ASOkai: A Modular Open-Source Framework for Systematic ASO Design and Evaluation

Antisense oligonucleotides (ASOs) are short, synthetic nucleic acid molecules that modulate gene expression by binding to complementary RNA sequences and directing their degradation or splicing modification. Their therapeutic potential has been demonstrated across a wide range of diseases, including neurological disorders and metabolic conditions, with several ASO-based drugs receiving clinical approval in recent years. However, translating a target gene of interest into a viable ASO therapeutic candidate remains a substantial challenge. The combinatorial space of candidate binding sites, chemical modification patterns, and backbone configurations grows rapidly with gene and oligonucleotide length, making exhaustive experimental screening impractical. Furthermore, prioritizing candidates requires their evaluation against sequence, thermodynamic, and specificity constraints.

ASOkai is an open-source Python workflow framework for systematic ASO design and evaluation. The platform organizes candidate analysis into complementary categories, including intrinsic sequence features, off-target risk profiling, target accessibility, and kinetic modeling of target knockdown informed by sequence, thermodynamic, and chemical features relevant to ASO efficacy. Specialized for modularity and interoperability, ASOkai supports both standalone use and integration into existing computational biology workflows, remaining flexible to new methods and use cases as the field evolves.

In a typical ASOkai workflow for ASOs acting via RNase-H1 mediated knockdown, the user provides a target gene from which ASOkai extracts and filters candidate binding sites based on criteria such as GC content and genome-wide uniqueness. Filtered candidates undergo screening for target accessibility and availability of repeated sites prone to RNase-H1 cleavage, followed by kinetic modeling of target knockdown using unspecific off-target profiles, and unintended gene knockdown arising from specific off-target interactions. A machine learning model trained on empirical antisense data then combines these multidimensional evaluations to identify optimal binding sites and their corresponding oligonucleotides.

For further information contact Seyedarash Ayatollahi (seyedarash.ayatollahi@b-tu.de).

Team

Members: Seyedarash Ayatollahi, Alexander Schliep, Nathalie Gocht, Aleksandra Khatova.