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 .
Election/Restrictions
Examiner notes that Applicant elects Group I, corresponding to claims 1-10, and that the restriction is traversed between Groups I and II. Examiner accepts Applicant’s arguments and correspondingly examines Groups I (Claims 1-10) and II (Claims 16-21) in this office action.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 03/07/2024 and 05/17/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Specification
The disclosure is objected to because of the following informalities:
Para[0032] recites “one of two solvents or is selected using valve”, which should be corrected to make the statement clearer.
Para[0043] recites “dropping a vertical line from certain local minima 506”, which is not shown in Fig. 5.
Para[0051] recites “small interfering peak 520” which should be corrected with the correct label.
Para[0061] recites “may be ranked higher than those with the smallest deviations”, which should be “may be ranked higher than those with the largest deviations.”
Appropriate correction is required.
Claim Objections
Claim 16 objected to because of the following informalities:
Claim 16 recites “second prospective peak integration”, which should be “the second prospective peak integration”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 17-19 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 17 recites “the display”. There is insufficient antecedent basis for this limitation in the claim.
Claim 18 recites “the peak integration parameters”. There is insufficient antecedent basis for this limitation in the claim.
Claim 19 recites “the peak characteristics”. There is insufficient antecedent basis for this limitation in the claim.
Claims that depend on the above rejected claims are also rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10 and 16-21 are rejected under 35 U.S.C. 101. The claimed invention is directed to the abstract concept of performing mental steps without significantly more. The claim(s) recite(s) the following abstract concepts in BOLD of
With regards to Claim 1,
A method for improving mass spectrometry system measurement, the method comprising:
accessing an ion data series for an ion count rate generated from ions detected by a detector of a mass spectrometry system;
generating a set of prospective peak integrations for a target peak in the ion data series, wherein each prospective peak integration in the set of prospective peak integrations is generated based on a different set of peak integration parameters, and each prospective peak integration is characterized by at least one peak characteristic;
providing, as input to a trained machine learning model, the at least one peak characteristic for each prospective peak integration in the set of prospective peak integrations;
processing the provided input, by the trained machine learning model, to generate an output from the trained machine learning model;
based on the output, generating a ranking of one or more of the prospective peak integrations; and
based on one of the prospective peak integrations, generating an ion amount represented by the target peak.
With regards to Claim 16,
A method for improving mass spectrometry system measurement, the method comprising:
accessing an ion data series for an ion count rate generated from ions detected by a detector of a mass spectrometry system;
generating, according to first peak integration parameters, a first prospective peak integration for an identified peak in the ion data series, wherein the first prospective peak integration is characterized by first peak characteristics;
generating, according to second peak integration parameters, a second prospective peak integration for the identified peak in the ion data series, wherein the second prospective peak integration is characterized by second peak characteristics;
providing, as input to a trained machine learning model:
the first peak characteristics; and
the second peak characteristics;
processing the provided input, by the trained machine learning model, to generate an output from the trained machine learning model;
based on the output, generating a ranking of the first prospective peak integration and second prospective peak integration; and
based on at least one of the first prospective peak integration or the second prospective peak integration, generating an ion amount represented by the identified peak.
Under step 1 of the eligibility analysis, we determine whether the claims are to a statutory category by considering whether the claimed subject matter falls within the four statutory categories of patentable subject matter identified by 35 U.S.C. 101: process, machine, manufacture, or composition of matter. The above claims are considered to be in a statutory category of a process.
Under Step 2A, Prong One, we consider whether the claims recite a judicial exception (abstract idea). In the above claim, the highlighted portions constitute an abstract idea because, under a broadest reasonable interpretation, they recite limitations that fall into/recite abstract idea exceptions. Specifically, under the 2019 Revised Patent Subject Matter Eligibility Guidance, they fall into the grouping of subject matter that, when recited as such in a claim limitation, cover performing mathematics or mental steps, see MPEP 2106.04(a)(2). Additionally, the claim limitations merely indicate a field of use or technological environment in which the judicial exception is performed, which is the field of improving mass spectrometry system measurement.
Next, under Step 2A, Prong Two, we consider whether the claims that recite a judicial exception are integrated into a practical application. In this step, we evaluate whether the claims recite additional elements that integrate the exception into a practical application of that exception.
This judicial exception is not integrated into a practical application because there is no improvement to another technology or technical field; improvements to the functioning of the computer itself; a particular machine; effecting a transformation or reduction of a particular article to a different state or thing. Examiner notes that even though the claimed methods are tied to a particular machine or apparatus (i.e. a mass spectrometry system), it does not represent an improvement to another technology or technical field as the mass spectrometry system was already produced before the mental steps explained in Step 2A Prong 1. Similarly, there are no other meaningful limitations linking the use to a particular technological environment. Finally, there is nothing in the claim that indicates an improvement to the functioning of the computer itself or transform a particular article to a new state.
