bDETAILED 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 .
Priority
This application was filed under 35 USC 371 as the National Stage application of PCT/US2021/044644, which claims priority to a US provisional, US 63151451 and US 63063401 filed on 02/19/2021 and 08/09/2020 respectively. The certified copy of the priority document was provided by the IB. The pending claims are afforded the effective filing date of 08/09/2020.
Information Disclosure Statement
The IDS filed 02/08/2023, 04/03/2023 and 10/15/2024 have each been entered and considered.
Claim Status
Claims 1–10 and 23–32 remain pending for examination, while claims 11–22 and 33–44 have been canceled. Please see the interview summary with the attorney regarding cancelled claims.
Claims 1-10 and 23-32 are pending and examined on the merits.
Claim 1-10 and 23-32 are rejected.
Drawings
The Figures 1 and 2 are objected to: Text, and subscripts of elements in the figures are indistinguishable, even upon enlargement. Fig. 2 is objected to because the legend identifying the nodes and connections in the plate notation is illegible. As a result, it cannot be verified that Figure 2 supports the specification’s description of the Bayesian network’s nodes (e.g., fold change chromosome X, fold change chromosome Y, FF_inferred depth) and their relationship to the sex chromosome probability determinations (XX, XXXX, XY, XXY, YYY). Accordingly, replacement drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to this Office action. The replacement sheet(s) should be labeled “Replacement Sheet” in the page header (as per 37 CFR 1.84(c)) so as not to obstruct any portion of the drawing figures. If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action.
Specification
The disclosure is objected to because of the following informalities:
The specification is objected to under 37 CFR 1.52(b) and MPEP 608.01 because the sub superscript notation in the equation on page 4-8 is illegible as filed, making it impossible to clearly identify the variables or confirm the equations defining the claimed Bayesian sex calling algorithms. Applicants is required to submit a substitute specification with properly formatted subscript/superscript, under 37 1.125(c) that no new matter has been added.
Claim Interpretation
The claims in this application are given their broadest reasonable interpretation (BRI) using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art.
Claim Rejections - 35 USC § 112b
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.
Claim 1, 5, 7, and 8 are 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 is rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor, or a joint inventor, regards as the invention.
Claim 1 recites a method for analyzing sex-chromosome aneuploidies of an individual comprising two principal steps: (1) “training a neural network model based on predetermined information related to at least one sex chromosome,” and (2) “determining the respective sex-chromosome status based on normalized read depth for a gene in a genome of the individual using a machine learning algorithm.” For the reasons set forth below, the metes and bounds of the claim cannot be determined by one of ordinary skill in the art.
The metes and bounds of claim 1 with respect to the models recited therein. Claim 1 introduces two apparently distinct computational elements, a “neural network model” in the training step and a “machine learning algorithm” in the determining step without clarifying whether these refer to the same model or to two separate models. A neural network is one species of machine learning algorithm, but the converse is not true: machine learning algorithm need not employ neural network structure (e.g., hidden layers or other structural elements characteristic of neural network). If the claim intends to for the “neural network model” trained in the first step to be the same element as the “machine learning algorithm” recited in the second step, antecedent basis is lacking and the claim should use consistent terminology. If, instead, the claim intends two different models, it is unclear what role, if any, the trained neural network model plays in the subsequently recited determining step, since the determining step is performed “using a machine learning algorithm” without reference back to the model trained in the first step. Either reading renders the scope of the claim indeterminate.
The training step recites training “based on predetermined information related to at least one sex chromosome,” but the claim does not identify what this predetermined information is (e.g., reference read-depth values, known sex-chromosome copy-number states, labelled training examples, or something else), nor does it specify what output the neural network model is trained to produce, or what detection task the training accomplishes. Without a defined training input, target, or objective, one of ordinary skill in the art cannot determine what is required to satisfy this limitation or how the trained neural network model relates to, or contributes to, the result of claimed method.
The determining step recites “a normalized read depth for a gene in a genome of the individual,” but the claim does not recite any step of obtaining a biological sample from the individual, sequencing that sample, or generating read-depth data from sequenced reads. The normalized read depth therefore appears in the claim without any antecedent source. In addition, the claim does not state what the read depth is normalized to (e.g., to a reference gene, chromosome, or sample; to sequencing depth; to a control population) or by what method the normalization method is performed, such that the metes and bound of the “normalized” cannot be ascertained. It is further unclear whether the normalized read depth is the sole input required to perform the determining step, or whether additional unrecited data is necessary to practice the claimed method, which is itself an indication that the claim fails to recite the steps necessary and sufficient to achieve the recited result.
