Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/29/2025 has been entered.
Status of Claims
This communication is a Non-Final Office Action in response to Applicant’s RCE for application number 18/587,219 received on 05/12/2026.
In accordance with Applicant’s amendment, claims 1-11, and 17-21 are amended, currently pending and have been examined.
Priority
Applicants claim for the benefit of a prior-filed application under 35 U.S.C. 119 and/or 35 U.S.C. 120 is acknowledged.
Response to Amendment
Applicant’s amendment necessitated the new ground(s) of rejection set forth in this Office Action.
Response to Arguments
Response to §101 arguments – Applicant’s arguments with respect to the §101 rejections previously applied to the claims have been considered and are unpersuasive.
Applicant argues (Remarks at pgs. 8-9): “With regard to Claim 1, the human mind is not equipped to access a trained machine learning model, nor is it equipped to access (specifically) BLUPs generated via execution of at least one mixed model, nor is it equipped to identify pairs of inbred lines based (specifically) on the trained machine learning model (i.e., based on the segment of the breeding pipeline to which the trained machine learning model is limited), nor is it equipped to execute the trained machine learning model to calculate a probability of advancement for individual ones of the potential hybrids, and nor is it equipped to actually (physically) advance one or more of the potential hybrids into a breeding pipeline (e.g., including crossing pairs of the inbred lines to actually produced the potential hybrids, etc.). These operations require, from a practical standpoint, either computer implementation/execution to perform or physical resources and physical activity (e.g., for actually crossing the pairs of inbred lines to produce the hybrids, etc.) - they cannot be mental processes.”. In response, Examiner respectfully disagrees and notes that as documented in the §101 rejections of the instant office action, the limitations for “accessing, by a computing device, a trained machine learning model”, “accessing, by the computing device, data specific to multiple inbred lines”, “via execution of at least one mixed model”, and “wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids” from claim 1, and “access a trained machine learning model specific to a segment of a breeding pipeline”, “access data specific to multiple inbred lines”, “via execution of at least one mixed model”, and “whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids” from claim 17 are identified as additional elements. Therefore, said steps are not considered by the Examiner to be abstract. Examiner therefore concludes: With respect to the limitations for “accessing, by a computing device, a trained machine learning model”, “via execution of at least one mixed model”, “by the computing device executing the trained machine learning model” from claim 1, and “access a trained machine learning model specific to a segment of a breeding pipeline“, “via execution of at least one mixed model”, and “calculate, with the trained machine learning model” from claim 17, these limitations fail to integrate the abstract idea into a practical application, add significantly more, or otherwise represent an improvement to technology because the provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception. Additionally, with respect to the limitations for accessing, by the computing device, data specific to multiple inbred lines from claim 1, and access data specific to multiple inbred lines from claim 17, these limitations fail to integrate the abstract idea into a practical application, add significantly more, or otherwise represent an improvement to technology because at most, they amount to insignificant extra-solution activity (e.g., mere data gathering), which does not integrate the abstract idea into a practical application. See MPEP 2106.05(g). Lastly, with respect to the limitations for wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids from claim 1, and whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids from claim 17, these limitations fail to integrate the abstract idea into a practical application, add significantly more, or otherwise represent an improvement to technology because at most, they amount to insignificant extra-solution activity (e.g., insignificant application), which does not integrate the abstract idea into a practical application. See MPEP 2106.05(g).
Applicant argues (Remarks at pgs. 9-10): “The Office also argues that limitations recited by Claim 1 fall under the "Mathematical Concepts" abstract idea grouping. See, Office action dated Feb. 4, 2026, at para. [0016]. However, a claim does "not recite a mathematical concept [], if it is only based on or involves a mathematical concept." See, MPFP G 2106.04(a)(2). This is certainly the case here. Claim 1, for example, does not provide a naked recitation of a specific mathematical algorithm, but rather leverages specific data (through execution of specific models) to generate a probability of advancement for potential hybrids within a breeding pipeline. In particular, the calculation is based on BLUPs generated for one or more specific traits of the multiple inbred lines used to produce the potential hybrids, where the one or more specific traits are desired for propagation into the breeding pipeline (via the potential hybrids). As such, there is a clear difference between the examples of mathematical relationships indicated in the PEG, and Claim 1. To be sure, Claim 1 is directed to generating a specific probability of advancement for potential hybrids within the breeding pipeline, based on specific representations of data (e.g., the BLUPs representative of the specific traits to be advanced in the pipeline, etc.), which is only based on or reliant on the alleged mathematical concept. Claim 1 is NOT directed to a mathematical concept or, more generally, any abstract idea. Notwithstanding the above, it is also clear that Claim 1 integrates the alleged idea into a practical application. That is, Claim 1 does not simply apply a mental process or mathematical formula to a computer. Rather, Claim 1 recites a specific improvement to the field of agriculture and breeding, in detail, for advancing hybrids and propagating desired traits in a breeding pipeline, i.e., this is clearly a technological field. See, MPEP G 2106.04(d).”. In response, Examiner respectfully disagrees and notes: First, as stated in MPEP 2106.04(a)(2), it is important to note that a mathematical concept need not be expressed in mathematical symbols, because "[w]ords used in a claim operating on data to solve a problem can serve the same purpose as a formula." In re Grams, 888 F.2d 835, 837 and n.1, 12 USPQ2d 1824, 1826 and n.1 (Fed. Cir. 1989). See, e.g., SAP America, Inc. v. InvestPic, LLC, 898 F.3d 1161, 1163, 127 USPQ2d 1597, 1599 (Fed. Cir. 2018) (holding that claims to a ‘‘series of mathematical calculations based on selected information’’ are directed to abstract ideas); Digitech Image Techs., LLC v. Elecs. for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014) (holding that claims to a ‘‘process of organizing information through mathematical correlations’’ are directed to an abstract idea); and Bancorp Servs., LLC v. Sun Life Assurance Co. of Can. (U.S.), 687 F.3d 1266, 1280, 103 USPQ2d 1425, 1434 (Fed. Cir. 2012) (identifying the concept of ‘‘managing a stable value protected life insurance policy by performing calculations and manipulating the results’’ as an abstract idea); Second, contrary to Applicant’s argument, the claims recite a calculation of a probability, not “”generating a specific probability”. Furthermore, the calculation is based on BLUPs, which is data directed to linear unbiased predictions. Therefore, as currently recited, the claims recite limitations that fall under the Mathematical Concepts abstract idea grouping for mathematical relationships, mathematical formulas or equations, mathematical calculations. If Applicant doesn’t intend to claim a calculation of a probability based on specific data (e.g., BLUPs), Applicant may modify the claim language accordingly.
