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 Objections
Claim 12 objected to because of the following informalities: the phrase “obtaining a standard deviation template function from the expected value template function through machine learning computation comprises the following steps” is not correct grammatically. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-11 rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites limitations utilizing the term ‘weight’. It is unclear whether the term weight refers to the weighting of the claimed machine learning algorithm or the physical weight of the patient. For the purposes of this office action, this limitation will be interpreted to be referring to the weighting of the machine learning algorithm.
Dependent claims are rejected by virtue of their dependency.
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.
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(s) 1-6 and 8-11 are rejected under 35 U.S.C. 103 as being unpatentable over Sakarya (US 20240170099 A1) in view of Ardhanari (US 20240143838 A1).
Regarding claim 1, Sakarya teaches a calculation method ([0019] the method … calculates, for the genomic region, an indicativeness score representing a correlation between characteristic and methylation patterns)
for a brain functional imaging template ([0058] imaging technology; [0209] Examples of cancers that can be detected using the methods, systems and classifiers of the present invention include … brain cancer)
suitable for being established in a software program and read by a computer ([0025] In another aspect, a system comprising a hardware processor and a non-transitory computer-readable storage medium storing instructions that, when executed by the hardware processor, cause the hardware processor to perform the methods disclosed herein. Similarly a non-transitory computer readable storage medium storing instructions that, when executed by one or more processors, cause the processors to perform the methods disclosed herein)
selecting multiple sets of images from a known healthy human database ([0006] In some aspects, the method further includes obtaining a test sample, the test sample including a plurality of additional nucleic acid fragments and labelled with a chronological age of a test subject from whom the test sample is derived)
defining a position-age function by associating a position information in the set of images with an age information corresponding to the image ([0006] In some aspects, the method further includes obtaining a test sample, the test sample including a plurality of additional nucleic acid fragments and labelled with a chronological age of a test subject from whom the test sample is derived [0092] As used interchangeably herein, the term “methylation fragment” or “nucleic acid methylation fragment” refers to a sequence of methylation states for each CpG site in a plurality of CpG sites, determined by a methylation sequencing of nucleic acids (e.g., a nucleic acid molecule and/or a nucleic acid fragment). In a methylation fragment, a location and methylation state for each CpG site in the nucleic acid fragment is determined based on the alignment of the sequence reads (e.g., obtained from sequencing of the nucleic acids) to a reference genome. A nucleic acid methylation fragment comprises a methylation state of each CpG site in a plurality of CpG sites (e.g., a methylation state vector), which specifies the location of the nucleic acid fragment in a reference genome (e.g., as specified by the position of the first CpG site in the nucleic acid fragment using a CpG index, or another similar metric))
utilizing machine learning to compute the position-age function for obtaining a machine learning model and obtaining a corresponding weight information ([0005] The method includes generating a reduced feature set from the feature set based on the comparison of age residuals, wherein the reduced feature set includes a lesser number of genomic regions than the feature set, and the reduced feature set is used to train the machine-learned age-prediction model)
and calculating an expected value template function corresponding to the machine learning model based on the weight information and the age information ([0006] The method includes applying the trained age-prediction model to determine a predicted chronological age of the test subject from whom the test sample was derived based on methylation patterns of the additional nucleic acid fragments overlapping the one or more genomic regions in the feature set, and calculating an age residual as a difference between the labelled chronological age and the predicted chronological age of the test subject. The method includes determining that the test sample has a strong likelihood for presence of cancer in response to determining that the age residual is above a residual threshold).
Sakarya fails to teach nuclear medicine.
However, Ardhanari teaches nuclear medicine ([0023] Medical imaging data may include data associated with X-rays, CT scans, magnetic resonance imaging, ultrasounds, PET scans, nuclear medicine imaging)
Sakarya and Ardhanari are considered analogous because both disclose applications of machine learning algorithms to make medical determinations. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to apply nuclear medicine to the method outlined in Sakarya so that user data 108 may include data associated with the vital signs of the user (Ardhanari [0023]).
