StackPR is a new computational approach for large-scale identification of progesterone receptor antagonists using the stacking strategy

Abstract

Progesterone receptors (PRs) are implicated in various cancers since their presence/absence can determine clinical outcomes. The overstimulation of progesterone can facilitate oncogenesis and thus, its modulation through PR inhibition is urgently needed. To address this issue, a novel stacked ensemble learning approach (termed StackPR) is presented for fast, accurate, and large-scale identification of PR antagonists using only SMILES notation without the need for 3D structural information. We employed six popular machine learning (ML) algorithms (i.e., logistic regression, partial least squares, k-nearest neighbor, support vector machine, extremely randomized trees, and random forest) coupled with twelve conventional molecular descriptors to create 72 baseline models. Then, a genetic algorithm in conjunction with the self-assessment-report approach was utilized to determine m out of the 72 baseline models as means of developing the final meta-predictor using the stacking strategy and tenfold cross-validation test. Experimental results on the independent test dataset show that StackPR achieved impressive predictive performance with an accuracy of 0.966 and Matthew’s coefficient correlation of 0.925. In addition, analysis based on the SHapley Additive exPlanation algorithm and molecular docking indicates that aliphatic hydrocarbons and nitrogen-containing substructures were the most important features for having PR antagonist activity. Finally, we implemented an online webserver using StackPR, which is freely accessible at http://pmlabstack.pythonanywhere.com/StackPR. StackPR is anticipated to be a powerful computational tool for the large-scale identification of unknown PR antagonist candidates for follow-up experimental validation.

StackBRAF: A Large-Scale Stacking Ensemble Learning for BRAF Affinity Prediction

“…Nevertheless, the primary limitation of stacked models is that they can require high computational time when training with large datasets . Despite that the stacked models have been found to achieve high accuracies and have been applied in numerous drug design and healthcare prediction problems. ,− …”

“… 38 Despite that the stacked models have been found to achieve high accuracies and have been applied in numerous drug design and healthcare prediction problems. 25 , 39 − 41 …”

“…The canonical isomeric SMILES format was used to generate molecular fingerprints using PaDeL-Descriptor software . The SMILES strings have advantages in terms of their storage and easy handling compared to the 3D molecular structure or graph representation . The canonical isomeric SMILE is a stereochemistry unique SMILES notation that can be used to identify a unique compound with its stereochemistry .…”

“… 24 The SMILES strings have advantages in terms of their storage and easy handling compared to the 3D molecular structure or graph representation. 25 The canonical isomeric SMILE is a stereochemistry unique SMILES notation that can be used to identify a unique compound with its stereochemistry. 26 Molecular fingerprints represent the chemical substructures that are inherently present or absent in a molecule.…”

DeepAR: a novel deep learning-based hybrid framework for the interpretable prediction of androgen receptor antagonists

“…In this phase, we applied 12 well-known feature encodings to extract samples in the AR-TRN dataset, including CKD, CKDExt, CKDGraph, AP2D, KR, MACCS, Circle, Estate, Hybrid, PubChem, FP4C, and FP4. These molecular descriptors are widely used to represent several types of inhibitors [ 41 , 45 – 48 ]. In the meanwhile, 13 popular ML algorithms were selected for the construction of baseline models, including RF, AdaBoost (ADA), light gradient boosting machine (LGBM), partial least squares (PLS), multilayer perceptron (MLP), naive Bayes (NB), decision tree (DT), extremely randomized trees (ET), extreme gradient boosting (XGB), k-nearest neighbor (KNN), logistic regression (LR), support vector machine (SVM) combined with linear (SVMLN) and radial basis function (SVMRBF) kernels.…”