Cheminformatic Analysis and Machine Learning Modeling to Investigate Androgen Receptor Antagonists to Combat Prostate Cancer

Abstract

Prostate cancer (PCa) is a major leading cause of mortality of cancer among males. There have been numerous studies to develop antagonists against androgen receptor (AR), a crucial therapeutic target for PCa. This study is a systematic cheminformatic analysis and machine learning modeling to study the chemical space, scaffolds, structure−activity relationship, and landscape of human AR antagonists. There are 1678 molecules as final data sets. Chemical space visualization by physicochemical property visualization has demonstrated that molecules from the potent/active class generally have a mildly smaller molecular weight (MW), octanol−water partition coefficient (log P), number of hydrogen-bond acceptors (nHA), number of rotatable bonds (nRot), and topological polar surface area (TPSA) than molecules from intermediate/inactive class. The chemical space visualization in the principal component analysis (PCA) plot shows significant overlapping distributions between potent/active class molecules and intermediate/inactive class molecules; potent/active class molecules are intensively distributed, while intermediate/inactive class molecules are widely and sparsely distributed. Murcko scaffold analysis has shown low scaffold diversity in general, and scaffold diversity of potent/active class molecules is even lower than intermediate/inactive class molecules, indicating the necessity for developing molecules with novel scaffolds. Furthermore, scaffold visualization has identified 16 representative Murcko scaffolds. Among them, scaffolds 1, 2, 3, 4, 7, 8, 10, 11, 15, and 16 are highly favorable scaffolds due to their high scaffold enrichment factor values. Based on scaffold analysis, their local structure−activity relationships (SARs) were investigated and summarized. In addition, the global SAR landscape was explored by quantitative structure−activity relationship (QSAR) modelings and structure−activity landscape visualization. A QSAR classification model incorporating all of the 1678 molecules stands out as the best model from a total of 12 candidate models for AR antagonists (built on PubChem fingerprint, extra trees algorithm, accuracy for training set: 0.935, 10-fold cross-validation set: 0.735 and test set: 0.756). Deeper insights into the structure−activity landscape highlighted a total of seven significant activity cliff (AC) generators (ChEMBL molecule IDs : 160257, 418198, 4082265, 348918, 390728, 4080698, and 6530), which provide valuable SAR information for medicinal chemistry. The findings in this study provide new insights and guidelines for hit identification and lead optimization for the development of novel AR antagonists.

Classifying Beta-Secretase 1 Inhibitor Activity for Alzheimer’s Drug Discovery with LightGBM

“…Descriptors exhibiting zero variance across the dataset were removed, as they do not contribute to discrimination between active and inactive compounds. Additionally, we applied a threshold of 0.95 for multicollinearity, removing descriptors that were highly correlated with each other [33]. This step aimed to retain only the most relevant and non-redundant descriptors for our classification task.…”

Integrating Genetic Algorithm and LightGBM for QSAR Modeling of Acetylcholinesterase Inhibitors in Alzheimer's Disease Drug Discovery

“…Next, we removed duplicate data and left 6157 compounds. To carry out the classification process, we construct a class variable by converting the IC50 value to pIC50, and if the pIC50 value < 6, then the compound is assigned to an inactive class, and if pIC50 ≥, then the compound is active [24]. Among the 6157 compounds, 3591 of them (58.32%) were classified as inactive, and 2566 compounds (41.68%) were categorized as active.…”

“…We used Mordred to derive 1661 2D-molecular descriptors for each AChE inhibitor compound. Molecular descriptors with high correlation (>0.95) and low variance (<0.1) were eliminated, leaving 280 molecular descriptors [24].…”

Machine Learning Approaches to Investigate the Structure–Activity Relationship of Angiotensin-Converting Enzyme Inhibitors

“…4 Quantitative structure−activity/property relationship (QSAR/QSPR) represents an in silico mathematical model used for predicting the bioactivities or properties of compounds based on their structures and physicochemical parameters. 5,6 QSAR/QSPR is fundamentally based on two key principles: (i) the structure of a compound determines its bioactivity/property and (ii) compounds with more similar structures exhibit more similar bioactivities or properties. 6 Particularly, structural information on compounds is represented using a range of molecular descriptors or fingerprints.…”

“…5,6 QSAR/QSPR is fundamentally based on two key principles: (i) the structure of a compound determines its bioactivity/property and (ii) compounds with more similar structures exhibit more similar bioactivities or properties. 6 Particularly, structural information on compounds is represented using a range of molecular descriptors or fingerprints. These descriptors play a crucial role in determining the robustness, generalization, and predictability.…”