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.

The invention relates to a method for obtaining a protein from a plant material, wherein the method comprises the steps of i) mechanically disrupting the plant cells to obtain a plant juice in the presence of a reducing agent, ii) treating the plant juice to cause aggregation of chloroplast membranes, iii) removing the aggregated chloroplast membranes by precipitation and/or microfiltration, iv) subjecting the plant juice to ultrafiltration, and v) subjecting the soluble plant protein concentrate to hydrophobic column adsorption to remove residual chlorophyll, phenolic compounds and off-odors in a single column passage. The present invention also pertains to an apparatus and system for plant protein isolation based on this method. The isolated proteins can be economically obtained in batch scale and in large scale. Further, the invention is directed to a protein obtained by the method of the invention, a food product comprising thereof, and a use thereof.

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.

Provided herein are methods and compositions related to plant based meat substitutes which have properties similar to meat.

The invention relates to a method of producing a food or beverage product, comprising the steps of: providing an ingredient composition comprising micellar caseins, whey protein and plant protein having a pH of 5.9-7.1, preferably 6.2-6.8, and having a concentration of 1 to 15 wt. % of total proteins, and wherein the composition has a micellar casein to whey protein ratio of, 90/10 to 60/40 and a micellar caseins and whey protein to plant protein ratio of 80/20 to 20/80, adding divalent cations to provide a concentration of 2.0-10 mM free divalent cations in the ingredient composition and subsequently heat treating the ingredient composition to form agglomerated proteins comprising micellar casein, whey protein and plant proteins, the agglomerates having a size of 5 to 50 microns as measured by D(4,3) mean diameter as measured by laser diffraction. The invention also relates to a product obtained by this method.

Disclosed are plant protein concentrates prepared from whole plant seeds or alternatively, from seed cakes or press cakes or seed meals or non-toasted solvent-extracted press-cakes, and the like. Plant seeds or seed cakes or press cakes or seed meals or non-toasted solvent-extracted press-cakes, and the like, are deconstructed and separated into heavy protein-rich fractions and light oil-rich fractions. The deconstruction processes avoid the use of organic solvents and temperatures above 60° C. The separated fractions are then selectively processed to produce selected plant protein concentrates comprising at least about 65% (w/w) plant protein, from about 4% (w/w) to about 10% (w/w) plant oil, from about 0.5% (w/w) to about 15% (w/w) carbohydrates, water, and ash. The plant protein concentrates are suitable for use as ingredients in nutritional formulations.

Provided are methods for producing food products comprising recombinant components, and compositions used in and food products produced by such methods.

The present invention provides a protein material and food ingredient from a sustainable and stable source. The sustainable and stable source of the food or food ingredient is cellular biomass, for example an algal or microbial biomass. The invention discloses that the cellular biomass can be subjected to a series of steps to derive the protein material and food or food ingredient, which has high nutritional content and has pleasing organoleptic properties.

The invention is directed to a method of preparing a milk substitute from starch and protein that are first isolated from a root, tuber, cereal, nut or legume. The method comprises preparing an emulsion comprising at least 0.3 wt. % of emulsifying agent (native protein and optionally emulsifying starch), at least 0.2 wt. % denatured protein, and at least 1.0 wt. % of lipid. By first isolating the starch and protein from the plant source and then at a later step recombining these in the desired form and quantities, the invention allows for more control of the final composition and organoleptic properties of the milk substitute.

The present invention relates to a food composition, in particular a powder mix for beverages, based on leguminous-plant proteins, having improved organoleptic properties, in particular a reduced sandy mouthfeel, to a process in order to obtain said composition, and also to the uses thereof, in particular in the food-processing field and most particularly the preparation of food formulations.