Applicant argues (Remarks at pgs. 10-11): “In particular, Claim 1 recites an improvement to technology through the automated, objective, and repeatable advancement decisions for agricultural products in a breeding pipeline. In connection with such improvement, Claim 1 provides a multi-model approach to represent and identify the desired traits to be advanced (through the potential hybrids). Specifically, Clain 1 recites execution of a first mixed model to produce the BLUPs for the specific traits (to be included in the pipeline). Claim 1 then recite execution of a second machine learning model (based on the BLUPs as input) to calculate the probability of advancement of the hybrids to (or through) particular stages of the breeding pipeline (where the hybrids are formed from inbred lines having the specific traits). See, e.g., para. [0032] of the filed application. In this way, the models work together to provide a determination (in the form of the probability of advancement) as to whether or not the specific traits from the inbred lines will actually be propagated through the breeding pipeline via the hybrids. Moreover, the second machine learning model is specific to the segment of the breeding pipeline for which the hybrids (and corresponding traits) are to be advanced. In this way, the multi-model approach provides for a tailored decision to advance, or not, agricultural products in the breeding pipeline, where the decision is specific to the particular segment of the breeding pipeline for which advancement is being effected (by way of the specific second machine learning model). Further, by leveraging the multiple models in this manner, to objectively account for the specific traits (in the tailored manner), Claim 1 also departs substantially from what is conventional in the art, for example, where human breeders made the advancement decisions on limited or generic data. See, para. [0018] of Applicant's filed application. In addition, in providing the tailored decision to advance, or not, the hybrids into the breeding pipeline, Claim 1 also effectively transforms the breeding pipeline to include the particular traits from the inbred lines (as initially represented by the BLUPs). What's more, the execution of the first mixed model to produce the BLIPs and then the execution of the second machine learning model to calculate the probability of advancement of the hybrids (and corresponding traits) into the breeding pipeline is uniquely tied to this transformation, through the incorporation of the particular traits in the analysis (via the BLUPs). The transformation (and corresponding improvement) is therefore particularly tied to the unique application of the multiple models.”. In response, Examiner respectfully disagrees and notes that as documented in the §101 rejections of the instant office action, with respect to the machine learning model and the mixed model, these limitations fail to integrate the abstract idea into a practical application, add significantly more to the abstract idea, or otherwise represent an improvement to technology because the provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception.
Accordingly, the §101 rejections are maintained and updated to address the amendments.
Response to §103 arguments – Applicant’s arguments with respect to the §103 rejections previously applied to the claims are primarily raised in support of the amendments. The amendments and supporting arguments are believed to be fully addressed in the updated §103 rejections below.
Accordingly, the §103 rejections are maintained and updated to address the amendments.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-11, and 17-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-patentable subject matter. The claims are directed to an abstract idea without significantly more. The judicial exception is not integrated into a practical application. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The eligibility analysis in support of those findings is provided below, in accordance with the “2019 Revised Patent Subject Matter Eligibility Guidance” (published on 01/07/2019 in Fed. Register, Vol. 84, No. 4 at pgs. 50-57, hereinafter referred to as the “2019 PEG”) and further clarified in the “October 2019 Update: Subject Matter Eligibility” published on 10/17/2019) and as further set forth in MPEP 2106.
Step 1: The claimed invention is analyzed to determine if it falls outside one of the four statutory categories of invention. See MPEP 2106.03
Claims 1-11 are directed to a Method (i.e., Process), and claims 17-20 are directed to a System (i.e., Machine). Therefore, claims 1-11, and 17-20 are directed to patent eligible categories of invention. Accordingly, the claims satisfy Step 1 of the eligibility inquiry.
Step 2A, Prong 1: In prong one of step 2A, the claim(s) is/are analyzed to evaluate whether they recite a judicial exception. See MPEP 2106.04
Independent claim 1 recites a method for defining advancement of agricultural products in breeding. As drafted, the limitations recited by claim 1 fall under the “Mental Processes” abstract idea grouping by setting forth activities that could be performed mentally by a human (including an observation, evaluation, judgment, opinion). Additionally, some of the limitations recited by claim 1 also fall under the “Mathematical Concepts” abstract idea grouping for mathematical relationships, mathematical formulas or equations, mathematical calculations. The limitations recited by claim 1 are: “accessing, by a computing device, a trained machine learning model specific to a segment of a breeding pipeline, the segment defined by a relative maturity (RM) and a region, the machine learning model trained using historic hybrid field performance data and parental line genomic data; accessing, by the computing device, data specific to multiple inbred lines, the data including best linear unbiased predictions (BLUPs) generated for one or more specific traits of the multiple inbred lines via execution of at least one mixed model; identifying, by the computing device, pairs of the multiple inbred lines as combinations for producing potential hybrids, based on the RM and/or the region specific to the trained machine learning model; calculating, by the computing device executing the trained machine learning model based at least on the BLUPs generated for the one or more specific traits of the multiple inbred lines, a probability of advancement for individual ones of the potential hybrids produced from the multiple inbred lines including the specific traits in the breeding pipeline; and advancing one or more of the ones of the potential hybrids into the breeding pipeline, based on the calculated probability of advancement for the individual ones of the potential hybrids, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids; wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids.”. But for the additional elements recited in the claim limitations – underlined – to be analyzed under steps 2A, prong 2, and 2B, the steps in the claim limitations could be accomplished mentally, such as by human observation, evaluation, judgement, opinion, or with the help of pen and paper. Additionally, the step for “calculating a probability of advancement” recites an abstract idea directed to “Mathematical Concepts”.
