DETAILED ACTION
The applicant’s response, from 28 May 2026, has been fully considered. Amendments to the claims, from 28 May 2026, were received and entered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 2-3 and 17 are cancelled.
Claims 21-23 are newly added.
Claims 1, 4-16, and 18-23 are currently pending and under examination herein.
Claims 1, 4-16, and 18-23 are rejected.
Priority
The instant application claims priority as a 371 of PCT/EP2021/050743 filed 14 January 2021, which is a CIP of U.S. application 16796340 filed on 20 February 2020. In this action, claims 1, 4-16, and 18-23 are examined as though they had an effective filing date of 20 February 2020. In future actions, the effective filing date of one or more claims may change, due to amendments to the claims, or further analysis of the disclosure(s) of the priority application(s).
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on 28 May 2026 and 21 July 2026 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. These are in addition to the IDSs considered in the previous office action(s).
Drawings
The drawings filed on 19 August 2022 are accepted.
Claim Objections
The previously issued claim objections are withdrawn in response to the amendments which corrected the cited issues.
Claim Rejections - 35 USC § 112
The previously issued 35 USC 112(b) rejections are withdrawn in response to the amendments to the claims.
Claim Rejections - 35 USC § 101
Arguments associated with the previously issued 35 USC 101 rejection are
not considered persuasive (see response to arguments below the rejection). The
following rejection is reiterated and modified as has been necessitated by amendment.
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, 4-16, and 18-23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. In accordance with MPEP 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea or natural law (Step 2A, Prong 1). Claims 1, 4-14, and 21-23 are directed to a method and Claims 15-16 and 18-20 are directed to a system. In the instant application, the claims recite the following limitations that equate to an abstract idea:
Claim 1 recites the limitation - determining specific transport rates of one or more metabolites in the cell culture using the values obtained as input to a machine learning model trained to predict the specific transport rates of the one or more metabolites at a latest maturity of the one or more maturities or a later maturity based at least in part on the values of said one or more process conditions for the bioprocess at the one or more maturities, wherein the specific transport rate of a metabolite is a net amount of the metabolite transported between the cells and a culture medium, per cell and per unit of maturity; predicting one or more features of the bioprocess based at least in part on the determined specific transport rates, wherein predicting the one or more features of the bioprocess comprises: comparing the specific transport rates or values derived therefrom to one or more predetermined values; and determining, based on the comparing, whether the process is operating normally, wherein the process is considered to operate normally when the values of the specific transport rates or values derived therefrom are within a predetermined range of an average value for a corresponding variable in a set of reference bioprocesses; and determining, based on the comparing, to implement a corrective action. Based on the broadest reasonable interpretation, determining rates with a machine learning model, predicting features based on rates, comparing rates, determining if the process is occurring normally, comparing values to a range, and determining based on the comparing, encompasses equations and could practically be done by the human mind. This draws the limitations to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 6 recites the limitation - wherein predicting one or more features of the bioprocess comprising predicting the value of one or more critical quality attributes (CQAs) of the bioprocess using a predictive model that has been trained to predict CQAs using a set of predictor variables comprising the one or more specific transport rates. Based on the broadest reasonable interpretation, predicting features/values using a predictive model encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 7 recites the limitation - wherein the machine learning model is a regression model, or wherein the machine learning model is selected from a linear regression model, a random forest regressor; and or wherein the machine learning model comprises a plurality of machine learning models, wherein each machine learning model has been trained to predict the specific transport rates of an individually selected subset of the one or more metabolites. This limitation specifies the machine learning model implemented in the judicial exception of claim 1. The refined machine learning indicated by this limitation still represents a judicial expectation.
Claim 8 recites the limitation - wherein the machine learning model has been trained to jointly predict the specific transport rates of the one or more metabolites at a later maturity based at least in part on the values of one or more process conditions for the bioprocess at one or more preceding maturities. This limitation specifies the machine learning model implemented in the judicial exception of claim 1. The refined machine learning indicated by this limitation still represents a judicial expectation.
Claim 9 recites the limitation - the machine learning model has been trained to predict the specific transport rates of the one or more metabolites at a latest of the plurality of maturities or a later maturity based at least in part on the values of one or more process conditions for the bioprocess at the plurality of maturities. This limitation specifies the machine learning model implemented in the judicial exception of claim 1. The refined machine learning indicated by this limitation still represents a judicial expectation.
Claim 11 recites the limitation - wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations. Based on the broadest reasonable interpretation, predicting features and determining values encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 12 recites the limitation - wherein determining the concentration of a metabolite i (mi) at maturity k, where k is the maturity associated with the predicted specific transport rates, comprises integrating any of equations (4), (4a)-(4d) and (28) between a preceding maturity at which mi is known and maturity k [Equations here] where δm,i is the specific transport rate of metabolite i by the cells in the culture, mi is the concentration of metabolite i in the bioreactor, pmi is a pseudoconcentration of metabolite i in the bioreactor, V is a volume of the cell culture in the bioreactor, mF,i is the concentration of metabolite i in a feed flow, mH,i is the concentration of metabolite i in a harvest flow, mB,i is the concentration of metabolite i in a bleed flow, xv is a viable cell density in the bioreactor, and FF, FH and FB are volumetric feed, harvest and bleed flow rates, ε is a parameter and fML.i(u, m, s) represents the predictions from the machine learning model. Based on the broadest reasonable interpretation, determining using equations encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 13 recites the limitation - determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity. Based on the broadest reasonable interpretation, determining values encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 14 recites the limitation - predicting effect of a particular value of a process parameter at a later maturity by including the particular value in the material balance equations, a kinetic growth model and/or the input values used by the machine learning model to predict specific transport rates at a further maturity. Based on the broadest reasonable interpretation, predicting effects encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 15 recites the limitation - determining specific transport rates of one or more metabolites in the cell culture using the values obtained as input to a machine learning model trained to predict the specific transport rates of the one or more metabolites at a latest maturity of the one or more maturities or a later maturity based at least in part on the values of said one or more process conditions for the bioprocess at the one or more maturities, wherein the specific transport rate of a metabolite is a net amount of the metabolite transported between the cells and a culture medium, per cell and per unit of maturity; predicting one or more features of the bioprocess based at least in part on the determined specific transport rates, wherein predicting one or more features of the bioprocess comprises: comparing the specific transport rates or values derived therefrom to one or more predetermined values; and determining, based on the comparing, whether the process is operating normally, wherein the process is considered to operate normally when the values of the specific transport rates or values derived therefrom are within a predetermined range of an average value for a corresponding variable in a set of reference bioprocesses; and determining, based on the comparing, to implement a corrective action. Based on the broadest reasonable interpretation, determining rates with a machine learning model, predicting features based on rates, comparing rates, determining if the process is occurring normally, comparing values to a range, and determining based on the comparing, encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 18 recites the limitation - wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity; or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations; or wherein predicting one or more features of the bioprocess comprises predicting the value of one or more critical quality attributes (CQAs) of the bioprocess using a predictive model that has been trained to predict CQAs using a set of predictor variables comprising the one or more specific transport rates. Based on the broadest reasonable interpretation, predicting features and determining values encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 19 recites the limitation - determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity, wherein determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model; or wherein the method further comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity, and using one or more of the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity. Based on the broadest reasonable interpretation, determining values encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 20 recites the limitation - wherein the method further comprises predicting effect of a particular value of a process parameter at a later maturity by including the particular value in the material balance equations, the kinetic growth model and/or the input values used by the machine learning model to predict specific transport rates at a further maturity. Based on the broadest reasonable interpretation, predicting the effect encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
Claim 22 recite the limitation - wherein the machine learning model has been trained to predict the specific transport rates of the one or more metabolites at a latest of two distinct maturities or a later maturity based at least in part on the values of one or more process conditions for the bioprocess at the two distinct maturities. This limitation specifies the machine learning model implemented in the judicial exception of claim 1. The refined machine learning indicated by this limitation still represents a judicial expectation.
