DETAILED ACTION
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 .
Status
This instant application No. 19/172,024 has claims 1-20 pending.
Priority / Filing Date
Applicant’s claim for priority of provisional application No. 63/633,397 is acknowledged. The effective filing date for this application is April 12, 2024.
Abstract
The abstract of the disclosure is objected due to the use of implied language. Note that in the abstract, the language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, “The disclosure concerns,” “The disclosure defined by this invention,” “The disclosure describes,” etc… See MPEP § 608.01(b).
Note that in the abstract, Applicant recites “Embodiments herein relate to…” on line 1. This citation clearly provokes the use of implied language. Revision and/or correction are required. One example is as follows:
“Chemical interaction is monitored ”
Drawings
The drawings filed on April 7, 2025 are acceptable for examination purposes.
Information Disclosure Statement
As required by M.P.E.P. 609(C), the Applicant’s submissions of the Information Disclosure Statements filed on April 7, 2025 and October 6, 2025 are acknowledged by the Examiner and the cited references have been considered in the examination of the claims now pending. As required by M.P.E.P. 609 C(2), a copy of each of the PTOL-1449s initialed and dated by the Examiner is attached to the instant Office action.
Claim Objections
Claims 16-17 are objected because each claim fails to provide proper antecedent basis for “the base dataset” which is/are not found previously in claims 11 and 15. Corrections are required.
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.
The claimed invention in claims 1-20 are directed to a judicial exception (i.e., an abstract idea) without significantly more.
Claims 1-20 pass step 1 of the 35 U.S.C. 101 analysis since each claim is directed to a method, a system comprising one or more processors (i.e., hardware components per [0095]-[0097] of instant specification and as known in the art), and a computer program product comprising a computer readable storage medium which excludes transitory signals per se ([00277] of instant specification).
Claims 1, 11, and 18 each recites, in part, elements that are directed to an abstract idea (“Courts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind.” Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015)). Each claim recites the limitations of identifying a raw dataset…; and generating matched data…comprising a set of matches… in each claim. The limitations, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitations in the mind but for the recitation of generic computer components (e.g., visually obtaining a raw dataset and/or writing down the observed data on paper; and mentally matching data between time series and chemical interaction and/or writing down on paper the matched data). That is, other than reciting generic components (e.g., memory, processor, and executable components), nothing in the claim precludes the limitations from being performed in the human mind per step 2A – prong 1 of the Abstract Idea Analysis. Thus, the limitations are parts of a mental process since they do not recite a specific improvement to the way the computer functions (e.g., improving memory usage or processing speed). Each claim uses high-level functional language such as identifying a raw dataset and generating matched data without specifying how the hardware is physically modified or how the technical steps different from a generic computer executing software. Thus, the claims, per step 2A – prong 2 of the Abstract Idea Analysis, cannot be integrated into a practical application. Each of the additional limitation(s) is no more than mere instructions to apply the exception using generic computer components (e.g., processor, memory, and computer-executable instructions).
The claims are reevaluated in step 2B to determining if each limitation is more than what is well-understood, routine, conventional activity in the field. The background of the limitations does not provide any indication that the computer components (e.g., AI model, computer processor executing instructions) are not off-the-shelf computer components. The Symantec, TLI, and OOP Techs court decisions cited in MPEP 2106.05(d)(II) indicate that mere receiving, generating, storing, determining, identifying, and transmitting of data over a network are a well-understood, routine, and conventional functions when claimed in a merely generic manner (as it is here). Accordingly, a conclusion that the claims are well-understood, routine, conventional (WURC) activity is supported under Berkheimer Option 2. For these reasons, there is no inventive concept in each claims, thus, the claims are ineligible.
Claim 2 further recites …the raw dataset comprises spectral vector data…obtained using an excitation beam… which narrows to a field-of-use limitation and data characterization. The data processing remains generic identification and matching done by a human mind and/or with the aid of pen/paper similar to the above analysis. Thus, the claim is ineligible.
