Optimizing Ionizable Janus Dendrimers for Dendrimersome-Mediated mRNA Delivery

AJAS · 2026

Overview

Ionizable lipid nanoparticles (LNPs) are the mainstream delivery mechanisms for mRNA vaccines. However, they have a low mRNA transfection efficiency (TE) and must be stored at very low temperatures. Ionizable Amphiphilic Janus Dendrimer (IAJD) delivery systems were recently developed to overcome such limitations and have emerged as a promising alternative due to their structural (one-component) simplicity and improved stability. However, the biochemical optimization of IAJD-based dendrimersome nanoparticles (DNPs) through in vitro and in vivo testing, despite the DNPs’ comparative structural simplicity, remains tedious. This project implements existing in vitro IAJD data to develop a machine learning (ML) model for predictive biochemical design optimization. Structural variables were systematically defined and encoded to computationally interpret molecular structures and generate novel candidates. Hyperparameter tuning was applied to refine each of the tested ML algorithms, and the best-performing prediction model for TE prediction was selected: eXtreme Gradient Boosting. It was used to search for the optimal IAJD designs that maximize the predicted TE, ultimately yielding four optimal IAJD candidates with equivalent TE predictions: quantitatively measured with luminescence values of 5092988.5 RLU/cm2. Future work will be needed in vaccine development, but these findings highlight the potential of ML-driven optimization in accelerating mRNA vaccine development. Optimal IAJD designs for mRNA delivery for vaccine development using ML can shorten development time significantly.

Competition history

  • AJAS 2026 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: AAAS Annual Meeting (Confex) / American Junior Academy of Science

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google