Structural Analysis and Identification of Colloidal Aggregators in Drug Discovery

Abstract

Aggregation has been posing a great challenge in drug discovery. Current computational approaches aiming to filter out aggregated molecules based on their similarity to known aggregators, such as Aggregator Advisor, have low prediction accuracy, and therefore development of reliable in silico models to detect aggregators is highly desirable. In this study, we built a data set consisting of 12 119 aggregators and 24 172 drugs or drug candidates and then developed a group of classification models based on the combination of two ensemble learning approaches and five types of molecular representations. The best model yielded an accuracy of 0.950 and an area under the curve (AUC) value of 0.987 for the training set, and an accuracy of 0.937 and an AUC of 0.976 for the test set. The best model also gave reliable predictions to the external validation set with 5681 aggregators since 80% of molecules were predicted to be aggregators with a prediction probability higher than 0.9. More importantly, we explored the relationship between colloidal aggregation and molecular features, and generalized a set of simple rules to detect aggregators. Molecular features, such as log D, the number of hydroxyl groups, the number of aromatic carbons attached to a hydrogen atom, and the number of sulfur atoms in aromatic heterocycles, would be helpful to distinguish aggregators from nonaggregators. A comparison with numerous existing druglikeness and aggregation filtering rules and models used in virtual screening verified the high reliability of the model and rules proposed in this study. We also used the model to screen several curated chemical databases, and almost 20% of molecules in the evaluated databases were predicted as aggregators, highlighting the potential high risk of aggregation in screening. Finally, we developed an online Web server of ChemAGG (http://admet.scbdd.com/ChemAGG/index), which offers a freely available tool to detect aggregators.

ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties

“…Currently, there are many online prediction servers for the evaluation of certain ADMET parameters, such as SuperCYPsPred ( 47 ) for cytochrome activity prediction, eMolTox ( 48 ) for potential toxicity prediction, ChemAGG ( 49 ) for colloidal aggregators identification, etc. Meanwhile, several excellent online platforms have been proposed for more systematic and convenient ADMET predictions, including SwissADME ( 14 ), admetSAR 2.0 ( 13 ), FAF-Drugs4 ( 12 ), pkCSM ( 16 ) and vNN-ADMET ( 50 ).…”

Computational Approaches in Preclinical Studies on Drug Discovery and Development

“…In QSAR studies, compounds can be mathematically codified as molecular descriptors, and the relationship between molecular descriptors and defined properties is constructed by statistical methods, after which a generated model is used to predict the corresponding properties of new compounds (Michielan and Moro, 2010 ). This method first transforms molecular structure into molecular descriptors, which are then used to establish prediction models by using statistical approaches or machine learning techniques such as support vector machine (SVM) and K Nearest Neighbor (kNN) (Wang S. et al, 2016 ; Wu et al, 2019 ; Yang et al, 2019 ; Fu et al, 2020 ). For example, Schyman et al ( 2017 ) used the variable nearest neighbor (vNN) method to develop 15 ADMET prediction models and to use them to quickly assess some potential drug candidates, including toxicity, microsomal stability, mutagenicity, and likelihood of causing drug-induced liver injury.…”

Semi-automated workflow for molecular pair analysis and QSAR-assisted transformation space expansion

“…Based on our previous experiences, four effective ML algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and gradient boosting (GB), are provided in this pipeline for model construction [ 35 – 37 ]. According to our previous studies, a consensus model constructed by averaging the outputs of multiple individual models is recommended for the final predictions in this pipeline [ 38 – 41 ]. Considering the importance of model hyper-parameters, the MMPA-by-QSAR pipeline uses the grid search method and a validation set to optimize model hyper-parameters.…”