Claim 23 recites the limitation - wherein determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model, or wherein the method comprises using one or more of the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity. Based on the broadest reasonable interpretation, determining a value encompasses equations and could practically be done by the human mind. This draws the limitation to a mathematical concept and a mental process, which classifies the limitation as an abstract idea.
These limitations recite concepts of determining/predicting/comparing information and values and applying equations that are so generically recited that they can be practically performed in the human mind as claimed, which falls under the “Mental processes” and “Mathematical concepts” grouping of abstract ideas. A mathematical concept need not be expressed in mathematical symbols, because words used in a claim operating on data to solve a problem can serve the same purpose as a formula (MPEP 2106.04(a)(2)). Additionally, both product claims and process claims may recite mental processes, which can include a claim that requires a computer (MPEP 2106.04(a)(2)). Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas. As such, claims 1, 4-16, and 18-23 recite an abstract idea (Step 2A, Prong 1: YES).
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). These judicial exceptions are not integrated into a practical application because the claims do not necessarily (see response to arguments) recite an additional element that reflects an improvement to technology (MPEP § 2106.04(d)(1)). Rather, the claims provide insignificant extra-solution activity (MPEP § 2106.05(g)) and provide mere instructions to apply a judicial exception (MPEP § 2106.05(f)). Specifically, the claims recite the following additional elements:
Claim 1 recites obtaining values of one or more process conditions including one or more process parameters, one or more metabolite concentrations and/or one or more biomass-related metrics for the bioprocess at one or more maturities; outputting a signal to a user if the comparing indicates that the bioprocess is not operating normally; sending a signal to one or more effector device(s) to implement the corrective action
Claim 4 recites wherein the one or more process conditions include one or more process parameters selected from dissolved oxygen, dissolved CO2, pH, temperature, osmolality, agitation speed, agitation power, headspace gas composition, a flow rates selected from feed rate, bleed rate, and harvest rate, feed medium composition and volume of the culture; wherein the one or more process conditions include one or more biomass related metrics selected from viable cell density, total cell density, cell viability, dead cell density, and lysed cell density; and/or wherein the one or more metabolite concentrations include the concentration of one or more metabolites in a cellular compartment, in the culture medium compartment, or in the cell culture as a whole.
Claim 5 recites wherein said values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities, or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of a further process condition at the one or more maturities, or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of two further process conditions at the one or more maturities.
Claim 7 recites implementing an artificial neural network (ANN), and a combination thereof.
Claim 9 recites wherein obtaining values of one or more process conditions at one or more maturities comprises obtaining values of the one or more process conditions at a plurality of maturities.
Claim 10 recites wherein the values of one or more process conditions used as input to the machine learning model are associated with a plurality of maturities that are separated from each other by a difference in maturity that is approximately equal to the difference in maturity between the values used to train the machine learning model.
Claim 15 recites at least one processor; and at least one non-transitory computer readable medium containing instructions; obtaining values of one or more process conditions including one or more process parameters, one or more metabolite concentrations and/or one or more biomass-related metrics for the bioprocess at one or more maturities; outputting a signal to a user if the comparing indicates that the bioprocess is not operating normally; sending a signal to one or more effector device(s) to implement the corrective action; wherein the system further comprises, in operable connection with the processor, one or more of: a user interface, wherein the instructions further cause the processor to provide, to the user interface for outputting to a user, one or more of: the value of the one or more specific transport rates or variables derived therefrom, result of the comparison step, and a signal indicating that the bioprocess has been determined to operate normally or to not operate normally; one or more biomass sensor(s); one or more metabolite sensor(s); one or more process condition sensors; and one or more effector device(s).
Claim 16 recites wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value, or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values(s) of at least one further process condition, or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values of at least two further process conditions or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value including the concentration of one or more metabolites for which specific transport rates are determined.
Claim 21 recites wherein the one or more values of metabolite concentrations include the concentration of one or more metabolites for which specific transport rates are determined.
There are no limitations that indicate that the claimed determining/predicting/ comparing information and values and applying equations require anything other than generic computing systems. As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. There is no indication that these steps are affected by the judicial exception in any way and thus do not integrate the recited judicial exception into a practical application. As such, claims 1, 4-16, and 18-23 are directed to an abstract idea (Step 2A, Prong 2: NO).
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). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite conventional additional elements that equate to mere instructions to apply the recited exception in a generic way or in a generic computing environment. The claims also recite conventional additional elements that represent insignificant extra-solution activities.
As discussed above, there are no additional limitations to indicate that the claimed determining/predicting/comparing information and values and applying equations require anything other than generic computer components in order to carry out the recited abstract idea in the claims. Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea or natural law eligible. MPEP 2106.05(f) discloses that mere instructions to apply the judicial exception cannot provide an inventive concept to the claims. As specified in MPEP 2106.05(g), extra-solution activities can be understood as incidental to the primary process or product that are merely a nominal or tangential addition to the claim. Insignificant extra-solution activities include mere data gathering, selecting a particular data source or type of data to be manipulated, and displaying information. Additionally, the specification indicates it is typical (i.e., routine) for a bioreactor to be associated with instrumentation that continuously measures process conditions and includes samples of the culture taken periodically (Page 1, Lines 13-18). The specification also indicates multivariate statistical models have become a popular and commercially available (i.e., routine) tool for identifying process conditions that are important (Page 1, Lines 24-29). Additionally, Kadlec et al. (2009, Computers and Chemical Engineering, Vol. 33: 795-814, cited in previous office action) also demonstrates that artificial neural networks are amongst the most popular (i.e. conventional) modeling techniques for estimating conditions within a bioreactor (Page 796, Column 1, Paragraph 2) and using the information as an indicator that enables the process to be adjusted (Page 803, Column 1, Paragraph 3; Page 805, Column 2, Paragraph 2).
The additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the claims do not amount to significantly more than the judicial exception itself (Step 2B: No). As such, Claims 1, 4-16, and 18-23 are not patent eligible.
Response to arguments
Applicant argues the newly added limitation, "outputting a signal to a user if the comparison step indicates that the bioprocess is not operating normally; and/or determining based on the comparing to implement a corrective action and sending a signal to one or more effector device(s) to implement the corrective action", integrates any such abstract idea into a practical application (Page 12, Paragraph 3 of remarks). The examiner agrees that the new limitation “implement the corrective action” added to the independent claims is an additional element that represents an improvement to technology (MPEP 2106.04(d)(1)). However, for this limitation to integrate the judicial exceptions into a practical application, it must be presented as an active step of the method that is required (not optional or only present in some embodiments). The newly added limitation, “implement the corrective action”, is currently incorporated as part of a limitation introduced by an “and/or” which is interpreted to indicate the improvement to technology is optional. For the limitation to integrate the judicial exception into a practical application, there cannot be an embodiment where that step does not occur. Outputting a signal to a user if the comparison step indicates that the bioprocess is not operating normally in not considered an improvement to technology under MPEP 2106.04(d)(1), but as a conventional additionally element that does not integrate the judicial exceptions as indicated by MPEP 2106.04(d). Therefore, the claims do not currently integrate the judicial exceptions into a practical application as recited and the rejection stands.
Claim Rejections - 35 USC § 102
The previously issued 35 USC 102 rejection is withdrawn in response to applicant arguments. Particularly, applicant argued that the transport rate required by the independent claims is not taught by Willson et al. as defined by the claim (Page 13, Paragraph 3 of the remarks). While the teachings of Willson et al. make the specific rate as claimed obvious, the examiner agrees that because the teachings incorporate obviousness (see 35 USC 103 Rejection Below), making a 102 rejection is inappropriate. An updated search did not result in new 102 art.