Regarding claim 2, Sakarya teaches setting a threshold to exclude an outlier from the sets of images ([0119] The analytics system may determine that a certain fragment with one or more CpG sites has an indeterminate methylation status over a threshold number or percentage, and may exclude such fragments or selectively include such fragments but build a model accounting for such indeterminate methylation statuses)
Regarding claim 3, Sakarya teaches for the age information in the sets of images, calculating a loss function of the age information and integrating the loss function of the age information into a loss set function; and defining the loss function corresponding to a difference in the loss set function that is greater than the threshold as the outlier ([0195] the binary cancer classifier may be a L2-regularized logistic regression classifier that is trained using a log-loss function).
Regarding claim 4, Sakarya teaches dividing into multiple classification data based on degree of image severity in the known healthy human database; setting a corresponding sampling rate value based on the classification data; and defining the sampling rate value which is less than the threshold as the outlier ([0156] the p-value score may be adjusted, e.g., for multiple hypothesis testing by controlling for a false positive rate, a family-wise error rate, a false discovery rate, etc.; it is well known in the art that the p-value which is adjusted in this citation is affected by sample size and thus is affected by sampling rate)
Regarding claim 5, Sakarya teaches dividing into multiple classification data based on degree of image severity in the known healthy human database ([0208] the methods and systems of the present invention can be trained to detect or classify multiple cancer indications. For example, the methods, systems and classifiers of the present invention can be used to detect the presence of one or more, two or more, three or more, five or more, ten or more, fifteen or more, or twenty or more different types of cancer)
And defining the sampling classification data which is greater than the threshold as the outlier ([0119] The analytics system may determine that a certain fragment with one or more CpG sites has an indeterminate methylation status over a threshold number or percentage, and may exclude such fragments or selectively include such fragments but build a model accounting for such indeterminate methylation statuses).
Sakarya fails to teach multiplying the classification data by a fixed value to obtain multiple sampling classification data.
However, Ardhanari teaches multiplying the classification data by a fixed value to obtain multiple sampling classification data ([0088] multiplying the square of each coefficient by a scalar amount to penalize large coefficients)
Sakarya and Ardhanari are considered analogous because both disclose applications of machine learning algorithms to make medical determinations. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to multiply data points in the classification data by a scalar value in order to penalize large coefficients (Ardhanari [0023]).
Regarding claim 6, Sakarya teaches calculating a position value in the position information to obtain the weight information corresponding to the position value ([0157] In some embodiments, the analytics system calculates a p-value score for each methylation state vector compared to methylation state vectors from fragments in a healthy control group. The p-value score can describe a probability of observing the methylation status matching that methylation state vector or other methylation state vectors even less probable in the healthy control group. In order to determine a DNA fragment to be anomalously methylated, the analytics system can use a healthy control group with a majority of fragments that are normally methylated. When conducting this probabilistic analysis for determining anomalous fragments, the determination can hold weight in comparison with the group of control subjects that make up the healthy control group. To ensure robustness in the healthy control group, the analytics system may select some threshold number of healthy individuals to source samples including DNA fragments)
and computing a position-loss function ([0195] classifier may be a L2-regularized logistic regression classifier that is trained using a log-loss function)
Sakarya fails to teach calculating multiple neighboring position values adjacent to the position value to obtain the weight information corresponding to the neighboring position values; comparing the weight information corresponding to the neighboring position values with the weight information corresponding to the position value; and computing the position-loss function by using a gradient descent method to correct the weight information.
However, Ardhanari teaches calculating multiple neighboring position values adjacent to the position value to obtain the weight information corresponding to the neighboring position values; comparing the weight information corresponding to the neighboring position values with the weight information corresponding to the position value ([0104] additional information may include network statistics for a given node of network, such as a distributed storage node, e.g. the latencies to nearest neighbors in a network graph, the identities or identifying information of neighboring nodes in the network graph, the trust level and/or mechanisms of trust (e.g. certificates of physical encryption keys, certificates of software encryption keys, (in non-limiting example certificates of software encryption may indicate the firmware version, manufacturer, hardware version and the like), certificates from a trusted third party, certificates from a decentralized anonymous authentication procedure, and other information quantifying the trusted status of the distributed storage node) of neighboring nodes in the network graph, IP addresses, GPS coordinates, and other information informing location of the node and/or neighboring nodes, geographically and/or within the network graph. In some embodiments, additional information may include history and/or statistics of neighboring nodes with which the node has interacted)
and computing the position-loss function by using a gradient descent method to correct the weight information ([0085] an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine-learning model through any suitable process including without limitation gradient descent processes).
