scholarly journals Machine learning differentiates enzymatic and non-enzymatic metals in proteins

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Ryan Feehan ◽  
Meghan W. Franklin ◽  
Joanna S. G. Slusky
Keyword(s):  
Machine Learning ◽  
Metal Binding ◽  
Binding Sites ◽  
Active Sites ◽  
De Novo ◽  
Enzyme Design ◽  
Metal Binding Sites ◽  
Ensemble Machine Learning ◽  
Machine Learning Model ◽  
Physicochemical Features

AbstractMetalloenzymes are 40% of all enzymes and can perform all seven classes of enzyme reactions. Because of the physicochemical similarities between the active sites of metalloenzymes and inactive metal binding sites, it is challenging to differentiate between them. Yet distinguishing these two classes is critical for the identification of both native and designed enzymes. Because of similarities between catalytic and non-catalytic  metal binding sites, finding physicochemical features that distinguish these two types of metal sites can indicate aspects that are critical to enzyme function. In this work, we develop the largest structural dataset of enzymatic and non-enzymatic metalloprotein sites to date. We then use a decision-tree ensemble machine learning model to classify metals bound to proteins as enzymatic or non-enzymatic with 92.2% precision and 90.1% recall. Our model scores electrostatic and pocket lining features as more important than pocket volume, despite the fact that volume is the most quantitatively different feature between enzyme and non-enzymatic sites. Finally, we find our model has overall better performance in a side-to-side comparison against other methods that differentiate enzymatic from non-enzymatic sequences. We anticipate that our model’s ability to correctly identify which metal sites are responsible for enzymatic activity could enable identification of new enzymatic mechanisms and de novo enzyme design.

scholarly journals Machine Learning Differentiates Enzymatic and Non-Enzymatic Metals in Proteins

2021 ◽  
Author(s):  
Ryan Feehan ◽  
Meghan W. Franklin ◽  
Joanna S.G. Slusky
Keyword(s):  
Machine Learning ◽  
Metal Binding ◽  
Binding Sites ◽  
Active Sites ◽  
De Novo ◽  
Enzyme Design ◽  
Metal Binding Sites ◽  
Ensemble Machine Learning ◽  
Machine Learning Model ◽  
Physicochemical Features

AbstractMetalloenzymes are 40% of all enzymes and can perform all seven classes of enzyme reactions. Because of the physicochemical similarities between the active sites of metalloenzymes and inactive metal binding sites, it is challenging to differentiate between them. Yet distinguishing these two classes is critical for the identification of both native and designed enzymes. Because of similarities between these two types of metal binding sites, finding physicochemical features that distinguish active and inactive metal sites can indicate aspects that are critical to enzyme function. In this work, we develop the largest structural dataset of enzymatic and non-enzymatic metalloprotein sites to date. We then use a decision-tree ensemble machine learning model to classify metals bound to proteins as enzymatic or non-enzymatic with 92.2% precision and 90.1% recall. Our model scores electrostatic and pocket lining features as more important than pocket volume, despite the fact that volume is the most quantitatively different feature between enzyme and non-enzymatic sites. Finally, we find our model has overall better performance in a side-to-side comparison against other methods that differentiate enzymatic from non-enzymatic sequences. We anticipate that our model’s ability to correctly identify which metal sites are responsible for enzymatic activity could enable identification of new enzymatic mechanisms and de novo enzyme design.

scholarly journals Computational approaches for de novo design and redesign of metal-binding sites on proteins

2017 ◽  
Vol 37 (2) ◽  
Author(s):  
Gunseli Bayram Akcapinar ◽  
Osman Ugur Sezerman
Keyword(s):  
Metal Ions ◽  
Metal Binding ◽  
Binding Sites ◽  
Metal Ion ◽  
De Novo ◽  
De Novo Design ◽  
Ion Binding ◽  
Chemical Transformations ◽  
Metal Ion Binding ◽  
Metal Binding Sites

Metal ions play pivotal roles in protein structure, function and stability. The functional and structural diversity of proteins in nature expanded with the incorporation of metal ions or clusters in proteins. Approximately one-third of these proteins in the databases contain metal ions. Many biological and chemical processes in nature involve metal ion-binding proteins, aka metalloproteins. Many cellular reactions that underpin life require metalloproteins. Most of the remarkable, complex chemical transformations are catalysed by metalloenzymes. Realization of the importance of metal-binding sites in a variety of cellular events led to the advancement of various computational methods for their prediction and characterization. Furthermore, as structural and functional knowledgebase about metalloproteins is expanding with advances in computational and experimental fields, the focus of the research is now shifting towards de novo design and redesign of metalloproteins to extend nature’s own diversity beyond its limits. In this review, we will focus on the computational toolbox for prediction of metal ion-binding sites, de novo metalloprotein design and redesign. We will also give examples of tailor-made artificial metalloproteins designed with the computational toolbox.

scholarly journals BioMetAll: Identifying Metal-Binding Sites in Proteins from Backbone Preorganization

