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 .
Claim Status
Claims 21-39 are pending and examined on the merits.
Claims 1-20 are canceled.
Priority
The instant application claims priority to US Provisional Application 63/078,320, filed 09/14/2020. As such, the effective filing date assigned to each of claims 1-20 is 09/14/2020.
Withdrawn Rejections/Objections
Rejections and/or objections not reiterated from previous office actions are hereby
withdrawn in view of the amendments filed 11/12/2025.
All rejections of claims 1-20 are hereby withdrawn; their cancelation moots the
rejections.
The following rejections and/or objections are either maintained or newly applied. They constitute the complete set presently being applied to the instant application.
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 21-38 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The Supreme Court has established a two-step framework for this analysis, wherein a claim does not satisfy § 101 if (1) it is “directed to” a patent-ineligible concept, i.e., a law of nature, natural phenomenon, or abstract idea, and (2), if so, the particular elements of the claim, considered “both individually and as an ordered combination,” do not add enough to “transform the nature of the claim into a patent-eligible application.” Elec. Power Grp., LLC v. Alstom S.A., 830 F.3d 1350, 1353 (Fed. Cir. 2016) (quoting Alice, 134 S. Ct. at 2355). Applicant is also directed to MPEP 2106.
Step 1: The instantly claimed invention (claims 21-33, and 34 being representative) is directed to a method and a device (claims 35-37 and 38 being representative). Therefore, the instantly claimed invention falls into one of the four statutory categories. [Step 1: YES]
Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in in Prong Two if the recited judicial exception is integrated into a practical application of that exception.
Step 2A, Prong 1: Under the MPEP § 2106.04, the Step 2A (Prong 1) analysis requires determining whether a claim recites an abstract idea, law of nature, or natural phenomenon.
Claims 21-38 recite the following steps which fall under the mathematical concepts, mental processes, and/or certain methods of organizing human activity groupings of abstract ideas:
Claim 21 recites performing training iterations on the training metabolite features to identify the metabolite features; the limitation performing training iterations, for example, by using mathematical algorithm(s) (see specification [00591], is considered a mathematical calculation, and as such, falls into mathematical concepts groupings of abstract ideas.
Claim 21 further recites applying a library of authenticated metabolites to characterize the metabolite features; the limitation applying a library to characterize is considered, given the plain meaning of “applying”, is considered a mental process, since human mind is capable of characterizing data using a library of known data.
Claim 21 further recites identifying a subset of the metabolite features as selective metabolite features for the disease or disorder state, wherein the selective metabolite features comprise at least pyroglutamic acid; the limitation identifying, given the plain meaning of “identifying”, is considered a mental process of identifying data based on library matching.
Claim 21 further recites iteratively adjusting selective metabolite feature parameters until a performance threshold criterion is met; the limitation iteratively adjusting parameters involves mathematical algorithms/calculations (as claimed in claim 34: iteration is performed using unsupervised principal component analysis …), and as such, falls into mathematical concepts groupings of abstract ideas.
Claim 33 recites the training iterations are performed using unsupervised principal component analysis, run alignment, peak picking, adduct deconvolution, and/or positive polarity analysis; the limitation training using recited mathematical algorithms/calculations falls into mathematical concepts groupings of abstract ideas.
Claim 33 further recites a model is utilized to determine when the performance threshold criterion is met; the limitation utilizing a mathematical model is considered a mathematical calculation, and as such, falls into mathematical concepts groupings of abstract ideas.
Claim 33 further recites subjecting a plurality of corresponding metabolite feature data to a LightGBM machine learning model and a Random Forest (RF) machine learning model to generate classified corresponding metabolite feature data; the limitation subjecting data to a mathematical model/algorithm, is considered a mathematical calculation, and as such, falls into mathematical concepts groupings of abstract ideas.
Claim 33 further recites identifying a subset of the classified corresponding metabolite features as the selective metabolite features for a disorder using a SHapley Additive exPlanations (SHAP) method; the limitation Identifying using a SHAP method/ a mathematical algorithm is considered a mathematical calculation, and as such falls into mathematical concepts groupings of abstract ideas.
Claim 34 recites predicting characteristics of the sample of the patient; the limitation predicting, given the plain meaning of “predicting” is considered a mental process.
Claim 34 further recites generating diagnosis or prognosis criteria for clinical evaluation of the patient based on the predicted characteristics of the sample of the patient; the limitation generating a diagnostic or prognostic criteria can be practically performed in human mind (mental process), since human mind is capable of generating an indication based on the result of a data analysis.
Claim 35 recites identify compounds within the metabolite features; the limitation identifying, given the plain meaning of “identifying”, is considered a mental process of identifying data.
