Classifying metal‐binding sites with neural networks

Oostrom, Marjolein; Akers, Sarah; Garrett, Noah; Hanson, Emma; Shaw, Wendy; Laureanti, Joseph A.

doi:10.1002/pro.4591

Classifying metal‐binding sites with neural networks

Journal Article · Thu Feb 23 23:00:00 EST 2023 · Protein Science

DOI:https://doi.org/10.1002/pro.4591· OSTI ID:1958634

^[1]; Akers, Sarah ^[1]; Garrett, Noah ^[2]; Hanson, Emma ^[2]; ^[2]; Laureanti, Joseph A. ^[2]

National Security Directorate Pacific Northwest National Laboratory Richland Washington USA
Physical and Computational Sciences Directorate Pacific Northwest National Laboratory Richland Washington USA

Abstract

To advance our ability to predict impacts of the protein scaffold on catalysis, robust classification schemes to define features of proteins that will influence reactivity are needed. One of these features is a protein's metal‐binding ability, as metals are critical to catalytic conversion by metalloenzymes. As a step toward realizing this goal, we used convolutional neural networks (CNNs) to enable the classification of a metal cofactor binding pocket within a protein scaffold. CNNs enable images to be classified based on multiple levels of detail in the image, from edges and corners to entire objects, and can provide rapid classification. First, six CNN models were fine‐tuned to classify the 20 standard amino acids to choose a performant model for amino acid classification. This model was then trained in two parallel efforts: to classify a 2D image of the environment within a given radius of the central metal binding site, either an Fe ion or a [2Fe‐2S] cofactor, with the metal visible (effort 1) or the metal hidden (effort 2). We further used two sub‐classifications of the [2Fe‐2S] cofactor: (1) a standard [2Fe‐2S] cofactor and (2) a Rieske [2Fe‐2S] cofactor. The accuracy for the model correctly identifying all three defined features was >95%, despite our perception of the increased challenge of the metalloenzyme identification. This demonstrates that machine learning methodology to classify and distinguish similar metal‐binding sites, even in the absence of a visible cofactor, is indeed possible and offers an additional tool for metal‐binding site identification in proteins.

View Journal Article

Sponsoring Organization:: USDOE

OSTI ID:: 1958634

Alternate ID(s):: OSTI ID: 1958635
OSTI ID: 1961579

Journal Information:: Protein Science, Journal Name: Protein Science Journal Issue: 3 Vol. 32; ISSN 0961-8368

Publisher:: Wiley Blackwell (John Wiley & Sons)Copyright Statement

Country of Publication:: United Kingdom

Language:: English

References (37)

