DETAILED ACTION
Applicant’s response, filed Jan 30 2026, has been fully considered. Rejections and/or objections not reiterated from previous Office Actions are hereby withdrawn. 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 .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Status
Claims 1-8, 10, 13-14, 16, 20-24, 26, 29, 32, 52, and 54-57 are pending.
Claim 52 is withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a non-elected invention, as described above.
Claims 9, 11-12, 15, 17-19, 25, 27-28, 30-31, 33-51, and 53 are canceled.
Claims 54-57 are newly added.
Claims 1-8, 10, 13-14, 16, 20-24, 26, 29, 32, and 54-57 are rejected.
Priority
The instant Application claims domestic benefit to US provisional applications 62/749,359, filed Oct 23 2018, 62/833,044, filed Apr 12 2019, and 62/864,565, filed Jun 21 2019.
Applicant's claim for the benefit of a prior-filed application, PCT/US2019/057513, filed Oct 23 2019, is acknowledged.
However, the priority documents do not provide support for the new limitations of “A spectroscopy system… comprising: one or more spectroscopy probes…; one or more memories…; and one or more processors configured to… execute the control unit to control at least one parameter of the biopharmaceutical process using model predictive controls (MPC)” in claim 20 and “A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors for monitoring and/or controlling a biopharmaceutical process, the instructions comprising… controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound” in claim 54, similar to the reasons set forth below in the 35 USC 112(a) rejection.
Accordingly, each of claims 1-8, 10, 13-14, and 16, are afforded the effective filing date of Oct 23 2018, and claims 20-24, 26, 29, 32, and 54-57 are afforded the effective filing date of Apr 12 2021.
Claim Interpretation
The interpretation in the previous Office Action of “a control unit that implements model predictive controls (MPC) to control at least one parameter of the biopharmaceutical process” in claims 1 and 20 as invoking 35 USC 112(f) is withdrawn in view of the amendments submitted herein.
Claim Rejections- 35 USC § 112
The outstanding rejections to the claims are withdrawn in view of the amendments submitted herein.
35 USC § 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 20-24, 26, 29, 32, and 54-57 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. These rejections pertain to new matter. The rejection is newly stated and is necessitated by claim amendment.
Claim 20 recites “A spectroscopy system… comprising: one or more spectroscopy probes…; one or more memories…; and one or more processors configured to… execute the control unit to control at least one parameter of the biopharmaceutical process using model predictive controls (MPC)”. Claim 54 recites “A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors for monitoring and/or controlling a biopharmaceutical process, the instructions comprising… controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound”. The specification as published provides support for the system and non-transitory computer-readable storage medium as claimed at least at [0022-0032] and FIG. 1, which describes a computer and instructions stored therein in communication with a Raman Analyzer. The specification as published also provides support for such a system to be in communication with a glucose pump at least at [0047] and FIG. 2, which describes a structure necessary for controlling at least one parameter of the biopharmaceutical process. However, there is not support within the specification, nor has Applicant provided such support, for either a spectroscopy system comprising only probes, memory, and processors or a non-transitory computer-readable storage medium configured to store instructions executable by one or more processors controlling at least one parameter of the biopharmaceutical process using model predictive controls (MPC) without additional structural requirements. Therefore the limitations introduce new matter. Claims 21-24, 26, 29, 32, and 55-57 are rejected based on their dependency from claims 20 and 54.
35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 20-24, 26, 29, 32, and 54-57 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, regards as the invention. The instant rejection is newly stated and is necessitated by claim amendment.
Claim 20 recites “A spectroscopy system… comprising: one or more spectroscopy probes…; one or more memories…; and one or more processors configured to… execute the control unit to control at least one parameter of the biopharmaceutical process using a model predictive controls (MPC)”. Claim 54 recites “A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors for monitoring and/or controlling a biopharmaceutical process, the instructions comprising… controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound”. The interpretation of the limitations directed to “execute the control unit to control” in claim 20 and “controlling” in claim 54 encompass physical steps which require the use of a specific hardware for controlling biopharmaceutical processes, which is beyond the scope of a system with only probes, memory, and a processor or a non-transitory computer-readable storage medium configured to store instructions executable by one or more processors (see the specification as published at least at [0047]). The claims therefore are interpreted as functional limitations because they recite the act of controlling a biopharmaceutical process, rather than by the structure required (see MPEP 2173.05(g)). The functional limitations fail to provide a clear-cut indication of the scope of the subject matter embraced by the claim, and are therefore considered to be indefinite. The rejection may be overcome by amending the claims to include a synthesizer for performing these operations. Claims 21-24, 26, 29, 32, and 55-57 are rejected based on their dependency from claims 20 and 54.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 20-24, 26, 29, 32, and 54-57 are rejected under 35 U.S.C. 101 because the claimed invention is directed to one or more judicial exceptions without significantly more. Any newly recited portions are necessitated by claim amendment.
MPEP 2106 organizes judicial exception analysis into Steps 1, 2A (Prongs One and Two) and 2B as follows below. MPEP 2106 and the following USPTO website provide further explanation and case law citations: uspto.gov/patent/laws-and-regulations/examination-policy/examination-guidance-and-training-materials.
Framework with which to Evaluate Subject Matter Eligibility:
Step 1: Are the claims directed to a process, machine, manufacture, or composition of matter;
Step 2A, Prong One: Do the claims recite a judicially recognized exception, i.e. a law of nature, a natural phenomenon, or an abstract idea;
Step 2A, Prong Two: If the claims recite a judicial exception under Prong One, then is the judicial exception integrated into a practical application (Prong Two); and
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept.
Framework Analysis as Pertains to the Instant Claims:
Step 1
With respect to Step 1: yes, the claims are directed to a system and a non-transitory computer-readable storage medium, i.e., a process, machine, or manufacture within the above 101 categories [Step 1: YES; See MPEP § 2106.03].
Step 2A, Prong One
With respect to Step 2A, Prong One, the claims recite judicial exceptions in the form of abstract ideas. The MPEP at 2106.04(a)(2) further explains that abstract ideas are defined as:
mathematical concepts (mathematical formulas or equations, mathematical relationships and mathematical calculations);
certain methods of organizing human activity (fundamental economic practices or principles, managing personal behavior or relationships or interactions between people); and/or
mental processes (procedures for observing, evaluating, analyzing/ judging and organizing information).
With respect to the instant claims, under the Step 2A, Prong One evaluation, the claims are found to recite abstract ideas that fall into the grouping of mental processes (in particular procedures for observing, analyzing and organizing information) and mathematical concepts (in particular mathematical relationships and formulas) are as follows:
Independent claims 20 and 54: determine… a query point associated with scanning of the biopharmaceutical process by a spectroscopy system;
query…an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes selecting as training data, from among the plurality of observation data sets, observation data sets that satisfy one or more relevancy criteria with respect to the query point;
calibrate… using the selected training data, a local model specific to the biopharmaceutical process, the local model being a Gaussian process machine-learning model trained to predict analytical measurements based on spectral data inputs;
predict… an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process; and
determine… a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process.
