DETAILED ACTION
Applicant’s response filed 07/02/2026 has been fully considered. The following rejections and/or objections are either reiterated or newly applied.
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 .
Claim Status
Claims 52-53 are newly added by Applicant.
Claims 1-5, 8-10, 15-17, 19-20, 25-30, 38 and 40-51 are cancelled by Applicant.
Claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 are currently pending and are under examination.
Claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 are rejected.
Priority
The instant application claims domestic benefit as a 371 of International Application No. PCT/US2021/028649 filed 04/22/2021, which claims domestic benefit to U.S. Provisional Application No. 63/014,641 filed 04/23/2020. The claims to the domestic benefit are acknowledged. As such, the effective filing date for claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 is 04/23/2020.
Drawings
The objections to the drawings are withdrawn in view of amendments to specification and drawings. The drawings filed 10/21/2022 are accepted.
Information Disclosure Statement
The IDS filed 07/02/2026 follows the provisions of 37 CFR 1.97 and has been considered in full. A signed copy of the list of references cited from the IDS is included with this Office Action.
Claim Objections
The objections to claims 40 and 47 are withdrawn in view of claim amendments.
Withdrawn Rejections
35 USC 112(b)
The rejection of claims 18, 23-24, 31-32, 34, 40, 43 and 47 under 25 USC 112(b) is withdrawn in view of claim amendments.
35 USC 112(d)
The rejection of claim 11 under 35 USC 112(d) is withdrawn in view of claim amendment.
35 USC 101
The rejection of claim 39 under 35 U.S.C. 101 and section 33(a) of the America Invents Act as being directed to or encompassing a human organism is withdrawn because the claim has been limited to crops.
Claim Rejections - 35 USC § 112
35 USC 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 11 and 34 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
This rejection is newly recited as necessitated of claim amendment.
Claim 11 recites “the predicted phenotype”. It is unclear which predicted phenotype is referenced because claim 6 steps b and e predict phenotype data. Clarify which phenotype data is referenced.
Claim 34, lines 2-3, recites “the individuals of the first population” which lacks antecedent basis. This should be changed to “the crops of the first population”.
35 USC 112(d)
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
Claim 18 is rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends.
Claim 18 fails to include all the limitations of claim 6. Claim 6, step c, recites “a second population of crops” indicating at least two crops whereas claim 18, step c, recites “the second population is a single crop” indicating just one crop.
Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea and a natural phenomenon without significantly more.
Any newly recited portions herein are necessitated by claim amendment.
Step 1:
Step 1 asks whether the claims recite statutory subject matter. In the instant application, claims 6-7, 11-14, 18, 21-24, 31-37 and 52-53 recite a method and claim 39 recite a product. As such, these claims recite statutory subject matter (Step 1: YES).
Step 2A, Prong 1:
Claims that recite statutory subject matter are analyzed under Step 2A, Prong 1 to determine if they recite any concepts that equate to an abstract idea, law of nature or natural phenomena. The instant claims recite the following limitations that equate to one or more categories of judicial exception:
Claim 6 recites “a) generating a training dataset comprising genotype data, phenotype data, and envirotype data of a first population of crops in a first geographic area, wherein the first geographic area comprises a plurality of envirotypes, b) training, using the training dataset, a statistical model to generate a genomic relationship structure for each of two or more envirotypes in the plurality of envirotypes and predict phenotype data for a population of crops; c) providing a second population of crops in a second geographic area; d) obtaining genotype data and envirotype data of the second population in the second geographic area; e) predicting, using the statistical model, phenotype data of the second population in the second geographic area based on the genotype data and envirotype data of the second population; f) selecting one or more crops from the second population based on the predicted phenotype data of the second population;”
Claim 7 recites “a) the crops in the first population are hybrids and the crops in the second population are inbred lines or hybrids; b) the crops in the first population are inbred lines, breeding populations, or hybrids, and the crops in the second population are segregating lines from breeding populations; or c) the crops in the first population are parental lines and the crops in the second population are filial lines derived from the parental lines.”
