File 1 — Training Dataset (PubChem + ChEMBL) for Dr Lungker

Article Title: DrLungker: A Deep Ensemble Learning Framework for Predicting Anti-Lung Cancer Compound Activity and Validating Multitarget Potency through WaterMap, DFT, MD Simulations, and MM-GBSA AnalysisPublished in: Advanced Theory and SimulationsManuscript DOI: https://doi.org/10.1002/adts.202501550More Information: GitHub RepositoryDescriptionThis dataset (DrLungker_Dataset.csv) contains the fully curated molecular data used to train the DrLungker deep ensemble learning framework for predicting anti-lung cancer compound activity.Sources: PubChem and ChEMBL lung cancer bioassaysProcessing: Structure standardization, duplicate removal, descriptor generation using AlvaDesc and QikProp, and rigorous quality filteringContents: 26,396 unique compounds, each encoded with 5,883 molecular descriptorsUsage: Training the hybrid ResNet–FNN–LSTM ensemble using Averaging, Majority Voting, and Stacking techniquesThis dataset ensures full reproducibility of the DrLungker model and can be used for benchmarking, validation, and downstream computational drug-discovery applications.