Blending of compatible varieties of soybeans
Blending compatible soybean varieties addresses the challenges of achieving high protein and oil content in soybeans by leveraging synergistic effects, reducing the time and resources needed to produce high-yield, high-protein, and high-oil soybean products.
Patent Information
- Application Number
- PCT/US2024/030517
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-05-22
- Publication Date
- 2024-11-28
AI Technical Summary
Current plant breeding methods are laborious, time-consuming, and expensive, and often fail to achieve the desired grain composition profiles for soybeans with high protein and oil content, as genetic antagonism between traits makes it difficult to simultaneously improve yield and protein or oil content.
Blending compatible varieties of soybeans that individually cannot achieve the desired traits, allowing for the creation of a grain composition with targeted processor-preferred characteristics such as high protein and oil content, by planting and processing the blends to achieve synergistic effects.
This method significantly reduces the time and resources required to achieve desired post-harvest soybean compositions, enabling the production of high-yield, high-protein, and high-oil soybean products that would be difficult or impossible to achieve with single varieties, optimizing economic outcomes and processing efficiency.
Smart Images

Figure US2024030517_28112024_PF_FP_ABST
Abstract
Description
23979-20007.40 BLENDING OF COMPATIBLE VARIETIES OF SOYBEANS CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims priority to United States Provisional Patent Application No. 63 / 503,706, filed May 22, 2023, which is hereby incorporated herein by reference in its entirety. FIELD
[0002] The present disclosure relates generally to products derived from high protein soybeans, and more specifically to blends of compatible varieties of soybeans to achieve a certain processor preferred characteristics (e.g., of a processed soybean composition). BACKGROUND
[0003] There are certain threshold amounts of grain components that are commercially valuable. For example, a soybean variety that can reliably deliver a mean harvest dry weight yield of at least 55 bushels / acre with a grain content profile capable of achieving a white flake protein content of at least about 59.5% and an oil content of at least about 18% is highly desirable. However, single varieties of soybeans cannot typically achieve those thresholds at an industrial scale. This may be due to various reasons, including genetic and physiological antagonism between the features that make conventional crop improvement methods ineffective. For example, the higher the protein content of a variety, the more difficult it typically becomes to maintain, much less increase, the oil content.
[0004] Current methods of plant breeding are directed to improving the genetics of plants to produce better harvests, such as increased yield of harvested product. In the case of soybean, this increased yield is typically measured in the form of the weight of grain harvested per acre of land used to grow the plants. Soybean breeding therefore teaches that to achieve a processed composition after harvest that is desired by processers for food or feed, it is necessary to create a variety through the usual steps of plant breeding, including crossing and selection, to eventually arrive at offspring that reliably produce grain that achieve the processor’s desired thresholds.
[0005] The current methods of plant breeding aimed at creating new varieties are laborious, time consuming, and expensive. Even if a breeder has access to two varieties that seem to be promising parents, it will likely take at least 3 years of breeding to achieve offspring with the desired specification. Much of this time is spent waiting for plants to grow, develop seeds, or on other biological processes that cannot be circumvented.23979-20007.40
[0006] Furthermore, traditional plant breeding focuses on creating plants that grow well in the field. Growers purchase seed and invest resources associated cultivation, harvest, and production of the harvested grain and therefore target varieties that yield the most grain per unit area of their farm to maximize their return on the investment. Consequently, high yield has been the primary target trait on which plant breeders have focused their efforts. Although they may target other traits like stress tolerance, the art teaches that the goal of improving these traits is to protect the yield that will ultimately be realized from growing that variety.
[0007] Using current breeding methods taught in the art, researchers who lack a single variety that achieves a set of thresholds desired by a processor will typically be faced with at least several years of breeding before they can create a new variety that matches a new product specification desired by a processor. BRIEF SUMMARY
[0008] In some aspects, provided herein are methods to attain industrial harvests of soybeans that achieve the aforementioned grain content profile. Achieving certain composition profiles in a farmer’s harvest is highly desirable and generally has not been attained by current genetics or plant breeding methods. In some aspects, such grain composition profiles may be achieved by blending, such as mixing, the grains of at least two compatible varieties so that when the grain is processed, for example, made into oil, meal, white flake, protein extract, protein isolate, etc., the resulting product contains certain thresholds of components valuable to food and / or feed production.
[0009] In certain aspects, provided herein are methods that allow one to achieve valuable grain compositions, or processed soybean compositions derived from the grain, that circumvents the usual investment in resources and time required by traditional plant breeding. The methods provided may achieve a valuable grain composition and / or a processed grain composition by using at least two varieties that cannot achieve the composition on their own and methods of breeding new varieties that will be useful for such combinations and / or other combinations in the future.
[0010] The methods provided go beyond improving the performance of the plants while they grow in the field, and focus in on the value of post-harvest processed compositions of the plants or plant parts of plant parts. The methods provided dramatically reduce the time and resources that traditional plant breeding teaches are necessary to achieve a post-harvest grain or processed grain composition. Also disclosed are methods of breeding new varieties that are valuable23979-20007.40 primarily because they perform well in blends, despite exhibiting undesirable performance by those in the art when grown alone.
[0011] In certain aspects, provided is a method of producing grain from a blend of soybean varieties, wherein the grain has at least a first trait and a second trait, wherein each trait of the grain has a target value. In some embodiments, these traits are processor preferred characteristics (e.g., of a processed soybean composition). In certain embodiments, such traits may include, for example, oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color (e.g., as a result of the hilum), saponin, energy, flavor, texture, and functionality. The methods herein may achieve certain threshold levels of these traits when blended together. In certain embodiments, the blends can achieve a threshold level of any of the processor preferred characteristics and yield.
[0012] In some variations, the method comprises: a) planting seeds from at least two soybean varieties together; b) germinating the seeds and growing plants from the germinated seeds to maturity; and c) harvesting grain from the plants without separating the soybean varieties. In some embodiments, the soybean varieties comprise: a first soybean variety having (i) the first trait with a value that is higher than the target value of the first trait for the grain, and (ii) a second trait with a value that is lower than the target value of the second trait for the grain; and a second soybean variety having (i) the first trait with a value that is lower than the target value of the first trait for the grain, and (ii) the second trait with a value that is higher than the target value of the second trait for the grain. In some embodiments, the soybean varieties do not share a common parent. In some embodiments, the soybean varieties when planted as a blend yield grain with traits that are not achieved from planting any one of the individual soybean varieties alone.
[0013] In some variations of the foregoing, the method further comprises: processing the harvested grain to obtain a downstream product, wherein the first trait and the second trait in the downstream product are not achievable from grain obtained from each soybean variety alone.
[0014] In certain aspects, provided is a composition comprising a blend of least two varieties of soybeans. In some embodiments, the blend refers to a blend of seeds for planting. In other embodiments, the blend refers to a blend of grain for harvesting.23979-20007.40
[0015] In one aspect, provided is a composition comprising a blend of at least two varieties of soybeans, wherein the varieties have (i) relative maturities no greater than 0.4 and / or relative maturities within 0.2-0.3 of each other, and (ii) compatible herbicide tolerance traits; and wherein the varieties are blended at a ratio to yield grain that is processed to produce a downstream product having at least one property that is improved.
[0016] In certain embodiments, the varieties are blended at a ratio to (a) yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and / or (c) a mean yield of at least about 55 bushels per acre, or any combination of (a)-(c).
[0017] In some variations, the blend is a grain blend with improved saponin, higher harvest yield and / or greater protein content. In other variations, the blend is a grain blend with improved flavor, higher yield and / or protein content.
[0018] In some variations, the blends provided herein balance yield, protein and oil, and can be used to achieve economic outcomes that are currently hard to achieve using single varieties. Blending as described herein can create economic opportunity beyond genetics of single lines.
[0019] In some variations, blending as provided herein is not limited to improving growth or survivability of the plants in the field. Rather, the value chain extends beyond the harvest. The blends herein can achieve a desired combination of thresholds in harvested grain that is ultimately delivered to the processor. And while yield of grain from the field may be one of those thresholds, blending as provided herein includes optimizing other features that benefit steps after harvest, for example, a quality trait like protein content desired by the processor.
[0020] In certain variations, blending occurs substantially at any point in the agricultural process. In one variation, the blends are created during or after harvest. In another variation, blending occurs after the grain is harvested and before it is delivered to the processor, e.g., between trucks containing grain from different varieties. In yet another variation, blending in occur “in the bag”.
[0021] The methods herein allow for blending seed to achieve desired features related to protein content, yield, food functionality and others. For example, in some variations, planting different blends achieve a high yield blend of grain with, for example, a certain combination of protein content and quality protein percentage at the crush facility which will produce a soy protein isolate with certain food functionality features.23979-20007.40 DESCRIPTION OF THE FIGURES
[0022] The present application can be understood by reference to the following description taken in conjunction with the accompanying figures.
[0023] FIG.1 depicts a system for automatically determining compositions for blended seed mixtures to improve resultant grain characteristics, in accordance with some embodiments.
[0024] FIG.2 depicts a method for automatically determining compositions for blended seed mixtures, breeding / selecting a variety for one or more blend ingredients, blending seeds to create a blended seed mixture, and producing grain from the blended seed mixture to improve resultant grain characteristics, in accordance with some embodiments.
[0025] FIG.3 depicts a method for automatically selecting varieties for blending to achieve improved resultant grain characteristics, in accordance with some embodiments.
[0026] FIG.4 depicts a method for determining a blend composition to achieve a target specification, in accordance with some embodiments.
[0027] FIG.5A depicts protein and yield values for varieties of Yucatan plants, according to Example 1.
[0028] FIG.5B depicts target product specifications, blended seed mixture proportions, and resultant blended grain traits, according to the Example 1.
[0029] FIG.5C depicts a comparison of traits for grain from a blend computed using only active Yucatan plants versus a computed blended resultant grain using a discarded variety of Yucatan, according to Example 1.
[0030] FIG.6A depicts protein and yield values for varieties of Yucatan plants, according to Example 2.
[0031] FIG.6B depicts target product specifications, blended seed mixture proportions, and resultant blended grain traits, according to the Example 2.
[0032] FIG.6C depicts a comparison of traits for grain from a blend computed using only active Yucatan plants versus a computed blended resultant grain using a discarded variety of Yucatan, according to Example 2.23979-20007.40
[0033] FIGS.7, 8, and 9A-9C depict exemplary embodiments of blending at different timepoints in cultivation, harvesting, and during / after processing. DETAILED DESCRIPTION
[0034] The following description sets forth exemplary compositions, methods, parameters and the like. It should be recognized, however, that such description is not intended as a limitation on the scope of the present disclosure but is instead provided as a description of exemplary embodiments.
[0035] In some aspects, provided herein are ways of achieving harvests with certain desired features, such as processor preferred characteristics (e.g., of a processed soybean composition). The blends in the methods herein can be useful to achieve a threshold level of one or more of the processor preferred characteristics, which may include, for example, oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color (e.g., as a result of the hilum), saponin, energy, flavor, texture, and functionality. In certain embodiments, the blends can achieve a threshold level of any of the processor preferred characteristics and yield of the harvested grain blend.
[0036] For example, in some embodiments, the blends result in a harvest of high-yield and high-protein grain, wherein the harvest comprises more than one variety. In certain embodiments, seeds from two different varieties with complementary traits are planted near one so that when they are harvested, the grain is a blend of both varieties, and the blend achieves certain desired thresholds. In other embodiments, the grains from two varieties are harvested separately and blended before being crushed. In certain variations, computer modeling, artificial intelligence, etc. may be used to determine which varieties to blend, when they are harvested, and when the grain is blended.
[0037] The methods provided herein offer a way of selecting a blend of seeds from the huge number of possible blends a typical breeding program presents. In certain aspects, the method comprises: assessing (e.g., testing, phenotyping, analyzing, etc.) at least two soybean varieties for their performance related to at least two traits (e.g., oil, protein, yield) while growing in the field; using the data collected to compare the performance of the varieties head-to-head and reveal the likelihood of each variety achieving a certain threshold of oil, protein and / or yield; selecting a ratio of the varieties to generate a blend; planting the blend of seeds in a field;23979-20007.40 harvesting grain without separating the varieties such that the grain harvested forms a blended harvest product; and achieving target values for the traits. In some embodiments, the method further comprises: processing the grain blend to create a downstream product (e.g., a processed end product such as meal, white flake, protein extract or protein isolate) that meets certain specifications.
[0038] In some aspects, provided is method of producing grain from a blend of soybean varieties, wherein the grain has at least a first trait and a second trait, wherein each trait of the grain has a target value. In some embodiments, the method comprises: a) planting seeds from at least two soybean varieties together, and wherein the soybean varieties comprise: a first soybean variety having (i) the first trait with a value that is higher than the target value of the first trait for the grain, and (ii) a second trait with a value that is lower than the target value of the second trait for the grain, and a second soybean variety having (i) the first trait with a value that is lower than the target value of the first trait for the grain, and (ii) the second trait with a value that is higher than the target value of the second trait for the grain; b) germinating the seeds and growing plants from the germinated seeds to maturity; and c) harvesting grain from the plants without separating the soybean varieties.