Dependent claim 32: cause… (i) spectral data that the spectroscopy system generated when the actual analytical measurement was obtained, and (ii) the actual analytical measurement of the biopharmaceutical process, to be added to the observation database; and
determine… that at least the predicted analytical measurement does not satisfy one or more model performance criteria, wherein determining that at least the predicted analytical measurement does not satisfy the one or more model performance criteria includes generating a credibility interval associated with the predicted analytical measurement and comparing the credibility interval to a pre-defined threshold.
Dependent claims 22-24, 26, 29, and 55-57 recite further steps that limit the judicial exceptions in independent claim 20 and, as such, also are directed to those abstract ideas. For example, claims 22-24 and 55-57 further limit the steps of determining a query point and selecting training data recited in claims 20 and 54; claim 26 further limits the local model of claim 20; and claim 29 further limits the predicted analytical measurement recited in claim 20.
The abstract ideas recited in the claims are evaluated under the Broadest Reasonable Interpretation (BRI) and determined to each cover performance either in the mind and/or by mathematical operation because the method only requires a user to manually predict an analytical measurement. Without further detail as to the methodology involved in “determining”, “querying”, “calibrating”, “predicting”, “adding”, and “determining”, under the BRI, one may simply, for example, use pen and paper to determine a query point, query a database to select appropriate training data, calibrate a local model with the training data, predict an analytical measurement using the local model, adding data to a database, and determining that the predicted analytical measurement does not satisfy model performance criteria. Those steps directed to calibrating a local model, the local model being a Gaussian process machine-learning model trained, predicting using the local model, and determining a confidence indicator using the local model require mathematical techniques as the only supported embodiments, as is disclosed in the specification at: [0050-0057; 0059].
Therefore, claims 20 and 54 and those claims dependent therefrom recite an abstract idea [Step 2A, Prong 1: YES; See MPEP § 2106.04].
Step 2A, Prong Two
Because the claims do recite judicial exceptions, direction under Step 2A, Prong Two, provides that the claims must be examined further to determine whether they integrate the judicial exceptions into a practical application (MPEP 2106.04(d)). A claim can be said to integrate a judicial exception into a practical application when it applies, relies on, or uses the judicial exception in a manner that imposes a meaningful limit on the judicial exception. This is performed by analyzing the additional elements of the claim to determine if the judicial exceptions are integrated into a practical application (MPEP 2106.04(d).I.; MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the judicial exceptions, the claim is said to fail to integrate the judicial exceptions into a practical application (MPEP 2106.04(d).III).
Additional elements, Step 2A, Prong Two
With respect to the instant recitations, the claims recite the following additional elements:
Independent claim 20: control, based at least in part on the predicted analytical measurement of the biopharmaceutical process and the credibility bound, a control unit; and
execute the control unit to control at least one parameter of the biopharmaceutical process using model predictive controls (MPC).
Independent claim 54: controlling, by the one or more processors and based at least in part on the predicted analytical measurement of the biopharmaceutical process and the credibility bound, a control unit comprising software instructions stored in a memory; and
controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound.
Dependent claim 32: obtain an actual analytical measurement of the biopharmaceutical process.
The claims also include non-abstract computing or data gathering elements. For example, independent claim 20 includes a spectroscopy system comprising one or more spectroscopy probes collectively configured to (i) deliver source electromagnetic radiation to the biopharmaceutical process and (ii) collect electromagnetic radiation while the source electromagnetic radiation is delivered to the biopharmaceutical process, one or more memories collectively storing (i) an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and (ii) software instructions defining a control unit that implements model predictive controls (MPC) to control at least one parameter of the biopharmaceutical process, and one or more processors. Claim 21 further limits the spectroscopy system of claim 20 to a Raman spectroscopy system. Claim 32 further includes an analytical instrument. Claim 54 includes a non-transitory computer-readable storage medium configured to store instructions executable by one or more processors.
Considerations under Step 2A, Prong Two
With respect to Step 2A, Prong Two, the additional elements of the claims do not integrate the judicial exceptions into a practical application for the following reasons. Those steps directed to data gathering, such as “obtaining” an actual analytical measurement, and to data outputting, such as “controlling” a control unit, perform functions of collecting and outputting the data needed to carry out the judicial exceptions. Data gathering and outputting do not impose any meaningful limitation on the judicial exceptions, or on how the judicial exceptions are performed. Data gathering and outputting steps are not sufficient to integrate judicial exceptions into a practical application (MPEP 2106.05(g)). The “controlling” limitation also falls under mere instructions to apply the judicial exceptions to a particular technological field, and therefore do not provide a practical application (MPEP 2106.05(f)).
The steps of “execute the control unit to control at least one parameter of the biopharmaceutical process using model predictive controls (MPC)” in claim 20 and “controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound” in claim 54 are considered to merely apply the judicial exceptions to the technical environment of a biopharmaceutical process because neither claim recites the required structure to perform these actions (see the above 35 USC 112(a) and (b) rejections). Therefore, these steps merely add the words “apply it” with the judicial exception (see MPEP 2106.05(f)).
Further steps directed to the additional non-abstract computing elements do not describe any specific computational steps by which the “computer parts” perform or carry out the judicial exceptions, nor do they provide any details of how specific structures of the computer, such as the computer-readable recording media, are used to implement these functions. The claims state nothing more than a generic computer which performs the functions that constitute the judicial exceptions. Hence, these are mere instructions to apply the judicial exceptions using a computer, and therefore the claim does not integrate that judicial exceptions into a practical application. The courts have weighed in and consistently maintained that when, for example, a memory, display, processor, machine, etc.… are recited so generically (i.e., no details are provided) that they represent no more than mere instructions to apply the judicial exception on a computer, and these limitations may be viewed as nothing more than generally linking the use of the judicial exception to the technological environment of a computer (MPEP 2106.05(f)).
Regarding the spectroscopy probes of claim 20 and the analytical instrument of claim 32, the structures recite only the structure to perform the additional element of collecting electromagnetic radiation and obtaining an actual analytical measurement, which are considered as data gathering steps. The spectroscopy probes and analytical instrument do not perform any of the recited judicial exceptions and only serve as structures to perform a data gathering step. Therefore, the spectroscopy probes and analytical instrument do not integrate the recited judicial exceptions into any practical application.
The specification discloses that the embodiments of the invention improve upon traditional techniques for spectroscopic analysis of biopharmaceutical processes through the learning and modeling platforms at [0008], but does not provide a clear explanation for how the additional elements provide these improvements. Therefore, the additional elements do not clearly improve the functioning of a computer, or comprise an improvement to any other technical field. Further, the additional elements do not clearly affect a particular treatment; they do not clearly require or set forth a particular machine; they do not clearly effect a transformation of matter; nor do they clearly provide a nonconventional or unconventional step (MPEP2106.04(d)).
Thus, none of the claims recite additional elements which would integrate a judicial exception into a practical application, and the claims are directed to one or more judicial exceptions [Step 2A, Prong 2: NO; See MPEP § 2106.04(d)].