Claim 35 further recites determining the presence or absence of a disease state; the limitations determining presence or absence of a state is considered a mental process of determining data based on the result of an analysis.
Claim 37 recites classifying patient metabolite features by selecting a subset of one or more of the metabolite features before inputting to the machine leaning model system, or excluding one or more of the metabolite features before inputting to the machine leaning model system; the limitation classifying by selecting data and excluding data can be practically performed in human mind (mental processes).
Claim 38 recites utilizing a machine leaning model trained using a plurality of metabolite features representing compounds of the sample and data identifying characteristics for the compounds; the limitation identifying, given the plain meaning of identifying is considered a metal process.
Claim 38 further recites predicting characteristics of the sample of the patient; the limitation predicting is considered a mental process.
Claim 38 further recites generating diagnosis criteria for clinical evaluation of the patient based on the predicted characteristics of the sample of the patient; the limitation generating a diagnosis based on an analysis is considered a mental process.
Dependent claims 22-32, and 36 provide further information.
Additionally, claims 21-38 recite a correlation between the presence of metabolite in a processed sample of a subject and a diagnostic or prognostic indication, and as such, falls into judicial exception of Laws of nature and natural phenomena. See MPEP 2106(b) I.
The identified claims recite a law of nature, a natural phenomenon (product of nature) and/or fall into one of the groups of abstract ideas of mathematical concepts, mental processes, and/or certain methods of organizing human activity for the reasons set forth above. See MPEP 2106.04 (a)(2) III and MPEP 2106.04 (b) I. Therefore, claims 1-20 are directed to one or more judicial exception(s) and require further analysis in Prong Two. [Step 2A, Prong 1: YES]
Step 2A: Prong 2: Under the MPEP § 2106.04, the Step 2A, Prong 2 analysis requires identifying whether there are any additional elements recited in the claim beyond the judicial exception(s), and evaluating those additional elements to determine whether they integrate the exception into a practical application of the exception. This judicial exception is not integrated into a practical application for the following reasons.
The additional elements of claim 21-38 include the following.
Claim 21 recites receiving a set of training metabolite features identified using liquid chromatography-mass spectrometry using samples from patients confirmed as having a disease or disorder and not having the disease or disorder; storing the trained parameters in memory for use by a metabolite feature identification system; and generating a predictive output.
Claim 22 recites obtaining by processing a raw subject sample by ultrafiltration prior to liquid chromatography.
Claim 23 recites the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography.
Claim 34 recites receiving test metabolite features of a sample of a patient, the test metabolite features being acquired by liquid chromatography-mass spectrometry; providing the test metabolite features to a machine learning network trained according to claim 21.
Claim 35 recites a system, comprising: a liquid chromatography unit; a mass spectrometry unit configured to conduct mass chromatography of the processed sample; one or more processors in communication with the mass spectrometry unit, the one or more processors configured to: receive the metabolite features from the mass spectrometry unit; and output at least one indication of the presence of the disease state, absence of the disease state or probability of the disease state in the patient.
Claim 38 recites a memory configured to store instructions; a processor disposed in communication with the memory, instructions; receive test metabolite features a sample of a patient, the test metabolite features being acquired by liquid chromatography-mass spectrometry; provide the test metabolite features to the trained machine learning model.
The additional elements of a system comprising a processor, instructions, memory, and storing are generic computer components and/or processes. The courts have found the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not integrate a judicial exception into a practical application. See MPEP 2106.05(f).
Furthermore, the additional elements of providing/inputting, obtaining and receiving data, and generating an output, and outputting an indication amount to necessary data gathering and outputting, and as such, considered insignificant extra-solution activities. See MPEP 2106.05(g).
Furthermore, the additional elements of a system, comprising: a liquid chromatography unit; a mass spectrometry unit configured to conduct mass chromatography, the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography, and ultrafiltration of the raw subject sample serve to collect data to be used by the judicial exception.
Therefore, the additionally recited elements amount to insignificant extra-solution activity and, as such, the claims as a whole do no integrate the abstract idea into practical application. Thus, claims 21-38 are directed to an abstract idea. [Step 2A, Prong 2: NO]
Step 2B: In the second step it is determined whether the claimed subject matter includes additional elements that amount to significantly more than the judicial exception. An inventive concept cannot be furnished by an abstract idea itself. See MPEP § 2106.05.
The claims do not include any additional steps appended to the judicial exception that are sufficient to amount to significantly more than the judicial exception.
The additional elements of claim 21-38 include the following.
Claim 21 recites receiving a set of training metabolite features identified using liquid chromatography-mass spectrometry using samples from patients confirmed as having a disease or disorder and not having the disease or disorder; storing the trained parameters in memory for use by a metabolite feature identification system; and generating a predictive output.