Finally, under Step 2B, we consider whether the additional elements are sufficient to amount to significantly more than the abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because every step in BOLD of Claims 1 and 16 point to a mental or mathematical step. In addition, in Claims 1 and 16 the step of being detected by a detector of a mass spectrometry system amounts to nothing more than necessary data gathering and outputting as recited in MPEP section 2106.05(g). Necessary data gathering (i.e. receiving data) and outputting is considered extra solution activity in light of Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092- 93 (Fed. Cir. 2015).
Claims 2-10 and 17-21 are rejected under 35 U.S.C. 101 as they are further directed to abstract ideas.
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.
Claim(s) 1, 3-4, 6-10, 16, and 18-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Dai (US 20120239306 A1), in view of Weigand (US 10627289 B1) and Tomlinson (US 5121443 A).
With regards to Claim 1, Dai teaches
accessing an ion data series for an ion count rate generated from ions (See Abstract “ analyzing data (i.e. accessing an ion data series) from a component separation/mass spectrometer (CS-MS)” and see para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”. Therefore, the data from the CS-MS is an ion-data series for an ion count rate which are generated from ions. Note that the intensity is an ion count rate, see para[0038] “the area of the selected intensity peak 225 may represent, for example, a relative quantity of the corresponding sample component (i.e., molecule, ion, or metabolite) within the sample”. In order for the area under the curve to be an amount of ions, the intensity is an ion count rate.) detected by a detector of a mass spectrometry system (See Abstract “a component separation/mass spectrometer (CS-MS) (i.e. a mass spectrometry system)” and Para[0029] “comprise a separator portion (i.e., a chromatograph) and/or a detector portion (i.e., a spectrometer) (i.e. the CS-MS is a detector)”);
generating a set of prospective peak integrations for a target peak (See Para[0043] “determine and designate (i.e. generate) the template integration procedure and to apply the template integration procedure to the selected intensity peaks of a second portion of the two-dimensional data sets, wherein the second portion of the two-dimensional data sets previously had the areas of the selected intensity peaks (i.e. the target peak is a single peak within the selected intensity peaks) thereof determined (i.e. generate, so both the template integration procedure and the other integration procedure are generated, making them combined a generated set of prospective peak integration procedures, and they are prospective as they can potentially accurately calculate the area) by one of the integration procedures other than the template integration procedure”.) in the ion data series (See Abstract “ analyzing data (i.e. accessing an ion data series) from a component separation/mass spectrometer (CS-MS)” and see para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”. Therefore, the data from the CS-MS is an ion-data series for an ion count rate which are generated from ions.), wherein each prospective peak integration in the set of prospective peak integrations is generated based on a different set of peak integration parameters, and each prospective peak integration is characterized by at least one peak characteristic (See Para[0043] “Namely, the various integration procedures may be designated as a "base-base" integration (see, e.g., FIG. 6a), a "base-drop" integration (see, e.g., FIG. 6c), a "drop-base" integration (see, e.g., FIG. 6b), or a "drop-drop" integration.” Therefore, from Fig. 6, we see that the peak characteristics of Fig. 6b are intensity peak origin 500 and intensity peak terminus 550 for the integration method of 6b, and we see that the peak characteristics of Fig. 6c are intensity peak origin 500 and intensity peak terminus 550 for the integration method of Fig. 6c (Examiner notes that 6c is for a different target peak than that of 6b, but according to Para[0043] above, two integration procedures can be used for one identified peak, so 6c is being shown here as an example of another integration method.). In addition, the peak integration parameters for the integration method of 6b are the baseline intensity 575 and element 600 while for 6c the peak integration parameters are the baseline intensity 575 and element 600, which are different from those of Fig. 6b.);
based on one of the prospective peak integrations, generating an ion amount represented by the target peak (See Abstract “The intensity peak (i.e. the target peak) indicates a sample component, and the area (i.e. calculated from the prospective peak integration, and it is prospective because it can potentially accurately calculate the area) thereof indicates a relative quantity of the sample component (i.e. the intensity peak generates an ion amount based on its area).”).
Dai is silent to the language of
providing, as input to a trained machine learning model, the at least one peak characteristic for each prospective peak integration in the set of prospective peak integrations;
processing the provided input, by the trained machine learning model, to generate an output from the trained machine learning model;
based on the output, generating a ranking of one or more of the prospective peak integrations.