Claim Rejections - 35 USC § 103
Arguments concerning the previously issued 35 USC 103 rejections are not considered persuasive (see response to arguments below the rejection). The following rejection is reiterated and modified as has been necessitated by amendment. Additional evidentiary sections have been incorporated from the cited texts, besides the sections cited in the prior office action, that were included to further clarify and explain the teachings of the art that were already presented in the prior office action.
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 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 1, 4-9, 11, 13-16, and 18-23 are rejected under 35 U.S.C. 103 as being unpatentable over Willson et al. (US 20120107921 A1, cited in previous office action), in view of Berry et al. (2016, Biotechnology Progress, Vol. 32, No. 1: 224-234, cited in previous office action). Italicized text from reference art. Underlined text correspond to amendments.
Applicable claims include:
Claim 1. A method for monitoring a bioprocess comprising a cell culture in a bioreactor, the method comprising: (Claim 1.i) obtaining values of one or more process conditions including one or more process parameters, one or more metabolite concentrations and/or one or more biomass-related metrics for the bioprocess at one or more maturities; (Claim 1.ii) determining specific transport rates of one or more metabolites in the cell culture using the values obtained as input to a machine learning model trained to predict the specific transport rates of the one or more metabolites at a latest maturity of the one or more maturities or a later maturity based at least in part on the values of said one or more process conditions for the bioprocess at the one or more maturities, wherein the specific transport rate of a metabolite is a net amount of the metabolite transported between the cells and a culture medium, per cell and per unit of maturity; (Claim 1.iii) predicting one or more features of the bioprocess based at least in part on the determined specific transport rates, wherein predicting the one or more features of the bioprocess comprises:(Claim 1.iv) comparing the specific transport rates or values derived therefrom to one or more predetermined values; and determining, based on the comparing, whether the process is operating normally, wherein the process is considered to operate normally when the values of the specific transport rates or values derived therefrom are within a predetermined range of an average value for a corresponding variable in a set of reference bioprocesses; and outputting a signal to a user if the comparing indicates that the bioprocess is not operating normally; and/or determining, based on the comparing, to implement a corrective action and sending a signal to one or more effector device(s) to implement the corrective action.
Claim 4. The method of claim 1, wherein the one or more process conditions include one or more process parameters selected from dissolved oxygen, dissolved CO2, pH, temperature, osmolality, agitation speed, agitation power, headspace gas composition, a flow rates selected from feed rate, bleed rate, and harvest rate, feed medium composition and volume of the culture; wherein the one or more process conditions include one or more biomass related metrics selected from viable cell density, total cell density, cell viability, dead cell density, and lysed cell density; and/or wherein the one or more metabolite concentrations include the concentration of one or more metabolites in a cellular compartment, in the culture medium compartment, or in the cell culture as a whole.
Claim 5. The method of claim 1, wherein said values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities, or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of a further process condition at the one or more maturities, or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of two further process conditions at the one or more maturities.
Claim 6. The method of claim 1, wherein predicting one or more features of the bioprocess comprising predicting the value of one or more critical quality attributes (CQAs) of the bioprocess using a predictive model that has been trained to predict CQAs using a set of predictor variables comprising the one or more specific transport rates.
Claim 7. The method of claim 1, wherein the machine learning model is a regression model, or wherein the machine learning model is selected from a linear regression model, a random forest regressor, an artificial neural network (ANN), and a combination thereof; and or wherein the machine learning model comprises a plurality of machine learning models, wherein each machine learning model has been trained to predict the specific transport rates of an individually selected subset of the one or more metabolites.
Claim 8. The method of claim 1, wherein the machine learning model has been trained to jointly predict the specific transport rates of the one or more metabolites at a later maturity based at least in part on the values of one or more process conditions for the bioprocess at one or more preceding maturities.
Claim 9. The method of claim 1, (Claim 9.i) wherein obtaining values of one or more process conditions at one or more maturities comprises obtaining values of the one or more process conditions at a plurality of maturities; (Claim 9.ii) and the machine learning model has been trained to predict the specific transport rates of the one or more metabolites at a latest of the plurality of maturities or a later maturity based at least in part on the values of one or more process conditions for the bioprocess at the plurality of maturities.
Claim 11. The method of claim 1, wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by:using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations.
Claim 13. The method of claim 11, further comprising determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity.
Claim 14. The method of claim 13, further comprising predicting effect of a particular value of a process parameter at a later maturity by including the particular value in the material balance equations, a kinetic growth model and/or the input values used by the machine learning model to predict specific transport rates at a further maturity.
Claim 15. A system for monitoring and/or controlling a bioprocess, the system including: at least one processor; and at least one non-transitory computer readable medium containing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method for monitoring a bioprocess comprising a cell culture in a bioreactor, the method comprising: (Claim 15.i) obtaining values of one or more process conditions including one or more process parameters, one or more metabolite concentrations and/or one or more biomass-related metrics for the bioprocess at one or more maturities; (Claim 15.ii) determining specific transport rates of one or more metabolites in the cell culture using the values obtained as input to a machine learning model trained to predict the specific transport rates of the one or more metabolites at a latest maturity of the one or more maturities or a later maturity based at least in part on the values of said one or more process conditions for the bioprocess at the one or more maturities, wherein the specific transport rate of a metabolite is a net amount of the metabolite transported between the cells and a culture medium, per cell and per unit of maturity; (Claim 15.iii) predicting one or more features of the bioprocess based at least in part on the determined specific transport rates, wherein predicting one or more features of the bioprocess comprises:(Claim 15.iv) comparing the specific transport rates or values derived therefrom to one or more predetermined values; and determining, based on the comparing, whether the process is operating normally, wherein the process is considered to operate normally when the values of the specific transport rates or values derived therefrom are within a predetermined range of an average value for a corresponding variable in a set of reference bioprocesses; and outputting a signal to a user if the comparing indicates that the bioprocess is not operating normally; and/or determining, based on the comparing, to implement a corrective action and sending a signal to one or more effector device(s) to implement the corrective action, wherein the system further comprises, in operable connection with the processor, one or more of: a user interface, wherein the instructions further cause the processor to provide, to the user interface for outputting to a user, one or more of: the value of the one or more specific transport rates or variables derived therefrom, [[the] result of the comparison step, and a signal indicating that the bioprocess has been determined to operate normally or to not operate normally; one or more biomass sensor(s); one or more metabolite sensor(s); one or more process condition sensors; and one or more effector device(s).
Claim 16. The system of claim 15, wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value, or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values(s) of at least one further process condition, or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values of at least two further process conditions or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value including the concentration of one or more metabolites for which specific transport rates are determined.
Claim 18. The system of claim 15, wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity; or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations; or wherein predicting one or more features of the bioprocess comprises predicting the value of one or more critical quality attributes (CQAs) of the bioprocess using a predictive model that has been trained to predict CQAs using a set of predictor variables comprising the one or more specific transport rates.
Claim 19. (Currently amended) The system of claim 18, wherein the method further comprises (Claim 19.i) determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity, (Claim 19.ii) wherein determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model; or wherein the method further comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity, and using one or more of the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity.
Claim 20. The system of claim 19, wherein the method further comprises predicting effect of a particular value of a process parameter at a later maturity by including the particular value in the material balance equations, the kinetic growth model and/or the input values used by the machine learning model to predict specific transport rates at a further maturity.
Claim 21. The method of claim 5, wherein the one or more values of metabolite concentrations include the concentration of one or more metabolites for which specific transport rates are determined.
Claim 22. The method of claim 9, wherein the machine learning model has been trained to predict the specific transport rates of the one or more metabolites at a latest of two distinct maturities or a later maturity based at least in part on the values of one or more process conditions for the bioprocess at the two distinct maturities.
Claim 23. The method of claim 13, wherein determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model, or wherein the method comprises using one or more of the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity.