Claim 22 recites obtaining by processing a raw subject sample by ultrafiltration prior to liquid chromatography.
Claim 23 recites the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography.
Claim 34 recites receiving test metabolite features of a sample of a patient, the test metabolite features being acquired by liquid chromatography-mass spectrometry; providing the test metabolite features to a machine learning network trained according to claim 21.
Claim 35 recites a system, comprising: a liquid chromatography unit; a mass spectrometry unit configured to conduct mass chromatography of the processed sample; one or more processors in communication with the mass spectrometry unit, the one or more processors configured to: receive the metabolite features from the mass spectrometry unit; and output at least one indication of the presence of the disease state, absence of the disease state or probability of the disease state in the patient.
Claim 38 recites a memory configured to store instructions; a processor disposed in communication with the memory, instructions; receive test metabolite features a sample of a patient, the test metabolite features being acquired by liquid chromatography-mass spectrometry; provide the test metabolite features to the trained machine learning model.
The additional elements of a system comprising a processor, instructions, memory, and storing are conventional computer components and/or processes. The courts have found the use of a computer or other machinery in its ordinary capacity for economic or other tasks (e.g., to receive, store, or transmit data) or simply adding a general-purpose computer or computer components after the fact to an abstract idea (e.g., a fundamental economic practice or mathematical equation) does not provide significantly more. See Affinity Labs v. DirecTV, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016) (cellular telephone); TU Communications LLC v. AV Auto, LLC, 823 F.3d 607,613,118 USPQ2d 1744, 1748 (Fed. Cir. 2016) (computer server and telephone unit).
Furthermore, the additional elements of providing/inputting, obtaining and receiving data, and generating an output, and outputting an indication amount to necessary data gathering and outputting and as such, considered insignificant extra-solution activities. See MPEP 2106.05(g).
Furthermore, the additional elements of the mass spectrometry comprise liquid chromatography quadrupole time-of-flight mass spectrometry, the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography, and ultrafiltration of the raw subject sample amount to well-understood, routine, and conventional methods and systems for pert arming mass spectrometry. This position is supported by Le et al. (Metabolic profiling by reversed-phase/ion-exchange mass spectrometry, Journal of Chromatography B, Volume 1143, 15 April 2020, 122072, pages 1-7). Le discloses that metabolic profiling is commonly achieved by mass spectrometry (MS) following reversed-phase (RP) and hydrophilic interaction chromatography (HILIC) and discloses an in-line RP-ion-exchange (IEX) column arrangement and a single LC system (abstract). Le further discloses performing mass spectrometry using quadrupole time of flight mass spectrometry (pg. 2, col. 2, last para.)
Additionally, Gao et al. (Development of simultaneous targeted metabolite quantification and untargeted metabolomics strategy using dual-column liquid chromatography coupled with tandem mass spectrometry, Analytica Chimica Acta, 11 December 2018, Pages 369-379). Gao teaches a simultaneous targeted quantification and untargeted metabolomics (STQUM) strategy based on dual LC-MS/MS for biomarker discovery (abstract).
Further Schultz et al. (Liquid Chromatography Quadrupole Time-of-Flight Characterization of Metabolites Guided by the METLIN Database, Nat Protoc. 2013 Feb 7;8(3):451–460) teaches that untargeted metabolomics provides a comprehensive platform to identify metabolites whose levels are altered between two or more populations using liquid chromatography quadrupole time-of-flight mass spectrometry (LC-Q-ToF-MS), to detect hundreds to thousands of peaks with a unique m/z and retention time are routinely detected from most biological samples in an untargeted profiling experiment (abstract).
Further, Thomas et al. (Urine Collection and Processing for Protein Biomarker Discovery and Quantification, Cancer Epidemiol Biomarkers Prev. 2010 Mar 23;19(4):953–959) teaches ultrafiltration of sample to be the best method for concentration and cleanup of peptide and protein components for biomarker discovery (abstract, pg. 3, para. 1).
Therefore, the additional element is not sufficient to amount to significantly more than the judicial exception.
Taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception(s). Even when viewed as a combination, the additional elements fail to transform the exception into a patent-eligible application of that exception. Thus, the claims as a whole do not amount to significantly more than the exception itself. [Step 2B: NO]
Therefore, the instantly rejected claims are not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
Response to Arguments
Applicant's arguments filed 11/12/2025 have been fully considered but they are not persuasive. Applicant states:
together with the limitations of claim 21 from which claim 33 depends, claim 33 recites additional elements in an ordered combination that amounts to significantly more than the judicial exception. See MPEP § 2106. The context of these "additional elements," of course is viewed from the perspective of the claim as "a whole." As the art of record does not establish the claimed ordered combination (e.g., liquid chromatography-mass spectrometry, metabolite feature identification and selectivity, library application, pyroglutamic acid as a selective metabolite feature, iterative adjustments to meet performance thresholds, and predictive output) is well-understood, routine, or conventional. While the Examiner has cited 4 references (Le, Gao, Schultz and Thomas) that provide various teachings concerning ultrafiltration, chromatography or mass spectrometry, they do not come close to establishing that the claimed ordered combination of elements is widely prevalent or in common use in the relevant industry. For relevant context, see R. Bahr, USPTO "Changes in Examination Procedure Pertaining to Subject Matter Eligibility, Recent Subject Matter Eligibility Decision (Berkheimer v. HP, Inc.)" (2018); Berkheimer v. HP Inc., 881F.3d1360 (Fed. Cir. 2018).
It is respectfully submitted that the above statement is not persuasive. The Applicant remarks are directed to Step 2B of 101 analyses, specifically evaluating additional elements to determine whether they amount to an inventive concept by considering them both individually and in combination to ensure that they amount to significantly more than the judicial exception itself.
An inventive concept "cannot be furnished by the unpatentable law of nature (or natural phenomenon or abstract idea) itself." Genetic Techs. Ltd. v. Merial LLC, 818 F.3d 1369, 1376, 118 USPQ2d 1541, 1546 (Fed. Cir. 2016). See also Alice Corp., 573 U.S. at 21-18, 110 USPQ2d at 1981 (citing Mayo, 566 U.S. at 78, 101 USPQ2d at 1968 (after determining that a claim is directed to a judicial exception, "we then ask, ‘[w]hat else is there in the claims before us?") (emphasis added)); RecogniCorp, LLC v. Nintendo Co., 855 F.3d 1322, 1327, 122 USPQ2d 1377 (Fed. Cir. 2017) ("Adding one abstract idea (math) to another abstract idea (encoding and decoding) does not render the claim non-abstract"). Instead, an "inventive concept" is furnished by an element or combination of elements that is recited in the claim in addition to (beyond) the judicial exception, and is sufficient to ensure that the claim as a whole amount to significantly more than the judicial exception itself. Alice Corp., 573 U.S. at 27-18, 110 USPQ2d at 1981 (citing Mayo, 566 U.S. at 72-73, 101 USPQ2d at 1966).
As stated above, the additional elements of claims 21-38 are a system comprising a processor, instructions, memory, and storing, which are conventional computer components and/or processes, that do not amount to significantly more. Furthermore, the additional elements of providing/inputting, obtaining and receiving data, and generating an output, and outputting an indication amount to necessary data gathering and outputting and as such, does not amount to significantly more. Furthermore, the additional elements of the mass spectrometry comprise liquid chromatography quadrupole time-of-flight mass spectrometry, the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography, and ultrafiltration of the raw subject sample amount to well-understood, routine, and conventional methods and systems for pert arming mass spectrometry, as such do not amount to significantly more.
The courts have found that using a general-purpose computer, adding extra solution activities, and inputting/outputting data do not amount to “significantly more” when recited in a claim with a judicial exception.
Additionally, with respect to applicant submitting that the cited 4 references (Le, Gao, Schultz and Thomas) do not come close to establishing that the claimed ordered combination of elements is widely prevalent or in common use in the relevant industry, examiner submits that although the courts often evaluate considerations such as the conventionality of an additional element in the eligibility analysis, the search for an inventive concept should not be confused with a novelty or non-obviousness determination. See Mayo, 566 U.S. at 91, 101 USPQ2d at 1973. As made clear by the courts, the "‘novelty’ of any element or steps in a process, or even of the process itself, is of no relevance in determining whether the subject matter of a claim falls within the § 101 categories of possibly patentable subject matter." Intellectual Ventures I v. Symantec Corp., 838 F.3d 1307, 1315, 120 USPQ2d 1353, 1358 (Fed. Cir. 2016) (quoting Diamond v. Diehr, 450 U.S. at 188–89, 209 USPQ at 9).
Furthermore, a response cannot be provided with regards to Applicant stating “For relevant context, see R. Bahr, USPTO "Changes in Examination Procedure Pertaining to Subject Matter Eligibility, Recent Subject Matter Eligibility Decision (Berkheimer v. HP, Inc.)" (2018); Berkheimer v. HP Inc., 881F.3d1360 (Fed. Cir. 2018)”, since Applicant does not point to specific examples and does not provide arguments.