Sakarya and Ardhanari are considered analogous because both disclose applications of machine learning algorithms to make medical determinations. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to compare a data point with its neighbors and then use gradient descent to improve the model in order to update one or more weights (Ardhanari [0085]).
Regarding claim 8, Sakarya teaches training the machine learning model by using the position-age functions and the age information of a batch ([0136] FIG. 4A illustrates training 400 of an age prediction model, according to one or more embodiments. The analytics system may perform some or all of the training 400. In other embodiments, other components in FIGS. 6A & 6B may perform some or all of the training 400. The training 400 yields a trained age prediction model, which may input methylation features for a set of age informative genomic regions and output a predicted age. The process of training 400 the age prediction model can be similarly applied to training other covariate prediction models. In embodiments with other covariates, the analytics system utilizes training samples with reported values for the covariate prediction model being trained)
Sakarya fails to teach using a gradient descent method to correct the weight information.
However, Ardhanari teaches using a gradient descent method to correct the weight information ([0085] an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine-learning model through any suitable process including without limitation gradient descent processes).
Sakarya and Ardhanari are considered analogous because both disclose applications of machine learning algorithms to make medical determinations. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to use gradient descent to improve the model in order to update one or more weights (Ardhanari [0085]).
Regarding claim 9, Sakarya teaches using a linear regression model for computing ([0015] the indicativeness score is determined by training a linear regression to regress chronological age from methylation density of non-cancer training samples)
Regarding claim 10, Sakarya teaches using an artificial neural network model for computing ([0004] training a machine-learned age-prediction model to determine a predicted chronological age of a tested individual from whom a test sample is derived)
Regarding claim 11, Sakarya teaches calculating a standard deviation function for an age range interval in the expected value template function; using machine learning to compute the standard deviation function to obtain a standard deviation machine learning model and obtain a corresponding standard deviation weight information; and calculating the standard deviation template function corresponding to the standard deviation machine learning model based on the standard deviation weight information and the age information ([0227] The right graph encompasses samples the classifier predicted to have cancer, i.e., positive results inclusive of both true positives and false positives. A residual threshold (shown as “z-score” above/below 4) was four standard deviations from the mean. Any sample with chronological age residual above the threshold was colored red with the remainder colored yellow).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Sakarya in view of Ardhanari as applied to claim 1 above, and further in view of Moreno.
Regarding claim 7, Sakarya teaches obtaining a position-loss function ([0195] classifier may be a L2-regularized logistic regression classifier that is trained using a log-loss function)
Sakarya fails to teach distinguishing multiple brain-area locations based on brain-area characteristics; comparing the weight information corresponding to the position information in the same brain-area location; and computing the position-loss function by using a gradient descent method to correct the weight information.
However, Ardhanari teaches using a gradient descent method to correct the weight information ([0085] an error function may be used in turn to update one or more weights, biases, coefficients, or other parameters of a machine-learning model through any suitable process including without limitation gradient descent processes).
Sakarya and Ardhanari are considered analogous because both disclose applications of machine learning algorithms to make medical determinations. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to use gradient descent to improve the model in order to update one or more weights (Ardhanari [0085]).
Sakarya in view of Ardhanari fails to teach distinguishing multiple brain-area locations based on brain-area characteristics; comparing the weight information corresponding to the position information in the same brain-area location.
However, Moreno teaches distinguishing multiple brain-area locations based on brain-area characteristics; comparing the weight information corresponding to the position information in the same brain-area location ([0212] The method may then compare the next brain network, by comparing the first brain region of the second brain network, with each of the other brain regions of the second brain network, until each brain region within each network is compared against each other region of its same network).
Sakarya as modified and Moreno are considered analogous because both disclose machine learning implemented methods to treat disorders that may or may not be in the brain. Therefore, it would have been obvious to one of ordinary skill in the art prior to the effective filing date of the pending application to compare different brain regions against one another in order to provide early detection of future brain injury by identifying areas of the brain that are functionally disconnected, but which have not yet experienced neurological death or physical deterioration (Moreno [0017]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GABRIEL VICTOR POPESCU whose telephone number is (571)272-7065. 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, Anne Kozak can be reached at (571) 270-0552. 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.
/GABRIEL VICTOR POPESCU/ Examiner, Art Unit 3797
/JOSEPH M SANTOS RODRIGUEZ/ Primary Examiner, Art Unit 3797
Prosecution Insights