Regarding Claims 1 and 15, Willson et al. teach (Claim 1.i) obtaining values of a process condition including a process parameter, a metabolite concentration and/or a biomass-related metrics for the bioprocess at a maturity (Paragraph 0063: The sensed, modeled, or hand-measured environmental conditions (or environmental inputs) may include a variety of parameters. Examples of environmental conditions include one or more of incident light such as photosynthetically active radiation, air and or water temperature, algal culture pH, dissolved oxygen, dissolved carbon, oxygen gas concentration, carbon gas concentration, dissolved carbon dioxide, algal culture density, and culture constituent levels). Willson et al. teach (Claim 1.ii) determining specific transport rates of a metabolite in the cell culture using the values obtained as input to a machine learning model trained to predict the specific transport rates of the metabolite at a later maturity based on the values of said process condition for the bioprocess at the maturities, wherein the specific transport rate of a metabolite is a net amount of the metabolite transported between the cells and a culture medium, per cell and per unit of maturity (Paragraph 0054: The model can predict algae growth from the set of conditions and a set of input variable (e.g., carbon supply rate). Then, the determination unit can use the model of the photobioreactor to determine the set of input variables that will result in a desired algae growth (predicting growth rate relies on C transfer rate); Paragraph 0055: configured to calculate a harvest time at which a future growth of algae equals a predetermined threshold growth of algae (e.g., between two to four grams per liter, up to five grams per liter or more) (Considers transfer rate based on cell culture density, related to a metabolism at time/maturities); Paragraph 0056: result in desired, improved, and/or optimal biomass growth, oil production, energy consumption, efficiency of CO2 utilization, and/or other important metrics of operation (Modeling incorporates predicting specific transfer rates/metabolism because it is used to enhance output); Paragraph 0063: The sensed, modeled, or hand-measured environmental conditions (or environmental inputs) may include a variety of parameters. Examples of environmental conditions include, but are not limited to, dissolved oxygen, dissolved carbon, oxygen gas concentration, carbon gas concentration, dissolved carbon dioxide, algal culture density, and culture constituent levels (metabolites and conditions measured/predicted); Paragraph 0064: the environmental conditions can be predicted and/or estimated through models; Paragraph 0065: Control system can use these sensed, sampled and/or modeled values to perform calculations that determine the desired operation parameters (transport rate predicted used to optimize, which would include transfer rates as indicated above); Paragraph 0066: Liquid control system can receive a measurement of the culture density at some interval (e.g., every 15 seconds, every minute, every hour, etc) (cell density and multiple units of time/maturity considered); Paragraph 0067: Examples of regulation objectives include, but are not limited to, delivering air and/or carbon dioxide in order to achieve a desired pH and/or carbon concentration to achieve maximum algal growth and/or lipid production, maintaining dissolved oxygen in an acceptable range, maintaining adequate culture mixing to ensure culture health, optimal usage of available light and nutrients, maintaining flow of gases (predicting metabolite transfer rate for optimizing growth and production); Paragraph 0068: The performance objectives of gas control system can include maximizing carbon dioxide utilization (Carbon dioxide utilization is interpreted as metabolite transfer rate which incorporates density and maturity information (see response to arguments)); Paragraph 0069: Similar to FIG. 1, in FIG. 2 examples of the environmental conditions that can be monitored, hand-sampled, predicted, received from external database, and/or modeled by the control system may include one or more of, air and/or water temperature, algal culture, dissolved oxygen, dissolved carbon, algal culture density, and algal culture constituent levels (e.g., constituent composition) (levels of metabolites in media and culture and conditions including density monitored and predicted); Paragraph 0071: Liquid control system monitors or estimates the values of culture conditions, including culture density and culture constituent levels, in order to determine desired timing and rates of liquid flow into and out of the bioreactor (cell density and media composition measured and used in prediction for optimizing); Paragraph 0074: Feedforward module can use a set of actual measurements of environmental parameters, photobioreactor configuration parameters, operating setpoints, and/or photobioreactor plant measured operation parameters as inputs to, or in conjunction with, a simulation model that calculates the desired feedforward control outputs that will enable the operation parameters of the PBR plant to reach or approach desired values (variables input into a prediction model); Paragraph 0079: model-based control of a photobioreactor may be used for growth optimization and to maximize the values of all products. the model-based control may be used to improve growth rate, improve oil yield, minimize nutrient costs, minimize energy utilization, and/or minimize other operating costs. Models of the organism and/or the photobioreactor may be used to control the system in a feedback manner (metabolism rates predicted to optimize performance); Paragraph 0082: Model based control may be used to maximize the net values that can be gained for some or all products of a photobioreactor based on current or future estimates of other factors (change in net values including growth/utilization predicted). This could include, for example, the control of harvesting rates, media addition, inoculum addition, nutrient addition, carbon dioxide addition, sparging rates, temperature, basin water levels, pressures in the system, pumping rates, and/or other means to mix the system (modeling to predict system requirements through predicting metabolism); Paragraph 0083: learning algorithms may be used to calibrate the photobioreactor system models and/or controllers, in which feedback may be employed to adapt or correct the system model and/or controllers to improve system performance (the predicting incorporates machine learning); Paragraph 0085: Embodiments of the present invention permit replacing sensors with models, maximizing performance (utilization and production), predicting future events and dynamically compensating ahead of time, and adapting to changing conditions (modeling predicts future values of the processes which include transfer rates); Paragraph 0092: empirical models (e.g., fit from data) (models fit from the data indicate they are trained); Paragraph 0093: Dynamic models (used to predict the values) can use one or more memory elements while some static models may be implemented without any stored values. Some examples include tap-delayed feedforward neural networks (modeling includes neural networks); Paragraph 0095: Measurement of these state variables may be one method of validating, configuring, or calibrating the model (indicates the models are trained). The model can use inputs to predict the outputs of the plant; Paragraph 0096: A model used for FF control should accurately model the requirements of the algae, such as the nutrients and amount of CO2 For the feedback control used in some embodiments of the present invention (transport rates of metabolites predicted and used). Paragraph 0128: Table 1: kCO2 (amount of gas consumed/produced per mass of microalgae growth and may be in units other than grams gas per grams microalgae)-gCO2/(galgae/L) (metabolite transfer based on culture density for a time period (i.e. it is specific)); Paragraph 0129: the growth rate may be a function of available light photons, available nutrients, dissolved CO2, dissolved O2, temperature, and media recipe (e.g., media pH). All of these can both be included in the model parameters considered here and be modeled as separate terms (growth rate is a transfer rate of nutrients from media which is modeled); Paragraph 0130: The water chemistry subsystem models both the dissolved gases and nutrients available to the microalgae in the media (transfer of metabolites between media and culture modeled). The dissolved gases are a function of both the gases being delivered from an external source and the internal gases being consumed and generated by the microalgae (metabolite transfer rates modeled and predicted); Paragraph 0206: The operational model can take into account the current value of all of the byproducts, the projected values over the next block of time (e.g., a period of days), the projected growth (based on the dynamic model), and the associated operating costs of running the reactor to determine the most profitable time to harvest (values predicted at multiple maturities to benefit production)). The text from the art indicates specific transport rates for metabolites are determined from machine learning models at various time points. No explicit definition of maturity was found within the specification. Maturity can be interpreted as any unit of time or way to describe the completion of the process of the bioreactor. The Information available for the determining includes metabolites of the media, cells, usage rates, density of the cell culture, and multiple units of time/maturities. The rates are presents in terms of net amount between the cells and media per a given culture density which is equivalent to cell density for a given time period. Additionally, the information is calculated considers cell density and time. This is used to optimizes bioprocesses within the bioreactor to enhance production. Therefore the recited specific transfer rate, in terms of per cell and per unit of maturity, is obvious in addition to being implicitly taught by Willson et al. Willson et al. teach (Claim 1.iii) predicting a feature of the bioprocess based on the