Claim 1 recites “determining the respective sex-chromosome status” and “output the respective sex-chromosome status of the individual” but does not define what is meant by “status.” It is unclear, for example, whether “status” refers to the presence or absence of a particular sex-chromosome, the identity of which sex chromosomes are present, the copy number of one or more sex chromosomes (i.e., an aneuploidy calls consistent with the claim’s preamble), or whether the reads are attributable to a fetal versus maternal source. This ambiguity is compounded by the absence of limitation clarifying whether the claimed method is intended to be performed or any individual generally, or is specific to a pregnant individual (e.g., in the context of noninvasive prenatal testing), which would inform whether “the individual” and the source of the genomic material are the same person. Relatedly, it is unclear how the claimed method would accommodate a determination of the sex of a twin, or of multiple fetuses, where the individual from whom the sample is obtained is not herself the subject of the sex-chromosome status determination. Because the claim’s preamble recites “analyzing sex-chromosome aneuploidies of an individual,” but the body of the claim does not clarify which individual’s status being determined or reported, the scope of “individual” and “status” cannot be determined with reasonable certainty.
Considered as a whole, claim 1 recites a training step that operates on undefined “predetermined information” to produce an unspecified trained neural network model, and a separate determining step that applies an undefined normalized read depth to a “machine learning algorithm” to output an undefined “status,” without ever positively reciting step of obtaining genomic or sequence information from the individual and without trying that individual-specific information to either recited model. As presently claimed, the method does not particularly point out and distinctly claim the necessary and sufficient data and processing steps by which the recited “machine learning algorithm” is configured to receive the normalized read depth as n input and output the respective-sex chromosome status of the individual, as required by the last clause of the claim. Consequently, a person of ordinary skill in the art would be unable to determine the scope of the claimed invention with reasonable certainty.
The phrase in claim 5 "determining a complex sex phenotype" reads as a step-plus-function limitation. Under MPEP 2181, a method step recited in functional terms without a clear disclosure of the acts, materials, or sequence required to achieve that function is indefinite. The claim fails to provide the specific steps, analytical tools, or biological/computational metrics (e.g., genetic markers, hormone levels, or physical trait algorithms) that define the boundaries of this determination. Because the exact steps for making this determination are ambiguous, a person of ordinary skill in the art cannot ascertain the metes and bounds of the claim to avoid infringement.
Regarding claim 7, the claim uses highly ambiguous conditional language (“wherein the method provides a negative result...”). It leaves the metes and bounds of the claim scope unclear because one of ordinary skill in the art cannot determine with a reasonable degree of certainty exactly what active steps must be performed to achieve this "negative result" as opposed to other outcomes. The phrase “provides a negative result” is an attempted functional limitation covering what the process does (or rather, fails to produce), rather than the positive, structural steps defining how the process is actually carried out. Under MPEP 2173.05(g) Functional Limitations, using purely qualitative, functional features without a defined quantitative metric, formula, or clear step-by-step performance instruction in the specification renders the scope of the claim fundamentally vague and indefinite.
The phrase in claim 8, "determines the respective sex-chromosome status via Bayesian statistics of the read depth and allosome data" relies on a broad, functional, and purely mathematical placeholder. According to MPEP 2173.05(g), a claim term is indefinite if it introduces a mathematical formula or algorithm without defining the specific steps, parameters, or relationships required to perform the calculation. Bayesian statistics is a vast mathematical field. The claim fails to inform a person of ordinary skill in the art (PHOSITA) exactly how the read depth and allosome data are processed. It does not provide the specific priors, likelihood functions, or computational steps, rendering the metes and bounds of the claim scope unclear and functionally boundless.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10 and 23-32 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of mental steps, mathematic concepts, organizing human activity, or a natural law without significantly more.
Applicant is directed to MPEP 2106 for the most current and complete guidelines in the analysis of patent- eligible subject matter. The current MPEP is the primary source for the USPTO' s patent eligibility guidance.
With respect to step (1): YES, the claims are drawn to statutory categories: In accordance with MPEP § 2106, the instant claims 1-10, are drawn to a process (method), claims 23- 32 are drawn to a system, and therefore are found to recite statutory subject matter.
With respect to step (2A) (1): YES, the claims recite an abstract idea, law of nature and/or natural phenomenon. The claims explicitly recite elements that, individually and in combination, constitute one or more judicial exceptions (JE).