Claim 3 further recites …normalizes the matched data by summing together two or more aspects of the raw dataset… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally calculating the sum of two or more aspects of the raw dataset). Thus, the claim is ineligible.
Claim 4 further recites …generates the matched data based on spectroscopy setting… which uses configuration or setting parameters to guide processing in a conventional manner. There is no particular non-generic spectroscopic control or hardware interaction is claimed but using a setting value in the software logic. Thus, the claim is ineligible.
Claim 5 further recites …normalizes the matched data by averaging together two or more aspects of the raw dataset… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally calculating the average of two or more aspects of the raw dataset). Thus, the claim is ineligible.
Claim 6 further recites …characterizes a suggested reasoning for a gap in the matched data… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally suggesting a reasoning for the found gap). Thus, the claim is ineligible.
Claim 7 further recites …remove a non-conforming aspect of the spectral vector data…from the raw dataset which is still a generic data cleaning by removing outliers (i.e., cosmic radiation artifacts). The claim does not specify a particular detection algorithm or hardware-level modification. The desired result is obtained using a generic processing component based on generic data. Thus, the claim is ineligible.
Claim 8 further recites …evaluates a trend at the set of matches… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally evaluating a trend); and …generates a notification corresponding to progress… which is an extra-solution and WURC activity similar to the above analysis (e.g., generating a notification via a GUI when a certain condition is met) Thus, the claim is ineligible.
Claim 9 further recites …outputs a suggestion of a change to a parameter…or directs a change of the parameter of the reaction device. The suggesting or directing parameter changes is abstract decision-making with non-concrete control algorithm, actuator interface or specific control logic is being claimed. The claim elements only use analyzed results to advise or command a change in a generic way. Thus, the claim is ineligible.
Claim 10 further recites …identifies a second raw dataset…, generates a second set of matches…, correlates the first set of matches… which can be done in a human mind with the aid of pen/paper similar to the above analysis (e.g., mentally identifying the second raw dataset, writing down on paper the set of matches, and mentally correlating the first and second set of matches). Thus, the claim is ineligible.
Claim 12 further recites …the raw dataset comprises spectral vector data…obtained using an excitation beam… which narrows to a field-of-use limitation and data characterization; and …the generating the matched data is executed based on a specified time zone setting which is a routine data-handling procedure wherein the abstract matching logic takes time zone parameters into account with no particular time-sync or clock-control solution is being claimed. Thus, the claim is ineligible.
Claim 13 further recites generating…display data… which is an extra-solution and WURC activity of data displaying similar to the above analysis. Thus, the claim is ineligible.
Claim 14 further recites …normalizing…the matched data by averaging together two or more aspects of the raw dataset… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally calculating the average of two or more aspects of the raw dataset). Thus, the claim is ineligible.
Claim 15 further recites …identifying…a data subset of the matched data… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., visually identifying a data subset for mental calculation). Applicant is noted that using an mathematical model to select a data subset for aggregation is a high-level ML application by just applying the mathematical model to data on a generic computer. Thus, the claim is ineligible.
Claim 16 further recites …customizing…by aggregating the base dataset…wherein the constituent-specific dataset is smaller…. which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally aggregating the base dataset with a constituent-specific dataset) wherein weighting one dataset more heavily than another is a routine mathematical practice of dataset weighting. Thus, the claim is ineligible.
Claim 17 further recites …customizing…by filtering the base dataset…to remove data… which can be implemented in a human mind and/or with the aid of pen/paper similar to the above analysis (e.g., mentally filtering dataset with a certain similarity condition). Thus, the claim is ineligible.
Claims 19-20 are also ineligible for the similar reasons presented above.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 4, 6, and 8-11 are rejected under AIA 35 U.S.C. 102(a)(1) as being anticipated by Webster et al. (Pub. No. US 2019/0137338, published on May 9, 2019; hereinafter Webster).