Therefore, claims 21-38 are rejected under U.S.C 101.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 21, 25-31, and 34-39 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Hooser et al. (US 11894139 B1).
Regarding claim 21, 34, 35, 38, and 39, Hooser discloses platforms, systems, media, and methods for assessing an individual for one or more diseases, disorders, or conditions. A machine learning algorithm can be used to provide the assessment based on personalized data derived from the individual. The personalized data can include metabolite data from a specimen or biological sample of the individual. Hooser further discloses (a) a processor; (b) a non-transitory computer readable medium encoded with software comprising one or more machine learning algorithms together with instructions configured to cause the processor to: (i) receive data related to a specimen taken from the individual; and (ii) provide the data as input to the one or more machine learning algorithms, wherein the one or more machine learning algorithms use the data to generate a classification of the individual relative to a plurality of related classifications (col. 1, para. 3-4); reading on limitations of computer-implemented method of training a machine learning model for metabolite feature identification, comprising the steps:
Hooser further discloses identifying discriminating metabolites, between samples obtained from reference subjects (e.g., healthy subjects or subjects with a different disease) using known statistical tests (col. 71, para. 1). Hooser further discloses metabolite detection techniques such as liquid chromatography-mass spectrometry (col. 69, para. 1) for analyzing input data for one or more biomarkers to generate output relating to differential classifications or associations such as the presence or likelihood of a disease, disorder, or condition or trait (col. 70, para. 1); reading on limitations of receiving a set of training metabolite features identified using liquid chromatography-mass spectrometry using samples from patients confirmed as having a disease or disorder and not having the disease or disorder;
Hooser further discloses that the model or algorithm undergoes machine learning using training data that includes metabolite data for individuals (col. 62. Para. 1); reading on limitations of performing training iterations on the training metabolite features to identify the metabolite features;
Hooser further discloses that a list of the most discriminating metabolites can be obtained by ranking the metabolites by statistical means such as their feature importance. Hooser further discloses ranking and identifying metabolites (col. 71, para. 1). Hooser further discloses selecting information of the discriminating metabolites subsequently imported into a machine learning algorithm to obtain a statistical or mathematical model ( e.g., a classifier) that classifies the metabolic data with accuracy, sensitivity, and/or specificity (col. 72, para. 2). Hooser further discloses that feature selection comprises screening for or identifying features based on annotation(s) from one or more databases (col. 59, L. 9-16). Hooser further discloses that the metabolite features comprise at least pyroglutamic acid/5-oxoproline (col. 31-32, Table 2); reading on limitations of applying a library of authenticated metabolites to characterize the metabolite features; identifying a subset of the metabolite features as selective metabolite features for the disease or disorder state, wherein the selective metabolite features comprise at least pyroglutamic acid;
Hooser further discloses that the cutoff feature importance value for determining the discriminating metabolite can be adjusted for one or more models (col. 71. Para. 1); reading on limitations of iteratively adjusting selective metabolite feature parameters until a performance threshold criterion is met;
Hooser further discloses that the system or apparatus can comprise a data storage unit or memory for storing data (col. 76, para. 3); reading on limitations of storing the trained parameters in memory for use by a metabolite feature identification system;
Hooser further discloses that generating a classification based on data such as metabolite
data which may then be used to determine whether an individual has or is at risk of having a disease, disorder, or condition (col. 77, last para.); reading on limitations of generating a predictive output, wherein the predictive output comprises an indication of whether the selective metabolite features correspond to the disease or disorder.
Further regarding claim 34, Hooser discloses a classifier model is trained using test and control or reference samples. Hooser further discloses that metabolites that discriminate test cases and reference samples in the training group can be analyzed and ranked (col. 73, last para.; col. 74, para.1).
Further regarding claim 35, Hooser discloses a system for generating a classification of an individual relative to one or more related classifications (col. 76, para. 1) using detection techniques such as a liquid chromatography mass spectrometry unit (col. 69).
Further regarding claim 38, Hooser discloses a processor; and a non-transitory computer-readable medium including instructions executable by the processor and configured to cause the processor to: (a) receiving data relating to a specimen taken from the individual; (b) providing the data as input to one or more machine learning algorithms; and (c) generating, using the one or more machine learning algorithms, a classification of the individual relative to a plurality of related classifications based on the data (col. 76, para. 2).
Further regarding claim 39, Hooser discloses any treatment known in the field for the diseases, disorders, or conditions including but not limited to treatments for those diseases, disorders, or conditions recited in Table 1, for example, influenza or respiratory virus (col. 13, Table 1).