The instant claims are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong 1). The instant claims recite the following limitations that equate to an abstract idea or law of nature:
Claim 1 and 23 recites
“Training a neural network model based on predetermined information related to at least one sex chromosome.” Applying data to an unspecified neural network model, for an unspecified purpose. (Mathematical concept) MPEP 2106.04(a))
“Determining the respective sex-chromosome status based on a normalized read depth for a gene in a genome of the individual using a machine learning algorithm.” Applying data values to an unspecified, untrained machine learning algorithm (Mathematical concept) MPEP 2106.04(a))
“A method for analyzing sex-chromosome aneuploidies of an individual.” This statement represents the naturally occurring relationship between anomalous sex chromosome data and a naturally occurring phenotype. (Law of nature) (MPEP 2106)
Claim 3 and 25 recites “The method of claim 1 wherein the method comprises providing a twin sex calling.” (Mental process and Mathematical concept)
Claim 4 and 26 recites “the method of claim 3 wherein the twin sex calling comprises calling sexes among the following three phenotypes: two XX twins, two XY twins, and one XX twin and one XY twin.” (Mathematical concept and mental process) It determined entirely by executing a mathematical algorithm, equation, or calculating statistical relationships.
Claim 5 and 27 recites “the method comprises determining a complex sex phenotype.” (mental process)
Claim 6 and 28 further modify claim 5 or 27 which identified as a mental process. Claim 6 and 28 modify the disorder to be observed or identified and they are also a mental process.
Claim 7 and 29 recites “the method of claim 1 wherein the method provides a negative result where the respective sex-chromosome status is determined to be anomalous.” (Mental process) Making an observation that sex-chromosome status is anomalous or “negative” falls into mental process.
Claim 8 and 30 recites “The method of claim 1 wherein the method determines the respective sex- chromosome status via Bayesian statistics of the read depth and allosome data. (mathematical concept and mental process)
Claim 9 and 31 recites “The method of claim 1 wherein the method determines the respective sex- chromosome status via graphing of the read depth and allosome data.” (Mathematical concept and mental process)
Claim 10 and 32 recites “graphing a sample as a point in a two-dimensional plane. (Mental process) Graphing data coordinates or translating raw data into a 2D plot is considered a mathematical relationship or calculation.
As such claims 1-10, and 23-32 recite an abstract idea (Step 2A, Prong 1: YES).
With respect to step 2A (2): NO. The claims were examined further to determine whether they integrated any JE into a practical application (MPEP 2106.04(d)). The claimed additional elements are analyzed alone, or in combination to determine if the JE is integrated into a practical application (MPEP 2106.05(a-c, e, f and h)).
Specifically, the claims recite the following additional elements:
Claim 1 and 23 recites “A neural network model based on predetermined information related to at least one sex chromosome” The neural network is an additional element to the abstract idea.
Claim 2 and 24 recites “determining the respective sex-chromosome status is based on the normalized read depth and at least one of fetal fraction data and fold change data.”
Claim 23 recites “A system adapted to analyze sex-chromosome aneuploidies of an individual comprising: a neural network model trained based on predetermined information.”
Claim 1 does not recite any additional elements except “neural network”. The neural network is an additional element to the abstract idea; however, it is completely generically described and therefore is a field of use type limitation. MPEP 2106.05(h). Also “training a neural network” and “machine learning algorithm is configured to receive, as inputs, the normalized read depth, and output the respective sex-chromosome status of the individual” are data gathering steps. Claims 2 and 24 recite the additional element of describing data collected. Collecting data is extra solution activity, required to carry out the abstract idea. MPEP 2106.05(g). Claim 23 recites a general-purpose computer system which fails to provide a practical application of the abstract ideas. MPEP 2106.05 A, B, G, H.
Therefore claims 1, 2, 23 and 24 recite the additional non-abstract element(s) of data gathering, or a description of the data gathered.
Data gathering steps are not an abstract idea, they are extra-solution activity, as they collect the data necessary to carry out the JE. MPEP 2106.05(g).
The data gathering does not impose any meaningful limitation on the JE, or how the JE is performed. MPEP 2106.05(g).
The core of the claimed inventions remains the algorithmic determination/prediction of a sex type and bioinformaticians and geneticists routinely rely on publicly available genomic data (specially information of X and Y chromosome) to sort out sex of a species.
