Designing lipid nanoparticles using a transformer-based neural network

The RNA medicine revolution has been spurred by lipid nanoparticles (LNPs). The effectiveness of an LNP is determined by its lipid components and their ratios; however, experimental optimization is laborious and does not explore the full design space. Computational approaches such as deep learning can be greatly beneficial, but the composite nature of LNPs limits the effectiveness of existing single molecule-based algorithms to LNPs. Addressing this, our approach integrates the multi-component and multimodal features of composite formulations such as LNPs to predict their performance in an end-to-end manner. Here we generate one of the largest LNP datasets (LANCE) by varying LNP formulations to train our deep learning model, COMET. This transformer-based neural network not only accurately predicts the efficacy of LNPs but is adaptable to non-canonical LNP formulations such as those with two ionizable lipids and polymeric materials. Furthermore, COMET can predict LNP performance in a cell line outside of LANCE and predict LNP stability during lyophilization using only small training datasets. Experimental validation showed that our approach can identify LNPs that exhibit strong protein expression in vitro and in vivo, promising accelerated development of nucleic acid therapies with extensive potential across therapeutic and manufacturing applications.

Authors

Institutions

Publication Details

Journal
Nature Nanotechnology
Published
2025-08-15
DOI
https://doi.org/10.1038/s41565-025-01975-4
Citations
22
Primary Topic
Lipid Membrane Structure and Behavior
Type
article
Field-Weighted Citation Impact
17.73

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Designing lipid nanoparticles using a transformer-based neural network

Joshua D. Bernstock, Xisha Huang, Yuebin Huang, Art Brown et al.
22 citations
Nature Nanotechnology
Lipid Membrane Structure and Behavior
17.73
article

Designing lipid nanoparticles using a transformer-based neural network

Joshua D. Bernstock, Xisha Huang, Yuebin Huang, Art Brown, Giovanni Battista Traverso, Deepak A. Subramanian, Alvin Chan, Michelle T. Sun, Louis DeRidder, Hao Song, Ameya R. Kirtane, Ceara Byrne, Miguel Jiménez, Qing Rui Qu, Taksim Ahmed, Jonathan Woo, Rowan Honeywell, J. L. Cobb, Bruna dos Santos, Rajib Dey, Isaac Diaz Becdach, Charles Hanhurst, Leah S Prizant, Rika Semalty
article en
22 citations

Abstract

The RNA medicine revolution has been spurred by lipid nanoparticles (LNPs). The effectiveness of an LNP is determined by its lipid components and their ratios; however, experimental optimization is laborious and does not explore the full design space. Computational approaches such as deep learning can be greatly beneficial, but the composite nature of LNPs limits the effectiveness of existing single molecule-based algorithms to LNPs. Addressing this, our approach integrates the multi-component and multimodal features of composite formulations such as LNPs to predict their performance in an end-to-end manner. Here we generate one of the largest LNP datasets (LANCE) by varying LNP formulations to train our deep learning model, COMET. This transformer-based neural network not only accurately predicts the efficacy of LNPs but is adaptable to non-canonical LNP formulations such as those with two ionizable lipids and polymeric materials. Furthermore, COMET can predict LNP performance in a cell line outside of LANCE and predict LNP stability during lyophilization using only small training datasets. Experimental validation showed that our approach can identify LNPs that exhibit strong protein expression in vitro and in vivo, promising accelerated development of nucleic acid therapies with extensive potential across therapeutic and manufacturing applications.

Nature NanotechnologyVol. 20(10)
Broad Institute (US), Boston University (US), Brigham and Women's Hospital (US), Northeastern University (US), University of Minnesota (US), Harvard University (US), The University of Queensland (AU), Nanyang Technological University (SG), University of Toronto (CA), Massachusetts Institute of Technology (US)
National Science Foundation, Brigham and Women's Hospital, Massachusetts Institute of Technology, Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Ministry of Education - Singapore, Nanyang Technological University, Advanced Research Projects Agency, National Cancer Institute
Industry, innovation and infrastructure
Openalex Percentile: Top 0%
Lipid Membrane Structure and Behavior
17.73
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.