Regarding claims 25 and 26, Hooser discloses that the panel of biomarkers used to classify or evaluate the status of a disease, disorder, or condition as disclosed herein comprises one or more metabolites selected from Table 2. In some cases, the panel of biomarkers comprises at least 1, 2, 3, 4, 5, 6, 7, 8, 19, 10, 15, 20, 25, 30, 35, 40, 45, 50, 60, 70, 80, 90, 100, 150, 200, 250, 300, 350, 400, 450, 500, 550, 600, 650, 700, 750, 800, 850, 900, or 950 or more metabolites from Table 2 (col. 30, para. 3); reading on limitations of wherein the selective metabolite features comprises three or more features in claim 25 and wherein the selective metabolite features comprise five or more features in claim 26.
Regarding claim 27, Hooser discloses non-limiting examples of diseases, disorders, and conditions, for example, Influenza, respiratory syncytial virus (RSV) infection (Table 1); reading on limitations of the predictive output relates to influenza or infection by another respiratory virus.
Regarding claim 28, Hooser discloses that an individual specimen such as a biological sample can be evaluated to generate a metabolite profile. The metabolite profile can be classified on a spectrum of a plurality of diseases, disorders, or conditions (see Table 1). Hooser further discloses that the classification is generated using classifiers trained using one or more machine learning algorithms having a score and/or indicator of the accuracy or confidence of the classification, where the score can be used to evaluate individual disease states and track signs of progress or decline associated with given conditions and interventions, over periods of time (col. 9, para. 2-3); reading on limitations of wherein the predictive output relates to an infectious disease state, a cancer state, graft rejection state, a blood disorder, a soft tissue disorder, or an autoimmune disease state.
Regarding claim 29, Hooser discloses that the algorithms provide a classification that stratifies a disease, disorder, or condition based on severity, grade, class, prognosis, or treatment of a particular disease, disorder, or condition, and/or other relevant factors (col. 9, para. 1); reading on limitations of wherein the predictive output comprises a prognosis or risk stratification.
Regarding claim 30, Hooser discloses providing a prediction or recommendation for treatment based on the classification or evaluation of one or more diseases, disorders, or conditions (col. 11, last para.); reading on limitations of the subject is identified as eligible for a treatment for the disease or disorder based on the predictive output without associated genetic or molecular data obtained from a raw sample corresponding to the processed sample.
Regarding claim 31, Hooser discloses any treatment known in the field for the diseases, disorders, or conditions including but not limited to treatments for those diseases, disorders, or conditions recited in Table 1, for example, influenza or respiratory virus (col. 13, Table 1); reading on limitations of wherein the method further comprises treating the subject for the influenza or respiratory virus.
Regarding claim 36, Hooser discloses that the system comprises a processor; and a non-transitory computer-readable medium including instructions executable by the processor and configured to cause the processor to: (a) receiving data relating to a specimen taken from the individual; (b) providing the data as input to one or more machine learning algorithms; and (c) generating, using the one or more machine learning algorithms, a classification of the individual relative to a plurality of related classifications based on the data (col. 76, para. 2); reading on limitations of the system comprises a processor and is operably connected with computer executable code, memory and data storage to support the method in an onboard computer or a remote computer.
Regarding claim 37, Hooser discloses that feature set is generated by selecting or screening for all biomarkers known to have some association with a particular biological trait or combination of traits inherently reducing processing time of the processor (col. 58, last para.); reading on limitations of reducing processing time of the processor when classifying patient metabolite features by selecting a subset of one or more of the metabolite features before inputting to the machine leaning model system, or excluding one or more of the metabolite features before inputting to the machine leaning model system.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Hooser et al. (US 11894139 B1), as applied to claims 21, 25-31, and 34-39 above, in view of Sugimoto et al. (JP 2020130131 A).
Claim 22 depends on claim 21. Limitations of claims 21 have been taught in the above rejections.
Regarding claim 22, Hooser discloses that the samples are processed samples obtained by raw subject samples (col. 69).
Further regarding claim 22, Hooser does not expressly disclose that the processing comprises ultrafiltration of the raw subject sample.
Sugimoto discloses a method for detecting microorganisms in a sample (abstract), where the sample includes nasopharyngeal swab (pg. 9, last para.), using ultrafiltration technique for sample having large amounts of liquid (pg. 10, para. 2), and where the microorganism to be detected is influenza virus (pg. 18, para. 3).
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method of Hooser and sage to have used the known ultrafiltration technique, as disclosed by Sugimoto to provide enhanced detection sensitivity. One of ordinary skill in the art would have been motivated to combine the method of Hooser and Sage with ultrafiltration technique of Sugimoto based on a finding that the Sugimoto contained a known technique that is applicable to the base method of Hooser and Sage. One of ordinary skill in the art would have been capable of applying this known technique to the to a known method of Hooser and Sage and the results would have been predictable.
