gao, Mu; Zhou, Hongyi; Skolnick, Jeffrey Scientific Reports, Vol. 9, Issue 1 https://doi.org/10.1038/s41598-019-40314-1	journal	March 2019
Distance-based protein folding powered by deep learning Xu, Jinbo Proceedings of the National Academy of Sciences, Vol. 116, Issue 34 https://doi.org/10.1073/pnas.1821309116	journal	August 2019
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
Allosteric Mechanism of Pyruvate Kinase from Leishmania mexicana Uses a Rock and Lock Model Morgan, Hugh P.; McNae, Iain W.; Nowicki, Matthew W. Journal of Biological Chemistry, Vol. 285, Issue 17 https://doi.org/10.1074/jbc.M109.079905	journal	February 2010
A novel sequence alignment algorithm based on deep learning of the protein folding code Gao, Mu; Skolnick, Jeffrey Bioinformatics, Vol. 37, Issue 4 https://doi.org/10.1093/bioinformatics/btaa810	journal	September 2020
PISCES: a protein sequence culling server Wang, G.; Dunbrack, R. L. Bioinformatics, Vol. 19, Issue 12 https://doi.org/10.1093/bioinformatics/btg224	journal	August 2003
Protein homology detection by HMM-HMM comparison Soding, J. Bioinformatics, Vol. 21, Issue 7 https://doi.org/10.1093/bioinformatics/bti125	journal	November 2004
How significant is a protein structure similarity with TM-score = 0.5? Xu, Jinrui; Zhang, Yang Bioinformatics, Vol. 26, Issue 7 https://doi.org/10.1093/bioinformatics/btq066	journal	February 2010
APoc: large-scale identification of similar protein pockets Gao, Mu; Skolnick, Jeffrey Bioinformatics, Vol. 29, Issue 5 https://doi.org/10.1093/bioinformatics/btt024	journal	January 2013
The Protein Data Bank Berman, H. M. Nucleic Acids Research, Vol. 28, Issue 1 https://doi.org/10.1093/nar/28.1.235	journal	January 2000
TM-align: a protein structure alignment algorithm based on the TM-score Zhang, Y. Nucleic Acids Research, Vol. 33, Issue 7 https://doi.org/10.1093/nar/gki524	journal	April 2005
SCOPe: Structural Classification of Proteins—extended, integrating SCOP and ASTRAL data and classification of new structures Fox, Naomi K.; Brenner, Steven E.; Chandonia, John-Marc Nucleic Acids Research, Vol. 42, Issue D1 https://doi.org/10.1093/nar/gkt1240	journal	December 2013
A Threading-Based Method for the Prediction of DNA-Binding Proteins with Application to the Human Genome Gao, Mu; Skolnick, Jeffrey PLoS Computational Biology, Vol. 5, Issue 11 https://doi.org/10.1371/journal.pcbi.1000567	journal	November 2009
Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model Wang, Sheng; Sun, Siqi; Li, Zhen PLOS Computational Biology, Vol. 13, Issue 1 https://doi.org/10.1371/journal.pcbi.1005324	journal	January 2017

Similar Records

High-Performance Deep Learning Toolbox for Genome-Scale Prediction of Protein Structure and Function

Conference · Mon Nov 01 00:00:00 EDT 2021 · OSTI ID:1840182

High throughput, accurate gene annotation through AI and HPC-enabled structural analysis

Technical Report · Fri Jun 07 00:00:00 EDT 2024 · OSTI ID:2222578

Structural Models and Sequence Alignment Results of the Rhodospirillum rubrum Proteome

Dataset · Fri Jul 07 00:00:00 EDT 2023 · OSTI ID:1987876

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
deep-learning
protein folding
protein structure prediction
sequence alignment
structural alignment

A General Framework to Learn Tertiary Structure for Protein Sequence Characterization

Citation Formats

References (34)

Similar Records

Related Subjects