Regarding claims 1, and 11, Webster clearly shows and discloses a computer-implemented method (Abstract); a system, comprising a memory that stores computer executable components; and a processor that executes the computer executable components stored in the memory to implement the method ([0018]-[0020]) comprising:
identifying, by an identifying component or a system operatively coupled to a processor, a raw dataset corresponding to a chemical interaction (Raman spectroscopy processes inelastic light scattering in order to provide specific information as to the presence of particular molecular bonds within the sample, [0084]. The controller 50 can collect Raman spectra that covers expected process variations that may occur within the bioreactor 10. The controller 60 can then determine the concentration of the one or more parameters, [0088]); and
generating, by a matching component or the system, matched data, the matched data comprising a set of matches between time series data and chemical interaction data (The amount of time the cell culture is propagated can vary depending upon various factors. In general, for instance, the cell culture can be propagated for a period of time from about 6 days to about 30 days, such as from about 8 days to about 20 days. In one embodiment, concentration measurements of one or more parameters can be obtained in the initial stages of cell growth. For instance, Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]),
wherein the time series data corresponds to a range of time over which the chemical interaction was observed (Measurements can be taken at least every 24 hours, such as at least every 20 hours, such as at least every 15 hours, such as at least every 10 hours, such as at least every 8 hours, such as at least every 4 hours, such as at least every 2 hours, such as at least every hour, such as at least every 30 minutes, such as at least every 10 minutes, such as at least every 5 minutes, [0084]), and
wherein the chemical interaction data is comprised by at least a portion of the raw dataset (one can observe the shift in photons from the original wavelength. For example, the interaction of the beam of light with chemical constituents within the cell culture results in laser photons being shifted up or down, [0082]).
Regarding claim 4, Webster further discloses generating the matched data based on a spectroscopy setting, wherein the spectroscopy setting corresponds to a spectroscopy device having been employed to generate the raw dataset (The autonomous control is coupled with Raman spectroscopy which allows for continuous or periodic noninvasive monitoring of one or more parameters within the bioreactor. Raman spectroscopy can, for instance, continuously monitor and collect information within a wavelength region, such as from about 800 nm to about 2500 nm, and collect information about the overtones of fundamental absorption bands observed, which can be used to determine parameter concentrations, [0058]).
Regarding claim 6, Webster further discloses characterizing a suggested reasoning for a gap in the matched data corresponding to a subrange of the range of time (The inclusion of such data may enable the development of an improved predictive model. For instance, product concentration is correlated with time and VCC, however this correlation varies significantly between cell lines and products. If the model was estimating product concentration from correlations with time and VCC this may help explain why the model was slightly off when predicting product concentration at later time points, for a cell line not included in the calibration model (FIG. 4G)), [0117]).
Regarding claim 8, Webster further discloses:
evaluating a trend at the set of matches (Referring to FIG. 5, glucose concentration is illustrated over time. As shown, the process of the present disclosure is capable of maintaining glucose levels within carefully controlled limits, especially in comparison to prior systems that simply adjust the feed rate of glucose based on daily measurements, [0119]); and
a notifying component that generates a notification corresponding to progress of a constituent involved in the chemical interaction as compared to a progress threshold (the controller can be programmed with a predictive model that can predict future concentrations of the one or more parameters to ensure that optimal conditions remain within the bioreactor from the beginning of the process to the end of the process. Programming the controller 60 with a predictive model, for instance, in combination with continuous monitoring, provides potential feedback control for very complex solutions, [0094]).
Regarding claim 9, Webster further discloses an adjusting component that, based on the generating of the set of matches, outputs a suggestion of a change to a parameter of a reaction device controlling progress of a constituent of the chemical interaction, or directs a change of the parameter of the reaction device (The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters. After receiving the information for a period of time, the controller 60 can then selectively increase or decrease a parameter influencing substance that may be fed or withdrawn from the bioreactor 10, [0096]).
