DETAILED ACTION
The amendment filed on 02/27/2026 has been entered and fully considered. Claims 21-37 and 40-47 are pending. Claims 26-28 have been withdrawn from consideration. Claims 21-25, 29-37 and 40-47 are considered on merits, of which claim 21 is amended.
Response to Amendment
In response to amendment, the examiner maintains rejection over the prior art established in the previous Office 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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claim 21-37 and 40-47 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1-24 of U.S. Patent No. 11,624,750, and over claim 1-17 of U.S. Patent No. 10,837,970. Although the claims at issue are not identical, they are not patentably distinct from each other because both the instant claims and the currently patented claims expressly recite the same subject matter, it would have been obvious to one of ordinary skill in the art at the time the invention was made to employ both device and methods, as recited in both sets of claims.
Claim Rejections - 35 USC § 102
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 21-23, 25, 29-36, 40-47 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Ruhaak et al. (Journal of Proteome Research, 2016) (Ruhaak).
Regarding claim 21, Ruhaak teaches a method for determining a prediction model for a classification of an unclassified human subject (abstract), the method comprising:
subjecting each of a plurality of biological samples to one or more proteases (trypsin) to produce a set of respective protease-processed samples (page 1003, par 4),
wherein each of the plurality of biological samples is from a human subject having a classification assigned based on having a disease or not having the disease (page 1003, par 3) and
wherein the plurality of biological samples comprises samples from human subjects having the disease and human subjects not having the disease (page 1003, par 3);
subjecting each protease-processed sample to a liquid chromatography multiple reaction monitoring mass spectrometry (LC-MRM-MS) technique configured to selectively interrogate target species of interest (page 1003, par 7-8),
wherein the target species of interest comprise a plurality of glycopeptides (page 1003, par 9);
analyzing the information obtained from the LC-MRM-MS technique to produce quantitation results for each protease-processed sample (page 1003, par 9); and
inputting the quantitation results of each protease-processed sample along with the associated classification to train a machine learning model to identify identify the condition associated site-specific glycosylation profile (page 1004, par 3).
Ruhaak expressly performs differential analysis of glycopeptide intensities to identify glycosylation changes associated with ovarian cancer and evaluates site-specific immunoglobulin glycosylation patterns indicative of disease. Applicant acknowledges that Ruhaak determines “site-specific glycosylation changes associated with ovarian cancer.”
Identifying sets of glycopeptides whose abundance patterns distinguish cancer samples from controls constitutes identifying a disease-associated glycosylation profile. The classifier built using these features therefore represents a model identifying such condition-associated glycosylation patterns.
Regarding claim 22, Ruhaak teaches that wherein the plurality of glycopeptides is associated with at least more than 50 glycoproteins (Fig. 2).
Regarding claim 23, Ruhaak teaches that wherein the disease is cancer (EOC) (Fig. 2).
Regarding claim 25, Ruhaak teaches that wherein the cancer is breast cancer, cervical cancer, or ovarian cancer (EOC) (Fig. 2)
Regarding claim 29, Ruhaak teaches that wherein the target species of interest comprise glycopeptides from one or more of alpha-1-acid glycoprotein, alpha-1-antitrypsin, alpha-1B-glycoprotein, alpha-2-HS-glycoprotein, alpha-2-macroglobulin, antithrombin-III, apolipoprotein B-100, apolipoprotein D, apolipoprotein F, beta-2-glycoprotein 1, ceruloplasmin, fetuin, fibrinogen, immunoglobulin (lg) A, IgG, IgM, haptoglobin, hemopexin, histidine-rich glycoprotein, kininogen-1, serotransferrin, transferrin, and vitronectin zinc-alpha-2-glycoprotein (Fig. 2).
Regarding claim 30, Ruhaak teaches that wherein the target species of interest comprise glycopeptides from one or more of immunoglobulin (lg) A, IgG, and IgM (Fig 2).
Regarding claim 31, Ruhaak teaches that wherein the quantitation results comprising information from IgG, IgA, and IgM glycopeptides of each protease-processed sample along with the associated classification (Fig. 2), and the inputting of the quantitation results comprise inputting the information from IgG, IgA, and IgM glycopeptides along with the associated classification to the machine learning method model implementing a combined discriminant analysis (page 1004, par 1).
Regarding claim 32, Ruhaak teaches that wherein the one or more proteases comprise a serine protease (page 1003, par 4).
Regarding claim 33, Ruhaak teaches that wherein the serine protease is selected from the group consisting of trypsin, chymotrypsin, endoproteinase, Arg-C, Glu-C, Lys-C, and proteinase K (page 1003, par 4).