Claim 11 recites “wherein the predicted phenotype comprises field testing performance of the selected one or more crops in a field.
Claim 12 recites “wherein the selected one or more crops are segregating lines, inbred lines, or hybrid lines.”
Claim 13 recites “wherein the selection is applied using a selection intensity.”
Claim 18 recites “a) the second population comprises crops with different genetic makeups from other crops in the second population; b) the second population comprises crops with the same genetic makeup as all other crops in the second population; or c) the second population is a single crop.”
Claim 21 recites “wherein the first geographic area and the second geographic area are the same geographic area.
Claim 22 recites “wherein the second geographic area is a target breeding zone or a target market zone.”
Claim 23 recites “wherein the envirotype data of a first population of crops is time data, location data, weather data, soil data, companion organism data, management data, crop canopy data, cultivation area data, or a combination thereof.”
Claim 24 recites “wherein: a) the time data is century data, decade data, year data, season data, month data, day data, hour data, minute data, second data, or a combination thereof; b) the location data is latitude, longitude, altitude, or a combination thereof; c) the weather data is temperature, humidity, pressure, zonal wind speed, meridional wind speed, long-wave radiation, fraction of total precipitation that is convective, convective available potential energy, potential evaporation, precipitation hourly total, short-wave solar radiation, photoperiod, or a combination thereof; d) the soil data is soil type, soil structure, soil moisture, soil depth, soil organic matter content, soil density, soil pH, soil fertility, soil salinity, or a combination thereof; e) the companion organism data is soil fauna, insects, animals, weeds, or a combination thereof; f) the management data is intercropping management, cover cropping management, rotating cropping management, or a combination thereof; and/or g) the crop canopy data is obtained from an aerial platform.”
Claim 31 recites “wherein the envirotype data of the first population of crops comprises a data structure grouped according to growth stages of the first population of crops.”
Claim 32 recites “wherein the envirotype data of a first population of crops is an envirotype map.”
Claim 33 recites “wherein the second population of crops are selected from the group consisting of maize, soybean, wheat, sorghum, barley, oats, rice, millet, canola, cotton, cassava, cowpea, safflower, sesame, tobacco, flax, sunflower, a grain crop, a vegetable crop, an oil crop, a forage crop, an industrial crop, a woody crop, and a biomass crop.”
Claim 34 recites “wherein the statistical model estimates effects of genetic markers in interaction with the envirotype on the phenotype of the individuals of the first population.”
Claim 35 recites “wherein the statistical model comprises a genotype variable, an envirotype covariate, and an interaction term between the genotype variable and the envirotype covariate.”
Claim 36 recites “wherein the statistical model is a linear regression model, a logistic regression model, a Bayesian ridge regression model, a lasso regression model, an elastic net regression model, a decision tree model, a gradient boosted tree model, a neural network model, or a support vector machine model.”
Claim 37 recites “wherein the predicted phenotype data of the second population are genomic estimated breeding values (GEBVs).”
Claim 39 recites “A variety developed by the method of claim 6.”
Claim 52 recites “wherein training the statistical model further comprises tuning the statistical model, validating the statistical model, and/or updating the statistical model.”
Limitations reciting a mental process.
Claims 6, 31, 34 and 52 contain limitations recited at such a high level of generality that they equate to a mental process because they are similar to the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), which the courts have identified as concepts that can be practically performed in the human mind. The paragraphs below discuss the broadest reasonable interpretation (BRI) of the limitations in these claims that recite a mental process.
Claims 6, steps a-b, and claim 34 include using pen and paper to collect data and perform calculations using a linear regression to generate a prediction. A human can practically train a linear regression on pen and paper. Claim 6, steps c-e, include performing the same calculations using a test set. Claim 6, step f, requires mental evaluation to select. Claim 31 includes organizing data. Claim 52 includes altering parameters of the linear regression.
Limitations reciting a mathematical concept.
Claim 6, steps b and e, and claims 34-37 recite limitations that equate to a mathematical concept because they are similar to the concepts of organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)), which the courts have identified as mathematical concepts. Claims 34-35 and 37 include performing calculations using the models recited in claim 36, wherein the output is a number such as breeding values. Claim 6, steps b and e, include performing calculations of a linear regression to generate a numerical output.