Independent claim 17 recites a system with the following limitations: “access a trained machine learning model specific to a segment of a breeding pipeline, the segment defined by a relative maturity (RM) and a region, the machine learning model trained using historic hybrid field performance data and parental line genomic data; access data specific to multiple inbred lines, the data including best linear unbiased predictions (BLUPs) generated for one or more specific traits of the multiple inbred lines via execution of at least one mixed model; identify pairs of the multiple inbred lines as combinations for producing potential hybrids, based on the RM and/or the region specific to the trained machine learning model; calculate, with the trained machine learning model, based at least on the BLUPs generated for the one or more specific traits of the multiple inbred lines, a probability of advancement for individual ones of the potential hybrids produced from the multiple inbred lines including the specific traits in the breeding pipeline; and advance one or more of the ones of the potential hybrids into the breeding pipeline, based on the calculated probability of advancement for the individual ones of the potential hybrids, whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids.”. But for the additional elements recited in the claim limitations – underlined – to be analyzed under steps 2A, prong 2, and 2B, the steps in the claim limitations could be accomplished mentally, such as by human observation, evaluation, judgement, opinion, or with the help of pen and paper. Additionally, the step for “calculating a probability of advancement” recites an abstract idea directed to “Mathematical Concepts”.
Dependent claim 19 further narrow the abstract idea and introduces the following additional elements for consideration under said steps below: planter.
Dependent claims 2-11, and 18, and 20-21 further narrow the abstract idea and do not introduce further additional elements for consideration under said steps
Step 2A, Prong 2: An evaluation is made whether a claim recites any additional element, or combination of additional elements, that integrate the judicial exception into a practical application of the exception. See MPEP 2106.04(d).
Regarding the computing additional elements, namely computing device, this additional element has been evaluated but fail to integrate the abstract idea into a practical application because they amount to using generic computing elements (based on Examiner’s interpretation set forth in Claim Interpretation section above) or instructions (software) to perform the abstract idea, similar to adding the words “apply it” (or equivalent), which merely serves to link the use of the judicial exception to a particular technological environment (generic computing environment). See MPEP 2106.05(f) and 2106.05(h).
With respect to the limitations for “accessing, by a computing device, a trained machine learning model”, “via execution of at least one mixed model”, “by the computing device executing the trained machine learning model” from claim 1, and “access a trained machine learning model specific to a segment of a breeding pipeline“, “via execution of at least one mixed model”, and “calculate, with the trained machine learning model” from claim 17, these limitations fail to integrate the abstract idea into a practical application because the provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception.
With respect to the limitations for accessing, by the computing device, data specific to multiple inbred lines from claim 1, and access data specific to multiple inbred lines from claim 17, these limitations fail to integrate the abstract idea into a practical application because at most, they amount to insignificant extra-solution activity (e.g., mere data gathering), which does not integrate the abstract idea into a practical application. See MPEP 2106.05(g).
With respect to the limitations for wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids from claim 1, and whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids from claim 17, these limitations fail to integrate the abstract idea into a practical application because at most, they amount to insignificant extra-solution activity (e.g., insignificant application), which does not integrate the abstract idea into a practical application. See MPEP 2106.05(g).
With respect to the planter introduced in claim 19, the planter has been considered under Step 2A Prong Two, however the planter is recited at a high level of generality and fails to provide a technical improvement or otherwise integrate the abstract idea into a practical application.
Dependent claims 2-11, and 18, and 20-21 recite the same abstract ideas (“mental processes” and “mathematical concepts”) as the independent claims along with further steps/details falling under the scope of the abstract idea itself, along with the same or substantially same additional elements addressed.
Accordingly, because the Step 2A Prong One and Prong Two analysis resulted in the conclusion that the claims are directed to an abstract idea, additional analysis under Step 2B of the eligibility inquiry must be conducted in order to determine whether any claim element or combination of elements amount to significantly more than the judicial exception.
Step 2B: The claims are analyzed to determine whether any additional element, or combination of additional elements, is/are sufficient to ensure that the claims amount to significantly more than the judicial exception. This analysis is also termed a search for "inventive concept." See MPEP 2106.05.
Regarding the computing additional elements, namely computing device, this/these additional element(s) has/have been evaluated, but fail to add significantly more to the claims because they amount to using generic computing elements (computer hardware) or instructions/software (engine) to perform the abstract idea, similar to adding the words “apply it” (or an equivalent), which merely serves to link the use of the judicial exception to a particular technological environment (network computing environment, the internet, online) and does not amount to significantly more than the abstract idea itself. Furthermore, Applicant’s specification recites the computing device at a high level of generality, which does not add significantly more to the abstract idea. Therefore, the computing additional elements merely describe generic computing elements or computer-executable instructions (software) merely serve to tie the abstract idea to a particular operating environment, which does not add significantly more to the abstract idea. See, e.g., Alice Corp., 134 S. Ct. 2347, 110 USPQ2d 1976; Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
With respect to the limitations for
“accessing, by a computing device, a trained machine learning model”, “via execution of at least one mixed model”, “by the computing device executing the trained machine learning model” from claim 1, and “access a trained machine learning model specific to a segment of a breeding pipeline“, “via execution of at least one mixed model”, and “calculate, with the trained machine learning model” from claim 17, these limitations fail to add significantly more to the abstract idea because the provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception. Therefore, the additional elements merely describe generic computing elements or computer-executable instructions (software) merely serve to tie the abstract idea to a particular operating environment, which does not add significantly more to the abstract idea. See, e.g., Alice Corp., 134 S. Ct. 2347, 110 USPQ2d 1976; Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
With respect to the limitations for accessing, by the computing device, data specific to multiple inbred lines from claim 1, and access data specific to multiple inbred lines from claim 17, these limitations fail to integrate the abstract idea into a practical application because at most, they amount to insignificant extra-solution activity (e.g., mere data gathering), which does not add significantly more to the judicial exception. See MPEP 2106.05(g). Furthermore, the accessing data insignificant extra-solution activity has been recognized as well-understood, routine, and conventional, and thus insufficient to add significantly more to the abstract idea. See MPEP 2106.05(d) - Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network).
