QSPR Prediction of the Stability Constants of Gadolinium(III) Complexes for Magnetic Resonance Imaging

Abstract

Gadolinium(III) complexes constitute the largest class of compounds used as contrast agents for Magnetic Resonance Imaging (MRI). A quantitative structure-property relationship (QSPR) machine-learning based method is applied to predict the thermodynamic stability constants of these complexes (log KGdL), a property commonly associated with the toxicity of such organometallic pharmaceuticals. In this approach, the log KGdL value of each complex is predicted by a graph machine, a combination of parametrized functions that encodes the 2D structure of the ligand. The efficiency of the predictive model is estimated on an independent test set; in addition, the method is shown to be effective (i) for estimating the stability constants of uncharacterized, newly synthesized polyamino-polycarboxylic compounds and (ii) for providing independent log KGdL estimations for complexants for which conflicting or questionable experimental data were reported. The exhaustive database of log KGdL values for 158 complexants, reported for potential application as contrast agents for MRI and used in the present study, is available in the Supporting Information (122 primary literature sources).

Coordination Chemistry and f-Element Complexation by Diethylenetriamine-N,N″-bis(acetylglycine)-N,N′,N″-triacetic Acid

“…Wang et al discussed this decrease in the complex stability in terms of the overall weakening of the Lewis base donor capacity of the amide groups, coupled with the lower basicity of the terminal amines . The overall 10 6 -fold decrease in the stability of the complexes observed here for DTTA-DAG throughout the lanthanide series has been consistently observed for different diamide-substituted reagents. ,,− …”

Predicting the Surface Tension of Liquids: Comparison of Four Modeling Approaches and Application to Cosmetic Oils

“…Details of the above steps are provided in a previous paper and references therein. The bias-variance dilemma applies to graph machines as well as to any machine learning method, so an appropriate model selection procedure must be performed.…”

“…For molecules that contain cycles, hence are represented by a cyclic graph, edges are deleted in order to form an acyclic graph in which every path of the graph has its end at a specific node called "output node". 42 and references therein. The bias-variance dilemma applies to graph machines as well as to any machine learning method, so an appropriate model selection procedure must be performed.…”

Contrast agents for cardiovascular magnetic resonance imaging: an overview

“…The chemical structure of a CA is fundamental for understanding its mode of action. By using the current CAs as a lead and the Structure-Activity Relationship (SAR), synthetic and medicinal chemists can predict and design improved CAs by tuning their capability to alter T 1 and T 2 , increase their stability 22 in the bloodstream and improve specificity for damaged CVS. Chemists can also design novel synthetic routes of promising CAs in a costeffective fashion.…”