20240016179. Selecting food ingredients from vector representations of individual proteins using cluster analysis and precision fermentation simplified abstract (Shiru, Inc.)
Selecting food ingredients from vector representations of individual proteins using cluster analysis and precision fermentation
Organization Name
Inventor(s)
Eyal Akiva of Foster City CA (US)
Geoffroy Dubourg-felonneau of Berkeley CA (US)
Akemi Kunibe of San Francisco CA (US)
Lawrence Lee of San Francisco CA (US)
Selecting food ingredients from vector representations of individual proteins using cluster analysis and precision fermentation - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240016179 titled 'Selecting food ingredients from vector representations of individual proteins using cluster analysis and precision fermentation
Simplified Explanation
The disclosed technology is a method for developing alternative protein sources for industrial food production. It involves evaluating naturally occurring proteins using a combination of computational analysis and empirical testing.
- The technology creates a database where each protein is characterized by vector representations of its structural and functional features.
- Proteins are grouped into clusters based on their similarity, with the degree of similarity adjusted to achieve a desired number of clusters.
- A representative protein is selected from each cluster for high-throughput expression and laboratory testing to assess its suitability for a specific food function.
- Proteins with high scores are identified as potential candidates for commercial food products.
- The process involves multiple cycles of machine learning, database mining, expression, and testing to identify suitable ingredients.
Potential applications of this technology:
- Developing alternative protein sources for industrial food production.
- Creating new ingredients for commercial food products.
Problems solved by this technology:
- Limited availability of alternative protein sources for industrial food production.
- Difficulty in identifying suitable proteins for specific food functions.
Benefits of this technology:
- Provides a systematic method for evaluating and selecting proteins for industrial food production.
- Enables the discovery of new protein candidates for commercial food products.
- Increases the availability of alternative protein sources for the food industry.
Original Abstract Submitted
this disclosure provides a technology for developing alternative protein sources for use in industrial food production. the technology evaluates naturally occurring proteins by a process that is done partly in silico and partly by empirical evaluation. a database is created in which each individual protein is characterized by vector representations of structural and functional features. clusters of individual proteins are formed by pairwise comparison of each protein's vector representation, adjusting the degree of similarity used to define clusters until a desired number of clusters are obtained. a protein representative is selected from each cluster for evaluation by high-throughput expression and laboratory testing for a particular food function. high scoring representatives identify clusters that can be mined for additional protein candidates. multiple cycles of the machine learning, database mining, expression and testing yield ingredients suitable for assessment as part of a commercial food product.