determined specific transport rates (Paragraph 0098: the main goals of the model are to maximize growth (and hence CO2 uptake) in the first stage and storage lipid accumulation in the second (i.e. growth and production are predicted from the predicted specific transport rates; also see above for predicting features of the bioprocess from carbon/nutrient utilization)) wherein predicting the one or more features of the bioprocess comprises: Willson et al. teach (Claim 1.iv) comparing the specific transport rates or values derived therefrom to a predetermined value; and determining, based on the comparing, whether the process is operating normally, wherein the process is considered to operate normally when the values of the specific transport rates or values derived therefrom are within a predetermined range of an average value for a corresponding variable in a set of reference bioprocesses; and outputting a signal to a user if the comparing indicates that the bioprocess is not operating normally (Paragraph 0055: a harvesting module that is configured to calculate a harvest time at which a future growth of algae equals a predetermined threshold growth of algae (the predetermined threshold indicates a comparison of growth rate which is a transfer rate of metabolites to a reference bioprocess that defines normal operation); The growth rate of the algae was also based from a directly metabolite transfer (Carbon uptake or nutrient change) (Page 4, Paragraph 0054: The model can predict algae growth from the set of conditions and a set of input variable (e.g., carbon Supply rate); Paragraph 0008: The feedback control unit can be configured to receive the sensing signal, compare the sensed condition with a setpoint condition, and generate a second control signal based on the comparison (generating a signal based on the comparison to a predetermined value (setpoint)); Paragraph 0012: The error generation module can be configured to generate an error signal when a difference between the sensed value and the expected value exceeds a predetermined threshold (see below for the display for the error signal) (comparison to the threshold indicates normal (non error state)); Paragraph 0074: Feedforward module can use a set of actual measurements of environmental parameters, photobioreactor configuration parameters, operating setpoints, and/or photobioreactor plant measured operation parameters as inputs to, or in conjunction with, a simulation model that calculates the desired feedforward control outputs that will enable the operation parameters of the PBR plant to reach or approach desired values (comparing values to determine normal based on predetermined values); Paragraph 0201: the amount of algae respirating compared to the amount doing photosynthesis is significant and more carbon dioxide addition may not be necessary at those times (optimizing based on determination of normal function); Paragraph 0254: In Stage 5, the model and actual outputs are compared. if actual value−measured value|>user defined threshold, then a fault or error is triggered (this makes it obvious is less than threshold, no error, which is interpreted as operating normally)). The limitation “determining, based on the comparing, to implement a corrective action and sending a signal to one or more effector device(s) to implement the corrective action” is considered optional because it is preceded by an “and/or”. Claim 15 recites the limitations of claims 1 directed to a system. Additionally, Willson et al. teach the method is performed by a computer (Paragraph 0256: Embodiments of the present invention may be provided as a computer program product that may include a machine-readable medium having stored thereon instructions that may be used to program a computer (or other electronic devices) to perform a process), which inherently contain program code, memory (including non-transitory computer readable medium), at least one processor, a display, and user interface. Additionally, Willson et al. teach a display (Paragraph 0062: a display device), user interface (Paragraph 0252: controller inputs are read in at interface), a biomass sensor (Paragraph 0139: dry mass from sensors), a metabolite sensor (Paragraph 0219: PBR Sensors are sensors that provide any measurements with information about the current state of the algae and surrounding media in the AGS. These measurements may include pH, dissolved carbon dioxide (aqueous), total dissolved carbon (TDC), dissolved oxygen, output (vent) carbon dioxide gas, output (vent) oxygen gas, temperature, pressure, flow rate, dry mass, optical density, cell count, chlorophyll mass, available nutrients), a process condition sensors (Paragraph 0210: dissolved O2 sensor), and an effector device (Paragraph 0054: the carbon supply unit can be associated with an actuator to control the carbon supply rate into the photobioreactor. Accordingly, the actuator may be configured to set the carbon supply rate based on the determined set of input variables can be adjusted).
Regarding Claim 4, Willson et al. teach a process conditions include one or more process parameters selected from dissolved oxygen, dissolved CO2, pH, temperature, osmolality, agitation speed, agitation power, headspace gas composition, a flow rates selected from feed rate, bleed rate, and harvest rate, feed medium composition and volume of the culture (Paragraph 0063: The sensed, modeled, or hand-measured environmental conditions (or environmental inputs) may include a variety of parameters. Examples of environmental conditions include one or more of incident light such as photosynthetically active radiation, air and or water temperature, algal culture pH, dissolved oxygen, dissolved carbon, oxygen gas concentration, carbon gas concentration, dissolved carbon dioxide, algal culture density, and culture constituent levels). The remainder of the limitation, “wherein the one or more process conditions include one or more biomass related metrics selected from viable cell density, total cell density, cell viability, dead cell density, and lysed cell density; and/or wherein the one or more metabolite concentrations include the concentration of one or more metabolites in a cellular compartment, in the culture medium compartment, or in the cell culture as a whole”, is interpreted as optional because of the “and/or”.
Regarding Claim 5, Willson et al. teach values of a process condition used to predict the specific transport rates of the metabolite include at least one metabolite concentration value at the maturity (Paragraph 0063: The sensed, modeled, or hand-measured environmental conditions (or environmental inputs) may include a variety of parameters. Examples of environmental conditions include one or more of incident light such as photosynthetically active radiation, air and or water temperature, algal culture pH, dissolved oxygen, dissolved carbon, oxygen gas concentration, carbon gas concentration, dissolved carbon dioxide, algal culture density, and culture constituent levels). These values were used to predict CO2 utilization (Paragraph 0068). The remainder of the limitation, “or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of a further process condition at the one or more maturities, or wherein the values of one or more process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value at the one or more maturities and at least the value(s) of two further process conditions at the one or more maturities”, is interpreted as optional because of the “or”s.
Regarding Claim 6, Willson et al. teach using a trained predictive model that has been trained using a set of predictor variables comprising the specific transport rate to predict features of the bioprocess of a bioreactor (Paragraph 0095: Measurement of these state variables (e.g. CO2 utilization) may be one method of validating, configuring, or calibrating the model; Also see regarding claim 1 for Willson teaching how the trained models generate predictions of features of the bioprocess including from using the transport rates). Additionally, Wilson et al. suggests incorporating quality of the product as part of prediction (Paragraph 0082: determine optimal operation of the photobioreactor to provide maximum value from all the products), as value is interpreted to be representative of quality. And Wilson et al. suggests using the predictive modeling for value (i.e. quality attribute) (Paragraph 0012: The modeling module can be configured to generate an expected value associated with the operating condition based on an algal growth model that relates growth of the algae in the photobioreactor to one or more environmental conditions and the operation condition).
Regarding Claim 7, Willson et al. teach the machine learning model is a regression model, or wherein the machine learning model is selected from a linear regression model, a random forest regressor, an artificial neural network (ANN), and a combination thereof; and or wherein the machine learning model comprises a plurality of machine learning models, wherein each machine learning model has been trained to predict the specific transport rates of an individually selected subset of the one or more metabolites (Paragraph 0068: The performance objectives of gas control system can include maximizing carbon dioxide utilization; Paragraph 0093: Dynamic models (used to predict the values) can use one or more memory elements while some static models may be implemented without any stored values. Some examples include a tap-delayed feedforward neural networks, recurrent neural networks, and echo state networks). This indicates the machine learning can be an artificial neural network.
Regarding Claim 8, Willson et al. teach the machine learning model has been trained to jointly predict the specific transport rates of the metabolite at a later maturity based at least in part on the values of a process condition for the bioprocess at a preceding maturities (Paragraph 0055: a harvesting module that is configured to calculate a harvest time at which a future growth of algae equals a predetermined threshold growth of algae; Paragraph 0054: The model can predict algae growth from the set of conditions and a set of input variable (e.g., carbon supply rate)).
