GPCR_LigandClassify.py; a rigorous machine learning classifier for GPCR targeting compounds

Abstract

The current study describes the construction of various ligand-based machine learning models to be used for drug-repurposing against the family of G-Protein Coupled Receptors (GPCRs). In building these models, we collected > 500,000 data points, encompassing experimentally measured molecular association data of > 160,000 unique ligands against > 250 GPCRs. These data points were retrieved from the GPCR-Ligand Association (GLASS) database. We have used diverse molecular featurization methods to describe the input molecules. Multiple supervised ML algorithms were developed, tested and compared for their accuracy, F scores, as well as for their Matthews’ correlation coefficient scores (MCC). Our data suggest that combined with molecular fingerprinting, ensemble decision trees and gradient boosted trees ML algorithms are on the accuracy border of the rather sophisticated deep neural nets (DNNs)-based algorithms. On a test dataset, these models displayed an excellent performance, reaching a ~ 90% classification accuracy. Additionally, we showcase a few examples where our models were able to identify interesting connections between known drugs from the Drug-Bank database and members of the GPCR family of receptors. Our findings are in excellent agreement with previously reported experimental observations in the literature. We hope the models presented in this paper synergize with the currently ongoing interest of applying machine learning modeling in the field of drug repurposing and computational drug discovery in general.

Chemokine Receptors—Structure-Based Virtual Screening Assisted by Machine Learning

“…For this reason, drug repositioning is frequently used to limit both the cost and the number of failures [ 50 ]. Computational methods, including machine learning or artificial intelligence, can be also used to significantly reduce the initial discovery costs [ 51 , 52 ]. Prediction models that utilize machine learning include, e.g., Glmnet, XGBoost, or LightGBM [ 53 ].…”

Relativistic quantum oscillator model under the effects of the violation of Lorentz symmetry by an arbitrary fixed vector field

“…[28], applied to spin-half fermions. The Klein-Gordon oscillator has been studied, for example, in cosmic string space-time with an external field [29], in the context of Kaluza-Klein theory [30][31][32][33][34], with non-inertial effects in cosmic string space-time [35,36], in the Som-Raychaudhuri space-time with a cosmic string [37], in a topologically non-trivial space-time [38], in a global monopole space-time with rainbow gravity [39], in a global monopole space-time [40,41], quantum behavior of a charged particle under a uniform magnetic field [42], relativistic quantum oscillator in a topologically charged Ellis-Bronnikov-type wormhole space-time [43]. Under Lorentz symmetry violation effects, the Klein-Gordon oscillator has been studied, for example, with a linear confining potential [44], with a Coulomb-type potential [45], relativistic scalar oscillator field [46,47], and the generalized Klein-Gordon oscillator [48,49].…”

Effects of Quantum Flux on Generalized KG-Oscillator in Ellis-Bronnikov-Type Wormhole with Point-Like Defect

“…For δ → 0, the function becomes Coulomb-type which we discussed earlier. This type of potential function has widely been investigated in the context of quantum systems both in the relativistic and non-relativistic limit [49][50][51][52][53][54]. Thereby, substituting this function (23) in the Eq.…”