Wiegand teaches
providing, as input to a machine learning model, the at least one peak characteristic for each prospective peak integration in the set of prospective peak integrations (See Column 7 lines 9-14 “90 spectra total were produced, 30 each with peak positions at 2917 cm−1 (unaltered), 2916 cm−1 and 2918 cm−1. A conventional algorithm and the relative algorithm (i.e. each prospective peak integration in the set of prospective peak integrations, where the set includes both the relative and the conventional algorithm, and they are prospective because they can potentially accurately calculate the area), according to the present disclosure described herein, were both used to integrate the peak areas, yielding two sets of areas. A linear regression (univariate) (i.e. a machine learning model) was done (i.e. processing the provided input by the machine learning model) on each set of areas (i.e. the at least one peak characteristic (the peak positions) was provided as input to the linear regression for the relative and conventional algorithms), and a plot of the error (true-predicted) was made for each linear regression (i.e. the error is from the output generated from the linear regression, making the error an output generated from the machine learning model).”);
processing the provided input, by the machine learning model, to generate an output from the trained machine learning model (See Column 7 lines 9-14);
based on the output, generating a ranking of one or more of the prospective peak integrations (See Column 7 lines 15-18 “ FIG. 9 shows a plot of the range of errors for both sets of data. As evident from these plots (i.e. based on the output of the linear regression, from which the error was calculated), in most cases, the reduction in error is dramatic when using relative integration of the present disclosure (i.e. generating a ranking, of the one or more of the prospective peak integrations, as it is shown that the relative integration performs more accurately than the conventional integration).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai wherein providing, as input to a machine learning model, the at least one peak characteristic for each prospective peak integration in the set of prospective peak integrations; processing the provided input, by the machine learning model, to generate an output from the machine learning model; based on the output, generating a ranking of one or more of the prospective peak integrations is done like in Weigand in order to rank the accuracy of each integration method and determine which one to use for accurate analysis of the target peak via using a machine learning method like linear regression that can input a peak characteristic.
Dai and Weigand are silent to the language of
a trained machine learning model.
Tomlinson teaches
a trained machine learning model (See Abstract “The peak data including the baseline level upon which the peak is superimposed is analyzed using one of lookup-tables, neural nets (i.e. a trained machine learning model, See Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net (i.e. providing as input to a machine learning model). The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”)”);
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein a trained machine learning model is used like in Tomlinson in order to utilize an automated method to compare the two prospective integration methods of Weigand.
With regards to Claim 3, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai further teaches
wherein the peak integration parameters include at least one of a smoothing parameter, an expected-time parameter, a filtering parameter, a baseline parameter (See Fig. 6 the baseline intensity 575), or a peak-splitting parameter.
With regards to Claim 4, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai further teaches
wherein the at least one peak characteristic includes at least one of: an integrated area (See Abstract “An integration procedure determines the area of selected peaks”), peak height, peak start time, peak end time, center time, peak width, and peak smoothness.
With regards to Claim 6, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai and Weigand are silent to the language of
wherein one or more of the peak integration parameters are also included as input to the trained machine learning model.
Tomlinson teaches
wherein one or more of the peak integration parameters are also included as input to the trained machine learning model (See Abstract “The peak data including the baseline level (i.e. the baseline level is a peak integration parameter (See Column 3 lines 59-62 “The blank chromatogram is subtracted from the chromatogram of interest before peak integration so as to obtain a baseline corrected chromatogram (i.e. the baseline is a parameter that can contribute to the peak integration)”) upon which the peak is superimposed is analyzed using one of lookup-tables, neural nets (i.e. a trained machine learning model, See Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”)” Therefore, the baseline level (i.e. at least one of the peak integration parameters) is input into the trained neural network.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein one or more of the peak integration parameters are also included as input to the trained machine learning model like in Tomlinson in order to provide a more informed output about the quality of the integration method being analyzed.
With regards to Claim 7, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai is silent to the language of
wherein the set of prospective peak integrations includes at least 50 prospective peak integrations.
Weigand teaches
wherein the set of prospective peak integrations includes at least 50 prospective peak integrations (See Column 6 lines 46-48 “Specify a window to find the peak maximum in terms of wavelength or wavenumber (e.g., 2915 cm−1 to 2919 cm−1)”. Therefore, an infinite number of prospective peak integrations are possible, with each prospective peak integration using a different number within the window, so a set of 50 prospective peak integrations can be defined by specifying 50 numbers within the window of 2915 cm−1 to 2919 cm−1. They are all prospective because they can potentially accurately calculate the area).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai wherein the set of prospective peak integrations includes at least 50 prospective peak integrations like in Weigand in order to have a multitude of options to determine the best integration method.
With regards to Claim 8, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai and Weigand are silent to the language of
wherein the trained machine learning model is one of a neural network, a support vector machine, a K-nearest neighbors algorithm, a hidden Markov model, or a random forest.