Regarding Claim 9, Willson et al. teach (Claim 9.i) obtaining values of a process condition at a maturity comprises obtaining values of the process condition at a plurality of maturities (Paragraph 0180: The outputs of the sub models provide calibration parameters. The real-time portion receives these calibration parameters once at the inception of the program and receives updated environmental data continuously via the loop returning. Each time updated environmental data is received, in the next step these inputs are used by the growth model to calculate CO2 required). Willson et al. teach (Claim 9.ii) the machine learning model has been trained to predict the specific transport rates of the one or more metabolites at a latest of the plurality of maturities or a later maturity based at least in part on the values of one or more process conditions for the bioprocess at the plurality of maturities (Paragraph 0095: Measurement of these state variables may be one method of validating, configuring, or calibrating the model; Paragraph 0096: A model used for feed forward control should accurately model the requirements of the algae, such as the nutrients and amount of CO2).
Regarding Claim 11, Willson et al. teach predicting a feature of the bioprocess comprises determining the value of a variable derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding metabolite at the later maturity (Paragraph 0180: The outputs of the sub models provide calibration parameters. The real-time portion receives these calibration parameters once at the inception of the program and receives updated environmental data continuously via the loop returning. Each time updated environmental data is received, in the next step these inputs are used by the growth model to calculate CO2 required). The remainder of the limitation, “or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations”, is interpreted as optional because of the “or”.
Regarding Claim 13, Willson et al. teach determining the value of a variable derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding metabolite at the later maturity, and using said concentration to determine the value of a biomass related metric at the later maturity (Paragraph 0225: Based on predicted photosynthetically active radiation, a CO2 prediction is calculated by the algal growth model (i.e., biomass)).
Regarding Claims 14 and 20, Willson et al. teach predicting effect of a particular value of a process parameter at a later maturity by including the particular value in the material balance equations, a kinetic growth model and/or the input values used by the machine learning model to predict specific transport rates at a further maturity (Paragraph 241: The dynamic process model employs signals from the environmental sensors and photobioreactors to simulate the relevant dynamics of the processes occurring within the photobioreactor that affect the parameters to be controlled. Relevant dynamics include light delivery to the active culture, gas transfer, algal photosynthesis, algal metabolism and nutrient uptake, algal culture hydrochemistry, and/or thermal behavior. The predictive feedforward controllers determine desired actuator behavior based on estimates of system parameters delivered by the dynamic process model). The predictive models include machine learning models (see regarding claim 7 of the current rejection). Claim 20 recites the limitations of claim 14 directed to a system.
Regrading Claim 16, Willson et al. teach wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value (Paragraph 0063: The sensed, modeled, or hand-measured environmental conditions (or environmental inputs) may include a variety of parameters. Examples of environmental conditions include one or more of incident light such as photosynthetically active radiation, air and or water temperature, algal culture pH, dissolved oxygen, dissolved carbon, oxygen gas concentration, carbon gas concentration, dissolved carbon dioxide, algal culture density, and culture constituent levels) (equivalent limitation to claim 5). These values were used to predict CO2 utilization (Paragraph 0068). The remainder of the limitation, “or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values(s) of at least one further process condition, or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value and values of at least two further process conditions or wherein the one or more values of process conditions used to predict the specific transport rates of the one or more metabolites include at least one metabolite concentration value including the concentration of one or more metabolites for which specific transport rates are determined”, is interpreted to be optional due to the “or”s.
Regarding Claim 18, Willson et al. teach predicting a feature of the bioprocess comprises determining the value of a variable derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding metabolite at the later maturity (Paragraph 0180: The outputs of the sub models provide calibration parameters. The real-time portion receives these calibration parameters once at the inception of the program and receives updated environmental data continuously via the loop returning. Each time updated environmental data is received, in the next step these inputs are used by the growth model to calculate CO2 required) (equivalent limitation to claim 11). The remainder of the limitation “or wherein predicting one or more features of the bioprocess comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, wherein determining the concentration of the corresponding one or more metabolites at the later maturity comprises solving respective material balance equations; or wherein predicting one or more features of the bioprocess comprises predicting the value of one or more critical quality attributes (CQAs) of the bioprocess using a predictive model that has been trained to predict CQAs using a set of predictor variables comprising the one or more specific transport rates”, is interpreted as optional because of the “or”s.
Regarding Claim 19, Willson et al. teach (Claim 19.i) determining the value of a variables derived from the specific transport rates by using the specific transport rates to determine the concentration of the corresponding metabolite at the later maturity, and using a said concentration to determine the value of a biomass related metric at the later maturity (Paragraph 0225: Based on predicted photosynthetically active radiation, a CO2 prediction is calculated by the algal growth model (i.e., biomass)) (equivalent limitation to claim 13). Willson et al. teach (Claim 19.ii) wherein determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model; (Paragraph 0085: An algal growth model captures algal growth dynamics inside a closed reactor, which is used to dynamically compensate for changing conditions; Paragraph 0098: the main goals of the model are to maximize growth (and hence CO2 uptake); Paragraph 0121: As microalgae grow, they consume carbon, which they get from CO2 and other nutrients from their surroundings and release O2. In general, microalgae biomass is 50% carbon by dry weight. A mole of CO2 has a mass of 44 grams and 12 of these grams come from carbon. Based on these premises, the expression that 1 gram of microalgae can fix 1.83 grams of CO2 may be derived as follows). The indicates that biomass is predicted with a growth model. The remainder of the limitation, “or wherein the method further comprises determining the value of one or more variables derived from the specific transport rates by: using the specific transport rates to determine the concentration of the corresponding one or more metabolites at the later maturity, and using one of more of said concentrations to determine the value of a biomass related metric at the later maturity, and using one or more of the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity”, is interpreted at optional because of the “or”.
Regarding Claim 21, Willson et al. teach the value of metabolite concentrations include the concentration of a metabolite for which specific transport rates are determined. As indicated in Willson et al. teachings of claim 1, CO2 is metabolite that is measured and the rate of CO2 utilization is predicted. Additionally, it would be obvious to measure the concentration of the metabolite used as input for the machine learning model that predicted the transfer rate of that metabolite (Paragraph 0009: The model of the photobioreactor can predict algae growth from the set of conditions and a set of input variables that include carbon supply rate (carbon is utilized (i.e. transferred) for growth)).
Regarding Claim 22, Willson et al. teach the machine learning model has been trained to predict the specific transport rates of the metabolite at a latest of two distinct maturities or a later maturity based on the values of a process condition for the bioprocess at the two distinct maturities (Paragraph 0219: PBR Sensors are sensors that provide any measurements with information about the current state of the algae and surrounding media in the AGS). Measurements may be frequent (e.g., multiple measurements per second) to less frequent (one a day to once a week), and may also be taken more frequently or less frequently than the examples given). This indicates measurements, which are used to train machine learning models (see above), are taken at multiple time points. See above for Willson et al. teachings using measurements to predict transport rates with a trained model. Additionally, it is obvious to repeat steps of the method, such as making an additional measurement after taken a measurement one time at a different time for predicting/training because it will increase the amount/breath of the training data (model fitting) which leads to enhanced model performance.
Regarding Claim 23, Willson et al. teach determining the value of a biomass related metric at the later maturity comprises solving a kinetic growth model (Paragraph 0085: An algal growth model captures algal growth dynamics inside a closed reactor, which is used to dynamically compensate for changing conditions; Paragraph 0098: the main goals of the model are to maximize growth (and hence CO2 uptake); Paragraph 0121: As microalgae grow, they consume carbon, which they get from CO2 and other nutrients from their surroundings and release O2. In general, microalgae biomass is 50% carbon by dry weight. A mole of CO2 has a mass of 44 grams and 12 of these grams come from carbon. Based on these premises, the expression that 1 gram of microalgae can fix 1.83 grams of CO2 may be derived as follows). The indicates that biomass is predicted with a growth model. The remainder of the limitation, “or wherein the method comprises using the said metabolite concentrations and/or biomass related metric values as inputs to the machine learning model to predict specific transport rates at a further maturity”, is interpreted as optional because of the “or”s.