Step 2B (MPEP 2106.05.A i-vi)
According to analysis so far, the additional elements described above do not provide significantly more than the judicial exception. A determination of whether additional elements provide significantly more also rests on whether the additional elements or a combination of elements represents other than what is well-understood, routine, and conventional. Conventionality is a question of fact and may be evidenced as: a citation to an express statement in the specification or to a statement made by an applicant during prosecution that demonstrates a well-understood, routine or conventional nature of the additional element(s); a citation to one or more of the court decisions as discussed in MPEP 2106(d)(II) as noting the well-understood, routine, conventional nature of the additional element(s); a citation to a publication that demonstrates the well-understood, routine, conventional nature of the additional element(s); and/or a statement that the examiner is taking official notice with respect to the well-understood, routine, conventional nature of the additional element(s).
With respect to the instant claims, the prior art review to Esmonde-White et al. (Analytical and Bioanalytical Chemistry, 2017, 409:637-649; previously cited) discloses that the use of Raman spectroscopy and NIR (i.e., spectroscopy probes configured to deliver source electromagnetic radiation to the biopharmaceutical process and collect electromagnetic radiation while the source electromagnetic radiation) as process analytical and control tools for pharmaceutical manufacturing and bioprocessing as well as obtaining analytical measurements via an analytical instrument, as recited in claim 32, are data gathering elements that are routine, well-understood and conventional in the art. Said portions of the prior art are, for example, the abstract and (p. 640, col. 2, par. 2; Fig. 2; entire document is relevant). Further, the courts have found that receiving and outputting data are well-understood, routine, and conventional functions of a computer when claimed in a merely generic manner or as insignificant extra-solution activity (see Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network), Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015), and OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93, as discussed in MPEP 2106.05(d)(II)(i)). As such, the claims simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception (MPEP2106.05(d)). The data gathering steps as recited in the instant claims constitute a general link to a technological environment which is insufficient to constitute an inventive concept which would render the claims significantly more than the judicial exception (MPEP2106.05(g)&(h)).
With respect to claims 20 and 54 and those claims dependent therefrom, the computer-related elements or the general purpose computer do not rise to the level of significantly more than the judicial exception. The claims state nothing more than a generic computer which performs the functions that constitute the judicial exceptions. Hence, these are mere instructions to apply the judicial exceptions using a computer, which the courts have found to not provide significantly more when recited in a claim with a judicial exception (see MPEP 2106.06(A)). The specification as published also notes that computer processors and systems, as example, are commercially available or widely used at [0027-0033]. The additional elements are set forth at such a high level of generality that they can be met by a general purpose computer. Therefore, the computer components constitute no more than a general link to a technological environment, which is insufficient to constitute an inventive concept that would render the claims significantly more than the judicial exceptions (see MPEP 2106.05(b)I-III).
Taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception(s). Even when viewed as a combination, the additional elements fail to transform the exception into a patent-eligible application of that exception. Thus, the claims as a whole do not amount to significantly more than the exception itself [Step 2B: NO; See MPEP § 2106.05].
Therefore, the instant claims are not drawn to eligible subject matter as they are directed to one or more judicial exceptions without significantly more. For additional guidance, applicant is directed generally to the MPEP § 2106.
Response to Applicant Arguments
At p. 13, section V., Applicant submits that the relevant structure for claim 20 to control the biopharmaceutical process is now recited in the limitation “execute the control unit to control at least one parameter of the biopharmaceutical process using model predictive controls (MPC)”.
It is respectfully submitted that this is not persuasive. As set forth in the above rejection, the limitation does not recite any structure that actually controls a physical biopharmaceutical process. Therefore, the control of the process is outside the scope of the current system, and merely recites and “apply it” step with the judicial exceptions. No practical application at Step 2A, Prong 2 is provided by such a limitation.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The 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.
A. Claims 1-3, 6, 8, 13-14, 20-22, 29, and 54-55 are rejected under 35 U.S.C. 103 as being unpatentable over Su et al. (Journal of Process Control, 2016, 43:1-9; cited on the Apr 12 2021 IDS), as evidenced by Alsaheb et al. (Der Pharmacia Letter, 2016, 8(9):217-225; previously cited), and in further view of Czeterko et al. (US 2019/0112569; priority to Oct 16 2017; previously cited) and Liu et al. (Journal of Process Control, 2013, 23(6):793-804; newly cited). Instantly claimed elements which are considered to be equivalent to the prior art teachings are described in bold for all claims. The instant rejection is newly stated and is necessitated by claim amendment.
The prior art to Su discloses an Extended Prediction Self-Adaptive Control (EPSAC) algorithm based on the Just-in-Time Learning (JITL) method which uses a set of local state-space models, each of which can be independently and simultaneously identified by the JITL method along the base trajectory (abstract). Su, indicated by the open circles, teaches the instant features, indicated by the closed circles, as follows.
Claim 1 discloses a computer-implemented method for monitoring and/or controlling a biopharmaceutical process. Claim 20 discloses a spectroscopy system for monitoring and/or controlling a biopharmaceutical process, the spectroscopy system comprising: one or more spectroscopy probes collectively configured to (i) deliver source electromagnetic radiation to the biopharmaceutical process and (ii) collect electromagnetic radiation while the source electromagnetic radiation is delivered to the biopharmaceutical process; one or more memories collectively storing (i) an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and (ii) software instructions defining a control unit that implements model predictive controls (MPC) to control at least one parameter of the biopharmaceutical process; and one or more processors. Claim 54 discloses a non-transitory computer-readable storage medium configured to store instructions executable by one or more processors for monitoring and/or controlling a biopharmaceutical process.
Su teaches a JITL-based EPSAC algorithm (abstract), which is considered to read on a computer-implemented method. However, Su does not teach a spectroscopy system as instantly claimed. See below for teachings by Czeterko regarding these features.
The steps of the method of claim 1, that the one or more processors of claim 20 are configured to perform, and that are included in the instructions of claim 54 comprise:
determining a query point associated with scanning of the biopharmaceutical process by a spectroscopy system;
Su teaches performing three steps when query data comes (p. 3, col. 2, par. 2). Su teaches measuring the polymorphic purity of L-glutamic acid production using Raman spectroscopy (i.e., scanning) for EPSAC control (i.e., a query point associated with scanning) (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3). The production of L-glutamic acid reads on a biopharmaceutical process because L-glutamic acid is a molecule which is used in biopharmaceutical applications, as evidenced by Alsaheb (abstract; entire document is relevant).
querying the observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes selecting as training data, from among the plurality of observation data sets, observation data sets that satisfy one or more relevancy criteria with respect to the query point;
Su teaches relevant data selection (i.e., querying) from a reference database (i.e., observation database) according to some similarity criterion with the query data (p. 3, col. 2, par. 2 through p. 4, col., 2, par. 2). Su teaches generating the reference database for the JITL identification of local state-space models by obtaining one hundred batches of process data with random magnitude changes to the constant addition flowrate of 8 mL/min of sulfuric acid to the l-glutamic acid production and measuring the polymorphic purity by Raman spectroscopy (i.e., each observation data set incudes spectral data) as well as mean crystal size and concentration/product yield at the batch end (i.e., each observation data set includes an actual analytical measurement) (p. 7, col. 1, par. 2-3; Fig. 3).
calibrating, using the selected training data, a local model specific to the biopharmaceutical process, the local model being a Gaussian process machine-learning model trained to predict analytical measurements based on spectral data inputs; and
Su teaches local model construction (i.e., calibrating) based on the relevant data (p. 3, col. 2, par. 2 through p. 4, col. 1, par. 1 and par. 4 through col. 2, par. 1). As Su teaches using a set of linear local models constructed for each sampling instant in the reference trajectory (p. 3, col. 1 through col. 2) and their application to the production of L-glutamic acid (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), it is considered that Su fairly teaches a local model specific to the biopharmaceutical process as instantly claimed. As Su teaches that the key idea of EPSAC is to predict nonlinear process variables by iterative optimization with respect to future trajectories (p. 2, col. 1, par. 2), it is considered that Su fairly teaches the local model being trained to predict analytical measurements based on spectral data inputs as instantly claimed.