Limitation reciting a natural phenomenon.
Claim 39 claims a physical product of a variety developed by claim 6. The BRI of claim 39 includes a variety of plant, which is a product of nature. See MPEP 2106.04(b)(II) regarding products of nature.
Limitations included in the recited judicial exception.
Claims 7, 11-13, 18, 21-24, and 32-33 further limit limitations that are part of the judicial exception but do not alter the fact that they are part of the recited judicial exception.
As such, claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 recite an abstract idea and a natural phenomenon (Step 2A, Prong 1: YES).
Additional Elements:
Once limitations have been identified that recite a judicial exception, the claims are evaluated for additional elements. The additional elements are then analyzed under Step 2A, Prong 2 then Step 2B. The instant claims recite the following additional elements:
Claim 6 recites “g) cultivating the one or more selected crops in the second geographic area to breed one or more varieties, wherein the one or more varieties exhibit suitable phenotype for the second geographic area”
Claim 14 recites “further comprising producing offspring from the selected one or more crops.”
Claim 53 recites “wherein cultivating the one or more selected crops in the second geographic area comprises crossing the one or more selected crops.”
These above recited additional elements are analyzed below under both Step 2A, Prong 2 and Step 2B:
Step 2A, Prong 2:
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). The judicial exception is not integrated into a practical application because the claims do not recite additional elements that reflect an improvement to a computer, technology, or technical field (MPEP § 2106.04(d)(1) and 2106.5(a)), require a particular treatment or prophylaxis for a disease or medical condition (MPEP § 2106.04(d)(2)), implement the recited judicial exception with a particular machine that is integral to the claim (MPEP § 2106.05(b)), effect a transformation or reduction of a particular article to a different state or thing (MPEP § 2106.05(c)), nor provide some other meaningful limitation (MPEP § 2106.05(e)). Rather, the claims include limitations that equate to an equivalent of the words “apply it” and/or to instructions to implement an abstract idea on a computer (MPEP § 2106.05(f)), insignificant extra-solution activity (MPEP § 2106.05(g)), and field of use limitations (MPEP § 2106.05(h)). The paragraphs below discuss the additional elements recited above in the instant claims.
Claim 6, step g, and claims 14 and 53 recite mere instructions to implement the abstract idea of claim 6, step f. This is because they recite the idea of a solution without providing details for how the solution to a problem is accomplished (MPEP 2106.05(f)(1)). Regarding claim 6, step g, of “to breed one or more varieties, wherein the one or more varieties exhibit suitable phenotype for the second geographic area” recites an intended use and is thus not required by the claim. Thus, step g only requires cultivating a crop based on an unspecified phenotype, which could be a poor crop yield. However, it is unclear what problem is solved by breeding/crossing a crop predicted to have poor crop yield. The same reasoning applies to claims 14 and 53.
As such, claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 are directed to an abstract idea and a natural phenomenon (Step 2A, Prong 2: NO).
Step 2B:
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). These claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because these claims recite additional elements that equate to instructions to apply the recited exception in a generic way and/or in a generic computing environment (MPEP § 2106.05(f)) and to well-understood, routine and conventional (WURC) limitations (MPEP § 2106.05(d)). The paragraphs below discuss the additional elements recited above in the instant claims.
Claim 6, step g, and claims 14 and 53 equate to mere instructions to “apply” the abstract idea, which cannot provide an inventive concept. See MPEP 2106.05(f). See above section Step 2A, Prong 2 for more details.
When claim 6, step g, is viewed in combination with claims 14 and 53, they recite WURC limitations as taught by Crossa et al. (“Crossa”; Trends in plant science 22, no. 11 (2017): 961-975; previously cited in PTO892 mailed 04/06/2026). Crossa reviews genomic selection and genomic-enabled prediction such as GxE interactions in plant breeding (abstract). FIG 1B, under section phenotypic + genomic selection, shows common maize breeding schemes which include crossing selected crops.