Regarding claim 10, Webster then discloses identifying a second raw dataset corresponding to the chemical interaction (Raman spectroscopy processes inelastic light scattering in order to provide specific information as to the presence of particular molecular bonds within the sample, [0084]. The controller 50 can collect Raman spectra that covers expected process variations that may occur within the bioreactor 10. The controller 60 can then determine the concentration of the one or more parameters, [0088]. The system can be configured to monitor glucose concentration in conjunction with at least one other parameter, such as lactate concentration, [0010], [0097]),
wherein the matching component generates a second set of matches between an extension of the time series data and second chemical interaction data comprised by the second raw dataset (The amount of time the cell culture is propagated can vary depending upon various factors. In general, for instance, the cell culture can be propagated for a period of time from about 6 days to about 30 days, such as from about 8 days to about 20 days. In one embodiment, concentration measurements of one or more parameters can be obtained in the initial stages of cell growth. For instance, Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]. It is clear that spectra parameters of lactate can be measures and collected subsequent to spectra parameters of lactose, [0010], 0097]),
wherein the extension of the time series data corresponds to a second range of time subsequent to the range of time (Measurements can be taken at least every 24 hours, such as at least every 20 hours, such as at least every 15 hours, such as at least every 10 hours, such as at least every 8 hours, such as at least every 4 hours, such as at least every 2 hours, such as at least every hour, such as at least every 30 minutes, such as at least every 10 minutes, such as at least every 5 minutes, [0084]. It is clear that spectra parameters of lactate can be measures and collected subsequent to spectra parameters of lactose within a different time period, [0010], 0097]), and
wherein the computer executable components further comprise an evaluating component that correlates the first set of matches to the second set of matches (Based upon the monitored concentration of both parameters, the controller 60 can then automatically make adjustments to the flow of one or more nutrient media into the bioreactor 10. The nutrient media, for instance, may contain glucose. In this manner, glucose concentrations can be maintained within preset parameters in conjunction with maintaining lactate concentrations within preset parameters. In one embodiment, for instance, glucose levels are maintained so as to minimize fluctuations in lactate levels and maintain lactate levels below desired set points, [0097]).
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.
Claims 2-3, 5, 13-14, 18, and 20 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Webster in view of Duong et al. (Pub. No. US 2008/0065334, published on March 13, 2008; hereinafter Duong).
Regarding claim 2, Webster further discloses the raw dataset comprises spectral data (Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]) corresponding to Raman spectroscopy readings obtained using an excitation beam on the chemical interaction (the light conveying device 50 is in communication with a Raman spectrometer 54. The light source 52 is for exposing a cell culture within the bioreactor 10 to a beam of light. The light conveying device 50 is then configured to convey scattered light reflected off of the cell culture to the Raman spectrometer 54 for determining the concentration of one or more parameters within the bioreactor 10. The Raman spectrometer 54 and/or the light source 52 can be in communication with a controller 60. The controller 60 can determine the concentration of one or more parameters within the bioreactor 10 from the information or data received from the Raman spectrometer 54, [0074]).
Duong then discloses the raw dataset comprises spectral vector data (determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Duong with the teachings of Webster for the purpose of detection for selective chemical compounds based on correlation between parameterized weight and predicted originals using spectral vectors.
