CDK2 inhibitors(Gwangju Institute of Science & Technology)

Characterizing the kinome selectivity profiles of kinase inhibitors is essential in the early stages of novel small-molecule drug discovery. This characterization is critical for interpreting potential adverse events caused by off-target polypharmacology effects and provides unique pharmacological insights for drug repurposing development of existing kinase inhibitor drugs. However, experimental profiling of whole kinome selectivity is still time-consuming and resource-demanding. Here, we report a deep learning classification model using an in-house built data set of inhibitors against 191 well-representative kinases constructed based on a novel strategy by systematically cleaning and integrating six public data sets. This model, a multitask deep neural network, predicts the kinome selectivity profiles of compounds with novel structures. The model demonstrates excellent predictive performance, with auROC, prc-AUC, Accuracy, and Binary_cross_entropy of 0.95, 0.92, 0.90, and 0.37, respectively. It also performs well in a priori testing for inhibitors targeting different categories of proteins from internal compound collections, significantly improving over similar models on data sets from practical application scenarios. Integrated to subsequent machine learning-enhanced virtual screening workflow, novel CDK2 kinase inhibitors with potent kinase inhibitory activity and excellent kinome selectivity profiles are successfully identified. Additionally, we developed a free online web server, KinomePro-DL, to predict the kinome selectivity profiles and kinome-wide polypharmacology effects of small molecules (available on kinomepro-dl.pharmablock.com). Uniquely, our model allows users to quickly fine-tune it with their own training data sets, enhancing both prediction accuracy and robustness.

Anti-EGFR antibodies show limited response in breast cancer, partly due to activation of compensatory pathways. Furthermore, despite the clinical success of cyclin-dependent kinase (CDK) 4/6 inhibitors in hormone receptor–positive tumors, aggressive triple-negative breast cancers (TNBC) are largely resistant due to CDK2/cyclin E expression, whereas free CDK2 inhibitors display normal tissue toxicity, limiting their therapeutic application. A cetuximab-based antibody drug conjugate (ADC) carrying a CDK inhibitor selected based on oncogene dysregulation, alongside patient subgroup stratification, may provide EGFR-targeted delivery.

Expressions of G1/S-phase cell cycle regulators were evaluated alongside EGFR in breast cancer. We conjugated cetuximab with CDK inhibitor SNS-032, for specific delivery to EGFR-expressing cells. We assessed ADC internalization and its antitumor functions in vitro and in orthotopically grown basal-like/TNBC xenografts.

Transcriptomic (6,173 primary, 27 baseline, and matched post-chemotherapy residual tumors), single-cell RNA sequencing (150,290 cells, 27 treatment-naïve tumors), and spatial transcriptomic (43 tumor sections, 22 TNBCs) analyses confirmed expression of CDK2 and its cyclin partners in basal-like/TNBCs, associated with EGFR. Spatiotemporal live-cell imaging and super-resolution confocal microscopy demonstrated ADC colocalization with late lysosomal clusters. The ADC inhibited cell cycle progression, induced cytotoxicity against high EGFR-expressing tumor cells, and bystander killing of neighboring EGFR-low tumor cells, but minimal effects on immune cells. Despite carrying a small molar fraction (1.65%) of the SNS-032 inhibitor, the ADC restricted EGFR-expressing spheroid and cell line/patient-derived xenograft tumor growth.

Exploiting EGFR overexpression, and dysregulated cell cycle in aggressive and treatment-refractory tumors, a cetuximab–CDK inhibitor ADC may provide selective and efficacious delivery of cell cycle–targeted agents to basal-like/TNBCs, including chemotherapy-resistant residual disease.