Regarding claim 34, Ruhaak teaches that wherein the plurality of biological samples are each selected from the group consisting of a whole blood sample, serum sample, and plasma sample (page 1003, par 4).
Regarding claim 35, Ruhaak teaches that wherein the plurality of biological samples are whole blood samples (page 1003, par 2).
Regarding claim 36, Ruhaak teaches that wherein the plurality of biological samples are serum samples (page 1003, par 4).
Regarding claim 38, Ruhaak teaches that wherein the machine learning method comprises a deep learning, neural network, discriminant analysis, support vector machine, random forest, nearest neighbor algorithm, or a combination thereof (page 1004, par 1).
Regarding claim 40, Ruhaak teaches that further comprising using the trained machine learning model to identify one or more glycopeptides indicative of the classification of an unclassified human subject (page 1003, par 3, page 1006, par 1).
Regarding claim 41, Ruhaak teaches that wherein the human subjects not having the disease are healthy donors (page 1003, par 2).
Regarding claim 42, Ruhaak teaches that wherein the LC-MRM-MS technique is performed on a triple quadrupole mass spectrometer (page 1003, par 7).
Regarding claim 43, Ruhaak does not specifically teach that wherein the triple quadrupole mass spectrometer has a mass accuracy of 10 ppm or better. However, since mass accuracy is important for the data analysis, it would have been obvious to one of ordinary skill in the art to optimize the mass accuracy of the triple quadrupole mass spectrometer by routine experimentation and use better mass spectrometer.
Regarding claim 44, Ruhaak teaches that wherein the plurality of biological samples comprises samples from at least 20 human subjects having the disease and at least 20 human subjects not having the disease (page 1003, par 3).
Regarding claim 45, Ruhaak teaches that wherein the plurality of biological samples comprises samples from at least 40 human subjects having the disease and at least 40 human subjects not having the disease (page 1003, par 3).
Regarding claim 46, Ruhaak teaches that the method further comprising:
comparing a prediction output of the machine learning model to a target output to determine an error value; and
updating parameters of the machine learning model based on the error value (page 1004, par 2).Regarding claim 47, Ruhaak teaches a method for determining a model for identifying a condition associated site-specific glycosylation profile (abstract), the method comprising:
subjecting each of a plurality of biological samples to one or more proteases (trypsin) to produce a set of respective protease-processed samples (page 1003, par 4),
wherein each of the plurality of biological samples is from a human subject having a classification assigned based on having a disease or not having the disease page 1003, par 3), and
subjecting each protease-processed sample to a liquid chromatography multiple reaction monitoring mass spectrometry (LC-MRM-MS) technique configured to selectively interrogate target species of interest (page 1003, par 7-8),
wherein the target species of interest comprise a plurality of glycopeptides (page 1003, par 9);
analyzing the information obtained from the LC-MRM-MS technique to produce quantitation results for each protease-processed sample (page 1003, par 9); and
inputting the quantitation results of each protease-processed sample along with the associated classification to train a machine learning model to identify the condition associated site-specific glycosylation profile (page 1004, par 3).
Ruhaak teaches:
• Serum samples from ovarian-cancer patients and healthy controls (page 1003, par 3);
• Trypsin digestion of glycoproteins (page 1003, par 4);
• LC–MRM–MS quantitation of multiple site-specific IgG glycopeptides (page 1003, par 7-8);
• Determination of site-specific glycosylation changes associated with ovarian cancer (page 1003, par 1; page 1008, par 4);
• Use of PLS-LDA classifiers and voting schemes to discriminate disease from control using those glycopeptide profiles (page 1004, par 2).
Thus, Ruhaak already teaches identifying a condition-associated site-specific glycosylation pattern and building a classification model, but only specifies linear discriminant analysis as the model type.
Ruhaak expressly teaches identifying site-specific glycosylation changes associated with ovarian cancer (page 1003, par 1, page 1008, par 4). In particular, Ruhaak quantifies individual IgG glycopeptides by LC–MRM–MS and reports that “These results strongly suggest that the total glycome profile is largely dominated by the highest abundance proteins and that protein- and site-specific glycosylation profiles will likely provide further insights into protein specific alterations in glycosylation of the glycans related to EOC and may serve as more specific biomarkers for EOC and its process,” (page 1008, par 4), thereby revealing a condition-associated, site-specific glycosylation profile. Ruhaak further constructs multivariate classifiers (PLS-LDA) trained on glycopeptide abundances and validates them using independent test sets, which inherently “determine a model for identifying a condition-associated site-specific glycosylation profile,” as claimed.
Ruhaak identify discriminative glycopeptides (features) whose relative abundances define disease-specific glycosylation patterns. The act of training a classifier on such features inherently yields a mapping between quantitative site-specific glycosylation profiles and disease state, satisfying the claimed output.