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Hooser et al. (US 11894139 B1), as applied to claims 21, 25-31, and 34-39 above, in view of Le et al. (Metabolic profiling by reversed-phase/ion-exchange mass spectrometry, Journal of Chromatography B, Volume 1143, 15 April 2020, 122072, pages 1-7).
Claim 23 depends on claim 21. Limitations of claims 21 have been taught in the above rejections.
Regarding claim 23, Hooser discloses that metabolites in a specimen can be determined using various molecular detection techniques such as mass spectrometry, nuclear magnetic resonance, chromatography, or other methods such as high performance liquid chromatography (HPLC), gas chromatography (GC), and capillary electrophoresis (CE) may be coupled to mass spectrometric analysis, a quadrupole time-of-flight (Q-TOF) mass spectrometer coupled to ultra-high performance liquid chromatography (UHPLC) instrument, with an electrospray ionization (ESI) source (col. 69).
Hooser does not expressly disclose that the liquid chromatography is two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography. Le discloses a RP-IEX two-column in-line method in which the RP column precedes the IEX column, where the RP column captures the slightly polar and non-polar compounds while the IEX column captures charged compounds for downstream feature selection and other data analysis (pg. 2, col. 1, para. 1; pg. 3, col. 2, last para.).
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method of Hooser to have used the known two column in-line liquid chromatography comprising reverse phase and ion exchange chromatography techniques, as disclosed by Le to provide enhanced separation and analysis capabilities. One of ordinary skill in the art would have been motivated to substitute the mass spectrometry of Hooser with specific LC-MS of Le based on a finding that the substituted components and their functions were known in the art. One of ordinary skill in the art could have substituted the MS device of Hooser with LC-MS of Le and this substitution would have yielded predictable results.
Claim 32 is rejected under 35 U.S.C. 103 as being unpatentable over Hooser et al. (US 11894139 B1), as applied to claims 21, 25-31, and 34-39 above, in view of Gamarra et al. (Pyroglutamic acidosis by glutathione regeneration blockage in critical patients with septic shock, Gamarra et al. Critical Care (2019) 23:162), in view of Shim et al. (Exploratory metabolomics of nascent metabolic syndrome, Journal of Diabetes and its Complications, Volume 33, Issue 3, March 2019, Pages 212-216), and further in view of Ariyoshi et al. (D-Glutamate is metabolized in the heart mitochondria, Scientific Reports | 7:43911, pages 1-9, Published: 07 March 2017).
Claim 32 depends on claim 25. Limitation of claim 25 have been taught in the above rejections.
Regarding claim 32, Hooser discloses that the selective metabolite features are selected from the group consisting of 5-oxoproline/pyroglutamic acid and other glutamate metabolites (Table 2). Hooser further discloses using mass spectrometry to detect and identify metabolites (col. 69).
Gamarra discloses that the high presence of PyroGlu contributes even further to GSH deficiency and would be an indicator of high oxidative stress. Gamarra further discloses that from these analyses, the concentrations of Glu and PyroGlu can be correlated with clinical outcomes (pg. 3, col. 1). Gamarra further discloses that patients with septic shock, where the original cause of septic shock was respiratory origin (see pg. 4, col. 1, Results; Table 1), manifest pyroglutamic acidosis that correlates with low levels of Glu (except urine Glu/Crea) which can be measured in both serum and urine, and low GPX1/Hb activity (pg. 9, col. 1 last para.).
Shim explores metabolomics of nascent metabolic syndrome and discloses that d-pyroglutamic acid (PGA) is altered in nascent MetS patients and correlates it with biomarkers of inflammation (abstract).
Further, Ariyoshi discloses that D-glutamate and 5-oxo-D-proline have bioactivities in mammals through the metabolism by D-glutamate cyclase (abstract).
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the method of Hooser to have used the known pyroglutamic acid-D5 which is correlated with inflammation and disease, as disclosed by Gamarra, Shim, and Aryoshi. One of ordinary skill in the art would have been motivated to combine these methods based on a finding that the method of Hooser contained the base method of training a machine learning model for metabolite identification and disease prediction. One of ordinary skill in the art could have include pyroglutamic acid-D5/ the deuterated analog of pyroglutamic acid since the -D5 version is used primarily as an internal standard in mass spectrometry to distinguish it from naturally occurring 5-oxoproline in samples to better diagnose diseases and the results of the combination would have been predictable because assaying pyroglutamic acid can be employed for diagnosis/prognosis of diseases.
Claim 33 is rejected under 35 U.S.C. 103 as being unpatentable over Hooser et al. (US 11894139 B1), as applied to claims 21, 25-31, and 34-39 above, in view of Sage et al. (US20230100616A1), and further in view of Yuan et al. (US12346778B2).