Regarding claim 3, Duong then discloses normalizing the matched data by summing together two or more aspects of the raw dataset (From laboratory set up, a set of single spectra of 11 chemicals using 16 elements is collected in the ENose sensor array; it is averaged and shown in FIG. 5, [0063]. It is clear that calculating the average requires summing of two or more collected elements) which are consecutively ordered by time over a subrange of the range of time (obtaining sampled data by sampling data from a database containing air samples of an unknown open environment; arranging data input in time intervals for each sensor; inputting a subset of the sampled data respective to time for each sensor; calculating operating points of the subset of the sampled data; linearizing the subset of the sampled data using the operating points; determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
Regarding claim 5, Duong further discloses normalizing the matched data by averaging together two or more aspects of the raw dataset (From laboratory set up, a set of single spectra of 11 chemicals using 16 elements is collected in the ENose sensor array; it is averaged and shown in FIG. 5, [0063]) which are consecutively ordered by time over a subrange of the range of time (obtaining sampled data by sampling data from a database containing air samples of an unknown open environment; arranging data input in time intervals for each sensor; inputting a subset of the sampled data respective to time for each sensor; calculating operating points of the subset of the sampled data; linearizing the subset of the sampled data using the operating points; determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
Regarding claim 13, Webster further discloses generating, by the system, display data comprising a concentration spectrum defining a concentration of a constituent of the chemical interaction over a subrange of the range of time (Referring to FIG. 5, glucose concentration is illustrated over time. As shown, the process of the present disclosure is capable of maintaining glucose levels within carefully controlled limits, especially in comparison to prior systems that simply adjust the feed rate of glucose based on daily measurements, [0119]).
Duong then discloses the raw dataset comprises spectral vector data (determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
Regarding claim 14, Duong further discloses normalizing, by the system, the matched data by averaging together two or more spectral vectors of the raw dataset (From laboratory set up, a set of single spectra of 11 chemicals using 16 elements is collected in the ENose sensor array; it is averaged and shown in FIG. 5, [0063]), wherein the two or more spectral vectors are consecutively ordered by time over a subrange of the range of time (obtaining sampled data by sampling data from a database containing air samples of an unknown open environment; arranging data input in time intervals for each sensor; inputting a subset of the sampled data respective to time for each sensor; calculating operating points of the subset of the sampled data; linearizing the subset of the sampled data using the operating points; determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
Regarding claim 18, Webster clearly shows and discloses a computer program product facilitating a process for chemical interaction monitoring, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, and the program instructions executable by a processor to cause the processor to implement the method ([0018]-[0020]) comprising:
identifying, by the processor, a raw dataset of spectral data corresponding to a chemical interaction (Raman spectroscopy processes inelastic light scattering in order to provide specific information as to the presence of particular molecular bonds within the sample, [0084]. The controller 50 can collect Raman spectra that covers expected process variations that may occur within the bioreactor 10. The controller 60 can then determine the concentration of the one or more parameters, [0088]); and
generating, by the processor, matched data comprising a set of matches between time series data and chemical interaction data (The amount of time the cell culture is propagated can vary depending upon various factors. In general, for instance, the cell culture can be propagated for a period of time from about 6 days to about 30 days, such as from about 8 days to about 20 days. In one embodiment, concentration measurements of one or more parameters can be obtained in the initial stages of cell growth. For instance, Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]),
wherein the time series data corresponds to a range of time over which the chemical interaction was observed (Measurements can be taken at least every 24 hours, such as at least every 20 hours, such as at least every 15 hours, such as at least every 10 hours, such as at least every 8 hours, such as at least every 4 hours, such as at least every 2 hours, such as at least every hour, such as at least every 30 minutes, such as at least every 10 minutes, such as at least every 5 minutes, [0084]), and
wherein the chemical interaction data is comprised by at least a portion of the spectral data of the raw dataset (one can observe the shift in photons from the original wavelength. For example, the interaction of the beam of light with chemical constituents within the cell culture results in laser photons being shifted up or down, [0082]).
Duong then discloses the raw dataset comprises spectral vector data (determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Duong with the teachings of Webster for the purpose of detection for selective chemical compounds based on correlation between parameterized weight and predicted originals using spectral vectors.