[0039] In some embodiments, the method further comprises: processing the harvested grain to obtain a downstream product, wherein the first trait and the second trait in the downstream product are not achievable from grain obtained from each soybean variety alone.
[0040] In some variations of the foregoing, the soybean varieties are grown together to maturity over a coextensive area. In some variation, the grain obtained after one growing cycle has at least the first trait and second trait at their respective target values.
[0041] The soybean varieties when planted as a blend yield grain with traits that are not achieved from planting any one of the individual soybean varieties alone. Such methods prevent significant advantages to traditional breeding in obtaining downstream products (e.g., a processed end product such as meal, white flake, protein extract or protein isolate) with specifications that cannot be achieved from any one of the individual soybean varieties alone.23979-20007.40 Such methods blend soybean varieties in a predetermined proportion to maximize the match of the grain to specifications of the downstream product.
[0042] The methods for selecting and / or breeding seeds of different varieties for blending to create a blended seed mixture that yields target grain characteristics are described below. Blending, e.g., in terms of types and ratios of varieties, at various timepoints in the agricultural process is also described below. The profile that may be achieved by blending, as well as synergistic effects from blending, are also described below. Selection Methods
[0043] In some aspects, also provided herein are methods for improving grain characteristics, and more specifically to methods for selecting and / or breeding seeds of different varieties for blending to create a blended seed mixture that yields target grain characteristics.
[0044] FIG.1 depicts a system 100 for automatically determining compositions for blended seed mixtures to improve resultant grain characteristics, in accordance with some embodiments. As described herein, system 100 may be configured to perform one or more of the techniques described herein, including for example methods for selecting varieties for inclusion in blended seed mixtures and for determining ratios of varieties to be used in creating blended seed mixtures.
[0045] System 100 may be an electronic, computerized system comprising a blend calculation system 102, which may comprise one or more processors, which may be provided locally, remotely, and / or in a distributed manner. The processors may include hardware processors and / or virtual processors. The one or more processors of system 102 may be configured to execute computer program code store in memory included in and / or accessible by system 100. Execution of the computer program code may cause system 100 to execute any one or more of the techniques described herein.
[0046] System 100 may include one or more data stores comprising computer memory that stores data regarding traits of various varieties of plants. The data stores may be provided as databases or as any other suitable data storage systems. In the example of system 100, existing variety trait data source 104 and development line trait data source 106 are provided separately from one another, and each are communicatively coupled to and configured to transmit data to blend calculation system 102. In the example shown, existing variety trait data source may store trait data for existing varieties of plants, and development line trait data source may store trait23979-20007.40 data for development lines (including data for current generations of development line varieties and projected / modeled / targeted data for future generations and / or an intended end point of a development line variety). (In other embodiments, a single data store may be used for existing- variety trait data and development-line trait data.)
[0047] For both data sources 104 and 106, trait data may include, for any given variety (extant or projected), trait data and associated metadata. Trait data may indicate one or more trait values for a given trait. For example, a given trait may be yield, and trait data for a given variety for yield may include one or more yield values. In some embodiments, only a single value may be stored for a given variety for a given trait, whether due to only having received a single value for the trait or due to computing a single average value for the trait. In some embodiments, a plurality of values may be stored for a given variety for a given trait, forming a distribution of trait values for that variety. This may be due to multiple observations made over time, due to multiple projections of the trait value made, and / or due to a projection of the trait value made with a given uncertainty window.
[0048] Metadata stored in association with a trait value may include data indicating time, place and / or manner of collection of the data. Metadata may include information indicating a reliability (e.g., a confidence value or score) of a trait value. Metadata stored in association with a trait value may, in some embodiments, indicate a p-value or other statistical tag for one or more trait values. For example, the system may determine a median trait value for a given variety for a given trait and may store metadata indicating which value is the median train value for the given variety. Additionally or alternatively, the system may determine p-values for a distribution of trait values, and may generate trait values and store them in association with a given p-value, such as a p-10, p-20, p-25, p-30, p-40, p-50, p-60, p-70, p-75, p-80, and / or p-90 value for a given variety for a given trait.
[0049] Data stored in data sources 104 and 106 may further indicate data indicating one or more classifications for a given variety. For example, classification data may indicate whether a given variety is an extant variety or a projected development-line result, dwarf-type or non-dwarf type, and / or determinant variety or non-determinant variety, branching type or non-branching type.
[0050] Data stored in data sources 104 and 106 may further indicate values for characteristics of the variety that are not traits of the resultant grain itself or of a product obtained from the resultant grain, but that are instead traits of the seed itself and / or the resultant crop (as distinct23979-20007.40 from the resultant grain or grain product). For example, data regarding seed size / shape for a given variety, crop height for a given variety, or other characteristics of the seed or crop may be stored. For characteristics of the seed or crop stored in data sources 104 and 106, one or more data values may be stored for a given variety in the same or similar manner as described above with respect to data values for grain (and / or grain product) trait values.
[0051] As shown in FIG.1, system 100 may further include user input device 108, which may be any suitable electronic user interface device (e.g., a keyboard, mouse, touch-screen device, or other computer interface device) configured to accept a suer input. Input device 108 may accept a user input indicating a target specification for a grain, where the target specification may indicate one or more target trait value thresholds. Target trait value thresholds may define a minimum target threshold, a maximum target threshold, or both. In the cases where both a minimum and maximum target threshold are defined, the thresholds may thus define a target range. As discussed above, systems described herein may optimize for more than one trait for a single blended seed mixture, such as two, three, or more traits. In cases where optimization is performed for more than one trait, this optimization may be based on a user input entered via device 108 indicating target values for more than one trait.
[0052] In some embodiments, a user input entered via input device 108 may indicate additional information in addition to one or more target trait values. For example, a user input may enter information indicating whether mixing and matching amongst different variety classifications is permissible for a desired seed blend. A user may enter information indicating a required development timeline for a desired seed blend to be available (which may govern whether ingredients for the blend must be presently available or can be bred / selected for over time). A user may enter information indicating relative importance of one or more traits which are to be optimized (and this information may be used to weight and / or score different potential blended seed mixtures for their viability). A user may enter information indicating economic resources or economic constraints (which may be used to exclude or to select certain potential blend ingredients and / or certain potential blend combinations).
[0053] Based on the received user input from device 108 and the data available in data sources 104 and 106, system 102 may select two or more varieties for blending to create a blended seed mixture, and may determine proportions by which the selected varieties should be blended in the seed mixture. The techniques for selection of varieties and determination of proportions are described in further detail below with reference to FIG.2 and elsewhere in this disclosure.23979-20007.40
[0054] After determining varieties for blending and proportions with which they should be blended, system 102 may generate output data indicating the varieties selected for blending and proportions with which they should be blended.
[0055] In some embodiments, the output data may be displayed or otherwise output via output / display device 110, which may be any suitable display device, audio output device, and / or haptic output device. Device 110 may be communicatively coupled to system 102 and configured to display and / or otherwise provide an output indication in response to receiving output data from system 102. While FIG.1 shows output / display device 110 separate from user input device 108, the two components may in some embodiments be provided as part of a single device.
[0056] In some embodiments, the output data may be transmitted to blend data store 112, where it may be stored in computer memory. Blend data store may be any suitable computer storage medium communicatively coupled to and configured to receive data from system 102.
[0057] In some embodiments, system 100 may generate instructions for automatically controlling one or more automated devices based on the output data generated by system 102. Thus, based on what varieties are selected by system 100 for blending and what proportions are determined by system 100 for the blend, system 100 may generate machine-readable instructions for automatically controlling one or more automated devices or systems. One or more processes may be triggered automatically in response to and based on the selected varieties and determined proportions.
[0058] In some embodiments, blend calculation system may transmit an electronic control signal to automated seed mixing device 114, which may be a mechanical device comprising a feeding mechanisms, sorting mechanisms, and / or mixing mechanisms configured to physically mix the selected seed varieties together with one another in the determined proportions.
[0059] FIG.2 depicts a method 200 for automatically determining compositions for blended seed mixtures, breeding / selecting a variety for one or more blend ingredients, blending seeds to create a blended seed mixture, and producing grain from the blended seed mixture to improve resultant grain characteristics, in accordance with some embodiments. In some embodiments, some or all of method 200 may be performed by a system for automatically determining compositions for blended seed mixtures to improve resultant grain characteristics, such as system 100. For illustrative and non-limiting purposes, reference may be made herein to method 200 being performed by system 100.23979-20007.40
[0060] FIG.1 shows method 100 divided into functional sub-portions for illustrative purposes and for added clarity. The first portion includes steps relating to determining blend ingredients and blending proportions for mixing seeds to create a blended seed mixture, including blocks 202-210. The second portion includes one or more steps for optionally breeding / selecting from a current variety of a plant in order to obtain a new variety that can be used as an ingredient in a blended seed mixture that was determined at the first portion; the second portion includes block 212. The third portion includes one or more steps for physically creating the blended seed mixture determined at the first portion, including blocks 214-216. Finally, the fourth portion includes steps for growing, harvesting, and threshing from the blended seed mixture, thereby obtaining the resultant grain and / or grain product having the target specification.
[0061] At block 202, in some embodiments, a system may receive trait data for a plurality of soybean varieties. For example, system 100 may receive trait data indicating one or more observed or modeled trait values for a respective plurality of soybean varieties. The trait data received may include any of the data described above with respect to the trait value data and associated metadata stored in data sources 104 and / or 106.
[0062] Trait data may be received at block 202 in response to a user input, a manual data upload, an automatic data upload, directly from one or more sensors, and / or as part of a data gathering procedure such as a data scraping procedure.
[0063] Trait data received by the system may be based on genomic predictions and / or based on physical measurements. The system may receive and store metadata indicating whether the basis for a given trait data is genomic predictions, physical measurements, or both.
[0064] In some embodiments, trait data may be received by the system by way of modeling trait data as a function of other observed traits. For example, protein in meal may be modeled as a function of protein in a bean. In this way, system 100 may augment the trait data available to the system to include trait data beyond that which is directly observed and / or directly received.
[0065] At block 204, in some embodiments, the system may receive input data indicating a target specification for a grain and / or grain product. For example, system 100 may receive a user input indicating target trait values for a plurality of traits. Target trait values may be input as minimum thresholds, maximum thresholds, and / or ranges for one or more traits. Target trait values may be input along with additional input data including, for example, any of the input data described above with reference to user input device 108 in system 100. For example, additional input data may include an indication of whether or not varieties can be blended across23979-20007.40 certain classifications (e.g., dwarf type and non-dwarf type), whether or not development-line varieties can be included in the blended seed mixture, requirements for a development timeline for the blended seed mixture, and / or economic constraints for development of the blended seed mixture.
[0066] While examples herein contemplate the system receiving a manual user input indicating a target specification, in some embodiments a target specification may be received from one or more automated systems, and / or may be computed or otherwise automatically generated by one or more systems, for example based on underlying user input, historical data, and / or sensor data.
[0067] At block 206, in some embodiments, the system may select a plurality of varieties for creating of a blended seed mixture to achieve the target specification. In some embodiments, blend calculation system 102 of system 100 may make this selection.
[0068] Selection of varieties for inclusion in a blended seed mixture may be based on identifying a set of varieties that can be blended to achieve the target specification (as discussed further herein with reference to block 208 and block 308). In order to determine whether a combination of varieties exists for which seeds van be blended to produce a resultant grain that meets the target trait specifications, a weighted average of trait values for the blend ingredients of a candidate blend composition may be computed to generate a blended trait value, and the system may assess whether any candidate blend composition has blended trait values that fall within the target trait value ranges for all traits.
[0069] In the event that no blends meet the target specification, the system may determine that no viable blend exists. In the event that compositions for only a single blend meet the target specification, the system may select the ingredients for that blend. In the event that compositions for more than one blend meet the target specification, the system may select the ingredients for one of the blends by determining which blend is capable of yielding blended trait values that are most desirable, for example by falling closest to the middle of target trait ranges, by maximizing traits for which maximization is desired, or by minimizing traits for which minimization is desired.
[0070] While computation of values for traits of resultant grain for a blended seed mixture, using a weighted average computation, may be used to assess whether a blended seed mixture meets a target specification, it may be desirable for the system to obviate the need to exhaustively compute trait values for every possible combination of ingredients at every possible23979-20007.40 composition. In fact, given the huge number of different varieties that may be available for blending, and given the large number of different compositional balances by which different varieties may be combined, it may be computationally infeasible or impossible to exhaustively compute across all possible combinations and compositional balances. Accordingly, the system may apply one or more techniques to limit the number of necessary computations, thereby conserving computational resources (and storage resources for results) and increasing efficiency of method 200.
[0071] Some exemplary techniques for improving computational efficiency and conserving computational resources when selecting varieties of seeds for blending are described at blocks 302-306 in FIG.3.