The additional limitation (data gathering) must have more than a nominal or insignificant relationship to the identified judicial exception to provide integration into a practical application. (MPEP 2106.05(g) citing Mayo, PerkinElmer, Inc. v. Interna Ltd, Intellectual Ventures LLC v. Erie Indem. Co., Electric Power Group LLC v. Alstom S.A.).
Under Alice Corp. v. CLS Bank Int'l, simply implementing or analyzing data using a generic, general-purpose computer does not transform an unpatentable abstract idea into a patent-eligible application.
Independent claims 1 and 23 imply the additional non-abstract element (EIA) of a general-purpose computer system or parts thereof based on assumption of necessity to run a neural network or machine learning algorithm.
The EIA do not provide any details of how specific structures of the computer elements are used to implement the JE. The claims require nothing more than a general-purpose computer to perform the functions that constitute the judicial exceptions. The computer elements of the claims do not provide improvements to the functioning of the computer itself (as in DDR Holdings, LLC v. Hotels.com LP); they do not provide improvements to any other technology or technical field (as in Diamond v. Diehr); nor do they utilize a particular machine (as in Eibel Process Co. v. Minn. & Ont. Paper Co.). Hence, these are mere instructions to apply the JE using a computer, and therefore the claim does not integrate that JE into a practical application.
Dependent claims 2-10 and 24-32 have been analyzed with respect to 2A-2. (MPEP 2106.05(a, b, c, e and h)).
Dependent claims 2-10 and 24-32 recite an abstract limitation to the JE reciting additional mathematic concepts, or mental processes or natural law. Additional abstract limitations cannot provide a practical application of the JE as they are a part of that JE.
Dependent claims 2 and 24 recite non-abstract limitations (EIA) which are directed to the data gathering, aspects of the data gathered, or to the output of results. As set forth above data gathering is pre-solution insignificant activity (MPEP 2106.05(g) citing OIP Tech Inc v. Amazon.com, Inc.) Describing aspects of the data gathered are similarly considered pre-solution insignificant activity. The output of results is post-solution insignificant activity (MPEP 2106.05(g) citing Apple v. Ameranth Inc.). Collectively they are extra-solution activity and insufficient to integrate the JE into a practical application.
Dependent claims 2-10 and 24-32 recites non-abstract limitations (EIA) directed to a generic determination of sex type. The determination step fails to integrate the JE into a practical application, as the step does not “affirmatively recite an action that effects a particular advancement of the computer technology. (MPEP 2106.04(d)(2)).
Dependent claims 2-10, 24-32 recites non-abstract limitations (EIA) directed to additional computer system elements. The computer elements of the claims do not provide improvements to the functioning of the computer itself (as in DDR Holdings, LLC v. Hotels.com LP); they do not provide improvements to any other technology or technical field (as in Diamond v. Diehr); nor do they utilize a particular machine (as in Eibel Process Co. v. Minn. & Ont. Paper Co.). Therefore, the computer system elements fail to integrate the JE into a practical application.
In combination, the limitations of data gathering, for the purpose of carrying out the JE, using a general-purpose computer merely provide extra-solution activity, and fail to integrate the JE into a practical application.
With respect to step 2B: NO. The claims recite a JE, do not integrate that JE into a practical application, and thus are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). The additional elements were considered individually and in combination to determine if they provide significantly more than the judicial exception. (MPEP 2106.05.A i-vi).
With respect to independent claims 1 and 23: The limitations identified above as non-abstract elements (EIA) related to data gathering do not rise to the level of significantly more than the judicial exception. Rabinowitz (US 9,639,657 B2) provides the necessary data gathered.
These elements meet the BRI of the identified data gathering limitations. As such, the prior art recognizes that this data gathering element is routine, well understood and conventional in the art (as in Alice Corp., CyberSource v. Retail Decisions, Parker v. Flook).
Activities such as data gathering do not improve the functioning of a computer, or comprise an improvement to any other technical field. The limitations do not require or set forth a particular machine, they do not effect a transformation of matter, nor do they provide an unconventional step (citing McRO and Trading Technologies Int’l v. IBG). Data gathering steps constitute a general link to a technological environment. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception are insufficient to provide significantly more (as discussed in Alice Corp.,).
With respect to independent claim 1 and 23: the limitations identified above as non-abstract elements (EIA) related to general-purpose computer systems do not rise to the level of significantly more than the judicial exception.
Hill provides the implied computer system comprising a neural network, which meets the BRI of the claimed computer system or computer system elements, comprising input, output/ display, a processor, and memory. (G3 Genes|Genomes|Genetics, Vol. 9, Issue 11, pp. 3575–3582)
As such, the prior art recognizes that these computing elements are routine, well understood and conventional in the art.
