Rational design of active pharmaceutical ingredient-based co-assembled nanoparticles for cancer immunotherapy

Area of Science:

• Biomedical Engineering
• Nanotechnology
• Machine Learning in Drug Discovery

Background:

• Co-delivery of multiple active pharmaceutical ingredients (APIs) is essential for cancer therapy but faces significant challenges.
• Nanomedicines offer potential for spatiotemporal co-delivery but often require extensive formulation screening, hindering drug discovery.
• Developing efficient strategies for rational nanomedicine design is critical for advancing cancer therapeutics.

Purpose of the Study:

• To develop a data-driven workflow utilizing machine learning (ML) to accelerate the rational design of ICG-templated API co-assembled nanoparticles.
• To identify key physicochemical properties influencing API and ICG co-assembly for nanoparticle design.
• To demonstrate the workflow's practicality in creating nanomedicines for immunomodulation and synergistic antitumor therapy.

Main Methods:

• Implementation of a machine learning (ML) model to predict and identify critical physicochemical properties for API co-assembly.
• Design and synthesis of ICG-templated nanoparticles incorporating specific APIs for targeted therapeutic effects.
• Evaluation of nanomedicine performance in terms of immune activation and antitumor efficacy compared to free APIs.

Main Results:

• The ML models successfully identified crucial properties affecting API and ICG co-assembly, guiding nanoparticle design.
• Co-assembled nano-adjuvants from lysosomal toll-like receptor 7/8 agonists were developed, enhancing antitumor immunity.
• Multi-drug nanomedicines, including AZD7762 and camptothecin, were created, demonstrating synergistic anticancer effects.
• Both nanomedicine formulations exhibited superior immune activation and antitumor efficacy compared to their individual free APIs.

Conclusions:

• The study presents a novel ML-aided workflow that significantly accelerates the rational design of co-assembled nanomedicines.
• This approach offers a feasible strategy for enhancing the efficacy of cancer immunotherapies and combination treatments.
• The developed workflow has broad implications for the efficient discovery and development of advanced nanomedicines for cancer treatment.