When these additional elements are considered individually and in combination, they do not provide an inventive concept because they equate to mere instructions to implement the abstract idea and to WURC limitation of plant breeding as taught by Crossa. Therefore, these additional elements do not transform the claimed judicial exception into a patent-eligible application of the judicial exception and do not amount to significantly more than the judicial exception itself (Step 2B: No).
As such, claims 6-7, 11-14, 18, 21-24, 31-37, 39 and 52-53 are not patent eligible.
Response to Arguments under 35 USC 101
Applicant's arguments filed 07/02/2026 have been fully considered but they are not persuasive.
Applicant argues claim 6 does not recite a mental process (pg. 15-17, sec. A1). Applicant’s argument is not persuasive because:
Step a-f recite an abstract idea. Step g recites an additional element. Steps a-e require collecting data and performing operations of a linear regression. A human can perform such calculations on pen and paper, especially because they are recited at such a high level of generality. The “genomic relationship structure” is so generically recited that it includes the inherent data structure performed in the calculations of a linear regression when multiplying independent predictors of genotype and envirotype variables to derive interaction terms that predict phenotypes. A human can train a linear regression on pen and paper by altering weights. Examiner agrees that claim 53 recites an additional element.
Applicant argues claim 6 does not recite math and analogizes Example 39 to claim 6 (pg. 17-19, sec. A2). Applicant’s argument is not persuasive because:
Claim 6 is distinct from Example 39 because it does not use images to train a neural network. Claim 6 encompasses training a linear regression using gradient descent, wherein the output is a number such as a breeding value. In this way, claim 6 recites math under its BRI.
Applicant argues claims 6 and 53 are not directed to methods of organizing human activity (pg. 19-21, sec. A3). Examiner agrees in view of the claim amendments.
Applicant argues the claims solve a technical problem of limited selection prediction accuracy caused by the inability of existing models to adequately capture marker-by-environment (MxE) interactions across distinct geographic envirotypes (pg. 21-23, sec. B-1). Claim 6 steps a-b confer the practical application represented by Model 3 in the specification, and the genomic relationship structure has a particular architectural distinction (pg. 23, sec. 2) (pg. 23-24, sec. 3). Applicant’s argument is not persuasive because:
Steps a-b recite an abstract idea. MPEP 2106.05(a) recites “the judicial exception alone cannot provide the improvement.” Even if steps a-b did recite additional elements, they would not be commensurate in scope with the improvement (MPEP 2106.05(a)). This is because Model 3 in specification para. [139] the effect of genetic markers varies across envirotypes by generating a genomic relationship matrix specific to each envirotype when estimating the effect of GxE interactions. This feature of Model 3, which in part confers the improvement, is not recited in the claims. Step b merely discloses a genomic relationship structure for each envirotype but does not specify the matrix or variance of marker effects. Moreover, the alleged solution does not identify technical improvements realized by the claim over the prior art because Messina et al. (European Journal of Agronomy 100 (2018): 151-162; previously cited on PTO892 mailed 04/06/2026) discloses steps a-b as shown in the rejection below.
Applicant argues claim 6 steps f-g recite a practical application of a crop-breeding process (pg. 24-25, sec. 4). Applicant’s arguments are not persuasive for the following reasons:
Step f recites a mental process. Step g equates to mere instructions to implement the abstract idea of step f, which is not a practical application under Step 2A, Prong 2. Step g only requires cultivating the one or more selected crop. The limitation of “to breed one or more varieties, wherein the one or more varieties exhibit suitable phenotype for the second geographic area” recites an intended use and is thus not required by the claim.
With this interpretation in mind, claim 6 cultivates one or more crops selected based on unspecified phenotype data, which could be anything, even poor crop yield. However, it is unclear how poor crop yield, for example, solves a problem or provides a practical application. Under this interpretation, claim 6 recites the idea of a solution without details of how the solution is accomplished, which does not provide a practical application (MPEP 2106.05(f)(1)).