[0072] At block 302, in some embodiments, selecting varieties for blending comprises excluding variety pairings with incompatible type mismatches. For example, pairings or groupings of varieties may be excluded from consideration for blending together with one another when not all of the varieties in the pairing or grouping are matched with one another with respect to certain classifications. For example, the system may exclude computations for blends that would blend dwarf-type and non-dwarf-type varieties with one another, branching- type and non-branching-type varieties with one another, extant varieties and development lines with one another, etc.
[0073] In some embodiments, excluding computations for blends that would include type mismatches may include excluding blends where one or more values of the varieties to be blended are not within a required window or range of one another. For example, in some embodiments, the system may require that height values for a mature crop for varieties to be blended together with one another cannot be mismatched by more than 25%, 50%, 75%, 100%, 150%, 200%, or 300%. Hypothetical blends that would violate this requirement may be excluded from computation at block 302. In another example, in some embodiments, the system may require that RM for varieties may not be mismatched by more than a certain number of days (e.g., 1 day, 2 days, 3 days, 5 days, 7 days, 10 days, 15 days, or 20 days), and / or that a RM for varieties may not be mismatched by more than a certain group score (e.g., by more than 0.1, 0.25, 0.5, 0.75, 1, 1.5, or 2). Hypothetical blends that would violate this requirement may be excluded from computation at block 302.
[0074] At block 304, in some embodiments, selecting varieties for blending comprises excluding variety pairings for which trait values do not bracket the target trait value. In order to23979-20007.40 obviate fruitless computations, the system may be configured to take advantage of the assumption that, if all trait values for blending ingredients are higher than the target blended trait value, or if all trait values for blending ingredients are lower than the target blended trait value, then no blending of said ingredients can achieve the target blended trait value. Accordingly, blends in which all trait values for blending ingredients are higher than the target blended trait value may be excluded from computation at block 304, and blends in which all trait values for blending ingredients are lower than the target blended trait value may be excluded from computation at block 304.
[0075] At block 306, in some embodiments, selecting varieties for blending comprises excluding varieties and / or blends that do not meet economic viability criteria. In some embodiments, an economic viability criteria may be indicated by a user input received by the system (e.g., at block 204 and / or via device 108). The system may determine that one or more varieties (or that one or more combinations of varieties) will violate economic viability criteria, and may exclude any such varieties and / or combinations of varieties from computations at block 306.
[0076] After any of the above exclusions from computations have been made, the system may determine, at block 308, whether any percentage blend of a given pairing or grouping of varieties exists such that the blended trait(s) will meet the target specification trait(s). In some embodiments, the system may require that resultant blended trait values satisfy matching criteria with respect to the target trait values. Matching criteria may require an exact value match, that an achieved value falls within a target range exactly, and / or that an achieved value exceeds (or does not exceed) a target threshold. In some embodiments, matching criteria may require a match, presence within a range, or threshold condition within an allowable error or margin, for example by falling within a predefined amount and / or predefined percentage of the target value(s).
[0077] As noted above, to determine whether a combination of varieties exists for which seeds can be blended to produce a resultant grain that meets the target trait specifications, a weighted average of trait values for the blend ingredients of a candidate blend composition may be computed to generate a blended trait value, and the system may assess whether any candidate blend composition has blended trait values that fall within the target trait value ranges for all traits. Additional detail regarding computing said weighted averages is provided below with reference to block 208 and with reference to the examples provided herein.23979-20007.40
[0078] Returning to FIG.2, the method may proceed from block 206 to block 208. At block 208, in some embodiments, the system may determine a blend composition for the blended seed mixture. That is, the system may determine what percentage of each selected (or potentially viable) blend ingredient should be included in the determined and output blended seed mixture.
[0079] FIG.4 shows optional sub-steps for determining the blend composition at block 208. As shown and described, determining the blend composition may in some embodiments be based on a weighted average computation. At block 402, in some embodiments, determining the blend composition comprises computing a weighted average of trait values of seed varieties included in the blended seed mixture, wherein the trait values are weighted for each respective variety according to the respective percentage of seed for that respective variety that is included in the blend mixture.
[0080] In some embodiments, a weighted average may be computed as follows for a blend of seeds of two varieties (var1 and var2), such that the weighted average yields predicted traits of the grain (or grain product) resulting from the blended seed mixture:
[0081] ^^^^^^^^^ ^^^^^^^^ ^ ^^^^^^^^^^^^^^^^ ^ ^^^^^^^^^^^^^^^^
[0083] where T1 is a trait value for a first trait (e.g., yield), T2 is a trait value for a second trait (e.g., protein), and % represents the percentage of the blend made up of seeds for each variety.
[0084] In some embodiments, in addition to or alternatively to computing a weighted average based on trait data itself for each variety, the system may compute a weighted average based on a delta-value for each variety, wherein the delta value for a variety represents the difference between the trait data for the respective variety and the target trait value. For example, this value may be calculated in accordance with the following equation for a blend of seeds of two variety (var1 and var2):
[0085] ^^^^^^^^^ ^^^^^^^^ ^ ^^^^^^^^^^^^^^^^ ^ ^^^^^^^^^^^^^^^^ ^
[0087] where M1 is a midpoint value for a first trait (e.g., yield), M2 is a midpoint value for a second trait (e.g., protein), ^1 is the difference between a trait value for a variety for the first trait23979-20007.40 and the trait value for the first trait for the target specification, ^2 is the difference between a trait value for a variety for the second trait and the trait value for the second trait for the target specification, and % represents the percentage of the blend made up of seeds for each variety.
[0088] In some embodiments, additionally or alternatively to computing a weighted average to predict the grain and / or grain product blended traits as explained above, the system may compute a weighted average to score a proposed blend according to trait data and according to one or more other considerations such as economic viability.
[0089] In some embodiments, weights may be assigned to different traits based on their economic importance or based on other functional importance to one or more technical and / or physical processes. In one example, protein may be weighted as slightly more important than yield, while both of those traits may be considerably more valuable than oil. Based on the importance assigned to different traits, the values calculated above (e.g., the M values such as M1 and M2) may be weighted to generate a economic-value-adjusted M-value.
[0090] In some embodiments, the economic-value-adjusted M-values for each trait for a proposed blend may then be summed, and the summed economic-value-adjusted M-value for the blend may be assessed with respect to one or more threshold values to determine value or viability of the proposed blend in the proposed proportions. In some embodiments, the highest summed economic-value-adjusted M-value across all blends for which such a value has been calculate may be selected.
[0091] It should be noted that selection of which trait values used for computations herein may be important, and may be adjustable depending on use cases, system settings, and / or user preferences. In some embodiments, when only a single trait value for a trait for a variety is available, then that trait value may be used for computations. In embodiments where multiple trait values for a trait for a variety are available, then the system may determine what value to use for computations. In some embodiments, a median value may be used. In some embodiments, an average value may be used. In some embodiments, the system may determine p-values for a distribution of trait values, and may generate trait values, such as a p-10, p-20, p- 25, p-30, p-40, p-50, p-60, p-70, p-75, p-80, and / or p-90 value for a given variety for a given trait, any one of which may be used for computations based on the particular needs of a use case or user preferences.
[0092] At block 404, in some embodiments, the system may adjust one or more weights based on modeled differences between seed blend percentages and resultant grain blend percentages.23979-20007.40 For example, if the system models that a seed variety must be present in a higher proportion in a blended seed mixture in order to result in a certain target proportion of the grain (or grain product) being resultant from that seed variety, then the system may apply one or more adjustments to the weighting values used in computing weighted averages or otherwise used in determining the blend composition at block 208.
[0093] Returning to FIG.2, after selecting the blend ingredients at block 206 and determining the proportion by which the selected blend ingredients should be mixed at block 208, the system may, at block 210, in some embodiments, generate and store output data indicating the selected varieties and the compositional amounts of each variety in the blended seed mixture. The generated output data may comprise an indication of the determined blend ingredients and the determined proportions with which they should be mixed for one or more determined blended seed mixtures, associated metadata, and / or associated instructions or other information regarding the determined blended seed mixture(s). In some embodiments, system 100 may provide the generated output to an output device for display and / or other output, such as device 110 as described above with reference to FIG.1. In some embodiments, system 100 may store the generated output data in any suitable computer-readable storage medium, such as by storing it in data store 112 as described above with reference to FIG.1.
[0094] Following generation of an output indicating a selected set of varieties for blending and proportions by which they should be blended to achieve the target specification at the “determining blend” portion of method 100, method 100 may proceed to the subsequent portions including breeding for the blend and / or blending itself.
[0095] Turning to the “breeding for blend” portion of method 100, the method may in some embodiments proceed to block 212. At block 212, in some embodiments, breeding and / or selection from a current variety to create a selected variety for use as a blend ingredient may be performed. Block 212 (and other “breeding for blend” steps may, in some embodiments, be performed only if method 100 has determined that a blend recipe should be used that requires one or more varieties of seeds that do not yet exist and that must be developed by breeding and / or selecting from a current variety to develop the blend ingredient for use in creating the blended seed mixture. As discussed above, breeding and / or selecting from a current variety to achieve a variety usable as an ingredient in a blended seed mixture may be able to be completed in fewer generations and less overall time (and with less monetary expense and less resource usage) than if an attempt were made to instead breed and / or select from a current variety all the23979-20007.40 way to the target specification, assuming that the latter is even possible for a given target specification.
[0096] Following the “breeding for blend” portion of method 100, the method may proceed to the “blending” portion of method 100. In some embodiments in which breeding for blending steps (e.g., block 212) are not performed, the “blending” portion may directly follow the “determining blend portion.”
[0097] At block 214, in some embodiments, the system may transmit a control signal to an automated seed blending device configured to cause the automated seed blending device to physically combine the selected seeds together into a blended seed mixture. This step may be performed in embodiments in which an automated seed blending device such as device 114 is used to physically obtain the desired amount of each seed variety, move the seed varieties together into a common container, and mix together the seed varieties, for example using one or more seed conveyors, e.g. conveyer belts, seed elevators, pneumatic and / or vacuum conveyers, hoppers, doors, stirrers, agitators, scales for weighing seed amounts, or the like.
[0098] At block 216, in some embodiments, blending together of the seeds for the selected varieties in the determined compositional proportions may be performed. Optionally, this step may be performed by an automated device such as device 114, for example by one or more industrial scale stirring devices that blends the two or more selected seed varieties together into a relatively homogeneous blended mixture of the seed varieties. In some embodiments, following being mixed together into a relatively homogeneous blended seed mixture, the blended seed mixture may be stored as a blended mixture and / or bagged as a blended mixture for shipment.
[0099] Following blending of the seed mixture, method 100 may proceed to the fourth and final growing, harvesting, threshing, and grain processing portion of the method.
[0100] At block 218, in some embodiments, planting of the blended seed mixture may be performed. The blended seed mixture may be planted over a coextensive area of land without sorting / separating the seed varieties from one another.
[0101] At block 220, in some embodiments, growing of the blended seed mixture to maturity may be performed, thereby producing a resultant blended crop. The crops may be treated during growth collectively with one another, for example by being commonly fertilized, watered, etc., without applying separate targeted treatments to separate varieties within the blended crop.23979-20007.40
[0102] At block 222, in some embodiments, harvesting of the resultant blended crop may be performed. Harvesting of the resultant blended crop may be performed collectively for the blended crop, without separately harvesting the different crop varieties within the blend and without separating the different crop varieties during or after harvest.
[0103] At block 224, in some embodiments, separation of grain from the harvested blended crop may be performed, thereby producing a blended grain mixture that, taken in the aggregate, achieves the target specification. Separation of the grain from the blended crop may be performed collectively for the blended grain, without separating the grain of one variety from the grain of another variety.
[0104] At block 226, in some embodiments, processing of the blended grain may be performed to create a processed blended grain product, wherein the processed blended grain product, taken in the aggregate, achieves the target specification. Processing of the blended grain to create a grain product may be performed collectively for the blended grain, without separating the grain of one variety from the grain of another variety and without separating the grain product of one variety from the grain product of another variety. Traits
[0105] In some embodiments, each trait is a processor preferred characteristic of a processed soybean composition obtained from the blend of soybean varieties. In some variations, the processor preferred characteristic is oil holding capacity (OHC) (g / g solids), water holding capacity (WHC) (g / g solids), least gelation concentration (LGC) (% solids), emulsion capacity (mL / g protein), foaming capacity (mL / g protein), foaming stability (%), gel texture (micro scale or large scale), bench texture (g), moisture (%), protein dispersibility, nitrogen / protein solubility, viscosity, protein (% DB), carbohydrate (% DB), crude fat / oil (% DB), crude fiber (% DB), ash (% DB), color (e.g., hilum color), flavor, energy (Kcal / lb), texture (e.g., gel texture) (g, micro scale or large scale), or functionality. In certain variations, the processor preferred characteristic is oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein, oligosaccharide, crude fat / oil, crude fiber, ash, color, saponins, texture, or functionality. In certain variations, the processor preferred characteristic is water holding capacity (WHC), oil holding capacity (OHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, micro texture, bench texture, gel texture, protein dispersibility, nitrogen / protein solubility, or viscosity, or any combination thereof.23979-20007.40
[0106] It should be understood that, in some variations, any one or more of the preferred characteristics described herein may be optimized using the blends in the methods provided herein as if each and every combination of the preferred characteristics were listed.