These elements do not improve the functioning of the computer itself, or comprise an improvement to any other technical field (Trading Technologies Int’l v IBG, TLI Communications). They do not require or set forth a particular machine (Ultramercial v. Hulu, LLC., Alice Corp. Pty. Ltd v. CLS Bank Int’l), they do not effect a transformation of matter, nor do they provide an unconventional step. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception are insufficient to provide significantly more (as discussed in Alice Corp., CyberSource v. Retail Decisions, Parker v. Flook, Versata Development Group v. SAP America).
Dependent claims 2-10 and 24-32 have been analyzed with respect to step 2B. MPEP 2106.06(a-h).
Dependent claims 3-10 and 25-32 each recite a limitation requiring additional mathematic concepts or mental processes. Additional abstract limitations cannot provide significantly more than the JE as they are a part of that JE (MPEP 2106.05).
In combination, the data gathering steps providing the information required to be acted upon by the JE, performed in a generic computer or generic computing environment fail to rise to the level of significantly more than that JE. The data gathering steps provide the data for the JE, which is carried out by the general-purpose computers. No non-routine step or element has clearly been identified.
The claims have all been examined to identify the presence of one or more judicial exceptions. Each additional limitation in the claims has been addressed, alone and in combination, to determine whether the additional limitations integrate the judicial exception into a practical application. Each additional limitation in the claims has been addressed, alone and in combination, to determine whether those additional limitations provide an inventive concept which provides significantly more than those exceptions. For these reasons, the claims, when the limitations are considered individually and as a whole, are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
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.
Claims 1, 8, 9, 10, 23, 30, 31, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Rabinowitz et al. (US 9,639,657 B2) in view of Hill et al. (G3 Genes|Genomes|Genetics, Vol. 9, Issue 11, pp. 3575–3582).
Regarding claim 1:
Rabinowitz et al. discloses a method for determining the ploidy state, i.e., aneuploidy status of chromosomes in a target individual, expressly including “the X chromosome, the Y chromosome” (claim 9), and further discloses screening for chromosomal conditions including “Klinefelter syndrome” and “Turner syndrome” (claim 11; column 2, lines 5-40; column 70, lines 1-40), both of which are canonical sex-chromosome aneuploidies. He further teaches a dedicated “sex chromosome technique” section, stating that “the techniques described above are designed for autosomic chromosomes; since the likely genetic states of the sex chromosomes (X and Y) are different, different techniques may be more appropriate” (Column 38, lines 25-35) “Sex Chromosome Technique”), thereby suggesting the limitation of “a method for analyzing sex-chromosome aneuploidies of an individual.”
Rabinowitz et al. discloses training a classification model on historical/predetermined genetic data: “from a training set made up of historical data, it may be possible to find means and standard deviations for these standardized means under the assumptions of monosomy, disomy and trisomy” and further “FIG. 3 shows a hypothesis distribution of monosomy (left), disomy (middle), and trisomy (right) using the Whole Chromosome Mean technique and using internal historical data as training data” (Column 28, lines 15-45, “Whole Chromosome Mean”). Rabinowitz et al. additionally discloses training data specific to the sex chromosomes in the “presence of parents” technique (“Training Distributions” section (Column 30, lines 40-70): “Having calculated a statistic Xp for each parent on a given chromosome, it can be compared to distributions for the cases of ‘parent present’ and ‘parent not present’… to calculate the probability of each”), which is expressly applied to sex-chromosome ploidy determination (claim 9).
However, Rabinowitz et al. does not explicitly disclose that the trained classifier is a neural network; Rabinowitz’s trained classifier is instead a Bayesian/statistical “expert technique” combiner.
Hill et al. remedies this deficiency. Hill et al. trains machine-learning classifiers including a “Convolutional Neural Network classifier” on chromosomal sequencing data to detect copy-number status: “how the machine learning algorithm (Random Forest 100 estimators and 500 estimators, Extra Trees 100 and 500 estimators, Decision Tree, and Convolutional Neural Network classifiers) … affects the ability to correctly classify a CNV” (Methods and Model, “Classifier optimization”; pg. 2, bottom). Hill et al. further discloses that “these vectors of statistics for windows with known copy number variants (CNVs) are then fed into a machine learning classifier, which identifies the values most important to the correct classification of the presence of a CNV” (Results and Discussion, “A machine learning classifier can detect CNVs with high accuracy”; pg. 4), i.e., the classifier (including the disclosed neural network variant) is trained on predetermined/known chromosomal copy-number data suggesting the limitation of “training a neural network model based on predetermined information related to at least one sex chromosome.”
