Classification of Metal Binders by Naïve Bayes Classifier on the Base of Molecular Fragment Descriptors and Ensemble Modeling

Abstract

Here, we report two‐class classification models for organic molecules (“ligands”) able to bind various metal cations in water. The modeling was performed on 30 data sets, each corresponding to a particular metal, using the Naïve Bayes method and the ISIDA fragment descriptors. The ligands were classified on weak and strong binders according to threshold of the logarithm of the stability constant of the 1 : 1 (metal : ligand) complexes. The “consensus models” consisted each of 50 best individual models demonstrated a good predictive performance in 5‐fold cross validation: the balanced accuracy (BA) varies from 0.965 (Yb3+) to 0.767 (Mg2+). The best predictions (BA>0.90) were obtained for the binders of rare‐earth metals (Yb3+, Tm3+, Er3+, Lu3+, Ho3+, Gd3+ and Dy3+) and Pb2+. For 17 small external test sets of new ligands, BA varies from 0.800 to 1. The impact of variables selection on the predictive performance of the models is discussed.

Rational Screening of Mn(II) Metal-Ligand Complexes for Using as MRI Contrast Agents Using Machine Learning

“…However, it is usually formulated as a regression problem. QSPR regression models were widely used for the modeling of metal complexation uisng organic ligands in water Baskin et al [2017], Chaube et al [2020], Gakh et al [1997], Solov'ev and Tsivadze [2023], Solov'ev et al [2000Solov'ev et al [ , 2006Solov'ev et al [ , 2013Solov'ev et al [ , 2019Solov'ev et al [ , 2015Solov'ev et al [ , 2014Solov'ev et al [ , 2012Solov'ev et al [ , 2021, Solov"ev and Varnek [2004], Solovev et al [2012], Uzal-Varela et al [2022], Kanahashi et al [2022], Kireeva et al [2023]. The data description used in this study is based on the molecular descriptors implemented in the Dragon software package Mauri et al [2006].…”

Innovative Materials Science via Machine Learning

“…Classification algorithm C4.5 [125] Analysis of the causes of Coffee defects by decision Tree [126] Naive Bayes [127] Classification of metal binders [128] SVM [129] Material monitoring and defect diagnosis [130] Prediction of rock brittleness [131] KNN [132] Prediction of process parameters of reinforced metal casting [133] Analysis of welding modeling of different materials [134] Adaboost [135] Temperature compensation of Silicon Piezoresistive pressure Sensor [136] Cart [137] Differential diagnosis of mucosanase [138] Clustering algorithm K-Means [139] Structural texture similarity recognition of materials [140] Establishment of parametric homogenized crystal plasticity model of single crystal Ni-base superalloy [141] EM [142] Estimation of dose distribution from positron emitter distribution combined with filtering [143] Correlation distribution Apriori [144] Identify the frequency trajectory of material transportation [145] Connection analysis PageRank [146] Measurement of hyperelastic materials [147] Remote protein homology detection [148] open-source material packages and machine learning frameworks could be effectively connected by the cloud-based interconnected applications. At present, in the research of machine learning in materials science, the materials-related open-source toolkits and programming language frameworks have been well designed by programming tools, which can provide great convenience for non-professional programming researchers, such as materials researchers.…”

QSPR Modeling of Potentiometric Mg2+/Ca2+ Selectivity for PVC‐plasticized Sensor Membranes

“…In several studies, the QSPR approach was successfully employed to predict the stability constants of various metal‐ligand complexes in solution and equilibrium characteristics in liquid extraction processes , and studies of metal toxicity . This method suits well for the modeling of complex media and allows taking into account several issues, such as solvation effects, additives, and solvents; therefore, the modeling results rely on the previous experimental data and correspond well to the results of subsequent experiments.…”