Tomlinson teaches
wherein the trained machine learning model is one of a neural network (See Abstract “The peak data including the baseline level upon which the peak is superimposed is analyzed using one of lookup-tables, neural nets (i.e. a trained machine learning model, See Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”)”), a support vector machine , a K-nearest neighbors algorithm, a hidden Markov model, or a random forest.
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein the trained machine learning model is one of a neural network, a support vector machine, a K-nearest neighbors algorithm, a hidden Markov model, or a random forest like in Tomlinson in order to clearly define an efficient and automated method to identify the best performing integration method.
With regards to Claim 9, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai further teaches
wherein the ion data series is part of a chromatogram (See Fig. 3, where the figure is a chromatogram, and the data points is the ion data series (See para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”), therefore making it a part of the chromatogram).
With regards to Claim 10, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai further teaches
wherein data points within the ion data series indicate an ion count rate and sampling interval time (See Abstract “ The intensity peak indicates a sample component, and the area thereof indicates a relative quantity of the sample component.” And see Fig. 3, where the data points comprising the curve is the ion data series, and they indicate an ion count rate via the y-axis and the sampling interval is indicated via the x-axis. Note that the intensity is an ion count rate, See Para[0038] “the area of the selected intensity peak 225 may represent, for example, a relative quantity of the corresponding sample component (i.e., molecule, ion, or metabolite) within the sample”. In order for the area under the curve to be an amount of ions, the intensity is an ion count rate.).
With regards to Claim 16, Dai teaches
accessing an ion data series for an ion count rate generated from ions (See Abstract “ analyzing data (i.e. accessing an ion data series) from a component separation/mass spectrometer (CS-MS)” and see para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”. Therefore, the data from the CS-MS is an ion-data series for an ion count rate which are generated from ions. Note that the intensity is an ion count rate, see Para[0038] “the area of the selected intensity peak 225 may represent, for example, a relative quantity of the corresponding sample component (i.e., molecule, ion, or metabolite) within the sample”. In order for the area under the curve to be an amount of ions, the intensity is an ion count rate.) detected by a detector of a mass spectrometry system (See Abstract “a component separation/mass spectrometer (CS-MS) (i.e. a mass spectrometry system)” and Para[0029] “comprise a separator portion (i.e., a chromatograph) and/or a detector portion (i.e., a spectrometer) (i.e. the CS-MS is a detector)”);
generating, according to first peak integration parameters, a first prospective peak integration for an identified peak in the ion data series, wherein the first prospective peak integration is characterized by first peak characteristics (See Para[0043] “determine and designate (i.e. generate) the template integration procedure (i.e. a first prospective peak integration, and it is prospective as it can potentially accurately calculate the area) and to apply the template integration procedure to the selected intensity peaks of a second portion of the two-dimensional data sets, wherein the second portion of the two-dimensional data sets previously had the areas of the selected intensity peaks (i.e. the identified peak is a single peak within the selected intensity peak) thereof determined by one of the integration procedures other than the template integration procedure (i.e. generate a second prospective peak integration, and it is prospective as it can potentially accurately calculate the area. Also the second prospective peak integration is for the same identified peak as the one for the template integration procedure.)”. The first prospective peak integration and the second prospective peak integration are therefore part of the ion data series, and it is an ion data series from the Abstract “ analyzing data (i.e. accessing an ion data series) from a component separation/mass spectrometer (CS-MS)” and see para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”. Therefore, the data from the CS-MS is an ion-data series for an ion count rate which are generated from ions. See also Para[0043] “Namely, the various integration procedures may be designated as a "base-base" integration (see, e.g., FIG. 6a), a "base-drop" integration (see, e.g., FIG. 6c), a "drop-base" integration (see, e.g., FIG. 6b), or a "drop-drop" integration.” Therefore, from Fig. 6, we see that the first peak characteristics (referring to Fig. 6b) are intensity peak origin 500 and intensity peak terminus 550 for the integration method of 6b (i.e. a first prospective peak integration), and we see that the second peak characteristics (referring to Fig. 6c) are intensity peak origin 500 and intensity peak terminus 550 for the integration method of 6c (i.e. a second prospective peak integration. Examiner notes that 6c is for a different identified peak than that of 6b, but according to Para[0043] above, two integration procedures can be used for one identified peak, so Fig. 6c is being shown here as an example of another integration method. ). In addition, the first peak integration parameters for the integration method of 6b are the baseline intensity 575 and element 600 (i.e. so the first prospective peak integration is generated according to them) while for Fig. 6c the second peak integration parameters are the baseline intensity 575 and element 600 (i.e. so the second prospective peak integration is generated according to them), which are different from those of Fig. 6b.);