[0107] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: OHC, and WHC; OHC, and LGC, OHC, and emulsion capacity; OHC, and foaming capacity; OHC, and foaming stability; OHC, and texture (e.g., gel texture and / or blench texture); OHC, and moisture; OHC, and protein dispersability; OHC, and nitrogen / protein solubility; OHC, and viscosity; OHC, and protein; OHC, and carbohydrate; OHC, and oligosaccharides; OHC, and sucrose; OHC, and crude fat / oil; OHC, and crude fiber; OHC, and ash; OHC, and color; OHC, and flavor; OHC, and saponins; OHC, and energy; OHC, and texture; or OHC, and functionality.
[0108] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: WHC, and LGC, WHC, and emulsion capacity;23979-20007.40 WHC, and foaming capacity; WHC, and foaming stability; WHC, and texture (e.g., gel texture and / or blench texture); WHC, and moisture; WHC, and protein dispersability; WHC, and nitrogen / protein solubility; WHC, and viscosity; WHC, and protein; WHC, and carbohydrate; WHC, and oligosaccharides; WHC, and sucrose; WHC, and crude fat / oil; WHC, and crude fiber; WHC, and ash; WHC, and color; WHC, and flavor; WHC, and saponins; WHC, and energy; WHC, and texture; or WHC, and functionality.
[0109] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: LGC, and WHC; LGC, and emulsion capacity; LGC, and foaming capacity; LGC, and foaming stability; LGC, and texture (e.g., gel texture and / or blench texture); LGC, and moisture; LGC, and protein dispersability; LGC, and nitrogen / protein solubility; LGC, and viscosity; LGC, and protein; LGC, and carbohydrate; LGC, and oligosaccharides;23979-20007.40 LGC, and sucrose; LGC, and crude fat / oil; LGC, and crude fiber; LGC, and ash; LGC, and color; LGC, and flavor; LGC, and saponins; LGC, and energy; LGC, and texture; or LGC, and functionality.
[0110] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: emulsion capacity, and WHC; emulsion capacity, and LGC, emulsion capacity, and foaming capacity; emulsion capacity, and foaming stability; emulsion capacity, and texture (e.g., gel texture and / or blench texture); emulsion capacity, and moisture; emulsion capacity, and protein dispersability; emulsion capacity, and nitrogen / protein solubility; emulsion capacity, and viscosity; emulsion capacity, and protein; emulsion capacity, and carbohydrate; emulsion capacity, and oligosaccharides; emulsion capacity, and sucrose; emulsion capacity, and crude fat / oil; emulsion capacity, and crude fiber; emulsion capacity, and ash; emulsion capacity, and color; emulsion capacity, and flavor; emulsion capacity, and saponins; emulsion capacity, and energy; emulsion capacity, and texture; or emulsion capacity, and functionality.23979-20007.40
[0111] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: foaming capacity and / or foaming stability, and WHC; foaming capacity and / or foaming stability, and LGC, foaming capacity and / or foaming stability, and emulsion capacity; foaming capacity and / or foaming stability, and texture (e.g., gel texture and / or blench texture); foaming capacity and / or foaming stability, and moisture; foaming capacity and / or foaming stability, and protein dispersability; foaming capacity and / or foaming stability, and nitrogen / protein solubility; foaming capacity and / or foaming stability, and viscosity; foaming capacity and / or foaming stability, and protein; foaming capacity and / or foaming stability, and carbohydrate; foaming capacity and / or foaming stability, and oligosaccharides; foaming capacity and / or foaming stability, and sucrose; foaming capacity and / or foaming stability, and crude fat / oil; foaming capacity and / or foaming stability, and crude fiber; foaming capacity and / or foaming stability, and ash; foaming capacity and / or foaming stability, and color; foaming capacity and / or foaming stability, and flavor; foaming capacity and / or foaming stability, and saponins; foaming capacity and / or foaming stability, and energy; foaming capacity and / or foaming stability, and texture; or foaming capacity and / or foaming stability, and functionality.
[0112] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: texture, and WHC; texture, and LGC, texture, and emulsion capacity; texture, and foaming capacity; texture, and foaming stability; texture, and moisture; texture, and protein dispersability;23979-20007.40 texture, and nitrogen / protein solubility; texture, and viscosity; texture, and protein; texture, and carbohydrate; texture, and oligosaccharides; texture, and sucrose; texture, and crude fat / oil; texture, and crude fiber; texture, and ash; texture, and color; texture, and flavor; texture, and saponins; texture, and energy; texture, and texture; or texture, and functionality.
[0113] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: moisture, and WHC; moisture, and LGC, moisture, and emulsion capacity; moisture, and foaming capacity; moisture, and foaming stability; moisture, and texture (e.g., gel texture and / or blench texture); moisture, and protein dispersability; moisture, and nitrogen / protein solubility; moisture, and viscosity; moisture, and protein; moisture, and carbohydrate; moisture, and oligosaccharides; moisture, and sucrose; moisture, and crude fat / oil; moisture, and crude fiber; moisture, and ash; moisture, and color;23979-20007.40 moisture, and flavor; moisture, and saponins; moisture, and energy; moisture, and texture; or moisture, and functionality.
[0114] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: protein dispersability, and WHC; protein dispersability, and LGC, protein dispersability, and emulsion capacity; protein dispersability, and foaming capacity; protein dispersability, and foaming stability; protein dispersability, and texture (e.g., gel texture and / or blench texture); protein dispersability, and moisture; protein dispersability, and nitrogen / protein solubility; protein dispersability, and viscosity; protein dispersability, and protein; protein dispersability, and carbohydrate; protein dispersability, and oligosaccharides; protein dispersability, and sucrose; protein dispersability, and crude fat / oil; protein dispersability, and crude fiber; protein dispersability, and ash; protein dispersability, and color; protein dispersability, and flavor; protein dispersability, and saponins; protein dispersability, and energy; protein dispersability, and texture; or protein dispersability, and functionality.
[0115] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: nitrogen / protein solubility, and WHC;23979-20007.40 nitrogen / protein solubility, and LGC, nitrogen / protein solubility, and emulsion capacity; nitrogen / protein solubility, and foaming capacity; nitrogen / protein solubility, and foaming stability; nitrogen / protein solubility, and texture (e.g., gel texture and / or blench texture); nitrogen / protein solubility, and moisture; nitrogen / protein solubility, and protein dispersability; nitrogen / protein solubility, and viscosity; nitrogen / protein solubility, and protein; nitrogen / protein solubility, and carbohydrate; nitrogen / protein solubility, and oligosaccharides; nitrogen / protein solubility, and sucrose; nitrogen / protein solubility, and crude fat / oil; nitrogen / protein solubility, and crude fiber; nitrogen / protein solubility, and ash; nitrogen / protein solubility, and color; nitrogen / protein solubility, and flavor; nitrogen / protein solubility, and saponins; nitrogen / protein solubility, and energy; nitrogen / protein solubility, and texture; or nitrogen / protein solubility, and functionality.
[0116] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: viscosity, and WHC; viscosity, and LGC, viscosity, and emulsion capacity; viscosity, and foaming capacity; viscosity, and foaming stability; viscosity, and texture (e.g., gel texture and / or blench texture); viscosity, and moisture; viscosity, and protein dispersability; viscosity, and nitrogen / protein solubility; viscosity, and protein; viscosity, and carbohydrate;23979-20007.40 viscosity, and oligosaccharides; viscosity, and sucrose; viscosity, and crude fat / oil; viscosity, and crude fiber; viscosity, and ash; viscosity, and color; viscosity, and flavor; viscosity, and saponins; viscosity, and energy; viscosity, and texture; or viscosity, and functionality.
[0117] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: protein, and WHC; protein, and LGC, protein, and emulsion capacity; protein, and foaming capacity; protein, and foaming stability; protein, and texture (e.g., gel texture and / or blench texture); protein, and moisture; protein, and protein dispersability; protein, and nitrogen / protein solubility; protein, and viscosity; protein, and carbohydrate; protein, and oligosaccharides; protein, and sucrose; protein, and crude fat / oil; protein, and crude fiber; protein, and ash; protein, and color; protein, and flavor; protein, and saponins; protein, and energy; protein, and texture; or23979-20007.40 protein, and functionality.
[0118] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: carbohydrate, and WHC; carbohydrate, and LGC, carbohydrate, and emulsion capacity; carbohydrate, and foaming capacity; carbohydrate, and foaming stability; carbohydrate, and texture (e.g., gel texture and / or blench texture); carbohydrate, and moisture; carbohydrate, and protein dispersability; carbohydrate, and nitrogen / protein solubility; carbohydrate, and viscosity; carbohydrate, and protein; carbohydrate, and sucrose; carbohydrate, and crude fat / oil; carbohydrate, and crude fiber; carbohydrate, and ash; carbohydrate, and color; carbohydrate, and flavor; carbohydrate, and saponins; carbohydrate, and energy; carbohydrate, and texture; or carbohydrate, and functionality.
[0119] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: oligosaccharides, and WHC; oligosaccharides, and LGC, oligosaccharides, and emulsion capacity; oligosaccharides, and foaming capacity; oligosaccharides, and foaming stability; oligosaccharides, and texture (e.g., gel texture and / or blench texture);23979-20007.40 oligosaccharides, and moisture; oligosaccharides, and protein dispersability; oligosaccharides, and nitrogen / protein solubility; oligosaccharides, and viscosity; oligosaccharides, and protein; oligosaccharides, and sucrose; oligosaccharides, and crude fiber; oligosaccharides, and ash; oligosaccharides, and color; oligosaccharides, and flavor; oligosaccharides, and saponins; oligosaccharides, and energy; oligosaccharides, and texture; or oligosaccharides, and functionality.
[0120] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: crude fat / oil, and WHC; crude fat / oil, and LGC, crude fat / oil, and emulsion capacity; crude fat / oil, and foaming capacity; crude fat / oil, and foaming stability; crude fat / oil, and texture (e.g., gel texture and / or blench texture); crude fat / oil, and moisture; crude fat / oil, and protein dispersability; crude fat / oil, and nitrogen / protein solubility; crude fat / oil, and viscosity; crude fat / oil, and protein; crude fat / oil, and carbohydrate; crude fat / oil, and oligosaccharides; crude fat / oil, and sucrose; crude fat / oil, and crude fiber; crude fat / oil, and ash; crude fat / oil, and color; crude fat / oil, and flavor;23979-20007.40 crude fat / oil, and saponins; crude fat / oil, and energy; crude fat / oil, and texture; or crude fat / oil, and functionality.
[0121] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: crude fiber, and WHC; crude fiber, and LGC, crude fiber, and emulsion capacity; crude fiber, and foaming capacity; crude fiber, and foaming stability; crude fiber, and texture (e.g., gel texture and / or blench texture); crude fiber, and moisture; crude fiber, and protein dispersability; crude fiber, and nitrogen / protein solubility; crude fiber, and viscosity; crude fiber, and protein; crude fiber, and carbohydrate; crude fiber, and oligosaccharides; crude fiber, and sucrose; crude fiber, and crude fat / oil; crude fiber, and ash; crude fiber, and color; crude fiber, and flavor; crude fiber, and saponins; crude fiber, and energy; crude fiber, and texture; or crude fiber, and functionality.
[0122] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: ash, and WHC; ash, and LGC,23979-20007.40 ash, and emulsion capacity; ash, and foaming capacity; ash, and foaming stability; ash, and texture (e.g., gel texture and / or blench texture); ash, and moisture; ash, and protein dispersability; ash, and nitrogen / protein solubility; ash, and viscosity; ash, and protein; ash, and carbohydrate; ash, and oligosaccharides; ash, and sucrose; ash, and crude fat / oil; ash, and crude fiber; ash, and color; ash, and flavor; ash, and saponins; ash, and energy; ash, and texture; or ash, and functionality.
[0123] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: color, and WHC; color, and LGC, color, and emulsion capacity; color, and foaming capacity; color, and foaming stability; color, and texture (e.g., gel texture and / or blench texture); color, and moisture; color, and protein dispersability; color, and nitrogen / protein solubility; color, and viscosity; color, and protein; color, and carbohydrate;23979-20007.40 color, and oligosaccharides; color, and sucrose; color, and crude fat / oil; color, and crude fiber; color, and ash; color, and flavor; color, and saponins; color, and energy; color, and texture; or color, and functionality.