Regarding claim 20, Duong further discloses normalizing, by the processor, the matched data by averaging together two or more spectral vectors of the raw dataset (From laboratory set up, a set of single spectra of 11 chemicals using 16 elements is collected in the ENose sensor array; it is averaged and shown in FIG. 5, [0063]), wherein the two or more spectral vectors are consecutively ordered by time over a subrange of the range of time (obtaining sampled data by sampling data from a database containing air samples of an unknown open environment; arranging data input in time intervals for each sensor; inputting a subset of the sampled data respective to time for each sensor; calculating operating points of the subset of the sampled data; linearizing the subset of the sampled data using the operating points; determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
Claim 7 is rejected under AIA 35 U.S.C. 103 as being unpatentable over Webster in view of Akkus et al. (Pub. No. US 2015/0204789, published on July 23, 2015; hereinafter Akkus).
Regarding claim 7, Webster further discloses the matched data comprises spectral vector data of the raw dataset (concentration measurements of one or more parameters can be obtained in the initial stages of cell growth. For instance, Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]), and
wherein the computer executable components further comprise:
a processing component that processes the matched data to remove a non- conforming aspect of the spectral vector data (When detecting Raman-shifted radiation scattered by a sample, for instance, other suitable filters can include cut-off filters, [0080]), and wherein the processing component removes the non-conforming aspect from the raw dataset (Next regions outside the fingerprint region were removed (<500 cm-1 and >1700 cm-1 for most models) to prevent these signals being given inappropriate weight in the resulting models (FIG. 2A). If left in these regions of noise can mask the impact of Raman regions correlated to changes in metabolite concentration (e.g., residual glucose concentration) hindering model robustness. After spectral trimming, different combinations of spectral pre-processing were applied and PLS models were constructed. The raw spectra from the different cell culture runs showed a baseline shift over the course of the experiments which was reduced by application of a 1st derivative filter (FIG. 2B), [0107]).
Akkus then discloses the non-conforming aspect of the spectral vector data corresponds to a cosmic radiation emission (The dark current noise due to deep cooling was acquired pre hoc and autocorrected for every image. Outlier points due to cosmic radiation were removed from the background corrected image, [0043]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Akkus with the teachings of Webster for the purpose of enhancing spectral data collected by a hyperspectral Raman imaging system having the ability to focus on excitation laser beam over a relatively wide field of view due offsetting errors associated with external radiation.
Claims 12, and 19 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Webster in view of Duong and further in view of Kitazawa et al. (Pub. No. US 2015/0139445, published on May 21, 2015; hereinafter Kitazawa).
Regarding claim 12, and 19, Webster then discloses the raw dataset comprises spectral data (Raman spectra can be obtained for different parameters over the first 1 to 6 days, such as over the first 2 to 4 days. The controller 60 can receive this information and begin building predictive data that predicts future concentrations of each of the monitored parameters, [0096]) corresponding to Raman spectroscopy readings obtained using an excitation beam (the light conveying device 50 is in communication with a Raman spectrometer 54. The light source 52 is for exposing a cell culture within the bioreactor 10 to a beam of light. The light conveying device 50 is then configured to convey scattered light reflected off of the cell culture to the Raman spectrometer 54 for determining the concentration of one or more parameters within the bioreactor 10. The Raman spectrometer 54 and/or the light source 52 can be in communication with a controller 60. The controller 60 can determine the concentration of one or more parameters within the bioreactor 10 from the information or data received from the Raman spectrometer 54, [0074]).
Duong then discloses the raw dataset comprises spectral vector data (determining a data distribution corresponding to the linearized subset of the sampled data; performing an independent component analysis (ICA) on the linearized subset of the sampled data by using the data distribution, wherein the ICA generates independent component vectors representing the subset of the sampled data, [0016]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Duong with the teachings of Webster for the purpose of detection for selective chemical compounds based on correlation between parameterized weight and predicted originals using spectral vectors.
Kitazawa then discloses the generating the matched data is executed based on a specified time zone setting (a spectrogram is one time-frequency representation. The spectrogram is data obtained by cutting an input temporal waveform signal by applying a window function while shifting a time zone for every predetermined time length, converting the frequencies of the cut signals by FFT or the like, and arranging the obtained frequency spectra in time series, [0032]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Kitazawa with the teachings of Webster, as modified by Duong, for the purpose of determining whether a plurality of acquired datasets contain a specific characteristic corresponding to a desired classification based on matching spectral data associated with the acquired datasets.