generating, according to second peak integration parameters, a second prospective peak integration for the identified peak in the ion data series, wherein the second prospective peak integration is characterized by second peak characteristics (See Para[0043] “determine and designate (i.e. generate) the template integration procedure (i.e. a first prospective peak integration, and it is prospective as it can potentially accurately calculate the area) and to apply the template integration procedure to the selected intensity peaks of a second portion of the two-dimensional data sets, wherein the second portion of the two-dimensional data sets previously had the areas of the selected intensity peaks (i.e. the identified peak is a single peak within the selected intensity peak) thereof determined by one of the integration procedures other than the template integration procedure (i.e. generate a second prospective peak integration, and it is prospective as it can potentially accurately calculate the area. Also the second prospective peak integration is for the same identified peak as the one for the template integration procedure.)”. The first prospective peak integration and the second prospective peak integration are therefore part of the ion data series, and it is an ion data series from the Abstract “ analyzing data (i.e. accessing an ion data series) from a component separation/mass spectrometer (CS-MS)” and see para[0036] “that sample component has been previously identified (i.e., as a particular molecule, ion, or metabolite) or not, via an intensity peak 225 (otherwise referred to herein as "selected intensity peak," "ion peak,", or "selected ion peak")”. Therefore, the data from the CS-MS is an ion-data series for an ion count rate which are generated from ions. See also Para[0043] “Namely, the various integration procedures may be designated as a "base-base" integration (see, e.g., FIG. 6a), a "base-drop" integration (see, e.g., FIG. 6c), a "drop-base" integration (see, e.g., FIG. 6b), or a "drop-drop" integration.” Therefore, from Fig. 6, we see that the first peak characteristics (referring to Fig. 6b) are intensity peak origin 500 and intensity peak terminus 550 for the integration method of 6b (i.e. a first prospective peak integration), and we see that the second peak characteristics (referring to Fig. 6c) are intensity peak origin 500 and intensity peak terminus 550 for the integration method of 6c (i.e. a second prospective peak integration. Examiner notes that 6c is for a different identified peak than that of 6b, but according to Para[0043] above, two integration procedures can be used for one identified peak, so Fig. 6c is being shown here as an example of another integration method. ). In addition, the first peak integration parameters for the integration method of 6b are the baseline intensity 575 and element 600 (i.e. so the first prospective peak integration is generated according to them) while for Fig. 6c the second peak integration parameters are the baseline intensity 575 and element 600 (i.e. so the second prospective peak integration is generated according to them), which are different from those of Fig. 6b.);
based on at least one of the first prospective peak integration or the second prospective peak integration, generating an ion amount represented by the identified peak (See Abstract “The intensity peak (i.e. the identified peak) indicates a sample component, and the area (i.e. calculated from the prospective peak integration, and it is prospective because it can potentially accurately calculate the area) thereof indicates a relative quantity of the sample component (i.e. the intensity peak generates an ion amount based on its area). Examiner notes that either the first prospective peak integration or the second prospective peak integration from the integration procedures of Dai can therefore generate the ion amount.”).
Dai is silent to the language of
providing, as input to a trained machine learning model:
the first peak characteristics; and
the second peak characteristics;
processing the provided input, by the trained machine learning model, to generate an output from the trained machine learning model;
based on the output, generating a ranking of the first prospective peak integration and second prospective peak integration.
Wiegand teaches
providing, as input to a machine learning model (See Column 7 lines 9-14 “90 spectra total were produced, 30 each with peak positions at 2917 cm−1 (unaltered), 2916 cm−1 and 2918 cm−1. A conventional algorithm and the relative algorithm, according to the present disclosure described herein, were both used to integrate the peak areas, yielding two sets of areas. A linear regression (univariate) (i.e. a machine learning model) was done (i.e. processing the provided input, by the machine learning model) on each set of areas (i.e. the peak characteristic (the peak position) was provided as input to the linear regression for each integration method, therefore the peak position for the conventional algorithm is the first peak characteristic and the peak position for the relative algorithm is the second peak characteristic), and a plot of the error (true-predicted) was made for each linear regression (i.e. the error is from the output generated from the linear regression, making the error an output generated from the machine learning model).”):
the first peak characteristic (See Column 7 lines 9-14); and
the second peak characteristic (See Column 7 lines 9-14);
processing the provided input, by the machine learning model, to generate an output from the machine learning model (See Column 7 lines 9-14);
based on the output, generating a ranking of the first prospective peak integration and second prospective peak integration (See Column 7 lines 15-18 “ FIG. 9 shows a plot of the range of errors for both sets of data. As evident from these plots (i.e. based on the output of the linear regression, from which the error was calculated), in most cases, the reduction in error is dramatic when using relative integration of the present disclosure (i.e. generating a ranking, of the first prospective peak integration (the conventional algorithm) and second prospective peak integration (the relative algorithm), as it is shown that the relative integration performs more accurately. The conventional algorithm and the relative algorithm are both prospective because they can potentially accurately calculate the area.).”).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai wherein providing, as input to a machine learning model: the first peak characteristic; and the second peak characteristic; processing the provided input, by the machine learning model, to generate an output from the machine learning model; and based on the output, generating a ranking of the first prospective peak integration and second prospective peak integration is done like in Weigand in order to rank the accuracy of each integration method and determine which one to use for accurate analysis of the target peak via using a machine learning method like linear regression that can input a peak characteristic.