[0124] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: flavor, and WHC; flavor, and LGC, flavor, and emulsion capacity; flavor, and foaming capacity; flavor, and foaming stability; flavor, and texture (e.g., gel texture and / or blench texture); flavor, and moisture; flavor, and protein dispersability; flavor, and nitrogen / protein solubility; flavor, and viscosity; flavor, and protein; flavor, and carbohydrate; flavor, and oligosaccharides; flavor, and sucrose; flavor, and crude fat / oil; flavor, and crude fiber; flavor, and ash; flavor, and color; flavor, and saponins; flavor, and energy; flavor, and texture; or flavor, and functionality.23979-20007.40
[0125] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: saponins, and WHC; saponins, and LGC, saponins, and emulsion capacity; saponins, and foaming capacity; saponins, and foaming stability; saponins, and texture (e.g., gel texture and / or blench texture); saponins, and moisture; saponins, and protein dispersability; saponins, and nitrogen / protein solubility; saponins, and viscosity; saponins, and protein; saponins, and carbohydrate; saponins, and oligosaccharides; saponins, and sucrose; saponins, and crude fat / oil; saponins, and crude fiber; saponins, and ash; saponins, and color; saponins, and energy; saponins, and texture; or saponins, and functionality.
[0126] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: texture, and WHC; texture, and LGC, texture, and emulsion capacity; texture, and foaming capacity; texture, and foaming stability; texture, and texture (e.g., gel texture and / or blench texture); texture, and moisture; texture, and protein dispersability;23979-20007.40 texture, and nitrogen / protein solubility; texture, and viscosity; texture, and protein; texture, and carbohydrate; texture, and oligosaccharides; texture, and sucrose; texture, and crude fat / oil; texture, and crude fiber; texture, and ash; texture, and color; texture, and flavor; texture, and energy; texture, and saponins; or texture, and functionality.
[0127] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: functionality, and WHC; functionality, and LGC, functionality, and emulsion capacity; functionality, and foaming capacity; functionality, and foaming stability; functionality, and texture (e.g., gel texture and / or blench texture); functionality, and moisture; functionality, and protein dispersability; functionality, and nitrogen / protein solubility; functionality, and viscosity; functionality, and protein; functionality, and carbohydrate; functionality, and oligosaccharides; functionality, and sucrose; functionality, and crude fat / oil; functionality, and crude fiber; functionality, and ash; functionality, and color;23979-20007.40 functionality, and flavor; functionality, and energy; functionality, and saponins; functionality, and texture.
[0128] It should be understood that, in other embodiments, the grain further has one or more additional traits (e.g., a third processor preferred characteristic, etc.) with a target value, as if each and every combination of the processor preferred characteristics were listed.
[0129] In certain variations, the blends can achieve a threshold level of any of the combination of the processor preferred characteristics: protein, and oil; protein, and oligosaccharide; protein, and carbohydrate; protein, and flavor; protein, and saponins; protein, and color; protein, carbohydrate, and flavor; protein, oligosaccharide, and saponins; or protein, oil, carbohydrate or oligosaccharide, and saponins or flavor.
[0130] In some variations of the foregoing, in addition to achieving the threshold level of any of the combination of the processor preferred characteristics as described herein, the blend also achieves a target yield of the harvested grain. It should be understood that “yield” for seed as planned for use in a blend is different than the target yield in the harvested grain blend that one seeks to achieve. The “yield” of a seed is a predicted yield, e.g., based on average yields of previous tests on that variety when grown in monoculture. The yield may be different from the yield that one seeks to achieve in the blend of harvested grain. In some variations, the predicted yield of a certain variety is different when blended with different varieties.
[0131] In other embodiments, the traits are counter-selective.
[0132] In some variations of the foregoing, the target value of the grain is an average amount. In other variations, the target value of the grain is a distribution range of the amount of the trait in a blend of harvested grain. Varieties23979-20007.40
[0133] In certain aspects, provided is blend of at least two varieties. In some embodiments, the blend comprises 2, 3, 4, 5, or 6 varieties; or between 2 and 10 varieties, or between 2 and 5 varieties. In one variation, the blend comprises 2 varieties. In another variation, the blend comprises 3 varieties.
[0134] In one aspect, provided is a blend of soybeans from at least two compatible varieties. In some embodiments, compatible varieties have (i) relative maturities no greater than 0.4 and / or relative maturities within 0.2-0.3 of each other, and (ii) compatible herbicide tolerance traits. In other embodiments, compatible varieties have (i) relative maturities no greater than 0.4 and / or relative maturities within 0.2-0.3 of each other, and (ii) statistically similar amino acid profiles.
[0135] In certain embodiments, the varieties have relative maturities no greater than 0.4; and / or relative maturities within 0.2-0.3 of each other. In other embodiments, the varieties do not exceed relative maturity differences of 0.75.
[0136] In some variations, relative maturity refers to the number of days to grow a variety in the field. For example, soybean maturity may be classified in different groups (MGs) ranging from 000 for the very early maturing varieties to 9 for the later. A variety is classified to a specific MG according to the length of period from planting to maturity. This phenological attribute is typically determined by two abiotic factors: photoperiod and temperature, and these factors can dictate the most suitable MG for a particular geographical location.
[0137] In certain embodiments, the varieties have compatible herbicide tolerance traits. In certain embodiments, the varieties are not a mix of determinant and indeterminant varieties. In certain embodiments, the varieties are not a mix of dwarf and non-dwarf type varieties.
[0138] In one variation, provided is a composition comprising a blend of seeds, e.g., a blend in bag (BIB), that comprises insect resistant variety(ies). In such variation, such blend of insect (e.g. soybean cyst nematode) susceptible may be cultivated with tolerant varieties to reduce the impact of insect predation on grain composition (e.g. oil, protein, etc.) and / or the quality of post- harvest food ingredients and intermediates.
[0139] In some embodiments, the varieties have statistically similar amino acid profiles. In some variations, the amino acid profile includes one or more of the following: alanine, arginine, aspartate, cystine / cysteine, glutamate, glycine, histidine, methionine, proline, serine, tyrosine, valine, threonine, lysine, leucine, isoleucine, phenylalanine, and tryptophan.23979-20007.40
[0140] Examples of soybean varieties that may be used in the blends described herein include varieties selected from Tables A and B below. Table A. Exemplary Soybean Varieties Suitable for Use in Blends Herein Protein (DB)Alanine4.07 3.924.16 4.22 4 4.09 4.39 4.08 4.17 4.28Arginine8.18 8.647.74 7.97 8.397.17 8.11 7.36 7.24Aspartate11.5 11.1711.76 11.74 11.43 11.75 11.63 11.48 11.81 11.81Cystine / Cysteine1.28 1.231.3 1.36 1.32 1.31 1.24 1.44 1.35 1.3Glutamate19.06 18.219.49 19 18.33 19.01 18.38 18.8 18.8 18.92Glycine4.19 4.034.29 4.3 4.12 4.24 4.36 4.22 4.28 4.33Histidine2.51 2.492.59 2.62 2.52 2.56 2.66 2.58 2.51 2.57Methionine1.32 1.311.39 1.41 1.38 1.37 1.36 1.46 1.42 1.38Proline5.2 55.18 4.98 5.1 5 5.05 5.09 5.1Serine5 4.815.11 5.09 4.86 5.03 5.07 5.09 5.11 5.17Tyrosine3.24 3.073.35 3.33.29 3.46 3.24 3.34 3.44Valine4.78 4.594.8 4.88 4.66 4.77 4.95 4.66 4.85 4.87Threonine3.7 3.583.79 3.86 3.68 3.79 4.02 3.83 3.87 3.98Lysine6.58 6.396.69 6.73 6.3 6.45 6.9 6.14 6.75 6.79Leucine7.49 7.147.67 7.32 7.61 7.82 7.5 7.67 7.79Isoleucine4.47 4.274.58 4.58 4.36 4.52 4.61 4.38 4.61 4.58Phenylalanine5.08 4.855.14 5.05 4.88 5.05 5.19 5.01 5.11 5.17Tryptophan1.36 1.341.39 1.41 1.36 1.37 1.41 1.38 1.44 1.49Total99.03 96.02100.698.46 99.54 100.22PDCAAS0.94 0.91 10.99 0.97 0.96 0.94 0.95 0.99 0.96 Table B. Harvest Composition Data for Exemplary Soybean Varieties Variety Variety Variety Variety Variety Variety Variety Variety Variety Variety Variety A B C D E F G H I J K Moisture (%) 6.93% 6.88% 9.04% 6.83% 6.94% 7.03% 7.24% 6.80% 9.02% 6.88% 6.57% Protein (% DB) 50.59% 50.56% 46.63% 48.29% 46.95% 49.97% 48.87% 41.03% 49.31% 45.79% 46.24% Crude Fat / Oil (% DB) 17.82% 17.05% 19.07% 18.66% 17.73% 17.34% 18.87% 21.72% 17.98% 19.84% 20.33% Crude Fiber (% DB) 4.90% 4.70% 5.40% 5.10% 5.50% 4.70% 4.00% 5.40% 5.70% 4.90% 4.60% Ash (% DB) 5.21% 5.07% 5.19% 5.04% 5.26% 5.00% 5.91% 5.63% 5.34% 5.05% 5.75%
[0141] In some embodiments, provided are blends comprising at least two varieties, wherein the blends achieve a threshold level of one or more of the processor preferred characteristics, which may include, for example, oil holding capacity (OHC), water holding capacity (WHC),23979-20007.40 least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color (e.g., as a result of the hilum), saponin, energy, flavor, texture, and functionality. In certain embodiments, the blends can achieve a threshold level of any of the processor preferred characteristics and yield of the harvested grain blend.
[0142] In other embodiments, provided is a blend comprising at least two varieties with improved saponin, higher harvest yield and / or greater protein content.
[0143] In yet other embodiments, provided is a blend comprising at least two varieties with improved flavor, higher yield and / or protein content.
[0144] In certain embodiments, other suitable blends may include: (1) a variety with ultra high protein, and low carbohydrates; and (2) a variety with high protein, low carbohydrates, and ultra low flavor. In one embodiment, the blend may be soybean varieties with such properties.
[0145] In certain embodiments, other suitable blends may include: (1) a variety with ultra high protein, and low oligosaccharide; and (2) a variety with high protein, low oligosaccharide, and ultra low saponins. In one embodiment, the blend may be soybean varieties with such properties.
[0146] In certain embodiments, other suitable blends may include: (1) a variety with ultra high protein; and (2) a variety with high protein, and low oligosaccharide.
[0147] Certain traits are antagonistically genetically related, for example, protein content and yield; and protein content and oil content. Selecting genetics that improve one of the pair tends to produce antagonistic results in the other trait. Conventional plant breeding and / or conventional genetic selection or modification are less effective at improving these types of traits simultaneously. This is a pervasive and persistent problem in agriculture and crop improvement.
[0148] Teachings herein provide a solution to this problem of improving two or more traits whose genetics behave antagonistically. In certain embodiments, two compatible soybean varieties are combined in such a way that a relatively homogenous blend of grain from the two is achieved. Unlike other teachings that focus solely on improving a crop’s performance in the field, teachings herein include ways to blend for the purposes of improving the efficiency of post-harvest processing steps and or improve the quality of food / feed ingredients. These blends are compositions that will be difficult, time consuming, or even impossible to achieve using a23979-20007.40 single soybean variety. Teachings herein explain why it is often not trivial to determine how and when to blend varieties to achieve certain post-harvest advantages. In certain embodiments, the blend compositions solve yield drag, or drag in some other trait.
[0149] In certain embodiments, the blend involves combining features from multiple varieties that are genetically antagonistic into a volume of harvested grain that can be fed into a processing line.
[0150] In one example, the blend comprises at least two varieties of soybeans, wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5% and a mean yield of at least about 55 or more bushels per acre.
[0151] In another example, the blend comprises at least two varieties of soybeans, wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 25% and a mean yield of at least about 55 or more bushels per acre.
[0152] In another example, the blend comprises at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and (c) a mean yield of at least about 55 or more bushels per acre.
[0153] In yet another example, the blend comprises at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that is more stable in terms of predictability from lot-to-lot for legume production as compared to when a blend is not used.
[0154] In yet another example, the blend comprises of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that improves amino acid profiles, volatiles, isoflavones and / or other flavor and / or food properties of a post-processing product. Blend Ratio
[0155] In some embodiments, at least two varieties (including, for example, at least two compatible varieties as described above) are blended at a ratio to: (a) yield grain that is processed to produce white flakes having a protein content of at least about 59.5%;23979-20007.40 (b) yield grain having an oil content of at least about 18%; and (c) obtain a mean yield of at least about 55 bushels per acre.
[0156] It should be understood that white flakes are generally made after dehulling and pressing soybeans out into thin flakes. This ruptures cells and releases the oil within, which can then be extracted from the flake to create an oil fraction and a defatted (white) flake portion. The resulting white flakes may have a broad range of applications in downstream processes.
