DigestAI news desk

Cut through the AI noise.

Research

DeepDelivery identifies human proteins for mRNA delivery

Researchers have developed DeepDelivery, an AI-driven platform designed to identify human proteins that can serve as scaffolds for mRNA delivery. This approach aims to overcome immune response issues associated with non-human components in current gene delivery vectors, which limit their use in chronic treatments.

1 source primary source

Key points

  • DeepDelivery AI platform identified 512 human protein candidates for mRNA delivery scaffolds.
  • Experimental validation confirmed 12 of 15 selected proteins functioned as effective delivery scaffolds.
  • TRIM family proteins showed strong activity, guiding specific domain engineering for improved delivery.

The platform screened the proteome and nominated 512 candidate proteins. Experimental validation confirmed that 12 of the 15 selected human proteins functioned effectively as scaffold components, facilitating particle formation and mRNA delivery. The study highlights that several tripartite motif (TRIM) family proteins, typically linked to antiviral responses, showed strong assembly and delivery activity.

Using model interpretability and perturbation analyses, the team identified specific TRIM domain features that influenced prediction scores. These insights guided the engineering of TRIM25-specific domains to improve delivery efficiency. The work establishes a framework for mining the human proteome for scaffold components in programmable mRNA delivery systems. The research was supported by various Chinese national and regional funding bodies, and the authors have filed patent applications for the discovered scaffold proteins.

Read the original at Nature Machine Learning primary sourceOpen source ↗
Topics · follow one to build your own front page
Shenzhen Institutes of Advanced TechnologyShenzhen PAM2L Biotechnologies Co., Ltd.DeepDeliveryGeorge M. ChurchYuting ChenGuanyang SuPeilin ZhaoXun, D.Li, L.

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Research

All →

Related stories