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 6-7, 11-12, 18, 21-24, 31-35, 37, 39 and 52 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Messina et al. (“Messina”; European Journal of Agronomy 100 (2018): 151-162; previously cited on PTO892 mailed 04/06/2026).
Any newly recited portions herein are necessitated by claim amendment. The bold and italicized text below are the limitations of the instant claims, and the italicized text serves to map the prior art onto the instant claims.
Claim 6:
A method for breeding one or more varieties suitable for a geographic area, comprising:
a) generating a training dataset comprising genotype data, phenotype data, and envirotype data of a first population of crops in a first geographic area, wherein the first geographic area comprises a plurality of envirotypes, b) training, using the training dataset, a statistical model to generate a genomic relationship structure for each of two or more envirotypes in the plurality of envirotypes and predict phenotype data for a population of crops;
Messina predicts crop yield by using a combination of a crop growth model (CGM) and whole genome prediction (WGP) methods called CGM-WGP (abstract) (FIG 1). The CGM-WGP model was trained on estimation sets comprising one, two or all three divergent environments along with associated phenotypic yield data and genotypic information of double hybrid (DH) crop lines (pg. 152, col. 1, para. 1) (sec. 2.6). The different environments are being interpreted as geographic areas. Alternatively, Messina discloses an empirical breeding experiment using the CGM-WGP model with four double haploid populations tested in different environmental fields (pg. 155, col. 1, para. 2).
In training, marker effects were used to predict yield performance in all three environments (pg. 155, col. 1, para. 2). Referring to CGM-WGP, Messina recites “[t]he relationship between marker effects and yield is established through the estimation of marker effects and biological parameters within the CGM. Because the selected genetic models result in the modulation of the strength of the relationship between the environment and a physiological process, and/or different physiological processes, genotype-by-environment (G×E), epistasis in the form of trait-by-trait genotype-by-genotype (G×G) and genotype by-environment-by-management (G×E×M) interactions are all emergent properties from the genetic variation effects in the functional equations that relate traits and the environment” (generate a genomic relationship structure for each of two or more envirotypes in the plurality of envirotypes) (pg. 152, col. 1, last para.).
c) providing a second population of crops in a second geographic area; d) obtaining genotype data and envirotype data of the second population in the second geographic area; e) predicting, using the statistical model, phenotype data of the second population in the second geographic area based on the genotype data and envirotype data of the second population;
An prediction set is used to validate the model, which contains genotype data (pg. 152, col. 1, para. 1). Figure 1 shows observed data for an individual which includes environmental data.
For an empirical breeding experiment, Messina recites “[a] leave-one-family-out cross-validation was conducted to assess prediction accuracy for grain yield. Here the CGM-WGP model was selected using an estimation data set based on the yield data from both the NWL and WL environments for three of the four DH populations and then used to predict the yield values of the fourth DH population for both the NWL and WL environments. This process was repeated until each population was left out once. Since the estimation set comprised yield data from both the yield in the NWL and WL environments this is a multi-environment estimation set” (pg. 155, col. 2, para. 2).
Additionally, sec. 3.5 uses a parametrized CGM-WGP model and applies it to a test population that only contains genotype and location data.
f) selecting one or more crops from the second population based on the predicted phenotype data of the second population; and g) cultivating the one or more selected crops in the second geographic area to breed one or more varieties, wherein the one or more varieties exhibit suitable phenotype for the second geographic area.
The CGM-WGP predicts crop yield and is used in plant breeding programs, specifically in early hybrid advancement stages of breeding program (abstract) (sec. 5). Thus, the test populations would be selected based on their precited crop yield (Figure 6). CGM-WGP is used for plant breeding applications to select plants that have a breeding value (abstract) (pg. 151, col. 1). CGM-WGP has been implemented with a function breeding program (pg. 152, col. 2, para. 1).