[0157] In other embodiments, at least two varieties (including, for example, at least two compatible varieties as described above) are blended at a ratio to yield grain that is processed to produce a downstream product having at least one property that is improved as compared to the weighted average of the at least one property of a processed form of each compatible variety alone. In some variations, properties of the downstream products may include oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color (e.g., as a result of the hilum), saponin, energy, flavor, texture, and functionality. In certain variations, properties of the downstream products may include water holding capacity (WHC), oil holding capacity (OHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, micro texture, bench texture, gel texture, protein dispersibility, nitrogen / protein solubility, or viscosity, or any combination thereof.
[0158] In some embodiments, the ratio of two varieties is at least 5:95, at least 10:90, at least 20:30, at least 30:70, or at least 40:60, at least 50:50, at least 60:40 or least 70:30; or between 50:50 and 90:10, between 50:50 and 80:20, or between 60:40 and 70:30, such that the blend yields grain that is processed to produce a downstream product having at least one property (such as the aforementioned properties) that is improved.
[0159] In some variations, such downstream products may include a food or feed ingredient or product, a protein isolate, other protein product, soybean seed hulls, meal, flake, flour, fiber, sugar, or oil product, or a food, feed, aqua, or industrial product, or any combination thereof. In certain embodiments, two varieties (including, for example, two compatible varieties as described above) are blended together. In some variations, one of the two compatible varieties is a higher protein variety and the other is a lower protein variety. In certain variations, one of the two compatible varieties is an ultra high protein variety (Variety 1) and the other is a high23979-20007.40 protein variety (Variety 2). In one variation of the foregoing, the ratio of Variety 1 to Variety 2 is at least 50:50, at least 60:40 or least 70:30; or between 50:50 and 90:10, between 50:50 and 80:20, or between 60:40 and 70:30.
[0160] In one variation, one variety is Cultivar 1967799 as disclosed in US patent 11,206,796, US PVP application 2020 / 0212, and CA PVP 22-10789. In another variation, another variety is Cultivar 172290521658 and disclosed in US patent 10631510, EU PVP 2022 / 0788, CA PVP 22-10876, and BR PVP 21806.000062 / 2022. Timing
[0161] In some embodiments, the blending is done at or before planting, such as while the varieties are seeds, for example a blend in a bag that the grower empties into a planter. These blends are planted as seed, grown as plants, and harvested as grain all as a blend. In some embodiments, the varieties are blended as they are harvested from the field. This can be done by planting the varieties in separate sections, e.g. strips, but close enough together that they can be harvested simultaneously by the combine head in a predictable ratio. The combine harvester head will span from one variety to the other, and blending occurs simultaneously with the cutting, threshing, and auguring and conveying that occurs in the combine as the two varieties are harvested together. A third type of blending occurs after the two varieties have been grown and harvested separately and then combined at some point before reaching the processing facility. In certain embodiments, the varieties are grown in different sections in the same field and can be combined in a bin or when loaded onto a truck for transportation. In certain embodiments, the varieties are grown in different fields entirely and at least one of the varieties is first transported to another location before blending occurs. Blending can occur at substantially any point before the blend is processed.
[0162] With reference to FIG.7, the benefit from blending is not exhausted at harvest. For example, yield benefit may be realized at harvest and / or at processing, but quality trait benefit can be realized later, e.g. during / after processing. The quality trait benefit may be any trait that the user desires.
[0163] With reference to FIG.8, the blending may occur at any time during the agricultural process. Thus, nodes and internodes in this figure are dashed to indicate they become points where the system can be adjusted. Due to this flexibility, the invention herein can be used in conjunction with computer / artificial intelligence (AI) / prediction systems to adjust (e.g., in real time) which varieties are blended and when in the process the blend occurs. Each dashed line23979-20007.40 above indicates a point where, for example, an AI system can make a prediction and recommendation for how to proceed. For example, based on a set of product specification thresholds, a computer / artificial intelligence (AI) / prediction system could predict which two varieties should be blended together at planting to produce the desired result, including the optimized ratio of the blend. Furthermore, if something happens during the growing season to throw that prediction off (like a drought or flood, or a change in the market that dramatically changes the desired product specification), the computer / artificial intelligence (AI) / prediction system can use data collected during the growing season to predict what the harvested blend will be as the plants grow and then recommend an additional blending step after harvest that should be made. This additional blend could involve adding more of a first variety or a second variety, or even a third variety, a fourth variety, etc., whether it is grown at the same location as the blend or grown elsewhere and combined (e.g. by truck) before processing. Thus, the process of blending described herein provides a new way to plant, grow, harvest, and process quality grain.
[0164] In some variations, the compositions (e.g., blends) described herein are based on determining the desirable endpoints / intermediates in the process, determining the ideal compositions to have at those points in the process, and then working backwards to the blend that will produce such target objectives. Thus, in some variations, blending as described herein serves as a way of achieving more stable processed outcomes from lot-to-lot than from singular varieties processed in isolation.
[0165] With reference to FIG.9A, blending occurs after harvest, whether the two varieties are grown in separate fields (top) or separately but in the same field (bottom). In either case, the combine harvests all of one variety, then the other variety, and the two varieties are kept separate until they are blended after harvest.
[0166] With reference to FIG.9B, two varieties are planted in sections in the same field, one variety per section (in this case, strips). The harvester harvests at least some portion of both varieties simultaneously. In certain embodiments, the two varieties are plated in alternating strips and the harvester collects multiple strips of each variety at the same time (top). In certain embodiments the varieties are planted in sections, one variety per section, but the sections of both varieties are harvested simultaneously. In certain embodiments, the varieties are not planted in equal proportions.23979-20007.40
[0167] With reference to FIG.9C, the blend occurs in the bag (a ‘blend in bag’ or BIB) and the varieties are intermingled together as they are grown. In such embodiment, the varieties are not separated by strips or sections.
[0168] When the varieties are grown together in the same location (e.g. as in FIG.9B and FIG.9C), the architecture of the varieties and competition between them produces a harvest composition that was previously unpredictable. For example, normally varieties are harvested as in the top diagram of FIG.9A (or FIG.9B scheme that closely approximates separate growing locations). To determine what ratio to blend the two varieties, various ratios of blends may be tested to arrive at an optimal ratio. However, working backwards from that ideal finished ratio to predict how to achieve it using the approach in FIG.9B or FIG.9C can be difficult and complicated, as there is unlikely to be a 1:1 correlation between the ratio of the two varieties that need to be planted in the field to achieve the ratio desired after harvest. In some variations, synergy may be achieved via a field growth interaction of the plants when grown / harvested together and a post-processing / food functionality interaction that occurs when the two varieties are processed together. Goals and Advantages of Blending
[0169] The goals of blending include, for example, optimizing economics (e.g. with high yield) and skipping processing steps (e.g. low oligosaccharides); empowering ingredient optimization in the field vs at the crush facility (which may present operational / logistical advantage, and enable future farm to plate linkage for specific ingredients); and in field blending may lead to reduced carbon output vs managing the blend at crush.
[0170] In some variations, the varieties are determined and bred to be of similar composition except for protein, oil and yield. In some variations, the meal or white flake or concentrate or isolate are of similar specifications and performance to the desired homogeneous unblended specification. In some variations, prediction from composite analyses and specifications are used to determine blending ratios. In some variations, in field measures are used to recalculate any shifts to blending in season.
[0171] The blending of varieties as provided herein optimize the economics of crop agriculture, especially for producing a harvest product that meets the threshold levels of multiple traits. In certain embodiments, the traits are antagonistically genetically related, for example, protein content and yield and or protein content and oil content.23979-20007.40
[0172] In some variations, various seed blends may be used to mitigate the effects of the environmental on the performance of genetics / germplasm.
[0173] In some embodiments, the downstream products of the blends described herein exhibit one or more synergistic complex traits, which may include protein content, yield, oil content, oligosaccharide content, saponins content, amino acid profile, and / or a functional property as described herein.
[0174] In some embodiments, blending may yield synergistic effects from mixing varieties with different functionality measurements. Varieties may have a mix of properties, for example, yield performance, water holding capacity (WHC), oil holding capacity (OHC), least gelation concentration (LGC), emulsion capacity (EC), foaming capacity (FC), foaming stability, micro texture, bench texture, or gel texture. In some variations, synergistic effects may be achieved by mixing better functionality varieties with better commercial performance varieties.
[0175] In some embodiments, the blends of varieties described herein yield a net protein pounds per acre advantage as compared to individual varieties. For example, even at a 10 bushels yield drag, the blends of varieties described herein can maintain a significant net protein pounds per acre advantage. Yield refers to bushels (e.g., 60 lbs of grain) per acre; and yield drag refers to the yield achieved relative to comparable market performance. Conventional yield is typically defined as the harvested seed dry matter per unit land area. Post-processing yield is typically the amount of a grain component that is recoverable by processing the grain, e.g., by conventional and / or industrial methods that create ingredients or ingredient intermediates associated with the production of food and / or feed, per unit area of land that was used to grow the beans. For example, the post-processing protein yield produced by a certain variety could be the amount of protein that is recovered in a white flake, a soy protein concentrate, or a soy protein isolate per acre of land that was used to grow the variety. Similarly, the post-harvest oil yield of a variety could be the amount of oil that is recovered from the variety during processing per acre of land used to grow the variety.
