Computer-Aided Drug Design Across Breast Cancer Subtypes: Methods, Applications and Translational Outlook

TL;DR

This review explores how computer-aided drug design helps develop better breast cancer treatments by targeting specific cancer subtypes more efficiently.

Contribution

The paper provides a comprehensive overview of CADD methods tailored to breast cancer subtypes and highlights AI-driven approaches for drug discovery.

Findings

CADD techniques like molecular docking and virtual screening are used to identify subtype-specific drug targets in breast cancer.

AI and machine learning are being integrated with traditional simulations to speed up drug discovery and improve candidate drug refinement.

Future progress depends on combining AI, multi-omics data, and digital pathology to enable personalized breast cancer therapies.

Abstract

Breast cancer is a heterogeneous malignancy with distinct molecular subtypes that complicate the development of effective therapies. Traditional drug discovery methods are often constrained by high cost and long development timelines, underscoring the need for more efficient, subtype-aware approaches. Computer-aided drug design (CADD) has emerged as a valuable strategy to accelerate therapeutic discovery and improve lead optimization. This review synthesizes advances from a subtype-centric perspective and outlines the application of CADD techniques, including molecular docking, virtual screening (VS), pharmacophore modeling, and molecular dynamics (MD) simulations, to identify potential targets and inhibitors in receptor-positive (Luminal), HER2-positive (HER2+), and triple-negative breast cancer (TNBC). In addition to traditional pipelines, we highlight artificial intelligence (AI)-enabled methods and a hybrid workflow in which learning-based models rapidly triage chemical space while physics-based simulations provide mechanistic validation. These approaches have facilitated the discovery of subtype-specific compounds and enabled the refinement of candidate drugs to enhance efficacy and reduce toxicity. Despite these advances, critical challenges remain, particularly tumor heterogeneity, drug resistance, and the need to rigorously validate computational predictions through experimental studies. Future progress is expected to be driven by the integration of AI, machine learning (ML), multi-omics data, and digital pathology, which may enable the design of more precise, subtype-informed, and personalized therapeutic strategies for breast cancer.

Figures