Rabinowitz et al. discloses normalizing raw signal/read-depth-analogous intensity data across the genome and using that normalized value as the direct input to its statistical classifier: “The first step is to normalize each target for variation in amplification. Then the means are adjusted with respect to the copy number call of the chromosome, normalizing with respect to a disomy. These normalized means may be referred to as the amplification adjusted means” and “the amplification normalized means may be normalized for chromosome variation. These means are referred to as the standardized means” (Detailed Description, “Whole Chromosome Mean”; column 28, lines 10-40). Rabinowitz further discloses that its statistical technique both receives this normalized measurement and outputs the copy-number/ploidy call: “a probability may be calculated using the measured mean intensities of the genotyping output data, and the expected mean intensities”, and “the ploidy state for the target individual is determined to be the ploidy state that is associated with the hypothesis whose probability is the greatest” (Detailed Description, “Some Embodiments”, column 29, lines 15-50) suggesting the limitation of “determining the respective sex-chromosome status based on a normalized read depth for a gene in a genome of the individual using a machine learning algorithm, wherein the machine learning algorithm is configured to receive, as inputs, the normalized read depth, and output the respective sex-chromosome status of the individual.”
To the extent Rabinowitz’s normalized signal (amplification-adjusted/standardized mean intensity) is not identical to sequencing “read depth,” Hill discloses the read-depth-based normalized-coverage analog and confirms it is a suitable, input feature for a trained classifier that outputs a copy-number/chromosome-status determination: “We reasoned that both standardized median and mean coverage should indicate if a window is an outlier from the average coverage… Here we define standardization as dividing the coverage by the mean or median of the coverage of all bases on the contig” (Methods and Model, “Machine learning method”, pg. 2, c1, middle). Hill's classifier is trained on “vectors of statistics” built from this normalized/standardized coverage and outputs a class label for copy-number status: “we used SKlearn to train a classifier based on the vectors assigned to each class”, “The classifiers were then used to assign classes to windows in the test sets” (Methods and Model, “Machine learning method”, pg.2, c1, bottom).
Rabinowitz and Hill are analogous art: both address the identical technical problem of calling chromosome copy number/ploidy state (including for the sex chromosomes, (Rabinowitz, claim 9) from normalized sequencing-derived signal, and both employ a trained statistical/machine-learning classifier operating on a training set of known copy-number outcomes to output a copy-number call. A PHOSITA would have recognized Rabinowitz’s Bayesian “expert technique” combiner and Hill’s trained classifiers (including its disclosed neural network) as interchangeable, art-recognized alternatives for the same function – mapping a normalized signal derived from sequencing data to a discrete chromosome-copy-number classification. Hill itself frames its neural-network-capable classifier as a direct, motivated substitute for classical statistical/Bayesian copy-number calling, explaining that “contemporary machine learning methods can classify windows across the genome with surprising accuracy, even using lower quality data” and that such methods are advantageous because “supervised machine learning techniques are generally less computationally intensive than unsupervised machine learning methods such as Approximate Bayesian Computation” (Introduction). This is an explicit teaching, suggestion, and motivation (MPEP § 2143(I)(G)) for a PHOSITA practicing Rabinowitz’s Bayesian sex-chromosome ploidy-calling method to substitute a trained neural network classifier such as Hill’s in place of Rabinowitz’s Bayesian expert-technique combiner, in order to obtain improved accuracy at lower sequencing coverage/cost – a substitution that constitutes nothing more than the simple substitution of one known element (a Bayesian statistical classifier) for another known element (a neural network classifier) performing the identical function (mapping normalized read-depth/coverage signal to a chromosome copy-number call), yielding the predictable result of a working sex-chromosome-aneuploidy classifier. (MPEP § 2143(I)(B)–(D); KSR, 550 U.S. at 416) (“if a technique has been used to improve one device, and a person of ordinary skill in the art would recognize that it would improve similar devices in the same way, using the technique is obvious unless its actual application is beyond his or her skill”). Both references further already contemplate application to human chromosome copy-number determination from short-read sequencing coverage, so no unpredictable results would arise from the combination, and a PHOSITA would have had a reasonable expectation of success.
