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 1-7 and 21-33 are pending. Claims 1-7 were amended. Claims 8-20 were canceled. Claims 21-33 are new.
Response to Arguments
Claim objections
Applicant’s amendment to claim 1 overcomes the objection to claim 1 set forth in the Non-Final Office Action mailed on March 24 2026.
The applicant canceled claim 9, so the objection to claim 9 set forth in the Non-Final Office Action mailed on March 24 2026 is now moot.
35 USC § 112
The rejection of claims 16-20 under 35 U.S.C. § 112(b) and claims 18-20 under 35 U.S.C. § 112(d), set forth in the Non-Final Office Action mailed on March 24, 2026, are withdrawn as moot in view of the cancellation of claims 16-20.
35 USC § 101
Claims 1, 21, and 28 have been analyzed for patent eligibility and found to recite a judicial exception but are integrated into a practical application as amended. The rejection of March 24, 2026, has been withdrawn.
The analysis concluded that under step 2A Prong Two of the Subject Matter Eligibility Test, claims 1, 21, and 28 integrate the recited judicial exception into a practical application by reciting controlling execution of a mass spectrometer to perform a mass spectrometry acquisition action based on the recommendation.
Therefore, claims 1, 21, and 28 and all the dependent claims are eligible at Prong Two Step 2A (see MPEP 2106.04(d)).
35 USC § 103
Applicants’ amendments with respect to claims 1-7 have been fully considered.
The applicant’s arguments that the prior art fails to teach real-time control, reinforcement learning, or neural network-driven acquisition actions are found to be unpersuasive.
The applicant’s argument regarding Gioioso’s not teaching obtaining a second mass spectrometry spectrum during execution of a mass spectrometry experiment is persuasive.
However, further consideration has found a prior art teaching of this approach, as discussed below.
Claim Objections
Claim 24 is objected to because of the following informalities:
Claim 24 recites the computer-implemented method “f claim 21”. The phrase “f claim 21” should be corrected to “of claim 21”
Appropriate correction is required.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or non-obviousness.
Claims 1-7 and 21-33 are rejected under 35 U.S.C. 103 as being unpatentable over Gioioso et al.(US 20220084802 A1) hereinafter Gioioso in view of Bazargan et al. (US 20210074533 A1) hereinafter Bazargan and Erickson et al. (Active Instrument Engagement Combined with a Real-Time Database Search for Improved Performance of Sample Multiplexing Workflows, J Proteome Res. 2019 Feb 4;18(3):1299–1306) hereinafter Erickson.
Regarding claim 1, Gioioso teaches a system (fig 10; 702, fig 7), comprising: at least one memory (1010, fig 10; 710, fig 7) that stores computer executable components; and at least one processor (1012,fig 10; 706, fig 7) that executes at least one of the computer executable components (AI Algorithm 726 and Al model 730, fig 7) that acquires data for a compound, the data defining a first mass spectrometry spectrum for the compound (P1 in fig 3; ¶ [0067]-¶ [0069]); and based on the data (training data 712) and employing an Al model (730) that is trained using reinforcement learning (AI model 730 or AI model 132 that can be trained via reinforcement learning ,¶[0021]) on an input dataset (dataset (712)) comprising an acquisition metric ( the training data includes performance indices and characteristics of the mass spectrometry data such as reproducibility 716, stability 718, data resolution 720, data intensity 722 and/or peak shape 724, fig. 7), and employing an associated score that is associated with the acquisition metric ((probability distributions)134 that assigns likelihood (fitness score ¶[92])(¶ [53])), generates a recommendation to perform a mass spectrometry action (system determines a "recommended configuration" of MS operating parameters for the MS apparatus (¶ [0108])) for the compound (the parameter values can be selected based on a particular sample to be analyzed ¶ [8]);
Gioioso describes a general AI/ML model and discloses that other types of AI/ML techniques
may be used (¶ [0103] & ¶ [0109]). Gioioso does not explicitly identify the model as a "neural network"(NN).
Bazargan teaches the use of ML models, including a "neural network" ¶ [0166], for determining or optimizing operating parameters of analytical instruments (including mass spectrometry systems) based on measured data and performance metrics.
It would have been obvious to one ordinary skill in the art at the time of the invention to
implement the reinforcement learning framework of Gioioso using a neural network structure as taught by Bazargan to create a control system capable of optimizing hardware parameters in real time for highly dynamic and transient samples, where manual tuning by a human expert is not feasible.
