Cited by 236RNA Interference and Gene DeliveryNanoparticle-Based Drug DeliveryAdvancements in Transdermal Drug Delivery

Accelerating ionizable lipid discovery for mRNA delivery using machine learning and combinatorial chemistry

Li, Bowen, Raji, Idris O., Gordon, Akiva G. R., Sun, Lizhuang, Raimondo, Theresa M., Oladimeji, Favour A., Jiang, Allen Y., Varley, Andrew +2 more·2024·Nature Materials

Abstract

To unlock the full promise of messenger (mRNA) therapies, expanding the toolkit of lipid nanoparticles is paramount. However, a pivotal component of lipid nanoparticle development that remains a bottleneck is identifying new ionizable lipids. Here we describe an accelerated approach to discovering effective ionizable lipids for mRNA delivery that combines machine learning with advanced combinatorial chemistry tools. Starting from a simple four-component reaction platform, we create a chemically diverse library of 584 ionizable lipids. We screen the mRNA transfection potencies of lipid nanoparticles containing those lipids and use the data as a foundational dataset for training various machine learning models. We choose the best-performing model to probe an expansive virtual library of 40,000 lipids, synthesizing and experimentally evaluating the top 16 lipids flagged. We identify lipid 119-23, which outperforms established benchmark lipids in transfecting muscle and immune cells in several tissues. This approach facilitates the creation and evaluation of versatile ionizable lipid libraries, advancing the formulation of lipid nanoparticles for precise mRNA delivery.

Integrity signals

Registry

Crossref · 10.1038/s41563-024-01867-3

Cites

32 of 32 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. Bergstra, J. & Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012).

Cited by

Still being checked.

Authors
Li, B., Raji, I. O., Gordon, A. G. R., Sun, L., Raimondo, T. M., Oladimeji, F. A., Jiang, A. Y., Varley, A., Langer, R. S., & Anderson, D. G.
Affiliations
  • University Health Network (CA)
  • Boston Children's Hospital (US)
  • Koch Institute for Integrative Cancer Research At MIT (US)
  • University of Michigan (US)
  • Harvard–MIT Division of Health Sciences and Technology (US)
  • University of Toronto (CA)
Corresponding author
  • Li, Bowen
  • Anderson, Daniel G.
Venue
Nature Materials
Published
2024-05-13
Volume
23
Issue
7
Pages
1002-1008
ISSN
  • 1476-1122 (ISSN-L)
  • 1476-4660
OpenAlex
W4396862222
Cited by
236
References
32
Citations by year
2026: 104 · 2025: 108 · 2024: 24
FWCI
27.18
Type
journal article
Language
en
Open access
closed
Locations
  • Nature Materials (publishedVersion)
  • PubMed (publishedVersion)
Funders
National Institutes of Health (5r61ai161805-03)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA Interference and Gene Delivery
  • Physical Sciences › Materials Science › Biomaterials › Nanoparticle-Based Drug Delivery
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Pharmaceutical Science › Advancements in Transdermal Drug Delivery
Keywords
ionizable lipids, lipid nanoparticles, mRNA delivery, mRNA therapeutics, combinatorial chemistry, machine learning, transfection efficiency, muscle cells, immune cells
MeSH terms
Machine Learning, Animals, Humans, Lipids, RNA, Messenger, Combinatorial Chemistry Techniques, Mice, Nanoparticles

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review