A Machine Learning Classification Model for Gold-Binding Peptides

Abstract

There has been growing interest in using peptides for the controlled synthesis of nanomaterials. Peptides play a crucial role not only in regulating the nanostructure formation process but also in influencing the resulting properties of the nanomaterials. Leveraging machine learning (ML) in the biomimetic workflow is anticipated to accelerate peptide discovery, make the process more resource-efficient, and unravel associations among attributes that may be useful in peptide design. In this study, a binary ML classifier is formulated that was trained and tested on 1720 peptide examples. The support vector machine classifier uses Kidera factors to categorize peptides into one of two groups based on their binding ability. The classifier exhibits satisfactory performance, as demonstrated by various performance metrics. In addition, key variables that bear a huge impact on the model were identified, such as peptide hydrophobicity. As these trends were derived from a large and diverse dataset, the insights drawn from the data are expected to be generalizable and robust. Thus, the presented ML model is an important step toward the rational and predictive peptide design.

Sequence rules for gold-binding peptides

“…Using machine learning in the form of association rule mining, an alternative method for the discovery of important positions and amino acids that are associated with binding affinity is presented. Although ML models have created in the past to study metal-binding peptides, [18][19][20]38,39 this is the rst attempt to use CBA to study their sequence patterns. Previous ML applications have focused on identifying the desired physicochemical properties of peptides associated with high binding affinity.…”

Material-specific binding peptides empower sustainable innovations in plant health, biocatalysis, medicine and microplastic quantification

“…Less important seems to be the presence of helical structures, or the preference between helices or bends. 525…”

“…Less important seems to be the presence of helical structures, or the preference between helices or bends. 525 In 2014, Palafox-Hernandez et al compared four gold and silver-binding eMBPs, namely AgBP1 (WAGAKRLVLRRE), AgBP2 (WALRRSIRRQSY), AuBP1 (TGIFKSARAMRN) and AuBP2 (EQLGVRKELRGV), on an experimental level and in silico to elucidate the molecular differences in binding. The preferred mode of gold binding is the direct interaction with the surface, while for binding silver the interaction was based on solventmediated interactions.…”

Characterization and Classification In Silico of Peptides with Dual Activity (Antimicrobial and Wound Healing)

“…This algorithm identifies clusters within the dataset by grouping peptides with similar properties. The resulting clustering information is then incorporated into the peptide database, assigning each peptide to its respective cluster [9,94]. A one-way ANOVA is carried out using SPSS version 27 (https://www.ibm.com/support/pages/ downloading-ibm-spss-statistics-27, accessed on 20 April 2023) [95].…”