Willson et al. does not explicitly teach predicting the value of a critical quality attributes (CQAs) of the bioprocess using a predictive model (Claim 6)
Regarding Claim 6, Berry et al. teach predicting critical quality attributes (CQAs) of the bioprocess using a predictive model (Page 229, Column 2, Paragraph 3: The percent of glycated antibody was determined by high resolution quadrupole time of flight mass spectrometry). Percent glycation was an estimate of product quality and a CQA (Page 225, Column 1, Paragraph 1: The concern that percent glycation could be considered a CQA for future programs motivated the development of a quickly applied yet controlled mitigation strategy). This indicates Percent glycation (an estimate of product quality and a CQA) is measured and related to glucose metabolism, which is determined by a predictive model (Page 229, Column 1, Paragraph 1: Using a glucose predictive PLS model, DataLink generated glucose process values). Therefore, this information suggests predicting future CQAs given a transport rate, which is taught by Wilson et al. As evidenced by Berry et al. teaching the importance of CQA for optimizing bioreactor systems (Page 232, Column 2, Paragraph 4: Changes to metabolite feeding and control can have significant effects on process performance and product quality attributes), which make it obvious to combine with Wilson who teaches transport rate as input to a model to make predictions for optimizing bioreactors.
It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to combine Berry et al. with Willson et al. Both references consider product quality. Willson et al. suggests that attributes of product quality, such as product value, are important considerations for process model optimization (Page 6, Paragraph 0077: A controller according to such embodiments maintains a constant culture density, or follows a culture density command trajectory. Such a command may be based on many factors including product pricing). Berry et al. teaches the specific utilization of product optimizing process models to consider quality, through the critical quality attribute (CQA) of percent glycation, which can result in the loss of product function (Page 225, Column 1, Paragraph 2). Berry et al. teaches the importance/utility of CQAs for optimizing processes within bioreactors (Page 224, Column 2, Paragraph 1: (CQAs) of a product within their defined range ultimately ensuring desired product quality and safety) and their relation to metabolic processes within bioreactors (Page 232, Column 2, Paragraph 4: Changes to metabolite feeding and control can have significant effects on process performance and product quality attributes; By introducing this control scheme quickly and early, process changes to accommodate it can be incorporated into process development) which is a major focus of Willson et al (see above rejection). Furthermore, one of ordinary skill in the art would predict that the methods could be readily combined with a reasonable expectation of success because both are within the same technical field – modeling/optimizing/predicting cellular processes within bioreactors.
Claims 1, 4-5, 7-11, 13-16, and 18-23 are rejected under 35 U.S.C. 103 as being unpatentable over Willson et al., as applied to claims 1, 4-9, 11, 13-16, and 18-23 above, in view of Rio-Chanona et al. (2018, AIChE Journal, Vol. 65, No. 3: 915-923, cited in previous office action). Italicized text from reference art. Underlined text correspond to amendments.
Applicable claims include:
Claims 1, 4-5, 7-9, 11, 13-16, and 18-23 are provided above.
Claim 10. The method of claim 1, wherein the values of one or more process conditions used as input to the machine learning model are associated with a plurality of maturities that are separated from each other by a difference in maturity that is approximately equal to the difference in maturity between the values used to train the machine learning model.
Regrading Claims 1, 4-5, 7-9, 11, 13-16, and 18-23, these limitations are taught by Willson et al. as indicated above.
Willson et al. does not explicitly teach values of a process condition input to a machine learning model are associated with maturities that are separated from each other by a difference approximately equal to the difference in maturity between the values used to train the machine learning model (Claim 10).
Regarding Claim 10, Rio-Chanona et al. teach the values of a process condition used as input to the machine learning model are associated with maturities that are separated from each other by a difference in maturit approximately equal to the difference in maturity between the values used to train the machine learning model. The machine learning models of Rio-Chanona et al. were trained on data from bioreactors run in batches to predict the biomass of a bioreactor that was run in batches (a batch in this case is interpreted as a complete growth to harvest cycle and a unit of maturity; therefore the maturities used in training and predicting were identical (i.e. complete batches)) (Page 918, Column 1, Paragraph 4: Upon completion of the integrated models, they (the scenarios) were applied to a batch operation; Page 918, Column 2, Paragraph 2: For each scenario, approximately 9000 data points were generated, resulting in 360,000 data points for the surrogate model construction (i.e., the training data represented batch runs); Page 920, Column 1, Paragraph 4: (The trained model) was applied to predict untested behaviors of the system throughout a large solution space of design variables to seek the optimal solution for further PBR design and batch operation).
It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to combine Rio-Chanona et al. with Willson et al. Willson et al. teach the implementation of machine learning models (see regarding claim 7 of the 103 rejection) but does not specify the parameters of a training dataset used to train the models. Rio-Chanona et al. teaches specific details of the training dataset for the machine learning models that would be applicable to the machine learning models used in Willson et al. Additionally, Rio-Chanona et al. teaches their methods are highly efficient and robust for modeling related to optimizing processes within bioreactors (Page 922, Column 2, Paragraphs 1-2: By implementing the robust hybrid stochastic optimization algorithm, optimal solutions with respect to different indices were successfully identified; from this detailed analysis, the current framework was demonstrated to combine great predictive capability with high computational efficiency, indicating its applicability for general biosystems modeling and optimization), which was a major focus of Willson et al. Furthermore, one of ordinary skill in the art would predict that the methods could be readily combined with a reasonable expectation of success because both are within the same technical field – utilizing machine learning methods to model cellular processes within bioreactors.
Claims 1, 4-5, 7-9, 11-16, and 18-23 are rejected under 35 U.S.C. 103 as being unpatentable over Willson et al., as applied to claims 1, 4-9, 11, 13-16, and 18-23 above, in view of Dorka (2007, Thesis, University of Waterloo: 1-185, cited in previous office action). Italicized text from reference art. Underlined text correspond to amendments.
Applicable claims include:
Claims 1, 4-5, 7-9, 11, 13-16, and 18-23 are provided above.
Claim 12. The method of claim 11, wherein determining the concentration of a metabolite i (mi) at maturity k, where k is the maturity associated with the predicted specific transport rates, comprises integrating any of equations (4), (4a)-(4d) and (28) between a preceding maturity at which mi is known and maturity k
PNG
media_image1.png
381
692
media_image1.png
Greyscale
where δm,i is the specific transport rate of metabolite i by the cells in the culture, mi is the concentration of metabolite i in the bioreactor, pmi is a pseudoconcentration of metabolite i in the bioreactor, V is a volume of the cell culture in the bioreactor, mF,i is the concentration of metabolite i in a feed flow, mH,i is the concentration of metabolite i in a harvest flow, mB,i is the concentration of metabolite i in a bleed flow, xv is a viable cell density in the bioreactor, and FF, FH and FB are volumetric feed, harvest and bleed flow rates, ε is a parameter and fML.i(u, m, s) represents the predictions from the machine learning model.
Regrading Claims 1, 4-5, 7-9, 11, 13-16, and 18-23, these limitations are taught by Willson et al. as indicated above.
Willson et al. does not explicitly teach one of the equations indicated to calculate change in a metabolite over time (Claim 12).
Regarding Claim 12, Dorka teaches determining the concentration of a metabolite i (mi) at maturity k, where k is the maturity associated with the predicted specific transport rates, comprises integrating any of equations (4), (4a)-(4d) and (28) between a preceding maturity at which mi is known and maturity k. Dorka teaches Equation 4.1 (Page 63, Paragraph 1, see image below), which is interpreted as equivalent to equation 4c, to calculate the change in the concentration of a metabolite over time based on the transportation rate and viable cell concentration at a maturity.