Claim 7:
Messin recites “[t]he four DH populations, referred to as DHPop1, DHPop2, DHPop3, DHPop4, were created from biparental crosses between six inbred lines, referred to as I1, I2, …, I6. The two parents of DHPop1, I1 and I2, were different from the four inbred lines, I3, I4, I5 and I6, used as parents to create the other three DH populations. One of the four remaining inbred lines, I3, was used as a common parent for all three remaining DH populations; DHPop2 parents I3/I4, DHPop3 parents I3/I5 and DHPop4 parents I3/I6. Thus, there is a closer pedigree relationship, based on the half-sib structure, between DHPop2, DHPop3 and DHPop4 than there is between any of these three populations and DHPop1” (the second population comrpises crops with different genetic makeups from other crops in the second population) (pg. 155, col. 1, para. 3). The DH lines were evaluated as F1 hybrids (the crops in the first populations are hybrids and the second population are hybrids) (sec. 2.5).
Claim 11:
CGM-WCP predicts crop yield in different environments (abstract).
Claims 12 and 18:
The DH lines are F1 hybrids and are all maize (the second population iis a single crop) (pg. 154, col. 2, para. 1) (abstract).
Claim 21:
The estimation set and prediction set are derived from the same DH lines, which are acquired from different environments types (pg. 155, col. 1, para. 1) (pg. 155, col. 2, para. 2). Environment types are being interpreted as geographic locations.
Claim 22:
Target environments were selected in the US corn-belt where DH line crop yield was simulated (Figure 6) (pg. 161, col. 1, last para.).
Claims 23-24:
Messina recites “[t]he environmental inputs (e.g., soil type, temperature) of environment j are represented by Ej, and denotes the residual variance for yield in that environment” (the soil data is soil type) (Figure 1) (sec. 2.1).
Claim 31:
For each environment, water availability during crop cycle was quantified by water SD ratios (sec. 2.5). Because this data is used to train the model, it inherently has a data structure to be inputted into a model and thus reads on the broadly recited “data structure.”
Claim 32:
Figure 6 shows a map (envirotype map) of simulated yields for major maize growing regions in the corn belt for 34 individuals of a breeding population with CGM parameters estimated from genetic marker data using the CGM-WGP model (sec. 3.5). Yields were simulated for two DH lines in 2263 grids in the corn belt (sec. 3.5).
Claim 33:
The DH populations are maize (sec. 2.5).
Claim 34:
Figure 1 and section 2.1 show the equation that models effects of genetic markers in different environments to predict a phenotype of crop yield.
Claim 35: CGM-WGP models gene x environment interactions to predict phenotypes (abstract). The model is:
PNG
media_image1.png
70
399
media_image1.png
Greyscale
(sec. 2.1). The envirotype covariate is
PNG
media_image2.png
50
48
media_image2.png
Greyscale
which denotes the residual variance for yield in a environment (sec. 2.1). Tti is the unobserved value for a physiological trait t and for individual i, and the prior for the unobserved Tti uses Bot as a trait specific intercept, ztik denotes the marker score of individual i at marker k for trait t and utk the effect of marker k for trait t (genotype variable). The Gaussian density function N represents an interaction term.
Claim 37:
Messina predicts crop yield of a prediction set containing genotype data using CGM-WGP trained on an estimation set containing genotype x environment data and phenotype data (pg. 152, col. 1, para. 1). WGP predicts breeding values (pg. 151, col. 1). Because Messina uses whole genome SNP data from a test population to predict crop yield crop (pg. 155, col. 1, para. 3), the predicted phenotype can be considered a genomic estimated breeding value.
Claim 39:
CGM-WGP is used for plant breeding applications to select plants that have a breeding value (abstract) (pg. 151, col. 1). Crop yield was virtually predicted in the US corn belt using two DH lines with untested phenotypes based on their genotypes (Figure 6) (pg. 155, col. 1, last para.) (sec. 3.5). Of the two DH lines, DH line 1 was predicted to perform better than DH line 2 in environments where yield was greater than 877 gm-2 (pg/ 160, col. 1, para. 1). The model is used in early hybrid advancement stages of a breeding program (pg. 160, col. 1, para. 2). Thus, the top predicted performer is selected for advancement in early hybrid stages of a breeding program which includes environmental trials. This procedure would result in different crop varieties.