Ruhaak expressly performs differential analysis of glycopeptide intensities to identify glycosylation changes associated with ovarian cancer and evaluates site-specific immunoglobulin glycosylation patterns indicative of disease. Applicant acknowledges that Ruhaak determines “site-specific glycosylation changes associated with ovarian cancer.”
Identifying sets of glycopeptides whose abundance patterns distinguish cancer samples from controls constitutes identifying a disease-associated glycosylation profile. The classifier built using these features therefore represents a model identifying such condition-associated glycosylation patterns.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ruhaak in view of Kailemia et al. (Anal Bioanal Chem, 2017) (Kailemia).
Regarding claim 24, Ruhaak does not specifically teach that wherein the cancer is breast cancer. However, in the analogous art of predicting a disease using glycopeptides as biomarker, Kailemia teaches that glycopeptide can be used to predict cancers, including breast cancer (page 398, par 1). That it would have been obvious to one of ordinary skill in the art to use quantified glycopeptide biomarker to predict breast cancer.
Claim(s) 37 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ruhaak in view of Zhang et al. (WO 2012/129408) (Zhang).
Regarding claim 37, Ruhaak does not specifically teach that wherein the plurality of biological samples are plasma samples. However, Zhang teaches that wherein the plurality of biological samples are plasma samples (page 3, line 19-20). It would have been obvious to one of ordinary skill in the art to use plasma sample for glycoprotein analysis, because plasma also have glycoproteins.
Response to Arguments
Applicant's arguments filed 02/27/2026 have been fully considered but they are not persuasive.
Applicant argues that Ruhaak fails to disclose “inputting the quantitation results of each protease-processed sample along with the associated classification to train a machine learning model”, and further argues that the statistical analyses described in Ruhaak are not equivalent to a machine learning model. Applicant also argues that Ruhaak does not disclose that the model output identifies a “condition-associated site-specific glycosylation profile.”
These arguments are not persuasive for the following reasons.
1. Ruhaak teaches training a classifier using labeled data
Ruhaak explicitly discloses applying statistical classification methods to glycopeptide intensity data in order to distinguish ovarian cancer samples from controls. As discussed in the Office Action, Ruhaak performs partial least-squares regression with linear discriminant analysis (PLS-LDA) to determine whether glycopeptide profiles can separate cancer samples from controls.
Such methods inherently require training data consisting of feature values and associated class labels (e.g., cancer vs. control) in order to generate a predictive model. Thus, Ruhaak necessarily inputs glycopeptide quantitation values together with their associated disease classifications during the model-building process.
Ruhaak further describes constructing classifiers using training data and evaluating them using cross-validation and independent test sets. Applicant acknowledges this disclosure, noting that Ruhaak develops classifiers and evaluates them using leave-one-out cross-validation and test sets.
A person of ordinary skill in the art would understand that building such classifiers inherently involves training a predictive model using labeled quantitative measurements, which corresponds to the claimed step of inputting quantitation results with associated classifications to train a model.
Therefore, Ruhaak teaches the claimed training step.
2. Statistical classifiers such as PLS-LDA constitute machine learning models
Applicant asserts that the classifiers described in Ruhaak are not machine learning models. This argument is unpersuasive.
PLS-LDA and similar statistical classification algorithms are well-recognized supervised machine learning techniques used to classify biological samples based on measured features. Ruhaak’s classifiers are trained on measured glycopeptide intensities and corresponding disease labels in order to predict sample class.
3. Ruhaak identifies condition-associated glycosylation profiles
Applicant also argues that Ruhaak does not disclose the output of identifying a “condition-associated site-specific glycosylation profile.”
However, Ruhaak expressly performs differential analysis of glycopeptide intensities to identify glycosylation changes associated with ovarian cancer and evaluates site-specific immunoglobulin glycosylation patterns indicative of disease. Applicant acknowledges that Ruhaak determines “site-specific glycosylation changes associated with ovarian cancer.”
Identifying sets of glycopeptides whose abundance patterns distinguish cancer samples from controls constitutes identifying a disease-associated glycosylation profile. The classifier built using these features therefore represents a model identifying such condition-associated glycosylation patterns.
Thus, Ruhaak teaches the claimed output.
Conclusion
THIS ACTION IS MADE FINAL. 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 XIAOYUN R XU, Ph. D. whose telephone number is (571)270-5560. The examiner can normally be reached M-F 8am-5pm.
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, Lyle Alexander can be reached at 571-272-1254. 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.
/XIAOYUN R XU, Ph.D./Primary Examiner, Art Unit 1797