PNG
media_image2.png
145
719
media_image2.png
Greyscale
Equation 4.1 of Dorka contains an additional variable for the culture time (t), which is present on both sides of the equation, indicating (t) will drop out for batch operations leaving an identical equation to 4c of the instant application. For additional clarification, Equation 4c is interpreted based on the defined variables as a change in a metabolite overtime equals a specific transport rate of metabolite times a viable cell density. The cited equation from Dorka is interpreted as a change in intracellular and extracellular metabolite concentrations overtime equals uptake/production rate of substrates/metabolites times viable cell concentration. Because change in metabolite overtime is equivalent to change in intracellular and extracellular metabolite concentrations, specific transport rate of metabolite is equivalent to uptake/production rate of substrates/metabolites, and viable cell density is equivalent to viable cell concentration, the equations are interpreted as equivalent.
It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to combine the methods of Dorka with Willson et al.
Willson et al. teach modeling cellular metabolism (Page 20, Paragraph 0241: The dynamic process model employs signals from the environmental sensors and photobioreactors to simulate the relevant dynamics of the processes occurring within the photobioreactor that affect the parameters to be controlled. Relevant dynamics include light delivery to the active culture, gas transfer, algal photosynthesis, algal metabolism and nutrient uptake) but does not specify a specific equation to calculate the changes in metabolite concentrations. Dorka teaches a specific equation for calculating changes in a metabolite concentration over time, which is applicable to the metabolic modeling suggested by Willson et al. Additionally, Dorka teaches the methods of modeling cellular processes presented represent an improvement over previous modeling methods (Page 117, Paragraph 1: The model is an improvement over pre-existing models of similar nature). Furthermore, one of ordinary skill in the art would predict that the methods could be readily combined with a reasonable expectation of success because both are within the same technical field –modeling cellular processes, including metabolism, within bioreactors.
Response to Arguments
Applicant Argues in the 102 (covering here because Willson is relied on in 103) section that the claim has been amended to expressly define "specific transport rates of a metabolite" and Wilson simply fails to describe any machine learning model that predicts specific transport rates of metabolites based on process conditions (Page 13, Paragraph 2 of remarks). The examiner agrees that Wilson does not explicitly teach the transport rate as claimed in an anticipatory fashion in terms of presented as the rate per cell per maturity. However, as explained in the expanded and updated 103 section demonstrating the teachings of Wilson et al., the recited limitations are obvious over the evidence provided. This includes using machine leaning models to predict specific transport rates (Paragraph 0069: Similar to FIG. 1, in FIG. 2 examples of the environmental conditions that can be monitored, hand-sampled, predicted, received from external database, and/or modeled by the control system may include one or more of, air and/or water temperature, algal culture, dissolved oxygen, dissolved carbon, algal culture density, and algal culture constituent levels (e.g., constituent composition); Paragraph 0082: Model based control may be used to maximize the net values that can be gained for some or all products of a photobioreactor based on current or future estimates of other factors. This could include, for example, the control of harvesting rates, media addition, inoculum addition, nutrient addition, carbon dioxide addition; Paragraph 0083: learning algorithms may be used to calibrate the photobioreactor system models and/or controllers, in which feedback may be employed to adapt or correct the system model and/or controllers to improve system performance; Paragraph 0085: Embodiments of the present invention permit replacing sensors with models, maximizing performance (utilization and production), predicting future events and dynamically compensating ahead of time, and adapting to changing conditions; Paragraph 0096: A model used for FF control should accurately model the requirements of the algae, such as the nutrients and amount of CO2; Paragraph 0128: Table 1: kCO2 (amount of gas consumed/produced per mass of microalgae growth and may be in units other than grams gas per grams microalgae)-gCO2/(galgae/L; Paragraph 0206: The operational model can take into account the current value of all of the byproducts, the projected values over the next block of time (e.g., a period of days)) (See rejection for more evidence). Additionally, as the cited text indicates, the transport rates or metabolites are calculated at culture densities for units of time. Therefore, while is the specific transport rate is not explicitly taught in the format indicated, it is obvious over the methods of Willson et al.
Applicant also argues Berry cannot and does not remedy the deficiencies of Wilson for Claim 6 (Predicting CQAs, Page 14, Paragraph 3 of the remarks). The examiner disagrees. As indicated in the rejection of claim 6, which has been expanded with additional evidence of the original teachings, Berry teaches the importance and utilization CQAs for optimizing processes within bioreactors relates it to the prediction of metalbillies. Willson is concerned with optimizing the functioning of bioreactors through predicting cellular processes, such as metabolic transfer rates (see above). Additional teachings on the motivations are presented in the rejection above. Therefore the combination of the two would motivate one of ordinary skill in the art to utilize CQA within process predictions of Wilson et al., as is deemed proper by MPEP 2143. Additionally, these pieces of art are analogous under MPEP 2141.01(a) because the references are from the same field of endeavor and reasonably pertinent to the same problem.
Applicant also argues Rio-Chanona cannot and does not remedy the deficiencies of Wilson as set out above because the model of Rio-Chanona is a completely different model from the one claimed for claim 10 (Page 14, Paragraph 5 of the remarks). The examiner disagrees. As indicated in rejection of claim which has been expanded with additional evidence of the original teachings the machine learning models of Rio-Chanona et al. were trained on data from bioreactors run in batches to predict the biomass of a bioreactor that was run in batches (i.e. the training and testing maturities were the same). Willson is concerned with optimizing the functioning of bioreactors thorough predicting cellular processes, such as growth rates and the accumulation biomass (see above). Additional teachings on the motivations are presented in the rejection above. Therefore, the combination of the two would motivate one of ordinary skill in the art to utilize the training methodologies for the learning models of Willson et al., as is deemed proper by MPEP 2143. Additionally, these pieces of art are analogous under MPEP 2141.01(a) because the references are from the same field of endeavor and reasonably pertinent to the same problem.
Applicant also argues Dorka cannot and does not remedy the deficiencies of Wilson for claim 12 because the document does not appear to disclose a machine learning model as claimed and the equation is not even the same context as in the present disclosure (Page 15, Paragraph 2 of the remarks). The examiner disagrees. As indicated in rejection which has been expanded with additional evidence of the original teachings Dorka is only utilized to provide an equation to determine the concentration of a metabolite at a time that is equivalent to equation 4c (see the rejection for how the equations are equivalent), which is what the claim is interpreted requesting. The cited equation from Dorka is interpreted as a change in intracellular and extracellular metabolite concentrations overtime equals uptake/production rate of substrates/metabolites times viable cell concentration. Willson is concerned with optimizing the functioning of bioreactors thorough predicting cellular processes, and considers all the variables of equation of Dorka with machine learning models (see above). Additional teachings on the motivations are presented in the rejection above. Therefore, the arts are not only related, but the combination of the two would motivate one of ordinary skill in the art to utilize the equation in the predictive modeling of Willson et al., as is deemed proper by MPEP 2143. Additionally, these pieces of art are analogous under MPEP 2141.01(a) because the references are from the same field of endeavor and reasonably pertinent to the same problem.
Applicant’s arguments are therefore not considered to be persuasive and the updated rejection stands.
Double Patenting
Arguments associated with double patenting over U.S. Patent 11542564 were found to be persuasive. Particularly, U.S. Patent 11542564 does not recite features of the amended independent claims including comparing the predicted value to a predetermined value to establish normal function. Arguments associated with double patenting over Application 18027045 were found to be persuasive. Particularly, US Application 18027045 does not recite features of the amended independent claims including determining to implement a corrective action and sending a signal to the effector device to implement the corrective action. No argument was found associated with double patenting over US Application 18574469. However, this rejection is dropped because US Application 18574469 does not recite features of the amended independent claims including comparing transport rates to a predetermined values to determine normal function.
Conclusion
No Claims are allowed.
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BLAKE H ELKINS whose telephone number is (571)272-2649. The examiner can normally be reached Monday-Friday 8-5PM.
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.
/B.H.E./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687
Prosecution Insights