[0176] In some variations, the post-processing product is derived from processing a final grain blend to produce a food or feed ingredient or product, for example, a protein isolate, other protein product, soybean seed hulls, meal, flake, flour, fiber, sugar, or oil product, or a food, feed, aqua, or industrial product. In some variations, the post-processing property refers to a property of a composition derived from processing a final grain blend to produce a food or feed23979-20007.40 ingredient or product, for example, a protein isolate, other protein product, soybean seed hulls, meal, flake, flour, fiber, sugar, or oil product, or a food, feed, aqua, or industrial product. ENUMERATED EMBODIMENTS
[0177] The following enumerated embodiments are representative of some aspects of the invention. 1. A composition comprising a blend of at least two varieties of soybeans, optionally, wherein the varieties have relative maturities no greater than 0.4 and / or relative maturities within 0.2-0.3 of each other, or the varieties do not exceed relative maturity differences of 0.75; and wherein the varieties are blended at a ratio to yield grain that is processed to produce a downstream product having at least one property that is improved. 2. The composition of embodiment 1, wherein the varieties are blended at a ratio to (a) yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and (c) a mean yield of at least about 55 or more bushels per acre. 3. The composition of embodiment 1 or 2, wherein the varieties have statistically similar amino acid profiles. 4. The composition of any one of embodiments 1 to 3, wherein the varieties have improved saponin, higher harvest yield and / or greater protein content. 5. The composition of any one of embodiments 1 to 3, wherein the varieties have improved flavor, and / or higher yield and / or protein content. 6. The composition of any one of embodiments 1 to 5, wherein the varieties have compatible herbicide tolerance traits. 7. The composition of any one of embodiments 1 to 6, wherein the blend is of two compatible varieties. 8. The composition of embodiment 7, wherein one variety is a higher protein variety and the other is a lower protein variety. 9. The composition of any one of embodiments 1 to 8, wherein the varieties are blended at a ratio to yield grain that is processed to produce a downstream product having at least one23979-20007.40 property that is improved as compared to the weighted average of the at least one property of a processed form of each variety alone. 10. The composition of embodiment 9, wherein the at least one property is water holding capacity (WHC), oil holding capacity (OHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, protein dispersibility, nitrogen / protein solubility, or viscosity, or any combination thereof. 11. The composition of embodiment 9 or 10, wherein the downstream product is a food or feed ingredient or product, a protein isolate, other protein product, soybean seed hulls, meal, flake, flour, fiber, sugar, or oil product, or a food, feed, aqua, or industrial product, or any combination thereof. 12. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5% and a mean yield of at least about 55 or more bushels per acre. 13. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 25% and a mean yield of at least about 55 or more bushels per acre. 14. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and (c) a mean yield of at least about 55 or more bushels per acre. 15. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that is more stable in terms of predictability from lot-to- lot for legume production as compared to when a blend is not used. 16. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that improves amino acid profiles, volatiles, isoflavones and / or other flavor and / or food properties of a post-processing product. 17. A method of producing grain from a blend of soybean varieties, wherein the grain has at least a first trait and a second trait, wherein each trait of the grain has a target value, the method comprising: a) planting seeds from at least two soybean varieties together, and23979-20007.40 wherein the soybean varieties comprise: a first soybean variety having (i) the first trait with a value that is higher than the target value of the first trait for the grain, and (ii) a second trait with a value that is lower than the target value of the second trait for the grain, and a second soybean variety having (i) the first trait with a value that is lower than the target value of the first trait for the grain, and (ii) the second trait with a value that is higher than the target value of the second trait for the grain; b) germinating the seeds and growing plants from the germinated seeds to maturity; and c) harvesting grain from the plants without separating the soybean varieties. 18. The method of embodiment 17, further comprising: processing the harvested grain to obtain a downstream product, wherein the first trait and the second trait in the downstream product are not achievable from grain obtained from each soybean variety alone. 19. The method of embodiment 17 or 18, wherein each trait is a processor preferred characteristic of a processed soybean composition obtained from the blend of soybean varieties. 20. The method of embodiment 19, wherein the processor preferred characteristic is oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color (e.g., as a result of the hilum), saponin, energy, flavor, texture, and functionality. 21. The method of embodiment 19 or 20, wherein the blend achieves the target value for each processor preferred characteristic and a target yield of the harvested grain. 22. The method of embodiment 17 or 18, wherein the first trait and the second trait are counter-selective. 23. The method of embodiment 17 or 18, wherein the first trait and the second trait are selected from the group consisting of protein content, oil content, carbohydrate content, oligosaccharide content, saponins content, and flavor.23979-20007.40 24. The method of embodiment 17 or 18, wherein the first trait is oil content, and the second trait is protein content. 25. The method of embodiment 17 or 18, wherein the first trait is protein content, and the second trait is oligosaccharide content. 26. The method of embodiment 17 or 18, wherein the first trait is protein content, and the second trait is flavor. 27. The method of embodiment 17 or 18, wherein the first trait is protein content, and the second trait is saponins content. 28. The method of any one of embodiments 17 to 27, wherein the grain further has a third trait with a target value. 29. The method of embodiment 28, wherein the first trait is protein content, the second trait is carbohydrate content, and the third trait is flavor. 30. The method of embodiment 28, wherein the first trait is protein content, the second trait is oligosaccharide content, and the third trait is saponins content. 31. The method of any one of embodiments 17 to 30, wherein the blend achieves a target yield of the harvested grain. 32. The method of any one of embodiments 17 to 31, wherein the target value is an average amount of the trait in a blend of harvested grain. 33. The method of any one of embodiments 17 to 31, wherein the target value is a distribution range of the amount of the trait in a blend of harvested grain. 34. The method of any one of embodiments 17 to 33, wherein the soybean varieties are not a mix of determinant and indeterminant varieties. 35. The method of any one of embodiments 17 to 34, wherein the soybean varieties are not a mix of dwarf and non-dwarf type varieties. 36. The method of any one of embodiments 17 to 35, wherein the soybean varieties when planted as a blend yield grain with traits that are not achieved from planting any one of the individual soybean varieties alone. 37. The method of any one of embodiments 17 to 36, wherein the soybean varieties are blended in a predetermined proportion to maximize the match of the grain to specifications of the downstream product.23979-20007.40 38. The method of any one of embodiments 17 to 37, wherein growing the soybean varieties to maturity comprises growing the soybean varieties together over a coextensive area. 39. The method of any one of embodiments 17 to 38, wherein growing the soybean varieties to maturity comprises mixing together seeds of the soybean varieties prior to planting them. 40. The method of any one of embodiments 17 to 39, wherein the grain obtained after one growing cycle has at least the first trait and second trait at their respective target values. 41. A method of determining a composition of a blended seed mixture made by blending seeds such that the resulting grown and harvested grain has a first blended trait value for a first trait and a second blended trait value for a second trait, the method comprising: at an electronic system comprising one or more processors and memory storing instructions configured to be executed by the one or more processors: receiving data representing a plurality of soybean varieties, wherein the data comprises, for each variety of the plurality of soybean varieties, an indication of one or more first trait values for the first trait for the respective variety and an indication of one or more second trait values for the second trait for the respective variety; receiving input data indicating a first target value for the first trait and a second target value for the second trait; selecting, from the plurality of soybean varieties, a pair of varieties for blending to achieve the first blended trait value and the second blended trait value, wherein the selection is based on the indication of one or more first trait values, the indication of one or more second trait values, and the input data indicating the first target value for the first trait and the second target value for the second trait; determining a blend percentage for blending seeds for the selected pair of varieties to produce the blended seed mixture, such that growing the blended seed mixture will produce a crop and resultant grain having the first blended trait value and the second blended trait value, wherein the determination of the blend percentage is based on the indication of one or more first trait values, the indication of one or more second trait values, and the input data indicating the first target value for the first trait and the second target value for the second trait; and generating and storing an output indicating the selected pair of varieties and the determined blend percentage for the selected pair of varieties.23979-20007.40 42. The method of embodiment 41, further comprising blending the seeds for the selected pair of varieties according to the determined blend percentage to produce the blended seed mixture. 43. The method of embodiment 41, further comprising, at the electronic system comprising one or more processors, transmitting a control signal to an automated device that causes the automated device to blend the seeds for the selected pair of varieties according to the determined blend percentage to produce the blended seed mixture. 44. The method of any one of embodiments 41 to 43 , further comprising: planting the blended seed mixture; growing the selected and planted seed mixture to maturity to produce the crop; and harvesting the crop; separating the resultant grain from the harvested crop, wherein the resultant grain has the first blended trait and the second blended trait. 45. The method of embodiment 41, wherein: one of the varieties of the selected pair of varieties is a predicted breeding line result at the time of its selection; and the method further comprises: breeding a current variety over a plurality of growing cycles to create the predicted breeding line result; and blending the seeds for the selected pair of varieties according to the determined blend percentage to produce the blended seed mixture. 46. The method of embodiment 41, wherein selecting the pair of varieties comprises: determining that, for the first trait, the pair of varieties do not both have a first trait value that is above the first target value and do not both have a first trait value that is below the first target value; determining that, for the second trait, the pair of varieties do not both have a second trait value that is above the second target value and do not both have a second trait value that is below the second target value. 47. The method of embodiment 41, wherein selecting the pair of varieties comprises determining that the pair of varieties can be blended to meet a plurality of predefined criteria, wherein the criteria comprise matching criteria for the first target value for the first trait and matching criteria for the second target value for the second trait.23979-20007.40 48. The method of embodiment 41, wherein selecting the pair of varieties comprises determining that the pair of varieties can be blended to meet a plurality of predefined criteria, wherein the criteria comprise economic viability criteria. 49. The method of embodiment 41, wherein determining the blend percentage comprises: calculating a first weighted average of first trait values for the pair of varieties, wherein weighting of the first weighted average is based on a percentage of each variety in the blended seed mixture, such that the first weighted average of the first trait values indicates the blended first trait value that satisfies matching criteria with the first target value; and calculating a second weighted average of second trait values for the pair of varieties, wherein weighting of the second weighted average is based on the percentage of each variety in the blended seed mixture, such that the second weighted average of the second trait values indicates the blended second trait value that satisfies matching criteria with the second target value. 50. The method of embodiment 41, wherein: the data representing the plurality of soybean varieties comprises, for each variety of the plurality of soybean varieties, an indication of a first trait confidence value for each of the respective varieties and a second trait confidence value for each of the respective varieties. 51. The method of embodiment 41, wherein: determining the blend percentage comprises computing a first blended trait confidence value for the first blended trait value and computing a second blended trait confidence value for the second blended trait value. 52. The method of embodiment 41, wherein: the data representing the plurality of soybean varieties comprises, for each variety of the plurality of soybean varieties, an indication of a classification of a third trait value for a third trait for the respective variety; selecting the pair of varieties for blending comprises determining that the third trait values for the pair satisfy compatibility criteria with respect to one another. 53. The method of embodiment 52, wherein: the third trait is maturity; and the compatibility criteria comprise that the relative maturity difference for the pair of varieties does not exceed a predefined maturity difference.23979-20007.40 54. The method of embodiment 52, wherein: the third trait is status as dwarf type or non-dwarf type; and the compatibility criteria comprise that the pair of varieties are either both dwarf type or both non-dwarf type. 55. The method of embodiment 52, wherein: the third trait is status as determinant variety or non-determinant variety; and the compatibility criteria comprise that the pair of varieties are either both determinant variety or both non-determinant variety. 56. The method of embodiment 52, wherein: the third trait is crop height; and the compatibility criteria comprise that the relative crop height difference for the pair of varieties does not exceed 50%. 57. The method of embodiment 52, wherein: the third trait is status as an existing germplasm or a predicted breeding line result; and the compatibility criteria comprise that the pair of varieties are either both existing germplasm or both predicted breeding line result. 58. A method of breeding a new soybean variety and growing a blended mixture of soybean varieties comprising the new soybean variety, such that the resulting grown and harvested grain has a first blended trait value for a first trait and a second blended trait value for a second trait, the method comprising: at an electronic system comprising one or more processors and memory storing instructions configured to be executed by the one or more processors: receiving data representing a plurality of soybean varieties, wherein the data comprises, for each variety of the plurality of soybean varieties, an indication of one or more first trait values for the first trait for the respective variety and an indication of one or more second trait values for the second trait for the respective variety; receiving input data indicating a first target value for the first trait and a second target value for the second trait; selecting, from the plurality of soybean varieties, a pair of varieties for blending to achieve the first blended trait value and the second blended trait value, wherein the selection is based on the indication of one or more first trait values, the indication of one or more second trait values, and the input data indicating the first target value for the first trait and the second target23979-20007.40 value for the second trait, wherein one of the varieties of the selected pair of varieties is a predicted breeding line result at the time of its selection; and determining a blend percentage for blending seeds for the selected pair of varieties to produce a blended seed mixture, such that growing the blended seed mixture will produce a crop and resultant grain having the first blended trait value and the second blended trait value, wherein the determination of the blend percentage is based on the indication of one or more first trait values, the indication of one or more second trait values, and the input data indicating the first target value for the first trait and the second target value for the second trait; breeding a current variety over a plurality of growing cycles to create the predicted breeding line result; blending seeds for the selected pair of varieties according to the determined blend percentage to produce the blended seed mixture; planting the blended seed mixture; growing the blended seed mixture to maturity to produce the crop; harvesting the crop; and separating the resultant grain from the harvested crop, wherein the resultant grain has the first blended trait and the second blended trait. EXAMPLES
[0178] The presently disclosed subject matter will be better understood by reference to the following Examples, which are provided as exemplary of the invention, and not by way of limitation. Example 1: Soybean
[0179] In this example, a soybean meal product that has high protein, low oligosaccharide, and low saponin content is described. Two varieties were blended in a bag: a first variety has ultra high protein (“UHP”), low oligosaccharide (“Low Oligo”); a second variety has high protein (“HP”), low oligosaccharide, ultra low saponins (“ULS”). The end product from blending was observed to be high in protein, low in oligosaccharides, and low in saponins. See Tables 1a and 1b below. The soybean meal product was observed to have a balanced amino acid profile suitable for animal feed applications.23979-20007.40 Table 1a.Table 1b.Example 2: Comparing Different Blend Ratios of Two Compatible Soybean Varieties
[0180] In this example, two compatible soybean varieties are blended together at different ratios. The two varieties used in this example are Variety I and Variety C, which were found to be compatible varieties, having close relative maturities and similar amino acid compositions. In this example, these two varieties are blended at a ratio of 60:40 and 40:60 Variety I to Variety C.
[0181] The blends at 60:40 and 40:60 were observed over a distribution (P10, P20, P30, P40, P50, P60, P70, P80, and P90) with respect to white flake protein content, oil content and mean yield. The 60:40 blend was observed to have at least 59.5% white flake protein at P20, whereas the 40:60 blend did not achieve this target objective at P20. Both blends were observed to have at least 18% oil content at P20. The 60:40 blend achieved 55 bu / acre at P50, and the 40:60 blend achieved this target objective at P30. Overall, based on these observations, the 60:40 blend was selected as a potential commercially viable blend over the 40:60 blend.
[0182] White flour was produced from Variety I, Variety C and the 60:40 blend, by dehulling, grinding, defatting and sieving. Referring to Table 2 below, WHC, OHC, LGC, Foaming, and Gel texture micro scale were similar across Variety I, Variety C and the 60 / 40 blend; however, emulsion capacities of Variety C and the 60:40 blend were unexpectedly higher than Variety I.
[0183] Variety I is Cultivar 1967799 as disclosed in US patent 11,206,796, US PVP application 2020 / 0212, and CA PVP 22-10789. Variety C is Cultivar 172290521658 and disclosed in US patent 10631510, EU PVP 2022 / 0788, CA PVP 22-10876, and BR PVP 21806.000062 / 2022.23979-20007.40 Table 2. Processor-Preferred Characteristic Variety I Variety C 60 / 40 Blend Water holding capacity (WHC) (g / g solids) - micro 1.93± 0.02 2.14 ± 0.04 1.9 ± 0.03 Oil holding capacity (O HC) (g / g solids) - micro 1.82 ± 0.03 1.82 ± 0.03 1.81 ± 0.05 Least gelation concentration (LGC) (% solids) - micro 13 13 13 Emulsion capacity (ml / g protein) 1240 ± 28 2020 ± 0 1680 ± 28 Foaming Capacity (ml / g protein) 572 ± 8 589 ± 10 604 ± 6.9 Foaming Stability (%) 67.8 ± 0.2 68.5± 1.9 70.4± 0.7 Gel texture (g) - micro scale 3130.5 ± 3056.8 ± l 3075.1 ± 201.l 97.6 152.2 Example 3: Field Trials
[0184] Field trials on a 60:40 blend of Cultivar 1967799 : Cultivar 172290521658 were conducted. A thoroughly-mixed 60:40 blend of the two seeds was created in seed bags using a standard seed counter. Seeds were then transferred to a mechanized planter and planted at a density of 180,000 plants / acre over an area of approximately 5 acres in standard commercial production settings. Plants were cultivated using standard methods and the resulting grain harvested six months later, in the fall. Yield data was measured using an on-combine device. Samples of the grain harvested at various points in the field were subjected to NIR analysis to determine protein and oil content on a dry basis. Example 4: Yucatan plant, variety SB-23.7371.0037
[0185] FIG.5A depicts protein and yield values for varieties of Yucatan plants, according to Example 1. The scatter-plot in FIG.5A shows yield values and protein values for a large number of varieties of Yucatan plant. Yellow points show those varieties that meet genomic selection (GS) prediction specifications, teal points show those varieties that fail GS specification predictions, and navy points show those varieties that are null for trait marker(s). The point near the top of the scatter-plot that is circled shows a variety SB-23.7371.0037 that was discarded in early population development because trait markers were not heterozygous or homozygous for one or more traits of interest. The table in FIG.5A shows trait values for protein, oil, yield, and maturity for variety SB-23.7371.0037.
