Development of CDK-targeted scoring functions for prediction of binding affinity.

Cyclin-dependent kinase (CDK) is an interesting biological macromolecule due to its role in cell cycle progression, transcription control, and neuronal development, to mention the most studied biological activities. Furthermore, the availability of hundreds of structural studies focused on the intermolecular interactions of CDK with competitive inhibitors makes possible to develop computational models to predict binding affinity, where the atomic coordinates of binary complexes involving CDK and ligands can be used to train a machine learning model. The present work is focused on the development of new machine learning models to predict binding affinity for CDK. The CDK-targeted machine learning models were compared with classical scoring functions such as MolDock, AutoDock 4, and Vina Scores. The overall performance of our CDK-targeted scoring function was higher than the previously mentioned scoring functions, which opens the possibility of increasing the reliability of virtual screening studies focused on CDK.

Understanding the Structural Basis for Inhibition of Cyclin-Dependent Kinases. New Pieces in the Molecular Puzzle.

BACKGROUND: Cyclin-dependent kinases (CDKs) comprise an important protein family for development of drugs, mostly aimed for use in treatment of cancer but there is also potential for development of drugs for neurodegenerative diseases and diabetes. Since the early 1990s, structural studies have been carried out on CDKs, in order to determine the structural basis for inhibition of this protein target. OBJECTIVE: Our goal here is to review recent structural studies focused on CDKs. We concentrate on latest developments in the understanding of the structural basis for inhibition of CDKs, relating structures and ligand-binding information. METHOD: Protein crystallography has been successfully applied to elucidate over 400 CDK structures. Most of these structures are complexed with inhibitors. We use this richness of structural information to describe the major structural features determining the inhibition of this enzyme. RESULTS: Structures of CDK1, 2, 4-9, 12 13, and 16 have been elucidated. Analysis of these structures in complex with a wide range of different competitive inhibitors, strongly indicate some common features that can be used to guide the development of CDK inhibitors, such as a pattern of hydrogen bonding and the presence of halogen atoms in the ligand structure. CONCLUSION: Nowadays we have structural information for hundreds of CDKs. Combining the structural and functional information we may say that a pattern of intermolecular hydrogen bonds is of pivotal importance for inhibitor specificity. In addition, machine learning techniques have shown improvements in predicting binding affinity for CDKs.