Claims 15-17 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Webster in view of Da Costa Martins (Pub. No. US 2021/0020276, published on January 21, 2021; hereinafter Martins).
Regarding claim 15, Martins then discloses identifying, by a machine learning model, a data subset of the matched data for being aggregated, wherein the data subset corresponds to a set of specified measurement factors (When any new spectra is projected into the feature space and has no neighbors, its immediately quarantined. If it has neighbors, the learning process begins using Algorithms 1 and 2 for searching both local models and build the local co-variance map. Only when a new data in conjunction with the quarantined data are able to produce a consistent local model and model path, the data is certified to pass into the knowledgebase. The knowledgebase receives constant updates as new data is added, and predictions are extended to new regions of the feature space, [0125]).
It would have been obvious to an ordinary person skilled in the art at the time of the invention was effectively filed to incorporate the teachings of Martins with the teachings of Webster for the purpose of analyzing collected spectra using a machine-learning model to generate refined spectra from raw collected samples for enhanced quality control, authentication, and diagnostics.
Regarding claim 16, Martins further discloses customizing, by the system, the machine learning model by aggregating the base dataset with a constituent-specific dataset corresponding to a constituent of the chemical interaction (the sample is biological and the constituent or constituents are biological metabolites, in particular blood metabolites, [0075]. Spectroscopy AI applied to biological systems must always self-learn. The developed system is able to self-learn from an initial, very limited, knowledgebase, by constantly adding new data that the system cannot predict, [0133]), wherein the constituent-specific dataset is smaller than the base dataset and is weighted higher than the base dataset for the customizing (Only when a new data in conjunction with the quarantined data are able to produce a consistent local model and model path, the data is certified to pass into the knowledgebase, [0135]).
Regarding claim 17, Martins further discloses customizing, by the system, the machine learning model by filtering the base dataset, upon which the machine learning model operates, to remove data having a similarity level relative to a constituent-specific dataset corresponding to a constituent of the chemical interaction, wherein the similarity level does not satisfy a similarity level threshold (By performing this transformation, most of the unrelated systematic and random components of the spectra and composition are eliminated. The system self-learns how to extract the best combinations of μ that quantify a particular metabolite by evolutionary algorithms, such as, simplex, particle swarn optimization and genetic algorithms. Once a feature space transformation is learned for a particular sub-space, the system does not need to re-calculate, but uses the transformation directly to produce a prediction, [0141]).
Relevant Prior Art
The following references are deemed relevant to the claims:
Robertson et al. (Pub. No. US 2021/0215610) teaches using Raman spectroscopy to analyze biological samples and provide chemometric analysis, a Raman Chemometrics (Rametrix™) Toolbox and Raman spectral correction/baselining methods are developed and applied for use with MATLAB®. The LITE version of the Rametrix™ Toolbox provides a graphical user interface for applications of spectrum analysis.
O’Mahony-Hartnett et al. (Pub. No. US 2024/0168033) teaches determining a glycan structure on a glycosylated molecule using PAT tool, such as Raman spectroscopy, and generating a regression model that can be used by a computing device to determine a level of one or more glycan structures on the therapeutic protein within a bioreactor. A glycosylated molecule is produced having a desired glycan structure using a PAT tool that generates spectral data, and determining a level of one or more glycan structures on the therapeutic protein within a bioreactor by using one or more regression models.
Contact Information
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to Son Hoang whose telephone number is (571) 270-1752. The Examiner can normally be reached on Monday – Friday (7:00 AM – 4:00 PM).
If attempts to reach the Examiner by telephone are unsuccessful, the Examiner’s supervisor, Sherief Badawi can be reached on (571) 272-9782. 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 http://pair-direct.uspto.gov. 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.
/SON T HOANG/Primary Examiner, Art Unit 2169
December 27, 2025