See below for teachings by Liu regarding a Gaussian process machine-learned model trained to predict analytical measurements based on spectral data inputs.
predicting an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process;
Su teaches model prediction using the local model (p. 3, col. 2, par. 2 through p. 4, col. 1, par. 1 and col. 2, par. 3 through p. 6, col. 2, par. 2), where the optimal operating point is batch-end product quality based on polymorphic purity, crystal size, and product yield at the batch end (i.e., predicting an analytical measurement) (p. 6, col. 2, p.ar 3). Su teaches initializing the EPSAC controllers only after measurements of polymorphic purity by Raman spectroscopy were steadily available (p. 7, col. 1, par. 3), which reads on the local model analyzing spectral data as instantly claimed.
determining a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process; and
See below for teachings by Liu regarding this limitation.
controlling, by the one or more processors and based at least in part on the predicted analytical measurement of the biopharmaceutical process and the credibility bound, a control unit comprising software instructions stored in a memory; and
controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound.
Su teaches tuning parameters of a simulated model for product quality and control moves (p. 7, col. 2, par. 1). Su also teaches controlling L-glutamic acid production using the JITL-EPSAC algorithm (p. 7, col. 1, par. 3 through col. 2, par. 2; Fig. 4). Su does not controlling an actual biopharmaceutical process via a control unit.
See below for teaching by Czeterko regarding this limitation.
Su does not teach the spectroscopy system, a local model being a Gaussian process machine-learned model trained to predict analytical measurements based on spectral data inputs and which is used to determine a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process, or controlling an actual biopharmaceutical process via a control unit as instantly claimed.
However, the prior art to Czeterko discloses in situ Raman spectroscopy methods and systems for monitoring and controlling one or more process variables in a bioreactor cell culture in order to improve product quality and consistency (abstract). Czeterko teaches a system for controlling cell culture medium conditions including one or more processors in communication with a computer readable medium/memory storing software code for execution by the one or more processors [0010; 0053-0054]. Czeterko teaches a system which includes a Raman analyzer operatively connected to the bioreactor and computer system, where a Raman probe may be inserted into the bioreactor to raw spectral data of one or more process variables ([0041; 0050]; FIG. 2), which is considered to read on a probe as instantly claimed. Czeterko teaches a proportional-integral derivative (PID) controller (i.e., control unit) that is software which calculates the difference between the predefined set point and the measured process variable (for example, the measured nutrient concentration) and automatically apply an accurate correction ([0046; 0054]; FIG. 1).
Regarding claims 1, 20 and 54, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the method of Su as evidenced by Alsaheb and the system of Czeterko because both references disclose methods for model predictive control of biopharmaceutical processes. The motivation would have been to include the system of Czeterko to carry out the method of Su because such a modification represents the automating of a manual activity to control a biopharmaceutical process. The courts have held that broadly providing an automatic or mechanical means to replace a manual activity which accomplished the same result is not sufficient to distinguish over the prior art (In re Venner, 262 F.2d 91, 95, 120 USPQ 193, 194 (CCPA 1958); MPEP 2144.04(III)).
Neither Su as evidenced by Alsaheb or Czeterko teach a local model being a Gaussian process machine-learned model trained to predict analytical measurements based on spectral data inputs and which is used to determine a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process.
However, the prior art to Liu discloses an integrated nonlinear soft sensor modeling method is proposed for online quality prediction of multi-grade processes, where several single least squares support vector regression (LSSVR) models are first built for each product grade and, for online prediction of a new sample, a probabilistic analysis approach using the statistical property of steady-state grades is presented (abstract). Liu teaches that the probabilistic analysis approach involves examining variables in a Gaussian distribution, where the probability density distribution within a grade is a multivariate Gaussian (p. 795, col. 2-3, section 3.1). As the instant specification as published discloses that a “Gaussian process is a collection of random variables, any finite number of which have a joint Gaussian distribution” at [0051], it is considered that Liu fairly teaches a Gaussian process model as instantly claimed. Liu teaches that on the basis of the probability density function for each normal operating data of steady-state grade, a confidence bound (i.e., a credibility bound) can be defined as a likelihood threshold (p. 795, col. 2-3, section 3.1). Liu teaches using the confidence bounds to choose the correct local model for prediction (p. 801, col. 2, par. 2).
Regarding claims 1, 20, and 54, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the method of Su, as evidenced by Alsaheb and in view of Czeterko, with Liu because each reference discloses methods for process control techniques. The motivation to use a Gaussian process model and a confidence bound would have been to use the confidence bounds to choose the correct local model for prediction, as taught by Liu (p. 801, col. 2, par. 2). It therefore would have been obvious to one of ordinary skill in the art to substitute the models taught by Su with the Gaussian process model taught by Liu for the predictable result of predicting analytical measurements based on spectral data inputs.
Regarding claims 2 and 21, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches the method of claim 1 and the system of claim 20 as described above. Claims 2 and 21 further add that the spectroscopy system is a Raman spectroscopy system.
Su teaches measuring the polymorphic purity of L-glutamic acid production using Raman spectroscopy for EPSAC control (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3). Czeterko further teaches a system which includes a Raman analyzer ([0041; 0050]; FIG. 2).
Regarding claims 3, 22, and 55, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches the method of claim 1 and the system of claim 20 as described above. Claims 3, 22, and 55 further add that determining a query point includes determining the query point based at least in part on a spectral scan vector, the spectral scan vector being generated by the spectroscopy system when scanning the biopharmaceutical process; and that selecting as training data the observation data sets that satisfy one or more relevancy criteria with respect to the query point includes comparing the spectral scan vector on which determination of the query point was based to spectral scan vectors associated with the past observations of the biopharmaceutical processes.
Su teaches using Raman spectroscopy data to assess polymorphic purity to activate control actions (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), which reads on determining a query point based at least on spectral scan vector because the claim further limits the spectral scan vector to being generated by the spectroscopy system when scanning the biopharmaceutical process. As Su teaches generating Raman spectroscopy data from the biopharmaceutical process, it is considered that such data would inherently include a spectral scan vector. Su teaches designing a reference database from process data, which Su discloses are Raman spectroscopy measurements (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), and choosing a relevant dataset according to similarity criterion (p. 4, col. 1, par. 3 through col. 2, par. 1), which is considered to read on comparing a spectral scan vector of the query point to spectral scan vectors of past observations as instantly claimed.