With respect to the limitations for wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids from claim 1, and whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids from claim 17, these limitations fail to add significantly more because at most, they amount to insignificant extra-solution activity (e.g., insignificant application), which does not add significantly more to the judicial exception. See MPEP 2106.05(g): Cutting hair after first determining the hair style, In re Brown, 645 Fed. App'x 1014, 1016-1017 (Fed. Cir. 2016) (non-precedential).
With respect to the planter introduced in claim 19, the planter has been considered under Step 2A Prong Two, however the planter is recited at a high level of generality and fails to provide a technical improvement or otherwise add significantly more to the abstract idea.
Dependent claims 2-11, and 18, and 20-21 recite the same abstract ideas (“mental processes” and “mathematical concepts”) as the independent claims along with further steps/details falling under the scope of the abstract idea itself, along with the same or substantially same additional elements addressed.
In addition, when taken as an ordered combination, the ordered combination adds nothing that is not already present as when the elements are taken individually. There is no indication that the combination of elements integrates the abstract idea into a practical application. Their collective functions merely provide generic computer implementation. Therefore, when viewed as a whole, these additional claim elements do not provide meaningful limitations to transform the abstract idea into a practical application of the abstract idea or that, as an ordered combination, amount to significantly more than the abstract idea itself.
Claim Rejections - 35 USC § 103
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-11, and 17-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chavali et al. (WO 2019113468 A1, hereinafter “Chavali”), in view of Bhagat et al. (US 20220383428 A1, hereinafter “Bhagat”).
Regarding claims 1: Chavali teaches a method for defining advancement of agricultural products in breeding ([0002] The present disclosure generally relates to methods and systems for use in plant breeding, and in particular to methods and systems for identifying a set of progenies, from a pool of potential progenies, based on prediction frameworks and/or optimization frameworks, and populating a breeding pipeline with the identified set of progenies.) with limitations for:
accessing, by a computing device, a trained machine learning model specific to a segment of a breeding pipeline, the segment defined by a relative maturity (RM) and a region, ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).; [0033] once the prediction model is generated, the selection engine 110 further is configured to determine a prediction score, based on the prediction model, for each of the progenies in the pool of progenies introduced in the progeny start phase 104 and included in the cultivation and testing phase 106.; [0035] Then in the operation of the breeding pipeline 102 (in accordance with the present disclosure), based on the determined prediction scores, the selection engine 110 is configured to select ones of the progenies (from the pool) to be included in a group of progenies.; [0084] the selection engine 110 may evaluate performance of the method(s) and select, if necessary, the one that provides the best prediction for a given crop and/or a given region; Examiner’s Note: See the 35 USC 103 combination below for teachings pertaining to the relative maturity.);
the machine learning model trained using historic hybrid field performance data and parental line genomic data; ([0016] Progeny are generally organisms which descend from one or more parent organisms of the same species. Progeny may refer to, for example, a universe of all possible progenies from a particular breeding program, a subset of all possible progenies, or offspring from a plant which exhibits one or more different phenotypes, etc. Progenies may further include all offspring from a line and/or a cross in a given generation, certain offspring from a cross, or individual plants, etc.; [0017] As used herein, the term “origin” refers to the parent(s) of progeny, and is therefore interpreted as either singular or plural, as applicable. The phenotypic data, trait distribution, ancestry, genetic sequence, commercial success, and additional information of the origin are generally known and may be stored in memory described herein. Hereditary genetics indicate the traits of the parent(s) to be passed to the progeny. And, mutations, genetic recombination, and/or directed genetic modification may alter the genotype and resulting phenotype of the progeny vis-a-vis the origin.; [0019] genotypic data may be used, in connection or in combination with the phenotypic data described herein (or otherwise) (e.g., to further supplement the phenotypic data and/or to further inform the models, algorithms, and/or predictions herein, etc.), in one or more exemplary implementations, to aid in the selection of groups of progenies and/or identification of sets of progenies consistent with the description herein.; [0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).);
accessing, by the computing device, data specific to multiple inbred lines, the data including best linear unbiased predictions (BLUPs) generated for one or more specific traits of the multiple inbred lines via execution of at least one mixed model; ([0034] That said, it should be appreciated that the selection engine 110 may be configured to determine the prediction score based on ranking phenotypic data and/or on derived phenotypic data (e.g., best linear unbiased prediction (BLUP), etc.) associated with the progenies included in the data structure 112.; [0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).);
identifying, by the computing device, pairs of the multiple inbred lines as combinations for producing potential hybrids, based on the RM and/or the region specific to the trained machine learning model; ([0021] As shown in FIG. 1, the system 100 generally includes a breeding pipeline 102, which is provided to select a set of progenies from a pool of progenies to be advanced toward commercial product development. The breeding pipeline 102 generally defines a pyramidal progression, whereby it starts with a large number of potential progenies and successively narrows (e.g., reduces) the number of potential progenies to preferred and/or desired progenies. While the breeding pipeline 102 is configured to employ the selections provided herein, the breeding pipeline 102 may be configured to employ one or more other techniques which may include a wide range of methods known in the art, often depending on the particular plant and/or organism for which the breeding pipeline 102 is provided.; [0084] the selection engine 110 may evaluate performance of the method(s) and select, if necessary, the one that provides the best prediction for a given crop and/or a given region, for example.);
calculating, by the computing device executing the trained machine learning model based at least on the BLUPs generated for the one or more specific traits of the multiple inbred lines, a probability of advancement for individual ones of the potential hybrids produced from the multiple inbred lines including the specific traits in the breeding pipeline; ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).; [0034] That said, it should be appreciated that the selection engine 110 may be configured to determine the prediction score based on ranking phenotypic data and/or on derived phenotypic data (e.g., best linear unbiased prediction (BLUP), etc.) associated with the progenies included in the data structure 112.);