Claim 52:
A leave-one-family-out cross-validation was conducted to assess prediction accuracy for grain yield of the CGM-WGP model (pg. 155, col. 2, para. 2).
Response to Arguments under 35 USC 102
Applicant's arguments filed 07/02/2026 have been fully considered but they are not persuasive.
Applicant argues Messina does not teach step b in claim 6 (pg. 26, para. 3). Applicant’s argument is not persuasive because:
The CGM-WGP model was trained on estimation sets comprising one, two or all three divergent environments along with associated phenotypic yield data and genotypic information of double hybrid (DH) crop lines (pg. 152, col. 1, para. 1) (sec. 2.6). Marker effects were used to predict yield performance in all three environments (pg. 155, col. 1, para. 2). Messina also recites “[t]here was significant genetic variation for grain yield in the NWL and WL environments for all four DH populations. The magnitude of the variance components for yield in the WL environment was greater for DHPop3 and DHPop4 compared to DHPop1 and DHPop2” (pg. 158, col. 1, para. 2) (Table 5). These teachings demonstrate that genetic effects varied between environments.
Applicant argues Messina does not separately model how genetic marker effects differ by environment and does not generate a distinct genomic relationship structure for each environment (pg. 26, last para. – pg. 27, para. 1). Applicant’s argument is not persuasive because:
As discussed in the response above, Messina does model how genetic markers vary in each environment, rather than teaching a “static” model that does not allow marker effects to vary across environments. Furthermore, Messina recites “[n]egative prediction accuracies were not observed for CGM WGP (r≥0.22, Table 1), indicating the algorithm was able to define genetic models for physiological adaptive traits that account for the presence of G×E interactions and the effect of the variable environments on the prediction of yield performance” (pg. 156, col. 2, para. 3). These genetic models are defined by the genetic markers.
Applicant argues that Messina does not teach the “genomic relationship structure” for a plurality of envirotypes in step b claim 6 (pg. 27, para. 2). Applicant’s argument is not persuasive because:
The phrase “genomic relationship structure” is so generically recited that the variable ztik, defined as the score of individual i at mark k for trait t, which is associated with yield of individual i in environment j in FIG 1 reads on a “genomic relationship structure” for each envirotype. This genomic relationship structure can also be interpreted as the defined genetic models for traits accounting for GxE interactions (pg. 156, col. 2, para. 3).
Claim Rejections - 35 USC § 103
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.
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 13-14 are rejected under 35 USC 103 for being unpatentable over Messina et al. (“Messina”; European Journal of Agronomy 100 (2018): 151-162; previously cited on PTO892 mailed 04/06/2026), as applied to the rejection of claim 6, in view of Yonezawa et al. (“Yonezawa”; Heredity 82, no. 4 (1999): 401-408; previously cited on PTO892 mailed 04/06/2026).
Any newly recited portions herein are necessitated by claim amendment. The limitations of claim 6 have been taught above by Messina in section under section 35 USC 102.
Claims 13-14:
Messina uses WGP in large commercial breeding programs to evaluate a fraction of new hybrids in multi-environmental trials (abstract) (pg. 151, col. 1-2). Messina implements CGM-WGP in a functional breeding program (pg. 152, col. 2, para. 1). However, Messina does not select a hybrid for a trial based on selection intensity to then produce offspring of a selected hybrid.
Yonezawa evaluates a selection efficiency metric in plant breeding that produces optimum selection procedures to produce new commercial varieties (abstract). Yonezawa recites “Figure 2 describes how selection intensity influences the selection efficiency S/t. The selection intensity in a range 0.05 < α < 0.10 is optimum, giving the highest selection efficiency (S/t) with the optimum selection cycles of six and seven” (pg. 404, col. 2, para. 2). Thus, a plant is selected based on selection intensity and is used in breeding cycles.
