Mana.bio Unveils AI-Driven Advances in RNA Delivery at ASGCT 2025
核心洞察
Mana.bio (搜索) presented three posters at ASGCT 2025 showcasing their machine learning platform for designing lipid nanoparticles with improved safety and tissue specificity for RNA (搜索) therapeutics.
The company demonstrated significant progress in developing precision RNA (搜索) therapies targeting T-cells (搜索) and lung tissue, addressing key challenges in extra-hepatic RNA delivery.
By combining public and laboratory-generated data, Mana.bio (搜索)'s AI models can predict critical LNP attributes including physiochemical properties, tissue specificity, and in-vivo safety profiles.
Mana.bio (搜索), a biotechnology company at the intersection of artificial intelligence and RNA (搜索) therapeutics, announced today the presentation of new data demonstrating significant advances in their AI-driven platform for targeted RNA delivery. The findings were showcased in three poster presentations at the American Society of Gene & Cell Therapy (ASGCT) 2025 Annual Meeting in New Orleans.
The company's machine learning architecture has shown promising results in predicting lipid nanoparticle (LNP) safety and specificity, with particular achievements in developing precision RNA (搜索) therapies targeting T-cells (搜索) and lung tissue.
"At Mana.bio (搜索), we're pioneering the use of AI/ML to design LNP for delivering nucleic acid therapeutics," said Yogev Debbi, co-founder and CEO of Mana.bio. "The data we're presenting at ASGCT demonstrates our ability to rapidly design and optimize critical parameters of LNP safety and specificity to address key challenges in developing extra-hepatic RNA (搜索) therapies."
Advancing T-Cell and Lung-Targeted RNA Delivery
The first poster, titled "ML-Driven Design of Lipid Nanoparticles for In-Vivo T-Cell Delivery" (Poster AMA1447), highlights the company's progress in developing delivery systems specifically targeting T-cells (搜索), which could have significant implications for immunotherapy applications.
A second presentation, "Leveraging ML to Improve Potency and Safety of Lung-Targeted Lipid Nanoparticles" (Poster AMA1773), demonstrates how the platform can enhance both efficacy and safety profiles of LNPs designed to target lung tissue. This advancement could potentially address the significant unmet need for respiratory disease treatments through RNA (搜索) therapeutics.
Machine Learning Architecture for LNP Design
The third poster, "Learn-Design-Make-Generate: ML Platform for Developing Novel LNP Delivery Systems" (Poster AMA1775), provides an overview of Mana.bio (搜索)'s comprehensive machine learning architecture. This platform integrates public data with empirically generated laboratory data to train models capable of predicting critical LNP attributes.
The company's AI models can predict physiochemical properties, tissue specificity, and in-vivo safety profiles of lipid nanoparticles, potentially accelerating the development timeline for RNA (搜索) therapeutics while improving their precision.
Overcoming Key Challenges in RNA Therapeutics
RNA (搜索) therapeutics have shown tremendous potential across multiple disease areas, but delivery challenges—particularly to tissues beyond the liver—have limited their broader application. Mana.bio (搜索)'s approach leverages artificial intelligence to design lipid nanoparticles with enhanced tissue specificity, potentially expanding the range of diseases treatable with RNA medicines.
"These results underline the transformative potential of our platform to accelerate the LNP design process and enable precision genetic medicines for cancer (搜索), autoimmune (搜索), and respiratory diseases (搜索)," Debbi added.
The company's presentations at ASGCT highlight how AI can significantly streamline the LNP design and optimization process, potentially reducing development timelines while improving therapeutic outcomes. The integration of computational approaches with experimental validation represents a significant step forward in the RNA (搜索) therapeutics field.
Mana.bio (搜索) indicated that the complete poster presentations will be available on their website following the conclusion of the ASGCT meeting, which runs from May 13-17, 2025.