Related Experiment Video
Updated: Aug 9, 2026
A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
Published on: April 3, 2026
Discovery of Novel AURKA Inhibitors for Triple-Negative Breast Cancer (TNBC) Therapy via a Hybrid Virtual Screening
Pei Liu1,2, Yanqing Liu1,2, Xin Zhang1,2
1Affiliated Yongkang First People's Hospital and School of Pharmaceutical Sciences, Hangzhou Medical College, Hangzhou 310053, P. R. China.
Abstract:
Aurora kinase A (AURKA) is a pivotal driver of malignant progression and poor prognosis in triple-negative breast cancer (TNBC). In this study, we developed a cascaded AI-driven virtual screening pipeline, integrating sequence-based affinity prediction (PSICHIC), equivariant deep learning docking (KarmaDock), and geometric rescoring (DeepDock) to identify novel AURKA inhibitor candidates. From an in-house 160,000-compound screening library assembled from commercially available collections, three leads (compounds 3, 5, and 8) were selected and subsequently validated via HTRF biochemical assays, exhibiting potent enzymatic inhibition with IC50 values of 157 nM, 21.64 nM, and 46.03 nM, respectively. Cell-based assays demonstrated that compound 3 produced stronger short-term cell-growth inhibition in MDA-MB-231 (TNBC) cells compared to clinical benchmarks MLN8237 and CCT241736, whereas compounds 3 and 5 showed cell-growth inhibition in NIH/3T3 cells within the same concentration range as the reference inhibitors. Triplicate 500 ns molecular dynamics simulations supported stable binding modes of the identified leads in the AURKA binding pocket. Additional computational analyses further provided supportive information for subsequent lead optimization. This study provides a transparent and open-source workflow for AI-assisted identification of AURKA-active chemotypes.
Insights
Researchers developed an AI pipeline to find new Aurora kinase A (AURKA) inhibitors for triple-negative breast cancer (TNBC). Three compounds showed potent inhibition, with one outperforming clinical drugs in TNBC cell growth inhibition.
Area of Science:
- Medicinal Chemistry
- Computational Biology
- Oncology
Background:
- Aurora kinase A (AURKA) is a key factor in triple-negative breast cancer (TNBC) progression and poor patient outcomes.
- Targeting AURKA presents a therapeutic strategy for TNBC.
Purpose of the Study:
- To identify novel AURKA inhibitors using an AI-driven virtual screening pipeline.
- To validate the efficacy of identified compounds in biochemical and cell-based assays.
Main Methods:
- Developed a cascaded AI pipeline integrating PSICHIC, KarmaDock, and DeepDock for virtual screening.
- Screened an in-house library of 160,000 compounds.
- Validated lead compounds using HTRF biochemical assays and cell-based assays (MDA-MB-231, NIH/3T3).
- Performed molecular dynamics simulations to assess binding stability.
Main Results:
- Identified three potent AURKA inhibitor leads (compounds 3, 5, and 8) with IC50 values ranging from 21.64 nM to 157 nM.
- Compound 3 demonstrated superior short-term growth inhibition in TNBC cells compared to clinical benchmarks.
- Compounds 3 and 5 exhibited growth inhibition in NIH/3T3 cells comparable to reference inhibitors.
- Molecular dynamics simulations confirmed stable binding of the leads within the AURKA active site.
Conclusions:
- The AI-driven virtual screening workflow successfully identified novel AURKA inhibitors.
- The identified compounds, particularly compound 3, show promise as potential therapeutics for TNBC.
- This study offers a transparent, open-source approach for AI-assisted drug discovery targeting AURKA.
