LANTERN: A Machine Learning Framework for Lipid Nanoparticle Transfection Efficiency Prediction

2025-07-03

AI Summary

Low screening efficiency of ionizable lipids for RNA therapeutics and poor accuracy/generalizability of existing LNP transfection prediction models—due to low-quality experimental data and weak molecular feature representation—hinder rational design of RNA delivery systems. To address these challenges, we propose LANTERN, a machine learning framework that integrates chemically informative Morgan fingerprints with expert-curated molecular descriptors and employs a lightweight multilayer perceptron, thereby balancing predictive performance and model interpretability. In cross-dataset evaluation, LANTERN achieves R² = 0.8161 and Pearson correlation r = 0.9053, substantially outperforming the state-of-the-art model AGILE (R² = 0.2655). Moreover, LANTERN demonstrates superior stability and extrapolation capability across diverse lipid chemical spaces. This work provides a robust, interpretable, and generalizable predictive tool to accelerate the development of high-efficiency RNA delivery formulations.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The discovery of new ionizable lipids for efficient lipid nanoparticle (LNP)-mediated RNA delivery remains a critical bottleneck for RNA-based therapeutics development. Recent advances have highlighted the potential of machine learning (ML) to predict transfection efficiency from molecular structure, enabling high-throughput virtual screening and accelerating lead identification. However, existing approaches are hindered by inadequate data quality, ineffective feature representations, low predictive accuracy, and poor generalizability. Here, we present LANTERN (Lipid nANoparticle Transfection Efficiency pRedictioN), a robust ML framework for predicting transfection efficiency based on ionizable lipid representation. We benchmarked a diverse set of ML models against AGILE, a previously published model developed for transfection prediction. Our results show that combining simpler models with chemically informative features, particularly count-based Morgan fingerprints, outperforms more complex models that rely on internally learned embeddings, such as AGILE. We also show that a multi-layer perceptron trained on a combination of Morgan fingerprints and Expert descriptors achieved the highest performance ($ ext{R}^2$ = 0.8161, r = 0.9053), significantly exceeding AGILE ($ ext{R}^2$ = 0.2655, r = 0.5488). We show that the models in LANTERN consistently have strong performance across multiple evaluation metrics. Thus, LANTERN offers a robust benchmarking framework for LNP transfection prediction and serves as a valuable tool for accelerating lipid-based RNA delivery systems design.

Problem

• Predicting LNP transfection efficiency for RNA delivery
• Overcoming data quality and model accuracy limitations
• Accelerating ionizable lipid discovery for RNA therapeutics

Innovation

• Combines simpler models with chemically informative features
• Uses Morgan fingerprints and Expert descriptors
• Outperforms complex models like AGILE