While Gioioso’s software loop runs in real-time to tune the instrument, ¶ [104], its system is directed to pre-experiment parameter tuning. Furthermore, Gioioso’s system generates a recommended configuration of static hardware operating parameters to calibrate the instrument, ¶ [77] rather than recommending a dynamic real-time acquisition action like scan triggers.
Gioioso in view of Bazargan does not teach a computer executable component that acquires, using a mass spectrometer during execution of a mass spectrometry experiment, data for a compound, the data defining a first mass spectrometry spectrum for the compound. Gioioso does not teach based on the data acquired during the mass spectrometry experiment, generating a recommendation to perform a mass spectrometry acquisition action for the compound; and based on the recommendation, controls execution of the mass spectrometer to perform the mass spectrometry acquisition action and obtain a second mass spectrometry spectrum for the compound.
Erickson teaches a system that acquires, using a mass spectrometer during execution of a mass spectrometry experiment, data for a compound, the data defining a first mass spectrometry spectrum for the compound (Erickson teaches a system that captures fragment spectra (the first spectrum, or MS2 scan) in real-time within milliseconds as they are acquired during the execution of a multiplexed sample workflow, Abstract ).
Erickson further teaches a framework that based on the data acquired during the mass spectrometry experiment, generates a recommendation to perform a mass spectrometry acquisition action for the compound (Erickson teaches evaluating the acquired MS2 data on-the-fly to make dynamic acquisition decisions. The Real Time Search (RTS) algorithm processes the acquired first spectrum using probabilistic score to determine if a peptide of interest is present, generating a real-time decision on whether to trigger subsequent quantitative scans. Figure above page 1299 and last ¶ in col. 1, page 1300)
Erickson teaches a framework that based on the recommendation, controls, execution of the mass spectrometer to perform the mass spectrometry acquisition action and obtain a second mass spectrometry spectrum for the compound (Erickson teaches active instrument engagement where the system dynamically controls the execution of the mass spectrometer’s scan sequence in response to real-time data, figure 2, page 1303. If the probabilistic database search confidently identifies a peptide from the first spectrum (MS2), the system immediately instructs the mass spectrometer to perform an acquisition action-triggering and executing a quantitative scan (RTS-MS3) to obtain a second mass spectrometry spectrum for that targeted compound).
It would have been obvious to one ordinary skill in the art before the effective filling date of the invention to integrate Erickson’s active running environment to Gioioso’s in view of Bazargan’s system to actively run experiments, execute second scans, and collect data dynamically on the fly. Because by forcing the tuning loop to run the entire sequence on the fly, the neural network can optimize for stability at the actual quantitative read out level, ensuring that ratios are robust and repeatable across different runs.
Claims 21 and 28 recite the analogous limitations as claim 1 in statutory categories of a computer-implemented method and a computer program product, respectively. Gioioso also discloses a computer-implemented method (¶ [142]), a non-transitory computer-readable storage medium (¶ [23]). Claims 21 and 28 are rejected for the same reasons as set forth with respect to rejection of claim 1.
Regarding claim 2, Gioioso in view of Bazargan and Erickson teaches the system of claim 1 as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan and Erickson further teaches the recommendation (Erickson, selectively triggering MS3 scan fig. 2 and fig. 5 (E)) to employ for the mass spectrometry acquisition action (Erickson, figure 2, page 1303, If the probabilistic database search confidently identifies a peptide from the first spectrum (MS2), the system immediately instructs the mass spectrometer to perform an acquisition action-triggering and executing a quantitative scan (RTS-MS3) to obtain a second mass spectrometry spectrum for that targeted compound)
Gioioso in view of Bazargan teaches that the recommended configuration specifies values for parameters such as different types of voltages.
Gioioso in view of Bazargan doesn’t teach specifying an amount of a resource to employ for the mass spectrometry acquisition action.
Erickson teaches specifying an amount of a resource (the triggered acquisition action specifies instrument scan resources including the selection of a synchronous precursor selection (SPS) of 10 fragment ions to co-isolate, as well as maximum injection times of 150 ms and duty cycle limits for the quantitative MS3 scan, (MS analysis section, page 1301, first ¶))
It would have been obvious to one ordinary skill in the art before the effective filling date of the invention to modify Gioioso’s RL model to dynamically specify the scan resources (SPS notches and injection times) taught by Erickson, because controlling the resource amount is the only physical mechanism that allows AI to guarantee consistent, uniform spectral quality, thereby directly satisfying Gioioso in view of Bazargan’s goal of reducing data variability.