Regarding claim 6, Su as evidenced by Alsaheb and in view of Czeterko and Su teaches the method of claims 1 and 3 as described above. Claim 6 further adds that predicting the analytical measurement of the biopharmaceutical process includes: using the local model to analyze the spectral scan vector on which determination of the query point was based.
Su teaches using the reference trajectory made of process data, which Su discloses are Raman spectroscopy measurements (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), to obtain a series of local state-space models for prediction (p. 3, col. 1, par. 2; p. 4, col. 2, par. 3 through p. 6, col. 2, par. 2; p. 7, col. 1, par. 2), which is considered to read on using the local model to analyze the spectral scan vector on which determination of the query point was based as instantly claimed.
Regarding claim 8, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches the method of claim 1 as described above. Claim 8 further adds that determining a query point includes: determining the query point based at least in part on one or both of (i) a media profile associated with the biopharmaceutical process, and (ii) one or more operating conditions under which the biopharmaceutical process is analyzed.
Su teaches determining the local state-space model based on the glutamic acid concentration and the solution volume in the crystallizer (p. 7, col. 1, par. 1), which reads on one or more operating conditions under which the biopharmaceutical process is analyzed as instantly claimed.
Regarding claims 13 and 29, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches the method of claim 1 and the system of claim 20 as described above. Claims 13 and 29 further add that the predicted analytical measurement of the biopharmaceutical process is a media component concentration, a media state, a viable cell density, a titer, a critical quality attribute, or a cell state.
Su teaches measuring the concentration of glutamic acid in the model (p. 7, col. 1, par. 1), which reads on a media component concentration.
Regarding claim 14, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches the method of claim 1 as described above. Claim 14 further adds that the predicted analytical measurement of the biopharmaceutical process is (i) a concentration of glucose, lactate, glutamate, glutamine, ammonia, amino acids, Na+, or K+, (ii) pH, (iii) pCO2, (iv) pO2, (v) temperature, or (vi) osmolality.
Su teaches predicting the polymorphic yield of L-glutamic acid, which reads on the concentration of amino acids in the biopharmaceutical process.
B. Claims 4-5, 7, 10, 23-24, 26, and 56-57 are rejected under 35 U.S.C. 103 as being unpatentable over Su as evidenced by Alsaheb and in view of Czeterko and Liu as applied to claims 1, 3, 20, 22, and 54-55 above, and in further view of Chen et al. (6th International Symposium on Advanced Control of Industrial Processes, 2017, p. 559-564; cited on the Apr 12 2021 IDS). Instantly claimed elements which are considered to be equivalent to the prior art teachings are described in bold for all claims. The instant rejection is newly stated and is necessitated by claim amendment.
Regarding claims 4, 23, and 56, Su as evidenced by Alsaheb and in view of Czeterko and Liu teaches claims 1, 3, 20, 22, and 54-55 as described above. Claims 4 and 23 further add determining a query point further includes determining the query point based on a sample number associated with the spectral scan vector; and selecting as training data the observation data sets that satisfy one or more relevancy criteria with respect to the query point includes (i) comparing the spectral scan vector on which determination of the query point was based to spectral scan vectors associated with the past observations of the biopharmaceutical processes, and (ii) comparing the sample number associated with the query point to sample numbers associated with the past observations of the biopharmaceutical processes.
Su teaches using Raman spectroscopy data to assess polymorphic purity to activate control actions (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), which reads on determining a query point based at least on spectral scan vector which is considered to be generated by the spectroscopy system when scanning the biopharmaceutical process. As Su teaches generating Raman spectroscopy data from the biopharmaceutical process, it is considered that such data would inherently include a spectral scan vector. Su teaches designing a reference database from process data, which Su discloses are Raman spectroscopy measurements (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), and choosing a relevant dataset according to similarity criterion (p. 4, col. 1, par. 3 through col. 2, par. 1), which is considered to read on comparing a spectral scan vector of the query point to spectral scan vectors of past observations as instantly claimed. Su does not teach using a sample number as instantly claimed for these actions.
However, the prior art to Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen 2017 teaches using the sample number of the samples within the initial calibration database (p. 560, col. 1, par. 3; p. 562, col. 2, par. 3; Fig. 5-7) when selecting the most similar samples (p. 559, col. 2, par. 4).
Regarding claims 5 and 24, Su as evidenced by Alsaheb and in view of Czeterko, Liu, and Chen 2017 teaches the method of claims 1 and 3-4 and the system of claims 20 and 22-23 as described above. Claims 5 and 24 further adds selecting as training data the observation data sets that satisfy one or more relevancy criteria with respect to the query point includes: selecting the most recent k observation data sets for inclusion in the training data, which Su does not teach.
However, Chen 2017 teaches a model which allows for more impact of new samples (abstract) by using a prediction model established by forgetting and discounting old samples from the database to give more weight to newer samples (i.e., selecting the most recent k observation data sets for inclusion in the training data) (p. 560, col. 2, par. 10 through p. 561, col. 2, par. 3).
Regarding claims 7 and 57, Su as evidenced by Alsaheb in view of Czeterko and Liu teaches the claims 1, 3, and 54-55 as described above. Claims 7 and 57 further add that selecting as training data the observation data sets that satisfy one or more relevancy criteria with respect to the query point includes: calculating distances between (i) the spectral scan vector on which determination of the query point was based and (ii) the spectral scan vectors associated with the past observations of the biopharmaceutical processes; and selecting as the training data any of the spectral scan vectors associated with the past observations that are within a threshold distance of the spectral scan vector on which determination of the query point was based, which Su does not teach.
However, the prior art to Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen 2017 teaches a method for selecting the most similar samples (p. 559, col. 2, par. 4) by selecting local calibration samples by spectral distance measurements (p. 559, col. 2, par. 2; p. 560, col. 2, par. 3 through p. 561, col. 2, par. 3), where distance weights are calculated within certain limits (i.e., a threshold distance) (p. 561, equation 31).
Regarding claims 10 and 26, Su as evidenced by Alsaheb in view of Czeterko and Liu teaches the method of claim 1 and the system of claim 20 as described above. Claims 10 and 26 further add that calibrating a local model specific to the biopharmaceutical process includes: calibrating a model that is a function of both spectral data and sample number of a given observation data set. Su teaches determining the local state-space model based on the glutamic acid concentration and the solution volume in the crystallizer (p. 7, col. 1, par. 1), which reads on calibrating a model that is a function of spectral data as instantly claimed. Su does not teach calibrating a model that is a function of sample number of a given observation data set.
However, the prior art to Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen teaches using the sample number of the samples within the initial calibration database (p. 560, col. 1, par. 3; p. 562, col. 2, par. 3; Fig. 5-7) when selecting the most similar samples (p. 559, col. 2, par. 4) and determining the initial calibration model (p. 560, col. 1, par. 1-3).
Regarding claims 4-5, 7, 10, 23-24, 26, and 56-57, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the methods of Su, as evidenced by Alsaheb and in view of Czeterko and Liu, with Chen 2017 because each reference discloses methods for process control techniques. The motivation would have been to use a model which provides a balance between robustness (more initial samples included) and adaptability (more impact of new samples) while still accounting for the most similar samples as calculated by an improved distance measurement, as taught by Chen 2017 (abstract).