and advancing one or more of the ones of the potential hybrids into the breeding pipeline, based on the calculated probability of advancement for the individual ones of the potential hybrids, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids; ([0030] As mentioned above, the phenotypic data included in Table 1 is historical data (e.g., compiled through current and/or prior breeding cycles and/or experimentation in current and/or past years, cycles, etc.). As a result, in addition to the specific phenotypic data, Table 1 of the data structure 112 further includes an advancement decision for the plant associated with the data. As shown in Table 1, plants Pi, P.sub.4, and Ps were advanced (based on the True indication) in a breeding pipeline in a previous season, year, or other cycle, while plants P.sub.2 and P.sub.3 were not. In other words, the historical data in Table 1 also includes the historical selection of the progenies, where TRUE indicates the progeny was advanced in the breeding process and where FALSE indicates the progeny was not advanced in the breeding process.; [0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).);
wherein advancing the one or more of the ones of the potential hybrids includes crossing the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids produce the potential hybrids. ([0025] In the progeny start phase 104, a pool of potential progenies is provided from one or more sets of origins. The origins may be selected by a breeder, for example, or otherwise, depending on the particular type of plant, etc. The origins may also be selected, for example, based on origin selection systems and/or based (at least in part) on the methods and systems disclosed in U.S. Pat. App. 15/618,023, titled “Methods for Identifying Crosses for use in Plant Breeding,” the entire disclosure of which is incorporated herein by reference. Once the origins are selected, the pool of progenies is created from multiple crosses of the origins. The pool of progenies is then directed to the cultivation and testing phase 106, in which the progenies are planted or otherwise introduced into one or more growing spaces, such as, for example, greenhouses, shade houses, nurseries, breeding plots, fields (or test fields), etc. As needed, in some applications of the breeding pipeline 102, the pool of progenies may be combined with one or more tester plants, to yield a plant product suitable for introduction into the cultivation and testing phase 106.).
Chavali doesn’t explicitly teach:
the segment defined by a relative maturity (RM)
Bhagat teaches:
the segment defined by a relative maturity (RM) ([0013] FIG. 4 illustrates example locations of growing spaces in an example region, where the region is divided based on bands of relative maturity that may be used to filter data implemented in the system of FIG. 1; [0038] The data servers 114a-b, in turn, are configured to store the received data in one or more data structures. In general, in this example embodiment, the data servers 114a-b are configured to store data by year (e.g., Year_X, Year_X+1, etc.), which correspond to the different growing years (e.g., 2015, 2016, 2017, etc.). Then, for each year, the data structure will include the data for each of the growing spaces, seeds, harvested plant, etc. For example, for each field designation or identifier, the data structure may include an identifier for each seed planted in the field in the given year, for brands for seeds, for relative maturity, for types of insect protection traits, for seed treatment years, for side-by-side or S×S designations, for positions/distributions of seeds in fields, for location definitions of fields, for acreage of fields, for populations of seeds planted in fields, for average yields and harvest grain moisture (e.g., based on location and seed products, etc.), etc. The data may also include soil conditions, field elevations, precipitation amounts, irrigation amounts, or any other data indicative of the growing conditions for the seeds/plants in the field, etc. It should be appreciated that any available and/or desired data may be collected with regard to the plots, fields, etc., in the different growing spaces and/or the seeds planted therein.).
It would have been obvious to one of ordinary skill in the art, at the time of applicant’s invention, to combine Chavali with Bhagat’s feature(s) listed above. One would’ve been motivated to do so, so that the agricultural computer system 116 may be configured to build, or define, the training data set by filtering the accessed data, for the given region (Bhagat; [0057]). By incorporating the teachings of Bhagat, one would’ve been able to train the model specific to the segment defined by relative maturity.
Regarding claim 2: Chavali further teaches:
wherein the trained machine learning model includes a random forest model ([0031] The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).).
Regarding claim 3: Chavali further teaches:
wherein the BLUPs include BLUPs based on an interval, the interval including a number of years; ([0034] the selection engine 110 may be configured to determine the prediction score based on ranking phenotypic data and/or on derived phenotypic data (e.g., best linear unbiased prediction (BLUP), etc.) associated with the progenies included in the data structure 112.; [0029] that data structure 112 may include data indicative of various different characteristics and/or traits of the plants for the current and/or the last one, two, five, ten, fifteen, or more or less years of the plants through the cultivation and testing phase 106, or other growing spaces included in or outside the breeding pipeline 102, and also present data from the cultivation and testing phase 106.);
and/or wherein the one or more specific traits of the multiple inbred lines includes yield. ([0018] “Phenotypic data” as used herein includes, but is not limited to, information regarding the phenotype of a given progeny (e.g., a plant, etc.), or a population of progeny (e.g., a group of plants, etc.). Phenotypic data may include the size and/or heartiness of the progeny (e.g., plant height, stalk girth, stalk strength, etc.), yield, time to maturity, resistance to biotic stress (e.g., disease or pest resistance, etc.), resistance to abiotic stress (e.g., drought or salinity resistance, etc.), growing climate, or any additional phenotypes, and/or combinations thereof.).
Regarding Claim 4: Chavali further teaches:
wherein identifying the pairs of the multiple inbred lines includes identifying all unique pairs of one male of the inbred lines and one female of the inbred lines. ([0075] Further in the above equations, the term c.sub.M is a characteristics vector for male progenies. The term c.sub.R is a characteristics vector for female progenies.).
Regarding Claim 5: Chavali doesn’t teach:
further comprising, prior to calculating the probability of advancement, eliminating other ones of the potential hybrids, based on inclusion of the other ones of the potential hybrids in a database of prior hybrids.
Bhagat teaches:
further comprising, prior to calculating the probability of advancement, eliminating other ones of the potential hybrids, based on inclusion of the other ones of the potential hybrids in a database of prior hybrids. ([0076] The agricultural computer system 116 may then be programmed, or configured, optionally, to reduce the set of candidates seeds (e.g., by filtering, selection, etc.), based on the parameters of the specific candidate seeds.; Par. [0096] teaches crop rotation. Examiner notes that one of ordinary skill in the art would reasonably interpret crop rotation as the process of alternating crops to be grown between harvests, ensuring different crops are planted. Said person of ordinary skill in the art would reasonably interpret crop rotation to being equivalent to eliminating hybrids based on prior hybrids.).