Regarding claim 23:
Claim 23 recites a system substantially parallel to the method of claim 1, reciting “a system adapted to analyze sex-chromosome aneuploidies… comprising: a neural network model trained… the neural network model adapted to determine a respective sex-chromosome status…”
Rabinowitz discloses that its ploidy-calling method is implemented as a computer system, reciting in its own claim 1 the steps of “creating, on a computer, a set of at least one ploidy state hypothesis… and using two or more expert techniques to determine, on a computer… a statistical probability for each ploidy state hypothesis.” A programmed general-purpose computer executing Rabinowitz’s disclosed algorithm is a “system” under MPEP 2106 and In re Alappat, 33 F.3d 1526 (1994); the recitation that the classifier is “adapted to” perform the recited determination is given no additional patentable weight beyond the corresponding method steps of claim 1 under the functional-claiming analysis of MPEP § 2114(II) (“adapted to,” “configured to,” and similar functional language are evaluated by determining what structure or capability, if any, is required; a prior art apparatus that is capable of performing the recited function anticipates or renders obvious the functional recitation”). As mapped above for claim 1, the Rabinowitz/Hill combination discloses and/or renders obvious a computer-implemented system whose trained classifier (substituted, per the same KSR rationale set forth for claim 1, with Hill’s neural network classifier) is configured/adapted to receive normalized read depth and output sex-chromosome status. Claim 23 is therefore rejected on the same combination and the same rationale as claim 1.
Regarding claims 8 and 30:
Claims 8 and 30 recite determining sex-chromosome status “via Bayesian statistics of the read depth and allosome data.” (“Allosome” is simply the synonym for a sex chromosome.
Rabinowitz alone discloses this limitation. Rabinowitz expressly applies Bayesian inference to its normalized (amplification-adjusted/standardized) read-signal data to call ploidy: “in one embodiment, Bayes' rule may be used to find the probability of each hypothesis given the data” (Detailed Description, “Permutation Technique”, column 22, lines 15-45), and expressly extends its statistical framework to the sex chromosomes via the dedicated “Sex Chromosome Technique”(discussion and claim 9) (reciting “the X chromosome, the Y chromosome” as chromosomes to which the claimed statistical ploidy-calling techniques are applied). This limitation is therefore taught outright by Rabinowitz and is at minimum obvious in view of Rabinowitz’s explicit Bayesian-inference disclosure combined with its explicit sex-chromosome-specific application.
Regarding claims 9–10 and 31–32:
Claims 9–10 and 31–32 recite determining sex-chromosome status “via graphing of the read depth and allosome data,” wherein graphing comprises “graphing a sample as a point in a two-dimensional plane.”
Rabinowitz discloses this exact graphing technique: “FIG. 6 shows a plot of a set of single nucleotide polymorphisms. A normalized intensity of one channel output is plotted against the other” and “FIG. 7 shows a plot of a set of single nucleotide polymorphisms. A normalized intensity of one channel output is plotted against the other” (Brief Description of the Drawings, column 6, lines 5-40), i.e., each sample/locus is graphed as an (x, y) point in a two-dimensional plane of normalized signal-channel intensities – the direct read-depth-normalization analog. Rabinowitz further discloses this graphing technique applied specifically to ploidy-state discrimination via cumulative distribution function (CDF) curve plots for each parental/allelic context (FIGS. 1, 2A–2D), stating that “one set of expected canonical topologies is illustrated in FIGS. 2A-2D, for which the ploidy state may be called by visual inspection of the plots” (Detailed Description, “Permutation Technique”, column 22, lines 15-40), and that this technique is applied to the sex chromosomes (claim 9). These limitations are therefore taught outright by Rabinowitz.
Claims 2 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Rabinowitz et al. in view of Hill et al. as applied to the claims 1, 8, 9, 10, 23, 30, 31, and 32 above and further in view of Wang et al., (PLoS ONE 11(7): e0159648 (2016))
Rabinowitz et al. in view of Hill et al. are applied to the claims 1, 8, 9, 10, 23, 30, 31, and 32.
Rabinowitz et al. in view of Hill et al. does not explicitly teach the sex-chromosome-status determination which is based on the normalized read depth and at least one of fetal fraction data and fold change data.
Wang discloses these two additional inputs in the identical NIPT sex-chromosome-aneuploidy-calling context: Wang discloses computing “the percentage of reads mapped to each chromosome… using the number of UMRs in a selected chromosome, divided by the count of UMRs in all chromosomes” (i.e., a fold-change/chromosomal-representation value derived from normalized read counts) (Data analysis section, pg. 3, bottom and pg. 4, top), and Wang’s stated objective is “improving the accuracy of the current method” for “fetal sex prediction” and “SCAs detection” which depends on “fetal fraction” (Abstract).
