Quantum_Kinase_dataset

Here’s a clean one-paragraph description you can drop straight into your research paper: This dataset is a synthetic quantum-enhanced molecular screening benchmark designed for kinase–ligand interaction modeling using Quantum Machine Learning (QML) techniques. It contains 500 small-molecule compounds, each annotated with target kinase class, SMILES-based structural representations, quantum-physics descriptors (ground and excited state energies, energy gap, entanglement score, dipole moment, HOMO–LUMO gap, and quantum-state fidelity), and classical cheminformatics features such as molecular weight, LogP, TPSA, H-bond donors/acceptors, and rotatable bonds. Binding affinity (pKd) values are included as the regression target variable, enabling evaluation of hybrid QML–chemoinformatics models. The dataset was programmatically generated using randomized molecular structures and simulated quantum descriptors to support experimentation in quantum feature extraction, QPE-based modeling, and QML benchmarking. Although synthetic, the dataset follows real-world biochemical distributions and can be made publicly available through open repositories such as GitHub, Zenodo, or Kaggle for reproducible research, validation, and comparison of QML frameworks.