Machine learning techniques for protein function prediction Bonetta, Rosalin; Valentino, Gianluca Proteins: Structure, Function, and Bioinformatics, Vol. 88, Issue 3 https://doi.org/10.1002/prot.25832	journal	October 2019
Iron-Sulfur Cluster Biosynthesis Agar, Jeffrey N.; Dean, Dennis R.; Johnson, Michael K. Biochemistry and Physiology of Anaerobic Bacteria https://doi.org/10.1007/0-387-22731-8_5	book	January 2003
Classification of Proteins: Available Structural Space for Molecular Modeling Andreeva, Antonina Methods in Molecular Biology https://doi.org/10.1007/978-1-61779-588-6_1	book	January 2011
Metal ions in biological catalysis: from enzyme databases to general principles Andreini, Claudia; Bertini, Ivano; Cavallaro, Gabriele JBIC Journal of Biological Inorganic Chemistry, Vol. 13, Issue 8 https://doi.org/10.1007/s00775-008-0404-5	journal	July 2008
Catalysis by metallo-enzymes: The entatic state Williams, R. J. P. Inorganica Chimica Acta Reviews, Vol. 5 https://doi.org/10.1016/0073-8085(71)80016-5	journal	December 1971
Analysis of Catalytic Residues in Enzyme Active Sites Bartlett, Gail J.; Porter, Craig T.; Borkakoti, Neera Journal of Molecular Biology, Vol. 324, Issue 1 https://doi.org/10.1016/S0022-2836(02)01036-7	journal	November 2002
Molql: Towards a Common General Purpose Molecular Query Language Rose, Alexander S.; Sehnal, David; Bliven, Spencer Biophysical Journal, Vol. 114, Issue 3 https://doi.org/10.1016/j.bpj.2017.11.1910	journal	February 2018
iProStruct2D: Identifying protein structural classes by deep learning via 2D representations Nanni, Loris; Lumini, Alessandra; Pasquali, Federica Expert Systems with Applications, Vol. 142 https://doi.org/10.1016/j.eswa.2019.113019	journal	March 2020
Identification of Iron-Sulfur (Fe-S) Cluster and Zinc (Zn) Binding Sites Within Proteomes Predicted by DeepMind’s AlphaFold2 Program Dramatically Expands the Metalloproteome Wehrspan, Zachary J.; McDonnell, Robert T.; Elcock, Adrian H. Journal of Molecular Biology, Vol. 434, Issue 2 https://doi.org/10.1016/j.jmb.2021.167377	journal	January 2022
LmrR: A Privileged Scaffold for Artificial Metalloenzymes Roelfes, Gerard Accounts of Chemical Research, Vol. 52, Issue 3 https://doi.org/10.1021/acs.accounts.9b00004	journal	February 2019
Artificial Metalloenzymes: Reaction Scope and Optimization Strategies Schwizer, Fabian; Okamoto, Yasunori; Heinisch, Tillmann Chemical Reviews, Vol. 118, Issue 1 https://doi.org/10.1021/acs.chemrev.7b00014	journal	May 2017
Patterns of Ligands Coordinated to Metallocofactors Extracted from the Protein Data Bank Belmonte, Luca; Mansy, Sheref S. Journal of Chemical Information and Modeling, Vol. 57, Issue 12 https://doi.org/10.1021/acs.jcim.7b00468	journal	November 2017
The Depth of Chemical Time and the Power of Enzymes as Catalysts Wolfenden, Richard; Snider, Mark J. Accounts of Chemical Research, Vol. 34, Issue 12 https://doi.org/10.1021/ar000058i	journal	December 2001
Electrostatic Basis for Enzyme Catalysis Warshel, Arieh; Sharma, Pankaz K.; Kato, Mitsunori Chemical Reviews, Vol. 106, Issue 8 https://doi.org/10.1021/cr0503106	journal	August 2006
Protein Design: Toward Functional Metalloenzymes Yu, Fangting; Cangelosi, Virginia M.; Zastrow, Melissa L. Chemical Reviews, Vol. 114, Issue 7 https://doi.org/10.1021/cr400458x	journal	January 2014
Structural and Functional Aspects of Metal Sites in Biology Holm, Richard H.; Kennepohl, Pierre; Solomon, Edward I. Chemical Reviews, Vol. 96, Issue 7 https://doi.org/10.1021/cr9500390	journal	January 1996
Going beyond Structure: Nickel-Substituted Rubredoxin as a Mechanistic Model for the [NiFe] Hydrogenases Slater, Jeffrey W.; Marguet, Sean C.; Monaco, Haleigh A. Journal of the American Chemical Society, Vol. 140, Issue 32 https://doi.org/10.1021/jacs.8b05194	journal	July 2018
Kemp elimination catalysts by computational enzyme design Röthlisberger, Daniela; Khersonsky, Olga; Wollacott, Andrew M. Nature, Vol. 453, Issue 7192, p. 190-195 https://doi.org/10.1038/nature06879	journal	March 2008
Announcing the worldwide Protein Data Bank Berman, Helen; Henrick, Kim; Nakamura, Haruki Nature Structural & Molecular Biology, Vol. 10, Issue 12 https://doi.org/10.1038/nsb1203-980	journal	December 2003