Dai and Weigand are silent to the language of
a trained machine learning model.
Tomlinson teaches
a trained machine learning model. (See Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”)”);
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein a trained machine learning model is used like in Tomlinson in order to automatically determine the best possible integration technique to calculate the area under the peak curve (as defined in Weigand). Examiner notes that Dai already teaches first peak characteristics and second peak characteristics and that Weigand already teaches the process of inputting one peak characteristic for each prospective peak integration into the machine learning model. However, the trained machine learning model of Tomlinson teaches the insertion of first peak characteristics and second peak characteristics via the curvature data (See Column 21 lines 60-63 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net”. Therefore, the first peak characteristics are the data points of the curvature data from one part of the input signals, and the second peak characteristics are the data points of the curvature data from another part of the input signals.).
With regards to Claim 18, Dai, Weigand, and Tomlinson teach the limitations of Claim 16. Dai further teaches
wherein the peak integration parameters include at least one of a smoothing parameter, an expected-time parameter, a filtering parameter, a baseline parameter (See Fig. 6 the baseline intensity 575), or a peak-splitting parameter.
With regards to Claim 19, Dai, Weigand, and Tomlinson teach the limitations of Claim 16. Dai further teaches
wherein the peak characteristics include at least two of: an integrated area (See Abstract “An integration procedure determines the area of selected peaks”), peak height, peak start time, peak end time (See Para[0040] “the particular integration procedure implemented to determine the area of the selected intensity peaks may also be designated, in some instances, according to the relation of each of the intensity peak origin 500 (i.e. peak start time) and the intensity peak terminus 550 (i.e. peak end time) to the baseline intensity 575”), center time, peak width, and peak smoothness.
With regards to Claim 20, Dai, Weigand, and Tomlinson teach the limitations of Claim 16. Dai and Weigand are silent to the language of
wherein the trained machine learning model is one of a neural network, a support vector machine, a K-nearest neighbors algorithm, a hidden Markov model, or a random forest.
Tomlinson teaches
wherein the trained machine learning model is one of a neural network (See Abstract “The peak data including the baseline level upon which the peak is superimposed is analyzed using one of lookup-tables, neural nets (i.e. a trained machine learning model, See Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”)”), a support vector machine, a K-nearest neighbors algorithm, a hidden Markov model, or a random forest.
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein the trained machine learning model is one of a neural network, a support vector machine, a K-nearest neighbors algorithm, a hidden Markov model, or a random forest like in Tomlinson in order to clearly define an efficient and automated method to identify the best performing integration method.
Claim(s) (2, 5), (17, 21) is/are rejected under 35 U.S.C. 103 as being unpatentable over Dai (US 20120239306 A1), Weigand (US 10627289 B1), and Tomlinson (US 5121443 A) as applied to claims (1,16) above, and further in view of Burton (WO 2020250158 A1).
With regards to Claim 2, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai is silent to the language of
causing a display of one or more of the prospective peak integrations based on the ranking;
receiving a selection of one of the displayed prospective peak integrations; and
wherein generating the ion amount is based on the selected prospective peak integration.
Weigand further teaches
causing a display of one or more of the prospective peak integrations based on the ranking (See Fig. 9, where the error (i.e. interpreted as a score of the integration method, therefore constituting a representation of the ranking) is plotted (i.e. displayed) for each prospective integration method, and they are prospective because they can potentially accurately calculate the area.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai wherein causing a display of one or more of the prospective peak integrations based on the ranking is done like in Weigand in order to have a visual representation of the ranking of the integration methods which provides easy identification and comparison between the integration methods.
Dai, Weigand, and Tomlinson are silent to the language of
receiving a selection of one of the displayed prospective peak integrations; and
wherein generating the ion amount is based on the selected prospective peak integration.