It would have been obvious to one of ordinary skill in the art, at the time of applicant’s invention, to combine modified Chavali with Bhagat’s additional feature(s) listed above. One would’ve been motivated to do so in order to filter out candidate seeds inconsistent with the plant type and with the traits of the target seed (Bhagat; [0076]). By incorporating the teachings of Bhagat, one would’ve been able to eliminate hybrids prior to calculating the probability of advancement.
Regarding Claim 6: Chavali further teaches:
wherein each identified pair includes a male one of the multiple inbred lines and a female one of the multiple inbred lines ([0075] Further in the above equations, the term c.sub.M is a characteristics vector for male progenies. The term c.sub.R is a characteristics vector for female progenies.).
Regarding Claim 7: Chavali further teaches:
further comprising, prior to accessing the trained machine learning model: accessing historical hybrid field performance data associated with multiple test inbred lines and the region, ([0018] “Phenotypic data” as used herein includes, but is not limited to, information regarding the phenotype of a given progeny (e.g., a plant, etc.), or a population of progeny (e.g., a group of plants, etc.). Phenotypic data may include the size and/or heartiness of the progeny (e.g., plant height, stalk girth, stalk strength, etc.), yield, time to maturity, resistance to biotic stress (e.g., disease or pest resistance, etc.), resistance to abiotic stress (e.g., drought or salinity resistance, etc.), growing climate, or any additional phenotypes, and/or combinations thereof.; [0036] The selection engine 110 is further configured to identify a set of progenies, from the group of progenies, to advance to a next iteration of the cultivation and testing phase 106 and/or to advance to the validation phase 108. To do so, the selection engine 110 is configured to employ one or more additional algorithms, as described herein or otherwise, for example, to account for a predicted performance of the particular progeny (e.g., based on the prediction score, etc. Examiner notes that one of ordinary skill in the art would reasonably consider yield as a measure of hybrid field performance.) the historical hybrid field performance data including BLUPs generated for one or more traits of the multiple test inbred lines via execution of at least one mixed model and fate data for multiple hybrids including pairs of the multiple test inbred lines relative to a stage of the breeding pipeline; ([0015] In particular, the pool of progenies is reduced, initially, for example, to a group of progenies based on a prediction score for each of the progenies, which is indicative of a success of the progeny based on past selections of progenies (e.g., based on phenotypic data, etc.) and/or available relevant data associated with the progenies.; [0034] the selection engine 110 may be configured to determine the prediction score based on ranking phenotypic data and/or on derived phenotypic data (e.g., best linear unbiased prediction (BLUP), etc.) associated with the progenies included in the data structure 112. In such embodiments, the data is ranked with a top X number of progenies selected for advancement herein, whereby the rank is employed as a prediction score (e.g., TRUE/FALSE, etc.) for each progeny above a threshold (as compared to any modeling of the data included in the data structure 112).
and training the machine learning model based on at least a portion of the historical hybrid field performance data. ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).; [0032] the prediction model (or SVM model) training involves solving a convex optimization problem, which finds the optimal hyperplane (linear or nonlinear), which would be able to separate the positive and negative samples, based on the phenotypic data; [0053] teaches historical data being used to train the given models.).
Regarding Claim 8: Chavali further teaches:
further comprising validating the machine learning model based on data reserved from the accessed historical hybrid field performance data. ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).;[0018] “Phenotypic data” as used herein includes, but is not limited to, information regarding the phenotype of a given progeny (e.g., a plant, etc.), or a population of progeny (e.g., a group of plants, etc.). Phenotypic data may include the size and/or heartiness of the progeny (e.g., plant height, stalk girth, stalk strength, etc.), yield, time to maturity, resistance to biotic stress (e.g., disease or pest resistance, etc.), resistance to abiotic stress (e.g., drought or salinity resistance, etc.), growing climate, or any additional phenotypes, and/or combinations thereof.; [0032] the prediction model (or SVM model) training involves solving a convex optimization problem, which finds the optimal hyperplane (linear or nonlinear), which would be able to separate the positive and negative samples, based on the phenotypic data; [0053] teaches historical data being used to train the given models.); [0054] Once this data set is provided with the input data and response variable, the user segregates the data set, either randomly or along a logical delineation (e.g., year, month, etc.), into a training set, a validation set, and a testing set. The data set may be segregated, for example, into a set ratio of 70:20:10, respectively (or otherwise). With these three distinct data sets, the modeling is initiated for the training set of data by the selection of an algorithm, as listed above. If, for example, a random forest is selected as a potential algorithm for creating this prediction score, the user, in general, selects a well-supported coding package that implements random forests in a suitable coding language, such as R or python. Once the package and the language have been selected, for example scikit-leam in python, the user commences the process of building the code framework to specify, build, train, validate, and test the model.; [0055] When the framework is built, it is connected to the training data set, the validation set, and the testing set, in their appropriate locations. Thereafter, the algorithm hyperparameters, which are the parameters that define the structure of the algorithm itself, are tuned. Some random-forest-specific examples of these hyperparameters include tree size, number of trees, and number of features to consider at each split, but the specific nature of the hyperparameters will vary from algorithm to algorithm (and/or based on user inputs, phenotypes, etc.). To begin the tuning process, the model is trained using an initial set of hyperparameters— which can be chosen based on past experience, an educated guess, at random, or by other suitable manner, etc. During the training process, the algorithm will attempt to minimize the error between the classifications it is making and the true response values included in the data set. Once this process is complete, the error rate reported from the training process is validated through evaluation of the error rate of the trained model on the separate validation data set.; [0056] Once a model is generated through the training, validation and/or cross- validation as described above (i.e., based on the training and validation data sets), the model is further evaluated on the test data set to determine an expected performance of the model on data that is, at that time, new, unseen data to the model.).