2020 ◽  
Author(s):  
José-Emilio Sánchez-Aparicio ◽  
Laura Tiessler-Sala ◽  
Lorea Velasco-Carneros ◽  
Lorena Roldán-Martín ◽  
Giuseppe Sciortino ◽  
...  
Keyword(s):  
Metal Binding ◽  
Binding Sites ◽  
De Novo ◽  
Conformational Transition ◽  
Protein Backbone ◽  
Metal Binding Sites ◽  
Structural Match ◽  
Geometric Descriptors ◽  
Metal Migration

<div><div><div><p>With a large amount of research dedicated to decoding how metallic species bind to protein, in silico methods are interesting allies for experimental procedures. To date, computational predictors mostly work by identifying the best possible sequence or structural match of the target protein with metal binding templates. These approaches are fundamentally focused on the first coordination sphere of the metal. Here, we present the BioMetAll predictor that is based on a different postulate: the formation of a potential metal-binding site is related to the geometric organization of the protein backbone. We first report the set of convenient geometric descriptors of the backbone needed for the algorithm and their parametrization from a statistical analysis. Then, the successful benchmark of BioMetAll on a set of more than 50 metal-binding X-Ray structures is presented. Because BioMetAll allows structural predictions regardless of the exact geometry of the side chains, it appears extremely valuable for systems which structures (either experimental or theoretical) are not optimal for metal binding sites. We report here its application on three different challenging cases i) the modulation of metal-binding sites during conformational transition in human serum albumin, ii) the identification of possible routes of metal migration in hemocyanins, and iii) the prediction of mutations to generate convenient metal-binding sites for de novo biocatalysts. This study shows that BioMetAll offers a versatile platform for numerous fields of research at the interface between inorganic chemistry and biology, and allows to highlight the role of the preorganization of the protein backbone as a marker for metal binding.</p></div></div></div>

scholarly journals BioMetAll: Identifying Metal-Binding Sites in Proteins from Backbone Preorganization

2020 ◽  
Author(s):  
José-Emilio Sánchez-Aparicio ◽  
Laura Tiessler-Sala ◽  
Lorea Velasco-Carneros ◽  
Lorena Roldán-Martín ◽  
Giuseppe Sciortino ◽  
...  
Keyword(s):  
Metal Binding ◽  
Binding Sites ◽  
De Novo ◽  
Conformational Transition ◽  
Protein Backbone ◽  
Metal Binding Sites ◽  
Structural Match ◽  
Geometric Descriptors ◽  
Metal Migration

<div><div><div><p>With a large amount of research dedicated to decoding how metallic species bind to protein, in silico methods are interesting allies for experimental procedures. To date, computational predictors mostly work by identifying the best possible sequence or structural match of the target protein with metal binding templates. These approaches are fundamentally focused on the first coordination sphere of the metal. Here, we present the BioMetAll predictor that is based on a different postulate: the formation of a potential metal-binding site is related to the geometric organization of the protein backbone. We first report the set of convenient geometric descriptors of the backbone needed for the algorithm and their parametrization from a statistical analysis. Then, the successful benchmark of BioMetAll on a set of more than 50 metal-binding X-Ray structures is presented. Because BioMetAll allows structural predictions regardless of the exact geometry of the side chains, it appears extremely valuable for systems which structures (either experimental or theoretical) are not optimal for metal binding sites. We report here its application on three different challenging cases i) the modulation of metal-binding sites during conformational transition in human serum albumin, ii) the identification of possible routes of metal migration in hemocyanins, and iii) the prediction of mutations to generate convenient metal-binding sites for de novo biocatalysts. This study shows that BioMetAll offers a versatile platform for numerous fields of research at the interface between inorganic chemistry and biology, and allows to highlight the role of the preorganization of the protein backbone as a marker for metal binding.</p></div></div></div>

scholarly journals Rational design of metal-binding sites in domain-swapped myoglobin dimers

2021 ◽  
Vol 217 ◽  
pp. 111374
Author(s):  
Satoshi Nagao ◽  
Ayaka Idomoto ◽  
Naoki Shibata ◽  
Yoshiki Higuchi ◽  
Shun Hirota
Keyword(s):  
Metal Binding ◽  
Binding Sites ◽  
Rational Design ◽  
Metal Binding Sites

scholarly journals Electron transfer pathways in photoexcited lanthanide(III) complexes of picolinate ligands

2021 ◽  
Author(s):  
Daniel Kovacs ◽  
Daniel Kocsi ◽  
Jordann A. L. Wells ◽  
Salauat R. Kiraev ◽  
Eszter Borbas
Keyword(s):  
Electron Transfer ◽  
Metal Binding ◽  
Binding Sites ◽  
Secondary Amide ◽  
Metal Binding Sites ◽  
Electron Transfer Pathways

A series of luminescent lanthanide(III) complexes consisting of 1,4,7-triazacyclononane frameworks and three secondary amide-linked carbostyril antennae were synthesised. The metal binding sites were augmented with two pyridylcarboxylate donors yielding octadentate...

Sign in / Sign up

Export Citation Format

Share Document