Burton teaches
receiving a selection of one of the displayed prospective peak integrations (See Abstract “Two or more different peak integration areas are calculated for the at least one peak by applying the peak-finding algorithm with two or more different values for at least one peak-finding parameter. Two or more plots of the at least one peak that each shows graphically a different peak integration area are displayed on a display device at the same time. In response, data is received from a user selection device that indicates user selection of one of the two or more plots (i.e. receiving a selection of one of the displayed prospective peak integrations, and they are prospective because they can potentially accurately calculate the area).” Examiner notes that once the peak integration plot is selected, the ion amount (See Abstract “A mass spectrometer is instructed to measure a plurality of intensities of at least one ion ”, therefore, the peak integration areas correspond to ion amounts) is generated based on the selected prospective peak integration, and it is prospective because it can potentially accurately calculate the area.); and
wherein generating the ion amount is based on the selected prospective peak integration (See Abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai, Weigand, and Tomlinson wherein receiving a selection of one of the displayed prospective peak integrations; and wherein generating the ion amount is based on the selected prospective peak integration is done like in Burton in order to have a more interactive system that provides an accurate selection of the best integration method.
With regards to Claim 5, Dai, Weigand, and Tomlinson teach the limitations of Claim 1. Dai and Weigand are silent to the language of
wherein each prospective peak integration in the set of prospective peak integrations includes at least one respective peak quality metric, and the respective peak quality metrics are also included as input into the trained machine learning model.
Tomlinson teaches
the respective peak quality metrics are also included as input into the trained machine learning model (See Column 45 lines 27-34 “An important aspect of the neural net (i.e. a trained machine learning model see Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”) is to prescale the amplitude of the input data so that the input units of the neural net receive values ranging from 0.1 to 0.9. Also, the width of the input data is scaled so that the inflection points of the EMG curve fall within the time frame of the neural net input units because this scaling assures that the net processes data with the best signal-to-noise ratio.” Therefore, the signal to noise ratio for each data point in the input data is a respective peak quality metric that is input to the neural network of Weigand via the scaled inputs. So both the respective peak quality metrics (via the scaling of the inputs) and the peak characteristics (via the input data) are input.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein the respective peak quality metrics are also included as input into the trained machine learning model like in Tomlinson in order to uniformly determine the quality of a given peak integration method using an automated method via machine learning.
Dai, Weigand, and Tomlinson are silent to the language of
wherein each prospective peak integration in the set of prospective peak integrations includes at least one respective peak quality metric.
Burton teaches
wherein each prospective peak integration in the set of prospective peak integrations includes at least one respective peak quality metric (See Fig. 3, where the Noise Percentage reflects the amount of noise, therefore reflecting a peak quality metric. See also Para[0020] “ Figure 5 is an exemplary plot 500 of a chromatographic peak that is displayed to a user by a peak-finding algorithm and shows the incorrect integration of the chromatographic peak according to the parameters of Figure 3.” and see para[0033] “ Figure 6 is an exemplary display of three different possible integrations of the same peak shown in Figure 5”. Therefore, the three plots of Fig. 6 constitute the set of prospective peak integrations, and each plot is a prospective peak integration, and they are prospective because they can potentially accurately calculate the area), and these plots of Fig. 6 are derived from the output of values from Fig. 3, which include the respective peak quality metric of the noise for each plot.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai, Weigand, and Tomlinson wherein each prospective peak integration in the set of prospective peak integrations includes at least one respective peak quality metric like in Burton in order to uniformly determine the quality of a given peak integration method.
With regards to Claim 17, Dai, Weigand, and Tomlinson teach the limitations of Claim 16. Dai is silent to the language of
causing the display of at least one of the first prospective peak integration or the second prospective peak integration based on the ranking;
receiving a selection of one of the first prospective peak integration or the second prospective peak integration; and
wherein generating the ion amount is based on the selected prospective peak integration.
Weigand further teaches
causing the display of at least one of the first prospective peak integration or the second prospective peak integration based on the ranking (See Fig. 9, where the error (i.e. interpreted as a score of the integration method, therefore constituting a representation of the ranking) is plotted (i.e. displayed) for the normal (or conventional) integration (i.e. the first prospective peak integration) and the relative integration (i.e. the second prospective peak integration) . They are prospective because they can potentially accurately determine the area.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai wherein causing the display of at least one of the first prospective peak integration or the second prospective peak integration based on the ranking is done like in Weigand in order to have a visual representation of the ranking of the integration methods which provides easy identification and comparison between the integration methods.
Dai, Weigand, and Tomlinson are silent to the language of
receiving a selection of one of the first prospective peak integration or the second prospective peak integration; and
wherein generating the ion amount is based on the selected prospective peak integration.