Regarding Claim 9: Chavali further teaches:
further comprising outputting the calculated probability of advancement for the individual ones of the potential hybrids to a user. ([0043] The presentation unit 206 outputs, or presents, to a user of the computing device 200 (e.g., a breeder, etc.) by, for example, displaying and/or otherwise outputting information such as, but not limited to, selected progeny, progeny as commercial products, and/or any other types of data as desired.; [0089] As will be appreciated based on the foregoing specification, the above- described embodiments of the disclosure may be implemented using computer programming or engineering techniques, including computer software, firmware, hardware or any combination or subset thereof, wherein the technical effect may be achieved by performing at least one of the following operations: (a) accessing a data structure including data representative of a pool of progenies; (b) determining, by at least one computing device, a prediction score for at least a portion of the pool of progenies based on the data included in the data structure, the prediction score indicative of a probability of selection of the progeny based on historical data; (c) selecting, by the at least one computing device, a group of progenies from the pool of progenies based on the prediction score; (d) identifying, by the at least one computing device, a set of progenies, from the group of progenies, based on at least one of an expected performance of the group of progenies, risks associated with ones of the group of progenies and a deviation of the group of progenies from at least one profile; and (e) directing the set of progenies to a testing and cultivation phase of a breeding pipeline and/or to a validation phase of the breeding pipeline.).
Regarding Claim 10: Chavali further teaches:
wherein the crop includes corn ([0023] In this exemplary embodiment, the breeding pipeline 102 is described with reference to, and is generally directed to, corn or maize and traits and/or characteristics thereof.).
Regarding Claim 11: Chavali further teaches:
planting at least one plant, from the crossing of the pair(s) of the multiple inbred lines of the one or more of the ones of the potential hybrids, in a field included in the breeding pipeline, ([0025] Once the origins are selected, the pool of progenies is created from multiple crosses of the origins. The pool of progenies is then directed to the cultivation and testing phase 106, in which the progenies are planted or otherwise introduced into one or more growing spaces, such as, for example, greenhouses, shade houses, nurseries, breeding plots, fields (or test fields), etc.);
whereby the probability associated with the one or more of the ones of the potential hybrids is validated. ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms (See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).).
Regarding claims 17: Independent claim 17 recites a system for use in defining advancement of agricultural products in breeding (Chavali; [0002] The present disclosure generally relates to methods and systems for use in plant breeding, and in particular to methods and systems for identifying a set of progenies, from a pool of potential progenies, based on prediction frameworks and/or optimization frameworks, and populating a breeding pipeline with the identified set of progenies.), the system comprising at least one computing device configured to execute limitations that, but for the following limitation, are substantially similar to the limitations of independent claim 1, therefore the same analysis applies.
advance one or more of the ones of the potential hybrids into the breeding pipeline, based on the calculated probability of advancement for the individual ones of the potential hybrids, ([Abstract] The prediction score indicates a probability of selection of the progeny based on historical data.; [0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms (See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).);
whereby each of the one or more of the ones of the potential hybrids is created, planted and tested, thereby propagating the one or more specific traits in the breeding pipeline via the one or more of the ones of the potential hybrids. ([0037] Finally, in the breeding pipeline 102, the identified progenies from the selection engine 110 (in the set of progenies) are advanced to the validation phase 108, in which the progenies are exposed to pre-commercial testing or other suitable processes (e.g., a characterization and/or commercial development phase, etc.) with a goal and/or target to be planting and/or commercialization of the progenies. That is, the set of progenies may then be subjected to one or more additional/further tests and/or selection methods, trait integration operations, and/or bulking techniques to prepare the progenies, or plant material based thereon, for further testing and/or commercial activities. In one specific embodiment, one or more plants, derived from the identified progenies, are included in at least one growing space of the breeding pipeline 102, whereby the one or more plants are grown and subject to further testing and/or commercial activities.).
Regarding Claim 18: Chavali further teaches:
wherein the trained machine learning model includes a random forest model; ([0031] the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).);
wherein the BLUPs include BLUPs based on an interval, the interval including a number of years; ([0034] the selection engine 110 may be configured to determine the prediction score based on ranking phenotypic data and/or on derived phenotypic data ( e.g ., best linear unbiased prediction (BLUP), etc.) associated with the progenies included in the data structure 112.; [0029] that data structure 112 may include data indicative of various different characteristics and/or traits of the plants for the current and/or the last one, two, five, ten, fifteen, or more or less years of the plants through the cultivation and testing phase 106, or other growing spaces included in or outside the breeding pipeline 102, and also present data from the cultivation and testing phase 106.);
and wherein the one or more traits of the multiple inbred lines includes yield. ([0018] “Phenotypic data” as used herein includes, but is not limited to, information regarding the phenotype of a given progeny (e.g., a plant, etc.), or a population of progeny e.g., a group of plants, etc.). Phenotypic data may include the size and/or heartiness of the progeny e.g., plant height, stalk girth, stalk strength, etc.), yield, time to maturity, resistance to biotic stress (e.g., disease or pest resistance, etc.), resistance to abiotic stress (e.g., drought or salinity resistance, etc.), growing climate, or any additional phenotypes, and/or combinations thereof.).
Regarding Claim 19: Chavali further teaches:
wherein the at least one computing device is configured, in order to advance the one or more of the ones of the potential hybrids into the breeding pipeline, to: automatically direct the one or more of the ones of the potential hybrids into the breeding pipeline; ([0022] In certain breeding pipeline embodiments (e.g., large industrial breeding pipelines, etc.), testing, selections, and/or advancement may be directed to hundreds, thousands, or more origins, progenies, etc., in multiple phases and at several locations over several years to arrive at a reduced set of origins, progenies, etc., which are then selected for commercial product development. In short, the breeding pipeline 102 is configured, by the testing, selections, etc., included therein, to reduce a large number of origins, progenies, etc., down to a relatively small number of superior-performing commercial products.);
whereby the probability associated with the one or more of the ones of the potential hybrids is validated. ([0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms ( See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).).