C. Claims 16 and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Su as evidenced by Alsaheb and in view of Czeterko and Liu as applied to claims 1 and 20, and in further view of Hsiung et al. (US 2019/0236333; priority to Jan 26, 2018; previously cited). Instantly claimed elements which are considered to be equivalent to the prior art teachings are described in bold for all claims. The instant rejection is newly stated and is necessitated by claim amendment.
Regarding claims 16 and 32, Su as evidenced by Alsaheb in view of Czeterko and Liu teaches the method of claim 1 and the system of claim 20 as described above. Claims 16 and 32 further add:
obtaining, by an analytical instrument, an actual analytical measurement of the biopharmaceutical process (claim 16) or an analytical instrument configured to obtain an actual analytical measurement of the biopharmaceutical process (claim 32);
Su teaches obtaining one hundred batches of process data for producing L-glutamic acid and measuring the polymorphic purity by Raman spectroscopy as well as mean crystal size and concentration/product yield at the batch end (i.e., an actual analytical measurement) (p. 7, col. 1, par. 2-3; Fig. 3). As Su teaches obtaining an actual analytical measurement, it is considered that Su would have inherently had to have used an analytical instrument to perform the measurement.
causing, by the one or more processors, (i) spectral data that the spectroscopy system generated when the actual analytical measurement was obtained, and (ii) the actual analytical measurement of the biopharmaceutical process, to be added to the observation database; and
Su teaches generating the reference database for the JITL identification of local space models from the one hundred batches of process data (p. 7, col. 1, par. 2; Fig. 3), which reads on adding the spectral data and the analytical measurement to the observation database. As Su teaches an algorithm (abstract), it is considered that Su teaches a computer-implemented method which would inherently require a processor to perform the action as claimed.
determining, by the one or more processors, that at least the predicted analytical measurement does not satisfy one or more model performance criteria,
wherein determining that at least the predicted analytical measurement does not satisfy the one or more model performance criteria includes generating a credibility interval associated with the predicted analytical measurement and comparing the credibility interval to a pre-defined threshold, and
wherein obtaining the actual analytical measurement is performed in response to determining that at least the predicted analytical measurement does not satisfy the one or more model performance criteria.
Su does not teach the final 3 limitations.
However, the prior art to Hsiung discloses device for generating a classification model based on the information identifying the results of the set of spectroscopic measurements, wherein the classification model includes at least one class relating to a material of interest for a spectroscopic determination, and wherein the classification model includes a no-match class relating to at least one of at least one material that is not of interest or a baseline spectroscopic measurement (abstract). Hsiung teaches assigning particular samples based on a confidence metric (i.e., model performance criteria) in comparison to a threshold (i.e., a credibility interval) to a match or no-match class ([0080-0081; 0090]; FIG. 6, 630). Hsiung teaches that, based on determining that a confidence level associated with the classification does not satisfy a threshold confidence level, a control device provides an output indicating a classification failure ([0086]; FIG. 6, 660). Hsiung teaches that the control device may obtain additional information identifying the sample to determine which labeled class the sample belongs to or may determine that the sample is a no-match to any class [0092].
Regarding claims 16 and 32, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the methods of Su, as evidenced by Alsaheb in view of Czeterko and Liu, with Hsiung because each reference discloses methods for determining the classification of samples based on local models. The motivation to assign samples based on a confidence metric would have been to reduce a likelihood of a false-positive determination, as taught by Hsiung [0086]. Although Hsiung teaches obtaining additional information to identify the sample when it is a no match, Hsiung does not explicitly teach obtaining additional information of an actual analytical measurement in response to determining that at least the predicted analytical measurement does not satisfy the one or more model performance criteria, as instantly claimed. However, one of ordinary skill in the art would understand that such additional information could include an actual analytical measurement as taught by Su, based on common sense and knowledge already present in the prior art.
Response to Applicant Arguments
With respect to Applicant’s arguments under 35 USC 103, the arguments have been fully considered but are moot in view of the new grounds of rejection set forth above as necessitated by claim amendment herein.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-8, 10, 13-14, 16, 20-24, 26, 29, 32, and 54-57 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 6, 12-14, and 16-17 of copending Application No. 18/367,580 (reference application) in view of Su et al. (Journal of Process Control, 2016, 43:1-9; cited on the Apr 12 2021 IDS), Liu et al. (Journal of Process Control, 2013, 23(6):793-804; newly cited), Chen et al. (6th International Symposium on Advanced Control of Industrial Processes, 2017, p. 559-564; cited on the Apr 12 2021 IDS), and Hsiung et al. (US 2019/0236333; previously cited). The instant rejection is newly stated and is necessitated by claim amendment.
Instant claims
Reference claims
1. A computer-implemented method for monitoring and/or controlling a biopharmaceutical process, the method comprising:
determining, by one or more processors, a query point associated with scanning of the biopharmaceutical process by a spectroscopy system;
querying, by the one or more processors, an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes selecting as training data, from among the plurality of observation data sets, observation data sets that satisfy one or more relevancy criteria with respect to the query point;
calibrating, by the one or more processors and using the selected training data, a local model specific to the biopharmaceutical process, the local model being a Gaussian process machine-learning model trained to predict analytical measurements based on spectral data inputs; and
predicting, by the one or more processors, an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process;
determining, by the one or more processors, a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process;
controlling, by the one or more processors and based at least in part on the predicted analytical measurement of the biopharmaceutical process and the credibility bound, a control unit comprising software instructions stored in a memory; and
controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC).
1. A computer-implemented method for monitoring and/or controlling a biopharmaceutical process, the method comprising:
(as the reference claim recites a query point below, it is considered that such a query point would have inherently had to have been determined)
querying, by one or more processors and based on a first spectral scan vector of the biopharmaceutical process obtained by a spectroscopy system, an observation database comprising a plurality of observation data sets associated with past scans of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes determining first parameters defining a set of distributions for the first spectral scan vector, and selecting as training data, from among the plurality of observation data sets,
particular observation data sets based on (i) the first parameters and (ii) other parameters defining respective sets of distributions for the plurality of observation data sets;
calibrating, by the one or more processors and using the selected training data, a local model specific to the biopharmaceutical process, the local model being trained to predict analytical measurements based on spectral data inputs; and
predicting, by the one or more processors, an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process.
6. calibrating a Gaussian process machine learning model specific to the biopharmaceutical process.
14. The computer-implemented method of any one of claim 1, further comprising: controlling, by the one or more processors and based on the predicted analytical measurement of the biopharmaceutical process, at least one parameter of the biopharmaceutical process.