Claim 33 depends on claim 21. Limitations of claim 21 have been taught in the above rejections.
Regarding claim 33, Hooser discloses that the classifier used to generate predictions includes one or more selected feature spaces such as metabolite and these features obtained from a sample can be fed into the classifier or trained algorithm to generate one or more predictions. Hooser further discloses using algorithms including principal component analysis (PCA) for variable reduction in training (col. 74, last para.); reading on limitations of the training iterations are performed using unsupervised principal component analysis, run alignment, peak picking, adduct deconvolution, and/or positive polarity analysis. Hooser further discloses that the panel of biomarkers comprises a subset of metabolites selected from Table 2 that satisfy a threshold or performance metric as disclosed herein, for example, a correlation or association with one or more diseases, disorders, or conditions of interest having a certain p-value or metric such as PPV or AUC.
Sage discloses a computer-implemented method for determining patient outcome risk in a patient with a respiratory illness, the method comprising: a. obtaining a polypeptide level of one or more, preferably two or more, biomarkers (claim 60). Sage further discloses using the polypeptide level of several of the biomarkers in combination, as inputs for an algebraic calculation or machine learning model to determine patient outcome risk (claim 1) wherein the machine learning model comprises a decision tree (claim 51). Sage further discloses that machine learning models are run using selected biomarker and that the ML models include at least one model trained using patient data where ML model include Extreme Gradient Boosting™ (XGBoost™) software library, which provides a gradient boosting framework for solving regression and classification problems and that the gradient boosting model the ML models of the patient outcome prediction system can be used together with use of other ML models including random forest [0249-0251, 0254]. Sage further discloses that the relative feature importance of the biomarkers of the machine learning model can be given by their Shapley Additive Explanations (SHAP) values (claim 53, see also, Kendall's rank correlation of biomarkers [0303]; see [0155] for mass spectrometry biomarker detection).
Sage discloses using XGBoost for solving regression and classification problems [0251]. Sage does not expressly disclose that the gradient boosting is lightgbm.
Yuan discloses an AI-based condition classification system for patients with novel coronavirus, which includes: a classification model acquisition module for training one or more binary classification models that classify patient conditions according to patient data (abstract).
Yuan further discloses that the classification model acquisition module is configured to train a plurality of binary classification models that classify a patient condition according to a patient data, and obtain one binary classification model with a highest accuracy from the binary classification models as a target model, and determine interpretable features in the patient data (claim 1) and that patient data includes biochemical set (col. 1, para. 3).
Yuan further discloses that the binary classification (diseased or not diseased) models established by the 5 model training units are: XGBoost, LightGBM, random forest, CatBoost and logistic regression (claim 5).
Yuan further discloses that the decision-making unit is configured to select the most accurate binary classification model from the N trained binary classification models as the candidate model, and select the top K features (Interpretable Feature Selection to identify the most influential features for the chosen candidate model, enhancing model interpretability and explainability) with the highest feature importance as the interpretable features according to the feature importance output by the candidate model (col. 3, para. 2).
Yuan further discloses training and validating the candidate model and that after the training is completed, the optimal binary classification model outputs feature importance and the target model is obtained and adopted (col. 3, para. 1-3).
Yuan further discloses using decision-making unit to increase the interpretability of machine learning models (col. 3, para. 2).
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to combine the methods of Hooser, Sage, and Yuan, based on the finding that the combination represents the use of known techniques to improve similar methods. Hooser, Sage, and Yuan are directed to generating a diagnostic or prognostic indication. Hooser discloses training a machine learning model for metabolite identification and disease prediction. Sage disclosed using machine learning models such as XGBoost for their feature selection model. In the same field of research, Yuan provided the use of the specific gradient boost model, LightGBM, for the purpose of feature selection. Applying the LightGBM algorithm of Yuan to the feature selection method of Sage and Hooser would have allowed for a faster and more efficient feature selection, especially with large, high-dimensional datasets like metabolites data. One ordinary skilled in the art before he effective filing data of the claimed invention would have had a reasonable expectation of success at applying the method of Yuan to the base method of Hooser and Sage and this application would have been expected to have provided a more efficient prediction. Therefore, the invention would have been prima facie obvious to one of skill in the art before the effective filing date of the claimed invention, absent evidence to the contrary.
Conclusion
No claims are allowed.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GHAZAL SABOUR whose telephone number is (703)756-1289. The examiner can normally be reached M-F 7:30-5:00.
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, Larry D. Riggs can be reached at (571) 270-3062. 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.
/G.S./Examiner, Art Unit 1686
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686