Claims 22 and 29 are rejected for the same reasons as set forth with respect to rejection of claim 2.
Regarding claim 3, Gioioso in view of Bazargan and Erickson teaches the system of claim 1 as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan and Erickson further teaches the at least one of the computer executable components (Gioioso, AI Algorithm 726 and Al model 730, fig 7) further specifies the compound (ions associated with precursors with low energy spectra, Gioioso ¶[45]), or a fragmented compound (ions primarily from fragmented precursors, Gioioso [48]), from the first mass spectrometry spectrum ( MS/MS acquisition, Gioioso, [46]). Gioioso in view of Bazargan and Erickson teaches generating a recommendation for the mass spectrometry acquisition action (Erickson, figure 2, page 1303, If the probabilistic database search confidently identifies a peptide from the first spectrum (MS2), the system immediately instructs the mass spectrometer to perform an acquisition action-triggering and executing a quantitative scan (RTS-MS3) to obtain a second mass spectrometry spectrum for that targeted compound)
However, Gioioso in view of Bazargan does not teach specifying the compound, or a fragmented compound, from the first mass spectrometry spectrum, as a target of the mass spectrometry acquisition action.
Erickson teaches specifying the compound (the precursor peptide, conclusion), or a fragmented compound (specifically selecting fragment ions that match a b- or y– type ion from predicted peptide sequence, conclusion), from the first mass spectrometry spectrum (an MS2 fragment spectrum, conclusion) , as a target of the mass spectrometry acquisition action (SPS-MS3 scan, page 1300, col. 1, last ¶).
It would have been obvious to one ordinary skill in the art before the effective filling date of the invention to modify Gioioso in view of Bazargan’s spectral analysis to specify its compound and fragmented compound to be target of a subsequent scan (acquisition action) as taught by Erickson. This yields the expected benefit of ensuring that the triggered subsequent scans are tightly and dynamically focused on the actual, eluting analytes of interest to maximize quantitative precision.
Claims 23 and 30 are rejected for the same reasons as set forth with respect to rejection of claim 3.
Regarding claim 4, Gioioso in view of Bazargan and Erickson teaches the system of claim 1 as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan and Erickson further teaches at least one of the computer executable components (Gioioso, AI Algorithm 726 and Al model 730, fig 7).
Gioioso in view of Bazargan doesn’t teach specifying a plurality of targets corresponding to the compound, to be fragmented from the compound, or corresponding to one or more fragmented compounds from the first mass spectrometry spectrum, for which to obtain additional data by performance of the mass spectrometry acquisition action.
Erickson teaches a real Time Search (RTS) workflow where the client application evaluates a first mass spectrometry spectrum (an MS2 fragment spectrum) in real-time. Erickson further teaches upon confident peptide identification , the system dynamically specifies a plurality of targets corresponding to the compound (specifically selecting 10 fragment ions as targets for subsequent scan, (MS analysis section, page 1301, first ¶) , to be fragmented from the compound (the peptide ) , or corresponding to one or more fragmented compounds (the fragments must match a b- or y-type ion from the predicted peptide, (page 1301, col. 2, ¶ 2) from the first mass spectrometry spectrum (MS2, fig. 2 explanation under (C)), for which to obtain additional data by performance of the mass spectrometry acquisition action (teaches obtaining additional data, specifically, reporter ion intensities, and maximized signal-to-noise ratios by performing the SPS-MS3 acquisition action, page 1301 section “Proteome Informatics”).
It would have been obvious to one ordinary skill in the art before the effective filling date of the invention to modify Gioioso in view of Bazargan’s computer executable component to specify a plurality of targets as taught by Erickson, because this physical summation boosts the quantitative reporter signal, providing a clean, high intensity read-out that allows the neural network to calculate precise, noise-free fitness scores, enabling optimizing parameter weights on the fly with high accuracy.
Claims 24 and 31 are rejected for the same reasons as set forth with respect to rejection of claim 4.
Regarding claim 5, Gioioso in view of Bazargan and Erickson teaches the system of claim 1 as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan and Erickson further teaches wherein the at least one of the computer executable components (Gioioso, AI Algorithm 726 and Al model 730, fig 7) further obtains a metric of interest (Gioioso, peak shape 724, ¶[11]) for the compound, wherein the recommendation to perform the mass spectrometry action is at least partially based on the metric of interest (the Al algorithm 726 generates an output structure 734, which is a recommendation for parameter values. This selection is explicitly based on peak shape 724 ¶ [102-108]).
However, Gioioso in view of Bazargan doesn’t teach that the recommended action is acquisition action.
