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

Abstract

Drug resistance represents a major obstacle to therapeutic innovations and is a prevalent feature in prostate cancer (PCa). Androgen receptors (ARs) are the hallmark therapeutic target for prostate cancer modulation and AR antagonists have achieved great success. However, rapid emergence of resistance contributing to PCa progression is the ultimate burden of their long-term usage. Hence, the discovery and development of AR antagonists with capability to combat the resistance, remains an avenue for further exploration. Therefore, this study proposes a novel deep learning (DL)-based hybrid framework, named DeepAR, to accurately and rapidly identify AR antagonists by using only the SMILES notation. Specifically, DeepAR is capable of extracting and learning the key information embedded in AR antagonists. Firstly, we established a benchmark dataset by collecting active and inactive compounds against AR from the ChEMBL database. Based on this dataset, we developed and optimized a collection of baseline models by using a comprehensive set of well-known molecular descriptors and machine learning algorithms. Then, these baseline models were utilized for creating probabilistic features. Finally, these probabilistic features were combined and used for the construction of a meta-model based on a one-dimensional convolutional neural network. Experimental results indicated that DeepAR is a more accurate and stable approach for identifying AR antagonists in terms of the independent test dataset, by achieving an accuracy of 0.911 and MCC of 0.823. In addition, our proposed framework is able to provide feature importance information by leveraging a popular computational approach, named SHapley Additive exPlanations (SHAP). In the meanwhile, the characterization and analysis of potential AR antagonist candidates were achieved through the SHAP waterfall plot and molecular docking. The analysis inferred that N-heterocyclic moieties, halogenated substituents, and a cyano functional group were significant determinants of potential AR antagonists. Lastly, we implemented an online web server by using DeepAR (at http://pmlabstack.pythonanywhere.com/DeepAR). We anticipate that DeepAR could be a useful computational tool for community-wide facilitation of AR candidates from a large number of uncharacterized compounds.

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

“…4 A-E) and selected feature dataset (Fig. 4 B-F), and colored them based on their potential correlating factors [ 59 ].…”

StackER: a novel SMILES-based stacked approach for the accelerated and efficient discovery of ERα and ERβ antagonists

“…The second point is to utilize efficient molecular representation learning (MRL), such as Mol2vec 85 , geometry-enhanced MRL 86 and self-supervised pretrained learning 87 strategies. The last point pertains to incorporating StackER with novel ML frameworks, such as a pre-trained language model 88 and DL-based framework 25 , 89 .…”

TROLLOPE: A novel sequence-based stacked approach for the accelerated discovery of linear T-cell epitopes of hepatitis C virus

“…Firstly, although our probabilistic features have more discriminative ability in TCE-HCV identification, there is still room for further improvement. For future work, we plan to fuse our probabilistic features with fingerprint descriptors (i.e., Estate, MACCS, and PubChem [85][86][87]) and sequence-to-vector encodings (i.e., word2vec). Secondly, the performance of TROLLOPE might be improved by combining it with powerful deep learning (DL) approaches, such as deep neural network (DNN) and transfer learning [88,89].…”