It would have been prima facie obvious to have modified the plant breeding program implemented by the CGM-WGP model in Messina by selecting hybrids for trials based on intensity selection which includes cycles for breeding as taught by Yonezawa. Motivation is taught by Yonezawa who recites that their method provides optimum selection procedures to give the most opportunities for producing a sufficiently high genetic gain required for recognition of a new commercial plant variety (abstract) (pg. 406, col. 2, last para.). The method also helps solve a problem in plant breeding of whether to test many individuals with a low input assessment or a few individuals with a high input assessment (pg. 407, col. 2, para. 2). There would have been a reasonable expectation of success to select hybrids based on selection intensity because selection intensity selects plants to be parents in each cycle (i.e. each generation of plants).
Claim 36 is rejected under 35 USC 103 for being unpatentable Messina et al. (“Messina”; European Journal of Agronomy 100 (2018): 151-162; previously cited on PTO892 mailed 04/06/2026), as applied to the rejection of claim 6, in view of Crossa et al. (“Crossa”; rends in plant science 22, no. 11 (2017): 961-975; previously cited on PTO892 mailed 04/06/2026).
Any newly recited portions herein are necessitated by claim amendment. The limitations of claim 6 have been taught above by Messina in under section 35 USC 102.
Claim 36:
Messina discloses a Bayesian generalized linear hierarchical model to perform crop yield predictions (sec. 2.1) (Figure 1). However, Messina does not disclose a neural network for predictions.
Crossa reviews genomic selection (GS) in plant breeding (abstract). Crossa recites “[d]eep machine-learning methods using neural networking appear promising to increase the accuracy of genomic-enabled prediction” (pg. 973, para. 3).
It would have been prima facie obvious to have substituted the Bayesian generalized linear hierarchical model in Messina with a deep neural network to increase prediction accuracy as taught by Crossa (pg. 973, para. 3). The result of substituting these models would have yielded predictable results because they both use genotype, phenotype, and environmental variables to predict phenotypes of a test population (Crossa at pg. 969, last para – pg. 970, para. 2).
Claim 53 is rejected under 35 USC 103 for being unpatentable over Messina et al. (“Messina”; European Journal of Agronomy 100 (2018): 151-162; previously cited on PTO892 mailed 04/06/2026), as applied to the rejection of claim 6, in view of Louwaars (Euphytica 214, no. 7 (2018): 114; newly cited).
This rejection is newly recited as necessitated by claim amendment. The limitations of claim 6 have been taught in the rejection above by Messina under section 35 USC 102.
Claim 53:
Messina uses the CGM-WGP model for predicting crop yield and plant breeding, specifically in early hybrid advancement stages of breeding program (abstract) (sec. 5), where test populations are selected based on their precited crop yield (Figure 6). However, Messina does not cross the selected crops derived from the CGM-WGP models.
Louwaars discloses plant breeding and diversity (abstract) and describes a situation in the Netherlands where companies made crosses between the two best performing wheat varieties each year (pg. 2, col. 1, para. 1). It would have been prima facie obvious to cross the top producing crops in a given environment in Messina as taught by Louwaars because one of ordinary skill would recognize that such a cross could generate a better crop for a given environment. There would have been a reasonable expectation of success because the combination requires plant breeding.
Response to Arguments under 35 USC 103
Applicant's arguments on pg. 27-28 of the remarks filed 07/02/2026 have been fully considered, but they are not persuasive for the same reasons applied above under Response to Arguments under 35 USC 102 because Messina does teach all the limitations of amended claim 1.
Conclusion
No claims are allowed.
Relevant prior art includes: He et al. (NPL ref. 30 on IDS filed 05/22/2023; Theoretical and applied genetics, 132(11), 3143-3154) who discloses matrices for haplotype-based genomic predictions. Crossa et al. (“Crossa”; Trends in plant science 22, no. 11 (2017): 961-975; previously cited in PTO892 mailed 04/06/2026) discloses a model that allows marker effects to change in each environment.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Noah A. Auger whose telephone number is (703)756-4518. The examiner can normally be reached M-F 7:30-4:30 EST.
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, Karlheinz Skowronek can be reached at (571) 272-9047. 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.
/N.A.A./Examiner, Art Unit 1687
/KAITLYN L MINCHELLA/Primary Examiner, Art Unit 1685
Prosecution Insights