Chavali doesn’t teach:
generate executable instructions for a planter to plant at least one plant, consistent with the one or more of the ones of the potential hybrids, in a field included in the breeding pipeline;
and transmit the executable instructions to the planter, to cause the planter to plant the at least one plant, consistent with the one or more of the ones of the potential hybrids, in the field,
Bhagat teaches:
generate executable instructions for a planter to plant at least one plant, consistent with the one or more of the ones of the potential hybrids, in a field included in the breeding pipeline; ([0041] In connection therewith, it should be appreciated that the seeds planted in the different growing spaces may be in (or associated with) different categories (or statuses or availabilities or maturities, etc.), for example, within a commercial or breeding pipeline; [0081] Alternatively, this may include the agricultural computer system 116 generating planting instructions (e.g., scripts, etc.) based on the selected candidate seeds and providing the instructions to a planter whereby the planter operates, in response to the instructions, to plant the selected candidate seeds in the target field); [0123] seeds and planting instructions 1108 are programmed to provide tools for seed selection, hybrid placement;);
and transmit the executable instructions to the planter, to cause the planter to plant the at least one plant, consistent with the one or more of the ones of the potential hybrids, in the field, ([0081] This may include the grower/user receiving the selected candidate seeds and operating a planter to plant the seeds.; [0099] planting instructions generated by the agricultural computer system 116 and transmitted to a planter agricultural apparatus that then control operation of the planter agricultural apparatus to plant certain selected seeds).
It would have been obvious to one of ordinary skill in the art, at the time of applicant’s invention, to combine modified Chavali with Bhagat’s additional feature(s) listed above. One would’ve been motivated to do so, so that the grower is able to test the recommendation, and the seed seller associated with the agricultural computer system 116 (and/or the agricultural computer system 116 itself) is programmed or able to make recommendations of seeds to be included in the growing spaces 106 (Bhagat; [0081]). By incorporating the teachings of Bhagat, one would’ve been able to generate instructions and send those instructions to a planter to cause the planter to plant the hybrid according to the instructions.
Regarding Claim 20: Chavali further teaches:
further comprising separating each of the potential hybrids into one of multiple groups based on the probability of advancement for the potential hybrid; ([0015] Uniquely, the methods and systems herein permit identification of a set of progenies, from a pool of progenies, to be included in a breeding pipeline. In particular, the pool of progenies is reduced, initially, for example, to a group of progenies based on a prediction score for each of the progenies, which is indicative of a success of the progeny based on past selections of progenies (e.g., based on phenotypic data, etc.) and/or available relevant data associated with the progenies.);
and wherein automatically directing, by the computing device, the one or more of the ones of the potential hybrids into the breeding pipeline includes automatically directing the potential hybrids separated into a particular one of the multiple groups into the breeding pipeline. ([0035] the selection engine 110 is configured to select ones of the progenies (from the pool) to be included in a group of progenies. The selection may be based on the prediction scores relative to one or more thresholds, or it may be based on the prediction scores relative to one another, or otherwise.).
Regarding Claim 21: Chavali further teaches:
separating, by the computing device, each of the potential hybrids into one of multiple groups based on the calculated probability of advancement for the potential hybrid; and automatically directing, by the computing device, the one or more of the ones of the potential hybrids into the breeding pipeline based on the one or more of the ones of the potential hybrids being separated into a particular one of the multiple groups. ([Claim 9] a computing device coupled in communication with the data structure and configured to: access the phenotypic data in the data structure related to the pool of progenies; determine a prediction score for each of the progenies in the pool of progenies based on the accessed phenotypic data, the prediction score indicative of a probability of selection of the progeny based on historical data associated with the pool of progenies; select a group of progenies from the pool of progenies based on the prediction score for each of the progenies in the pool of progenies; identify a set of progenies, from the group of progenies, based on at least two of: expected performance of the progenies, a risk associated with the set of progenies, and a deviation of the set of progenies from at least one desired profile; and direct the set of progenies to a validation phase for planting and/or testing and/or to a validation phase of a breeding pipeline for commercialization.; [0031] In this exemplary embodiment, the selection engine 110 is configured to generate a prediction model, based on the historical data, in whole or in part, included in the data structure 112 and/or provided via one or more user inputs, decisions, and/or iterations, where the prediction model indicates a probability of an origin, progeny, etc., for example, being “advanced” (e.g., to the validation phase 108, etc.) as defined in the past based on a set of data, such as, for example, phenotypic data. The selection engine 110 may employ any suitable technique and/or algorithm to generate the prediction model (also referred to as a prediction algorithm). The techniques may include, without limitation, random forest, support vector machine, logistic regression, tree based algorithms, naive Bayes, linear/logistic regression, deep learning, nearest neighbor methods, Gaussian process regression, and/or various forms of recommendation systems techniques, methods and/or algorithms (See “Machine learning: a probabilistic perspective” by Kevin P. Murphy (MIT press, 2012), which is incorporated herein by reference in its entirety, to provide a manner of determining a probability of advance for a given set of data (e.g., yield, height, and standability for maize, etc.)).).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Gardiner LJ, Krishna R. Bluster or Lustre: Can AI Improve Crops and Plant Health? Plants (Basel). 2021 Dec 9;10(12), which discloses an overview of how AI algorithms are being applied to advance our understanding of plant health, and to highlight how they could be used to aid food security.
Esposito S, Carputo D, Cardi T, Tripodi P. Applications and Trends of Machine Learning in Genomics and Phenomics for Next-Generation Breeding. Plants (Basel). 2019 Dec 25;9(1):34, which discloses machine learning’s (ML) role in data-mining and analysis, and in providing relevant information for decision-making towards achieving breeding targets.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GABRIEL J TORRES CHANZA whose telephone number is (571)272-3701. The examiner can normally be reached Monday thru Friday 8am - 5pm ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Brian Epstein can be reached on (571)270-5389. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/G.J.T./Examiner, Art Unit 3625
/SARA GRACE BROWN/Primary Examiner, Art Unit 3625
Prosecution Insights