Highly accurate protein structure prediction with AlphaFold Jumper, John; Evans, Richard; Pritzel, Alexander Nature https://doi.org/10.1038/s41586-021-03819-2	journal	July 2021
Chicken fat for catalysis: a scaffold is as important for molecular complexes for energy transformations as it is for enzymes in catalytic function Laureanti, Joseph A.; O'Hagan, Molly; Shaw, Wendy J. Sustainable Energy & Fuels, Vol. 3, Issue 12 https://doi.org/10.1039/C9SE00229D	journal	January 2019
Artificial metalloenzymes: proteins as hosts for enantioselective catalysis Thomas, Christophe M.; Ward, Thomas R. Chemical Society Reviews, Vol. 34, Issue 4 https://doi.org/10.1039/b314695m	journal	January 2005
Design of a single protein that spans the entire 2-V range of physiological redox potentials Hosseinzadeh, Parisa; Marshall, Nicholas M.; Chacón, Kelly N. Proceedings of the National Academy of Sciences, Vol. 113, Issue 2 https://doi.org/10.1073/pnas.1515897112	journal	December 2015
The extended environment of mononuclear metal centers in protein structures Karlin, S.; Zhu, Z. -Y.; Karlin, K. D. Proceedings of the National Academy of Sciences, Vol. 94, Issue 26 https://doi.org/10.1073/pnas.94.26.14225	journal	December 1997
MetalPredator: a web server to predict iron–sulfur cluster binding proteomes Valasatava, Yana; Rosato, Antonio; Banci, Lucia Bioinformatics, Vol. 32, Issue 18 https://doi.org/10.1093/bioinformatics/btw238	journal	June 2016
High precision protein functional site detection using 3D convolutional neural networks Torng, Wen; Altman, Russ B. Bioinformatics, Vol. 35, Issue 9 https://doi.org/10.1093/bioinformatics/bty813	journal	September 2018
MetalPDB: a database of metal sites in biological macromolecular structures Andreini, Claudia; Cavallaro, Gabriele; Lorenzini, Serena Nucleic Acids Research, Vol. 41, Issue D1 https://doi.org/10.1093/nar/gks1063	journal	November 2012
UniProt: a worldwide hub of protein knowledge Consortium, The UniProt Nucleic Acids Research https://doi.org/10.1093/nar/gky1049		November 2018
Learning to discriminate between ligand-bound and disulfide-bound cysteines Passerini, A.; Frasconi, P. Protein Engineering Design and Selection, Vol. 17, Issue 4 https://doi.org/10.1093/protein/gzh042	journal	May 2004
Similarity Analysis of 3D Structures of Proteins Based Tile-CNN Qin, Shengwei; Li, Zhong; He, Lexuan IEEE Access, Vol. 8 https://doi.org/10.1109/ACCESS.2020.2977945	journal	January 2020
Characterizing and Predicting Catalytic Residues in Enzyme Active Sites Based on Local Properties: A Machine Learning Approach Bobadilla, Leonardo; Nino, Fernando; Cepeda, Edilberto 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering https://doi.org/10.1109/BIBE.2007.4375671	conference	October 2007
ImageNet: A large-scale hierarchical image database Deng, Jia; Dong, Wei; Socher, Richard 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2009 IEEE Conference on Computer Vision and Pattern Recognition https://doi.org/10.1109/CVPR.2009.5206848	conference	June 2009
Multi-view Convolutional Neural Networks for 3D Shape Recognition Su, Hang; Maji, Subhransu; Kalogerakis, Evangelos 2015 IEEE International Conference on Computer Vision (ICCV) https://doi.org/10.1109/ICCV.2015.114	conference	December 2015
From sequence to enzyme mechanism using multi-label machine learning De Ferrari, Luna; Mitchell, John BO BMC Bioinformatics, Vol. 15, Issue 1 https://doi.org/10.1186/1471-2105-15-150	journal	May 2014
3D deep convolutional neural networks for amino acid environment similarity analysis Torng, Wen; Altman, Russ B. BMC Bioinformatics, Vol. 18, Issue 1 https://doi.org/10.1186/s12859-017-1702-0	journal	June 2017
Formation of Unstable and very Reactive Chemical Species Catalyzed by Metalloenzymes: A Mechanistic Overview Fernandes, Henrique S.; Teixeira, Carla S. Silva; Sousa, Sérgio F. Molecules, Vol. 24, Issue 13 https://doi.org/10.3390/molecules24132462	journal	July 2019
Artificial Metalloenzymes: From Selective Chemical Transformations to Biochemical Applications Himiyama, Tomoki; Okamoto, Yasunori Molecules, Vol. 25, Issue 13 https://doi.org/10.3390/molecules25132989	journal	June 2020

Similar Records

Classifying Metal-Binding Sites with Neural Networks

Dataset · Wed Sep 07 00:00:00 EDT 2022 · OSTI ID:1923007

Classifying metal‐binding sites with neural networks

Citation Formats

References (37)

Similar Records

Related Subjects