20. A spectroscopy system for monitoring and/or controlling a biopharmaceutical process, the spectroscopy system comprising:
one or more spectroscopy probes collectively configured to (i) deliver source electromagnetic radiation to the biopharmaceutical process and (ii) collect electromagnetic radiation while the source electromagnetic radiation is delivered to the biopharmaceutical process;
one or more memories collectively storing an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement; and
one or more processors configured to determine a query point associated with scanning of the biopharmaceutical process by the spectroscopy system,
query the observation database, at least by selecting as training data, from among the plurality of observation data sets, observation data sets that satisfy one or more relevancy criteria with respect to the query point,
calibrate, using the selected training data, a local model specific to the biopharmaceutical process, the local model being a Gaussian process machine-learning model trained to predict analytical measurements based on spectral data inputs, and
predict an analytical measurement of the biopharmaceutical process, at least by using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process with the one or more spectroscopy probes;
using the local model to determine a confidence indicator associated with the predicted analytical measurement of the biopharmaceutical process; and
control, based at least in part on the predicted analytical measurement of the biopharmaceutical process and the confidence indicator, a control unit that implements model predictive controls (MPC) to control at least one parameter of the biopharmaceutical process.
16. A spectroscopy system comprising:
one or more spectroscopy probes collectively configured to (i) deliver source electromagnetic radiation to a biopharmaceutical process and (ii) collect electromagnetic radiation while the source electromagnetic radiation is delivered to the biopharmaceutical process; and
a computing system having one or more processors configured to:
query, based on a first spectral scan vector of the biopharmaceutical process obtained by the spectroscopy system, an observation database comprising a plurality of observation data sets associated with past scans of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes:
determining first parameters defining a set of distributions for the first spectral scan vector, and
selecting as training data, from among the plurality of observation data sets, particular observation data sets based on (i) the first parameters and (ii) other parameters defining respective sets of distributions for the plurality of observation data sets;
calibrate, using the selected training data, a local model specific to the biopharmaceutical process, the local model being trained to predict analytical measurements based on spectral data inputs; and
6. calibrating a Gaussian process machine learning model specific to the biopharmaceutical process.
predict an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process.
14. The computer-implemented method of any one of claim 1, further comprising: controlling, by the one or more processors and based on the predicted analytical measurement of the biopharmaceutical process, at least one parameter of the biopharmaceutical process.
54. A non-transitory computer-readable storage medium configured to store instructions executable by one or more processors for monitoring and/or controlling a biopharmaceutical process, the instructions comprising:
determining, by one or more processors, a query point associated with scanning of the biopharmaceutical process by a spectroscopy system;
querying, by the one or more processors, an observation database containing a plurality of observation data sets associated with past observations of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes selecting as training data, from among the plurality of observation data sets, observation data sets that satisfy one or more relevancy criteria with respect to the query point;
calibrating, by the one or more processors and using the selected training data, a local model specific to the biopharmaceutical process, the local model being a Gaussian process machine-learning model trained to predict analytical measurements based on spectral data inputs;
predicting, by the one or more processors, an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process;
determining, by the one or more processors, a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process;
controlling, by the one or more processors and based at least in part on the predicted analytical measurement of the biopharmaceutical process and the credibility bound, a control unit comprising software instructions stored in a memory; and
controlling, by the one or more processors executing the control unit, at least one parameter of the biopharmaceutical process using model predictive controls (MPC) and the credibility bound.
17. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
query, based on a first spectral scan vector of the biopharmaceutical process obtained by the spectroscopy system, an observation database comprising a plurality of observation data sets associated with past scans of biopharmaceutical processes, wherein each of the observation data sets includes spectral data and a corresponding actual analytical measurement, and wherein querying the observation database includes:
determining first parameters defining a set of distributions for the first spectral scan vector, and
selecting as training data, from among the plurality of observation data sets,
particular observation data sets based on (i) the first parameters and (ii) other parameters defining respective sets of distributions for the plurality of observation data sets;
calibrate, using the selected training data, a local model specific to the biopharmaceutical process, the local model being trained to predict analytical measurements based on spectral data inputs; and
predict an analytical measurement of the biopharmaceutical process, wherein predicting the analytical measurement of the biopharmaceutical process includes using the local model to analyze spectral data that the spectroscopy system generated when scanning the biopharmaceutical process.
6. calibrating a Gaussian process machine learning model specific to the biopharmaceutical process.
14. The computer-implemented method of any one of claim 1, further comprising: controlling, by the one or more processors and based on the predicted analytical measurement of the biopharmaceutical process, at least one parameter of the biopharmaceutical process.
2 and 21… wherein the spectroscopy system is a Raman spectroscopy system.
13. The computer-implemented method of claim 1, wherein the spectroscopy system is a Raman spectroscopy system.
3, 22, and 55… wherein:
determining a query point includes determining the query point based at least in part on a spectral scan vector, the spectral scan vector being generated by the spectroscopy system when scanning the biopharmaceutical process; and
selecting as training data the observation data sets that satisfy one or more relevancy criteria with respect to the query point includes comparing the spectral scan vector on which determination of the query point was based to spectral scan vectors associated with the past observations of the biopharmaceutical processes.
1…
querying, by one or more processors and based on a first spectral scan vector of the biopharmaceutical process obtained by a spectroscopy system;
and wherein querying the observation database includes determining first parameters defining a set of distributions for the first spectral scan vector, and
selecting as training data, from among the plurality of observation data sets.
13 and 29… wherein the predicted analytical measurement of the biopharmaceutical process is a media component concentration, a media state, a viable cell density, a titer, a critical quality attribute, or a cell state.
12. The computer-implemented method of claim 1, wherein the predicted analytical measurement of the biopharmaceutical process is osmolality, viability, viable cell density, or titer.
The reference patent does not claim the limitation “determining a credibility bound of the local model associated with the predicted analytical measurement of the biopharmaceutical process”. However, the prior art to Liu discloses an integrated nonlinear soft sensor modeling method is proposed for online quality prediction of multi-grade processes, where several single least squares support vector regression (LSSVR) models are first built for each product grade and, for online prediction of a new sample, a probabilistic analysis approach using the statistical property of steady-state grades is presented (abstract). Liu teaches that the probabilistic analysis approach involves examining variables in a Gaussian distribution, where the probability density distribution within a grade is a multivariate Gaussian (p. 795, col. 2-3, section 3.1). As the instant specification as published discloses that a “Gaussian process is a collection of random variables, any finite number of which have a joint Gaussian distribution” at [0051], it is considered that Liu fairly teaches a Gaussian process model as instantly claimed. Liu teaches that on the basis of the probability density function for each normal operating data of steady-state grade, a confidence bound (i.e., a credibility bound) can be defined as a likelihood threshold (p. 795, col. 2-3, section 3.1). Liu teaches using the confidence bounds to choose the correct local model for prediction (p. 801, col. 2, par. 2).
Regarding claims 1, 20, and 54, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the reference patent and Liu because each reference discloses methods for process control techniques. The motivation to use a Gaussian process model and a confidence bound would have been to use the confidence bounds to choose the correct local model for prediction, as taught by Liu (p. 801, col. 2, par. 2).
The reference patent does not claim the limitations of claims 4-8, 10, 14, 16, 23-24, 26, 32, and 53.
However, claims 4-8, 10, 14, 16, 23-24, 26, and 32 are not patentable over the reference application in view of Liu and Su et al. (Journal of Process Control, 2016, 43:1-9; cited on the Apr 12 2021 IDS), Chen et al. (6th International Symposium on Advanced Control of Industrial Processes, 2017, p. 559-564; cited on the Apr 12 2021 IDS), and Hsiung et al. (US 2019/0236333; previously cited).
