Related Experiment Video
Updated: May 8, 2026

Evaluation of the Efficacy And Toxicity of RNAs Targeting HIV-1 Production for Use in Gene or Drug Therapy
Published on: September 5, 2016
Hepatotoxic potential of therapeutic oligonucleotides can be predicted from their sequence and modification pattern
Peter H Hagedorn1, Victor Yakimov, Søren Ottosen
1Department of Informatics, Santaris Pharma A/S, Hørsholm, Denmark.
Abstract:
Antisense oligonucleotides that recruit RNase H and thereby cleave complementary messenger RNAs are being developed as therapeutics. Dose-dependent hepatic changes associated with hepatocyte necrosis and increases in serum alanine-aminotransferase levels have been observed after treatment with certain oligonucleotides. Although general mechanisms for drug-induced hepatic injury are known, the characteristics of oligonucleotides that determine their hepatotoxic potential are not well understood. Here, we present a comprehensive analysis of the hepatotoxic potential of locked nucleic acid-modified oligonucleotides in mice. We developed a random forests classifier, in which oligonucleotides are regarded as being composed of dinucleotide units, which distinguished between 206 oligonucleotides with high and low hepatotoxic potential with 80% accuracy as estimated by out-of-bag validation. In a validation set, 17 out of 23 oligonucleotides were correctly predicted (74% accuracy). In isolation, some dinucleotide units increase, and others decrease, the hepatotoxic potential of the oligonucleotides within which they are found. However, a complex interplay between all parts of an oligonucleotide can influence the hepatotoxic potential. Using the classifier, we demonstrate how an oligonucleotide with otherwise high hepatotoxic potential can be efficiently redesigned to abate hepatotoxic potential. These insights establish analysis of sequence and modification patterns as a powerful tool in the preclinical discovery process for oligonucleotide-based medicines.
Insights
Researchers developed a machine learning model to predict the liver toxicity of therapeutic antisense oligonucleotides. This tool helps design safer drug candidates by analyzing sequence patterns, reducing potential hepatotoxicity.
Area of Science:
- Pharmacology and Toxicology
- Medicinal Chemistry
- Bioinformatics
Background:
- Antisense oligonucleotides (ASOs) are emerging therapeutics that degrade target messenger RNAs.
- Hepatotoxicity, including hepatocyte necrosis and elevated alanine-aminotransferase, is a known side effect of some ASO treatments.
- Understanding sequence-specific determinants of ASO hepatotoxicity is crucial for safe drug development.
Purpose of the Study:
- To comprehensively analyze the hepatotoxic potential of locked nucleic acid-modified oligonucleotides in a preclinical mouse model.
- To develop a predictive model for identifying ASO sequences with high or low hepatotoxic potential.
- To guide the rational redesign of ASOs to mitigate liver toxicity.
Main Methods:
- Development of a random forests machine learning classifier based on dinucleotide composition of oligonucleotides.
- Training and validation of the classifier using a dataset of 206 locked nucleic acid-modified oligonucleotides with known hepatotoxic potential in mice.
- Analysis of individual dinucleotide contributions and their complex interplay in determining hepatotoxicity.
Main Results:
- The random forests classifier accurately distinguished between high and low hepatotoxic potential oligonucleotides with 80% accuracy (out-of-bag) and 74% accuracy on a validation set.
- Specific dinucleotide units were identified as either increasing or decreasing hepatotoxic potential.
- The model successfully guided the redesign of a high-hepatotoxicity oligonucleotide to significantly reduce its toxicity.
Conclusions:
- Sequence and modification pattern analysis is a powerful tool for predicting and mitigating ASO-induced hepatotoxicity.
- The developed classifier aids in the preclinical discovery and optimization of safer oligonucleotide-based therapeutics.
- This approach facilitates the development of next-generation ASO medicines with improved safety profiles.
Related Concept Videos
Pharmacogenetics of Phase II Enzymes: N-acetyltransferase, Thiopurine S-methyltransferase, UDP-glucuronosyltransferase
Transfer RNA Synthesis
Each of these chemical modifications is carried by a specific enzyme, post-transcription. All of these enzymes have unique base and site-specificity. Methylation, the most common chemical modification, is carried by at least nine different enzymes, with...
Drug Toxicity: Dose-Dependent Reactions
Inhibitors of Viral Protein Synthesis
Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase
Pharmacogenomics: Identification of New Drug Targets