Exploring Potency and Selectivity Receptor Antagonist Profiles Using a Multilabel Classification Approach: The Human Adenosine Receptors as a Key Study

Abstract

Nowadays, in medicinal chemistry adenosine receptors represent some of the most studied targets, and there is growing interest on the different adenosine receptor (AR) subtypes. The AR subtypes selectivity is highly desired in the development of potent ligands to achieve the therapeutic success. So far, very few ligand-based strategies have been investigated to predict the receptor subtypes selectivity. In the present study, we have carried out a novel application of the multilabel classification approach by combining our recently reported autocorrelated molecular descriptors encoding for the molecular electrostatic potential (autoMEP) with support vector machines (SVMs). Three valuable models, based on decreasing thresholds of potency, have been generated as in series quantitative sieves for the simultaneous prediction of the hA(1)R, hA(2A)R, hA(2B)R, and hA(3)R subtypes potency profile and selectivity of a large collection, more than 500, of known inverse agonists such as xanthine, pyrazolo-triazolo-pyrimidine, and triazolo-pyrimidine analogues. The robustness and reliability of our multilabel classification models were assessed by predicting an internal test set. Finally, we have applied our strategy to 13 newly synthesized pyrazolo-triazolo-pyrimidine derivatives inferring their full adenosine receptor potency spectrum and hAR subtypes selectivity profile.

The A3 adenosine receptor as multifaceted therapeutic target: pharmacology, medicinal chemistry, and in silico approaches

“…Subsequently, the same authors employed a multilabel classification approach combining the autocorrelated molecular descriptors (i.e. auto MEP) with SVMs on about 500 known hAR antagonists that included xanthine derivatives . Such multilabel classification approach allows the analysis of large data set that are nonmutually exclusive and overlapping classes, and pertinent to some hA 3 AR antagonists which may present good potency profiles for more than one receptor subtypes.…”

“…auto-MEP) with SVMs on about 500 known hAR antagonists that included xanthine derivatives. 329 Such multilabel classification approach allows the analysis of large data set that are nonmutually exclusive and overlapping classes, and pertinent to some hA 3 AR antagonists which may present good potency profiles for more than one receptor subtypes. Three quantitative models built on decreasing thresholds of potency were generated, for the simultaneous prediction of the hAR antagonists' profile at hA 1 , hA 2A , hA 2B , and hA 3 ARs with appreciable accuracy.…”

Predicting Subtype Selectivity for Adenosine Receptor Ligands with Three-Dimensional Biologically Relevant Spectrum (BRS-3D)

“…In fact, QSAR played an indispensable role in GPCR subtype selective ligand design1415, e.g., ARs16, dopamine receptors17, serotonin receptors 5HT1E/5HT1F18 and cannabinoid receptor CB1/CB21920. For AR ligands, Michelan et al .…”

“…For AR ligands, Michelan et al . introduced a multi-label classification approach, the so-called cross-training with SVM (ct-SVM), to derive compound potency profiles against human AR subtypes and to predict the selectivity16. They further applied SVM classification and regression in combination in predicting the selectivity profiles of adenosine A 2A and A 3 antagonists and their binding affinities21.…”

Enhancing reaction-based de novo design using a multi-label reaction class recommender

“…Training the recommender is, therefore, configured as a multi-label classification problem [14]. Multi-label classification approaches have previously been used to predict the activity profiles of small molecules against a panel of protein targets [15][16][17][18][19], drug side-effects [20], and to identify possible plant sources for natural products [21].…”