Abstract
This study introduces MolAI, a robust deep learning model designed for data-driven molecular descriptor generation. Utilizing a vast training data set of 221 million unique compounds, MolAI employs an autoencoder neural machine translation model to generate latent space representations of molecules. The model demonstrated exceptional performance through extensive validation, achieving an accuracy of >99.8% in regenerating input molecules from their corresponding latent space. This study showcases the effectiveness of MolAI-driven molecular descriptors by developing an ML-based model (iLP) that accurately predicts the predominant protonation state of molecules at neutral pH. These descriptors also significantly enhance ligand-based virtual screening and are successfully applied in a framework (iADMET) for predicting ADMET features with high accuracy. This capability of encoding and decoding molecules to and from latent space opens unique opportunities in drug discovery, structure-activity relationship analysis, hit optimization, de novo molecular generation, and training infinite machine learning models.