Predicting genotoxicity of viral vectors for stem cell gene therapy using gene expression-based machine learning

Area of Science:

• Biotechnology
• Molecular Biology
• Hematology

Background:

• Hematopoietic stem cell gene therapy offers promise for blood and immune disorders.
• Insertional mutagenesis from gene therapy vectors has led to hematological malignancies.
• Current in vitro assays for vector genotoxicity are limited.

Purpose of the Study:

• To develop a reliable in vitro assay for assessing gene therapy vector genotoxicity.
• To identify a gene expression signature indicative of insertional mutagenesis.
• To improve preclinical safety evaluation of gene therapy vectors.

Main Methods:

• Murine hematopoietic stem and progenitor cells were transduced with vectors.
• Gene expression profiling identified a signature linked to stemness and oncogenesis.
• A machine learning-based assay, Surrogate Assay for Genotoxicity Assessment (SAGA), was developed.
• SAGA detects the identified gene expression signature during in vitro immortalization.

Main Results:

• Genotoxic vectors induced a unique gene expression signature in transduced cells.
• SAGA achieved 90.9% accuracy in classifying benchmark vectors.
• SAGA demonstrated superior robustness, sensitivity, and speed compared to existing assays.
• SAGA accurately predicted mutagenic risk for vectors linked to clinical leukemic events.

Conclusions:

• SAGA provides a fast, robust tool for preclinical risk assessment of gene therapy vectors.
• This assay can enhance the safety of future gene therapy clinical trials.
• The findings pave the way for safer development of hematopoietic stem cell therapies.