Burton teaches
receiving a selection of one of the first prospective peak integration or the second prospective peak integration (See Abstract “Two or more different peak integration areas are calculated for the at least one peak by applying the peak-finding algorithm with two or more different values for at least one peak-finding parameter. Two or more plots of the at least one peak that each shows graphically a different peak integration area (i.e. in the case of two plots there is the first prospective peak integration in the first plot and the second prospective peak integration in the second plot, and they are prospective because they can potentially accurately calculate the area) are displayed on a display device at the same time. In response, data is received from a user selection device that indicates user selection of one of the two or more plots (i.e. receiving a selection of one of the first prospective peak integration or the second prospective peak integration).” Examiner notes that once the peak integration plot is selected, it allows for the ion amount (See Abstract “A mass spectrometer is instructed to measure a plurality of intensities of at least one ion ”, therefore, the peak integration areas correspond to ion amounts) to be generated based on the selected prospective peak integration, and it is prospective because it can potentially accurately calculate the area.); and
wherein generating the ion amount is based on the selected prospective peak integration (See Abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai, Weigand, and Tomlinson wherein receiving a selection of one of the first prospective peak integration or the second prospective peak integration; and wherein generating the ion amount is based on the selected prospective peak integration is done like in Burton in order to have a more interactive system that provides an accurate selection of the best integration method.
With regards to Claim 21, Dai, Weigand, and Tomlinson teach the limitations of Claim 16. Dai and Weigand are silent to the language of
wherein the first prospective peak integration has a first peak quality metric, the second prospective peak integration has a second peak quality metric, and the input to the trained machine learning model further includes the first peak quality metric and the second peak quality metric.
Tomlinson teaches
the input to the trained machine learning model further includes the first peak quality metric and the second peak quality metric (See Column 45 lines 27-34 “An important aspect of the neural net (i.e. a trained machine learning model see Column 21 lines 60-67 “calculate parameters 105 generates curvature data using the data provided by select data 104. The curvature data are input signals to a neural net. The neural net, which has been previously taught (i.e. making the neural network a trained machine learning model) to determine EMG peak parameters based upon curvature input signals, generates output signals corresponding to the EMG peak parameters best describing the input signals”) is to prescale the amplitude of the input data (i.e. the first peak quality metric is the prescaling of the amplitude) so that the input units of the neural net receive values ranging from 0.1 to 0.9. Also, the width of the input data is scaled (i.e. the second peak quality metric is the scaling of the width) so that the inflection points of the EMG curve fall within the time frame of the neural net input units because this scaling assures that the net processes data with the best signal-to-noise ratio.” Therefore, the first peak quality metric and the second peak quality metric are both input to the trained machine learning model.).
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai and Weigand wherein the input to the trained machine learning model further includes the first peak quality metric and the second peak quality metric like in Tomlinson in order to uniformly determine the quality of a given peak integration method using an automated method via machine learning.
Dai, Weigand, and Tomlinson are silent to the language of
wherein the first prospective peak integration has a first peak quality metric, the second prospective peak integration has a second peak quality metric.
Burton teaches
wherein the first prospective peak integration has a first peak quality metric, the second prospective peak integration has a second peak quality metric (See Fig. 3, where the Noise Percentage reflects the amount of noise, therefore reflecting a peak quality metric. See also Para[0020] “ Figure 5 is an exemplary plot 500 of a chromatographic peak that is displayed to a user by a peak-finding algorithm and shows the incorrect integration of the chromatographic peak according to the parameters of Figure 3.” and see para[0033] “ Figure 6 is an exemplary display of three different possible integrations of the same peak shown in Figure 5”. Therefore, each of the plots of Fig. 6 is a prospective peak integration, and they are prospective because they can potentially accurately calculate the area.), and these plots of Fig. 6 are derived from the output of values from Fig. 3, which include the peak quality metric of the noise for each plot. Therefore, in Fig. 6, the first prospective peak integration is 610 with a first peak quality metric, and the second prospective peak integration is 620 with a second peak quality metric.)
It would have been obvious to one of ordinary skill in the art before the effective filing date to modify Dai, Weigand, and Tomlinson wherein the first prospective peak integration has a first peak quality metric, the second prospective peak integration has a second peak quality metric like in Burton in order to uniformly determine the quality of a given peak integration method.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOSTOFA AHMED HISHAM whose telephone number is (571)272-8773. The examiner can normally be reached Monday - Friday, 7:00 a.m. - 4 p.m. ET.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Catherine Rastovski can be reached at (571) 270-0349. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/MOSTOFA AHMED HISHAM/Examiner, Art Unit 2857
/YOSHIHISA ISHIZUKA/Primary Examiner, Art Unit 2857
Prosecution Insights