Erickson teaches acquisition action (Erickson teaches active instrument engagement where the system dynamically controls the execution of the mass spectrometer’s scan sequence in response to real-time data, figure 2, page 1303.)
It would have been obvious to one ordinary skill in the art before the effective filling date of the claimed invention to use the peak shape as a metric of interest with AI model, as taught by Gioioso in view of Bazargan, to make a dynamic recommendation to trigger Erickson’s subsequent scan (MS3). If the peak shape is clean and symmetrical the scan would be done, and if the peak shape is distorted or asymmetric, the AI recommends modifying the subsequent scan. This integration prevents the instrument from wasting precious duty cycle on ratio-distorted data.
Claims 25 and 32 are rejected for the same reasons as set forth with respect to rejection of claim 5.
Regarding claim 6, Gioioso in view of Bazargan and Erickson teaches the system of claim 1, as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan and Erickson further teaches wherein the at least one of the computer executable components (Gioioso, AI Algorithm 726 and Al model 730, fig 7) further retrains the neural network (Bazargan, "neural network" ¶ [0166], and Gioioso, the tuning device 128 and its internal evaluation logic 132 which operates within RL framework (¶ [56] & ¶ [104]))), wherein the retraining comprises: generating a reward indicator (Gioioso, the system is configured to assign a score (such as fitness score, (likelihood that a selected value optimizes the goal,¶ [14])). The tuning device 128 deploys Al model 132 that includes probability distributions 134, ¶ [52] & ¶ [53]. Moreover, the system may penalize/reinforce configurations,¶ [118] according to the scores (probability distributions) assigned to the configuration) resulting from the recommendation of the mass spectrometry acquisition action, or from an execution of the mass spectrometry acquisition action recommended (tuning device 128 evaluates the "result of a recommended configuration" after it is run on the MS apparatus ¶[108]).
Gioioso in view of Bazargan and Erickson further teaches updating one or more weights employed by the neural network (Gioioso, tuning device 128, that is responsible for executing the logic described in updating step 818 that updates NN by the AI based on the scores assigned to the configurations (fig. 8, block 818) and the "amount of adjustment may be weighted based on the score", ¶ [122]) or performs an adjustment to the acquisition metric, based on the reward indicator (the system determines if values for parameters reduced data variability and, based on that determination, updates the model to select new sets of values, which constitutes an "adjustment to the acquisition metric" logic, fig8 blocks 814, 816 and 818).
Claims 26 and 33 are rejected for the same reasons as set forth with respect to rejection of claim 6.
Regarding claim 7, Gioioso in view of Bazargan and Erickson teaches the system of claim 1, as set forth with respect to rejection of claim 1.
Gioioso in view of Bazargan further teaches the at least one of the computer executable components (Gioioso, AI Algorithm 726 and Al model 730, fig 7) further retrains the neural network (Bazargan, "neural network" ¶ [0166], and Gioioso, the tuning device 128 and its internal evaluation logic 132 which operates within RL framework (¶ [56] & ¶ [104]))), according to a set of reward indicators (Gioioso, fig. 8, block 818) amortized over time (Gioioso, the system considers the standard deviation of fitness scores across the last 10 maximum scores to determine if the model has truly improved ¶ [98]) and obtained based on a plurality of recommendations (The system covers a plurality
of recommendations through its evolutionary algorithms which generate and evaluate multiple "candidate solutions" or "configurations" in iterative batches called generations, ¶ [71]. The system can
select one or more candidate configurations to be tested by the MS apparatus, ¶ [131]), including the recommendation to perform the mass spectrometry acquisition action (Erickson, teaches evaluating the acquired MS2 data-on-the-fly to make dynamic acquisition decisions. The Real Time Search (RTS) algorithm processes the acquired first spectrum using probabilistic score to determine if a peptide of interest is present, generating a real-time decision on whether to trigger subsequent quantitative scans, (Figure above page 1299 and last ¶ in col. 1, page 1300)).
Claim 27 is rejected for the same reasons as set forth with respect to rejection of claim 7.
Conclusion
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 SAEEDE NAFOOSHE whose telephone number is (571)272-8629. The examiner can normally be reached Monday-Friday 8:00 am -5:00pm.
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, Andrew Schechter can be reached at 571-272-2302. 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.
/SAEEDE NAFOOSHE/ Examiner, Art Unit 2857
/ANDREW SCHECHTER/ Supervisory Patent Examiner, Art Unit 2857
Prosecution Insights