Abstract: This disclosure provides a protein oleogel comprising plant protein dispersed in a liquid oil phase. The oleogel has a microstructure in the form of fibrils, sheets, or other particles with a high aspect ratio that are substantially not interconnected. It can be manufactured by a process that includes solubilizing and denaturing the protein in an aqueous liquid, flash freezing and drying the protein, and then gradually and gently adding a suitable oil or oil mixture. The protein microstructure releases some but not all of the oil when heated. The oleogel forms a spreadable emulsion in an aqueous liquid that is stable for at least six weeks without evidence of creaming. The oleogel may substitute for oils and fats of animal origin in food, food ingredients, cosmetics, and personal care products. This lessens the impact of food manufacturing on the environment, which helps mitigate climate change.

Abstract: 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.

Abstract: This disclosure provides a technology for developing individual proteins for use in industrial processes that include food production. The technology mines sequence data from protein databases by a process that is done partly in silico. Instead of sampling and testing a vast library of compounds, machine learning and implementation narrows the field of functional candidates by predictive modeling based on known protein structure. Candidate proteins that are selected by this analysis are then produced and screened in a high-throughput manner by recombinant expression and testing to determine whether they have a target function. Multiple cycles of the machine learning, database mining, expression, and testing are done to yield potential ingredients suitable for use in the production of foods, cosmetics, agricultural feed, pharmaceutical excipients, and other industrial products.

Abstract: This disclosure provides a technology for developing alternative protein sources for use in industrial food production. The technology mines sequence data by a process that is done partly in silico. Instead of sampling and testing a vast library of compounds, machine learning and implementation narrows the field of functional candidates by predictive modeling based on known protein structure. Candidate proteins that are selected by this analysis are then produced and screened in a high-throughput manner by recombinant expression and testing to determine whether they have a target function. Multiple cycles of the machine learning, database mining, expression, and testing are done to yield potential ingredients suitable for assessment as part of a commercial food product.

Abstract: This disclosure provides a technology for developing alternative protein sources for use in industrial food production. The technology mines natural sources by a process that is done partly in silico. Instead of sampling and testing a vast library of compounds, machine learning and implementation narrows the field of functional candidates by predictive modeling based on known protein structure. Candidate proteins that are selected by this analysis are then produced and screened in a high-throughput manner by recombinant expression and testing to determine whether they have a target function. Multiple cycles of the machine learning, database mining, expression and testing are done to yield potential ingredients suitable for assessment as part of a commercial food product.