[0186] FIG.5B depicts target product specifications, blended seed mixture proportions, and resultant blended grain traits, according to the Example 1.
[0187] The left side of FIG.5B shows a target product specification for Yucatan plant grain, showing target values for white flake, protein, oil, and yield.23979-20007.40
[0188] The right side of FIG.5B shows two different blend ratios for blending SB- 23.7371.0037 with another variety SB-23.7318.0038. At the top half of the right side, a blend of 85% for SB-23.7318.0038 and 15% for SB-23.7371.0037 is shown, along with computed aggregate traits for the resultant blended grain from the blended seed mixture at that ratio. At the bottom half of the right side, a blend of 60% for SB-23.7318.0038 and 40% for SB- 23.7371.0037 is shown, along with computed aggregate traits for the resultant blended grain from the blended seed mixture at that ratio. These computed aggregate traits may be computed using weighted averages for the blend ingredients, weighted according to the percent of the blended mixture attributable to each seed type, as described herein.
[0189] FIG.5C depicts a comparison of traits for grain from a blend using only active Yucatan plants versus the computed blended resultant grain for the 85%-15% blend, which uses a discarded variety, as described above for Example 1. As shown in FIG.5C, the specifications for the blend made using an 85%-15% ratio using a discarded variety has superior traits to the blend made using only active lines, demonstrating utility of the methods disclosed herein for effectively utilizing soybean varieties that would not otherwise be bred, further developed, or otherwise used. Example 5: Yucatan plant, variety SB-23.3375.0010
[0190] FIG.6A depicts protein and yield values for varieties of Yucatan plants, according to Example 2. The scatter-plot in FIG.6A shows yield values and protein values for a large number of varieties of Yucatan plant. Yellow points show those varieties that meet GS prediction specifications, teal points show those varieties that fail GS specification predictions, and navy points show those varieties that are null for trait marker(s). The point near the top of the scatter-plot that is circled shows a variety SB-23.3375.0010 that was discarded in early population development because trait markers were not heterozygous or homozygous for one or more traits of interest. The table in FIG.6A shows trait values for protein, oil, yield, and maturity for variety SB-23.7371.0037.
[0191] FIG.6B depicts target product specifications, blended seed mixture proportions, and resultant blended grain traits, according to the Example 2.
[0192] The left side of FIG.6B shows a target product specification for Yucatan plant grain, showing target values for white flake, protein, oil, and yield.23979-20007.40
[0193] The right side of FIG.6B shows two different blends for blending SB-23.3375.0010 with two different other varieties, SB-23.7818.0038 and SB-23.7294.0026. Both blends have the same ratio, using 20% SB-23.3375.0010 and 80% of the other respective variety. At the top half of the right side, the blend with SB-23.7818.0038 is shown, along with computed aggregate traits for the resultant blended grain from the blended seed mixture at that ratio. At the bottom half of the right side, the blend with SB-23.7294.0026 is shown, along with computed aggregate traits for the resultant blended grain from the blended seed mixture at that ratio. These computed aggregate traits may be computed using weighted averages for the blend ingredients, weighted according to the percent of the blended mixture attributable to each seed type, as described herein.
[0194] FIG.6C depicts a comparison of traits for grain from a blend using only active Yucatan plants versus the computed blended resultant grain for the blend with SB-23.7818.0038, which uses a discarded variety, as described above for Example 1. As shown in FIG.6C, the specifications for the blend made using the blend with a discarded variety has superior traits to the blend made using only active lines, demonstrating utility of the methods disclosed herein for effectively utilizing soybean varieties that would not otherwise be bred, further developed, or otherwise used. Example 6: Exemplary selection process
[0195] An example of selecting varieties of seeds to blend to achieve a target specification for resultant grain, and for determining a proportion in which said selected seeds should be blended, is provided.
[0196] First, a “processed soybean composition” is set as a target specification, wherein the composition defines certain threshold levels of desired traits. In this case, target traits for yield, protein, oil are set.
[0197] Then, a database of varieties is accessed and assessed according to methods described herein. The system automatically determines whether varieties represented in the database can meet the target specification either alone or in a blend.
[0198] Case 3 represents a breeding program for which none of the varieties outright achieve the specification and for which no combination of the varieties provides a between-point value that will achieve the specification. Thus, it will be necessary to incorporate new high-protein23979-20007.40 germplasm (and its associated drag for yield / protein) into a breeding program before starting breeding to attempt to meet the target specification.
[0199] Case 2 represents a situation in which all thresholds of the specification are satisfied by one variety (A1). No additional breeding / genetics are needed, and thus blending is unnecessary. However, because A1 barely satisfies Oil and protein, it cannot be used to compensate for A2 or A3’s lack in those traits. There is no way to breed with the other two and still achieve the threshold. If A1 has some other trait that makes it undesirable, breeding / genetics will need to be used to create a new variety. It may be possible to achieve the target specification by breeding A2xA3, eventually.
[0200] Case 1 represents another breeding program that has one variety that meets the target specification. However, again, if for any reason there is a need to use a variety aside from Var 4, it would be necessary without the inventions disclosed herein to initiate cycles of breeding. The inventions disclosed herein, however, teach that it is possible to achieve the target specification without breeding / genetics by blending two or more of the varieties according to the techniques disclosed herein. 1. Var4 may be able to be blended or bred with Var 1 to reach the target specification. 2. Var 1 may be able to be blended with Var 2 to achieve the target specification 3. Var1 may be able to be blended with Var5 to achieve the target specification.
[0201] Once the system has identified some potential combinations for blending, the system may determine whether there are the blending ratios of the varieties that will achieve the target specification. The system may further assess whether the blending ratios of the varieties are economically viable for downstream steps in the pipeline.
[0202] For Case 1, the system may compute a “between-point” values be for each trait for various blend ratios from 25%-75%? The following formula may be used:
[0203] (% Var 1 in the ratio) x (Yield delta Var 1) + (% Var 2 in the ratio) x (Yield delta Var 2) = between point
[0204] As shown, a 75:25 blend of Var1 and Var2 yields a value of 2.5 for protein.
[0205] Next, the system may weight the blends based on their economic value, to determine whether some ratios of the various possible blends may be more valuable.23979-20007.40
[0206] This economic analysis may be based primarily on assigning weights to the traits based on their importance to downstream stakeholders. In this example, protein is slightly more important than yield while both of those traits are considerably more valuable than oil.
[0207] Finally, the sum of the values calculated above are added together for each of the traits for each blend ratio.
[0208] This process reveals that the specification can be achieved using several different blend ratios between several different varieties. The most valuable blends and ratios appears to be a 1:3 ratio of Var2:Var4, followed by a 1:3 ratio of Var1:Var 4. On the other hand, it appears no blend of Var3 with Var5 will be valuable. Example 7
[0209] Table 3 below shows a target specification for yield, protein, and oil. Table 3.
[0210] The table shows three varieties and their traits for yield, protein, and oil. As shown, each variety meets the target specification for a respective one of the three traits but not for the other two. The techniques disclosed herein may be used to computationally assess whether a lend can be created to achieve the target specification by blending the three varieties together.
Claims
23979-20007.40 CLAIMS What is claimed is:
1. A method of producing grain from a blend of soybean varieties, wherein the grain has at least a first trait and a second trait, wherein each trait of the grain has a target value, the method comprising: a) planting seeds from at least two soybean varieties together, and wherein the soybean varieties comprise: a first soybean variety having (i) the first trait with a value that is higher than the target value of the first trait for the grain, and (ii) a second trait with a value that is lower than the target value of the second trait for the grain, and a second soybean variety having (i) the first trait with a value that is lower than the target value of the first trait for the grain, and (ii) the second trait with a value that is higher than the target value of the second trait for the grain; b) germinating the seeds and growing plants from the germinated seeds to maturity; and c) harvesting grain from the plants without separating the soybean varieties.
2. The method of claim 1, further comprising: processing the harvested grain to obtain a downstream product, wherein the first trait and the second trait in the downstream product are not achievable from grain obtained from each soybean variety alone.
3. The method of claim 1 or 2, wherein each trait is a processor preferred characteristic of a processed soybean composition obtained from the blend of soybean varieties.
4. The method of claim 3, wherein the processor preferred characteristic is oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color, saponin, energy, flavor, texture, and functionality.
5. The method of claim 3 or 4, wherein the blend achieves the target value for each processor preferred characteristic and a target yield of the harvested grain.23979-20007.40 6. The method of claim 1 or 2, wherein the first trait and the second trait are counter- selective.
7. The method of claim 1 or 2, wherein the first trait and the second trait are selected from the group consisting of protein content, oil content, carbohydrate content, oligosaccharide content, saponins content, and flavor.
8. The method of any one of claims 1 to 7, wherein the blend achieves a target yield of the harvested grain.
9. The method of any one of claims 1 to 7, wherein the target value is an average amount of the trait in a blend of harvested grain.
10. The method of any one of claims 1 to 7, wherein the target value is a distribution range of the amount of the trait in a blend of harvested grain.
11. The method of any one of claims 1 to 10, wherein the soybean varieties are not a mix of determinant and indeterminant varieties.
12. The method of any one of claims 1 to 10, wherein the soybean varieties are not a mix of dwarf and non-dwarf type varieties.
13. The method of any one of claims 1 to 12, wherein the soybean varieties when planted as a blend yield grain with traits that are not achieved from planting any one of the individual soybean varieties alone.
14. The method of any one of claims 1 to 13, wherein the soybean varieties are blended in a predetermined proportion to maximize the match of the grain to specifications of the downstream product.
15. The method of any one of claims 1 to 14, wherein growing the soybean varieties to maturity comprises growing the soybean varieties together over a coextensive area.
16. The method of any one of claims 1 to 15, wherein growing the soybean varieties to maturity comprises mixing together seeds of the soybean varieties prior to planting them.
17. The method of any one of claims 1 to 16, wherein the grain obtained after one growing cycle has at least the first trait and second trait at their respective target values.
18. A composition comprising a blend of at least two varieties of soybeans, wherein the varieties have relative maturities no greater than 0.4 and / or relative maturities within 0.2-0.3 of each other; and23979-20007.40 wherein the varieties are blended at a ratio to yield grain that is processed to produce a downstream product having at least one processor preferred characteristic that is improved. optionally, wherein the varieties are blended at a ratio to (a) yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and (c) a mean yield of at least about 55 or more bushels per acre; and optionally, wherein the varieties have statistically similar amino acid profiles.
19. The composition of claim 18, wherein the processor preferred characteristic is oil holding capacity (OHC), water holding capacity (WHC), least gelation concentration (LGC), emulsion capacity, foaming capacity, foaming stability, gel texture, bench texture, moisture, protein dispersibility, nitrogen / protein solubility, viscosity, protein, carbohydrate, oligosaccharide, sucrose, crude fat / oil, crude fiber, ash, color, saponin, energy, flavor, texture, and functionality.
20. The composition of claim 18 or 19, wherein the downstream product is a food or feed ingredient or product, a protein isolate, other protein product, soybean seed hulls, meal, flake, flour, fiber, sugar, or oil product, or a food, feed, aqua, or industrial product, or any combination thereof.
21. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5% and a mean yield of at least about 55 or more bushels per acre.
22. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 25% and a mean yield of at least about 55 or more bushels per acre.
23. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio to yield grain that is processed to produce white flakes having a protein content of at least about 59.5%, (b) yield grain having an oil content of at least about 18%, and (c) a mean yield of at least about 55 or more bushels per acre.23979-20007.40 24. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that is more stable in terms of predictability from lot-to- lot for legume production as compared to when a blend is not used.
25. A composition comprising a blend of at least two varieties of soybeans wherein the at least two varieties are blended at a ratio that improves amino acid profiles, volatiles, isoflavones and / or other flavor and / or food properties of a post-processing product.