Regarding claims 4, 23, and 56, Su teaches using Raman spectroscopy data to assess polymorphic purity to activate control actions (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), which reads on determining a query point based at least on spectral scan vector which is considered to be generated by the spectroscopy system when scanning the biopharmaceutical process. As Su teaches generating Raman spectroscopy data from the biopharmaceutical process, it is considered that such data would inherently include a spectral scan vector. Su teaches designing a reference database from process data, which Su discloses are Raman spectroscopy measurements (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), and choosing a relevant dataset according to similarity criterion (p. 4, col. 1, par. 3 through col. 2, par. 1), which is considered to read on comparing a spectral scan vector of the query point to spectral scan vectors of past observations as instantly claimed. Su does not teach using a sample number as instantly claimed for these actions.
However, the prior art to Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen 2017 teaches using the sample number of the samples within the initial calibration database (p. 560, col. 1, par. 3; p. 562, col. 2, par. 3; Fig. 5-7) when selecting the most similar samples (p. 559, col. 2, par. 4).
Regarding claims 5 and 24, Chen 2017 teaches a model which allows for more impact of new samples (abstract) by using a prediction model established by forgetting and discounting old samples from the database to give more weight to newer samples (i.e., selecting the most recent k observation data sets for inclusion in the training data) (p. 560, col. 2, par. 10 through p. 561, col. 2, par. 3).
Regarding claim 6, Su teaches using the reference trajectory made of process data, which Su discloses are Raman spectroscopy measurements (p. 6, col. 2, par. 3 through p. 7, col. 1, par. 3), to obtain a series of local state-space models for prediction (p. 3, col. 1, par. 2; p. 4, col. 2, par. 3 through p. 6, col. 2, par. 2; p. 7, col. 1, par. 2), which is considered to read on using the local model to analyze the spectral scan vector on which determination of the query point was based as instantly claimed.
Regarding claims 7 and 57, Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen 2017 teaches a method for selecting the most similar samples (p. 559, col. 2, par. 4) by selecting local calibration samples by spectral distance measurements (p. 559, col. 2, par. 2; p. 560, col. 2, par. 3 through p. 561, col. 2, par. 3), where distance weights are calculated within certain limits (i.e., a threshold distance) (p. 561, equation 31).
Regarding claim 8, Su teaches determining the local state-space model based on the glutamic acid concentration and the solution volume in the crystallizer (p. 7, col. 1, par. 1), which reads on one or more operating conditions under which the biopharmaceutical process is analyzed as instantly claimed.
Regarding claims 10 and 26, Su teaches determining the local state-space model based on the glutamic acid concentration and the solution volume in the crystallizer (p. 7, col. 1, par. 1), which reads on calibrating a model that is a function of spectral data as instantly claimed. Su does not teach calibrating a model that is a function of sample number of a given observation data set.
However, the prior art to Chen 2017 discloses a recursive modeling algorithm within a just-in-time framework by a moving window for dealing with the time-varying and non-linear problems in near infrared (NIR) spectroscopy modeling (abstract). Chen teaches using the sample number of the samples within the initial calibration database (p. 560, col. 1, par. 3; p. 562, col. 2, par. 3; Fig. 5-7) when selecting the most similar samples (p. 559, col. 2, par. 4) and determining the initial calibration model (p. 560, col. 1, par. 1-3).
Regarding claim 14, Su teaches predicting the polymorphic yield of L-glutamic acid, which reads on the concentration of amino acids in the biopharmaceutical process.
Regarding claims 16 and 32, Su teaches obtaining one hundred batches of process data for producing L-glutamic acid and measuring the polymorphic purity by Raman spectroscopy as well as mean crystal size and concentration/product yield at the batch end (i.e., an actual analytical measurement) (p. 7, col. 1, par. 2-3; Fig. 3). As Su teaches obtaining an actual analytical measurement, it is considered that Su would have inherently had to have used an analytical instrument to perform the measurement. o Su teaches generating the reference database for the JITL identification of local space models from the one hundred batches of process data (p. 7, col. 1, par. 2; Fig. 3), which reads on adding the spectral data and the analytical measurement to the observation database. As Su teaches an algorithm (abstract), it is considered that Su teaches a computer-implemented method which would inherently require a processor to perform the action as claimed. Su does not teach the final 3 limitations of the claim.
However, the prior art to Hsiung discloses device for generating a classification model based on the information identifying the results of the set of spectroscopic measurements, wherein the classification model includes at least one class relating to a material of interest for a spectroscopic determination, and wherein the classification model includes a no-match class relating to at least one of at least one material that is not of interest or a baseline spectroscopic measurement (abstract). Hsiung teaches assigning particular samples based on a confidence metric (i.e., model performance criteria) in comparison to a threshold (i.e., a credibility interval) to a match or no-match class ([0080-0081; 0090]; FIG. 6, 630). Hsiung teaches that, based on determining that a confidence level associated with the classification does not satisfy a threshold confidence level, a control device provides an output indicating a classification failure ([0086]; FIG. 6, 660). Hsiung teaches that the control device may obtain additional information identifying the sample to determine which labeled class the sample belongs to or may determine that the sample is a no-match to any class [0092].
Regarding claims 6, 8, 10, 14 and 55, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the reference application in view of Chen 2007 and the methods of Su, because each reference discloses methods for process control techniques. The motivation would have been to solve the limitations of previous Extended Prediction Self-Adaptive Control models, such as less accurate predictions due to process nonlinearity which leads to modeling error, using a set of local state-space models, as taught by Su (p. 1, col. 2, par. 2).
Regarding claims 4-5, 7, 23-24, 26, and 56-57, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the reference application in view of Chen 2007 and the methods of Chen 2017, because each reference discloses methods for process control techniques. The motivation would have been to use a model which provides a balance between robustness (more initial samples included) and adaptability (more impact of new samples) while still accounting for the most similar samples as calculated by an improved distance measurement, as taught by Chen 2017 (abstract).
Regarding claims 16 and 32, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine, in the course of routine experimentation and with a reasonable expectation of success, the reference application in view of Chen 2007 and the methods of Hsiung because each reference discloses methods for determining the classification of samples based on local models. The motivation to assign samples based on a confidence metric would have been to reduce a likelihood of a false-positive determination, as taught by Hsiung [0086]. Although Hsiung does not explicitly teach obtaining the actual analytical measurement is performed in response to determining that at least the predicted analytical measurement does not satisfy the one or more model performance criteria, as instantly claimed, Hsiung does teach obtaining additional information to identify the sample. One of ordinary skill in the art would understand that such additional information could include an actual analytical measurement as taught by Su, based on common sense.
Response to Applicant Arguments
With respect to Applicant’s arguments under Double Patenting, the arguments have been fully considered but are moot in view of the new grounds of rejection set forth above as necessitated by claim amendment herein.
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.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JANNA NICOLE SCHULTZHAUS whose telephone number is (571)272-0812. The examiner can normally be reached on Monday - Friday 8-4.
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, Olivia Wise can be reached on (571)272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.N.S./Examiner, Art Unit 1685
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685