A PHOSITA combining Rabinowitz/Hill with Wang’s art-recognized NIPT-specific covariates (fetal fraction, chromosomal read-count fold-change) would have been motivated to add these known, predictive covariates as additional classifier inputs to improve the accuracy of the combined Rabinowitz/Hill sex-chromosome classifier in the NIPT setting specifically – a straightforward application of a known technique (adding known predictive features to a trained classifier) to improve a similar method in the same way (MPEP § 2143(I)(C)), yielding the predictable result of improved classification accuracy, consistent with Wang’s own stated purpose of reducing false-negative and false-positive rates in fetal sex/SCA calling.
Claims 3, 4, 25, and 26 are rejected under 35 U.S.C. 103 as being unpatentable over Rabinowitz et al. in view of Hill et al. as applied to the claims 1, 8, 9, 10, 23, 30, 31, and 32 above and further in view of Norwitz, et al. (J. Clin. Med. 2019, 8(7), 937)
Regarding claims 3-4 and 25-26:
Rabinowitz et al. in view of Hill et al. are applied to the claims 1, 8, 9, 10, 23, 30, 31, and 32.
Rabinowitz et al. in view of Hill et al. does not explicitly teach the method/system provides a “twin sex calling” comprising calling sexes “among the following three phenotypes: two XX twins, two XY twins, and one XX twin and one XY twin.
Norwitz discloses individual fetal sex calling for twin pregnancies from cfDNA-based NIPT with 100% accuracy across the full space of same-sex and different-sex twin outcomes: “Individual fetal sex for both twins was also called with 100% accuracy” and Norwitz’s study cohort and reported analysis expressly spans monozygotic twins (necessarily concordant, i.e., either two XX or two XY) and dizygotic twins (which may be concordant or discordant, i.e., one XX and one XY), with “Zygosity was correctly predicted in 100% of cases” as a companion determination used to interpret the individual sex calls (Abstract). Calling individual fetal sex for each of two co-twins necessarily requires discriminating among precisely the three phenotype categories recited in claims 4/26, and Norwitz’s disclosed method – evaluating “Y-chromosome loci” for “fetal sex” independently for each twin – directly performs that discrimination (Abstract, Introduction).
A PHOSITA implementing the sex-chromosome-status classifier of Rabinowitz/Hill would have been motivated to extend that classifier to twin gestations using Norwitz’s disclosed twin-sex-calling framework, because both address the identical clinical objective (accurate, non-invasive determination of fetal sex-chromosome status from maternal plasma cfDNA sequencing) and Norwitz demonstrates that individual-fetus sex determination in twins is achievable to clinical-grade accuracy using the same class of normalized-sequencing-signal-based classification employed in Rabinowitz/Hill. This is the combination of prior art elements (a trained normalized-read-depth sex-chromosome classifier with a known technique (per-fetus twin sex discrimination, Norwitz) each performing its known function, to yield the predictable result of a twin-capable sex-chromosome-status classifier. MPEP § 2143(I)(A).
Claims 5, 6, 7, 27, 28, and 29 are rejected under 35 U.S.C. 103 as being unpatentable over Rabinowitz et al. in view of Hill et al., Norwitz, et al. as applied to the claims 1, 3, 4, 8, 9, 10, 23, 25, 26, 30, 31, and 32 above and further in view of Hochstenbach et al. (Clin. Case Rep. 2018;6(3):611–615 (published Mar. 7, 2018))
Regarding claims 5-6 and 27-28:
Rabinowitz et al. in view of Hill et al. and Norwitz, et al. as applied to the claims 1, 3, 4, 8, 9, 10, 23, 25, 26, 30, 31, and 32.
Rabinowitz et al. in view of Hill et al. and Norwitz, et al. does not explicitly teach the method/system determines a “complex sex phenotype” comprising “vanishing twins and mosaic monosomy.
Hochstenbach discloses the vanishing-twin confound directly in the sex-chromosome/aneuploidy NIPT context, reporting a case in which “the male specific fetal cfDNA was suspected to stem from a vanishing twin—maybe the carrier of a trisomy 21—that was either not recognized or not indicated on the consent form for NIPT,” ultimately confirmed where “the pregnancy had started as twin and later continued as a singleton pregnancy” (case narrative); Hochstenbach’s title and abstract confirm the reference concerns “discordant NIPT result in a viable trisomy-21 pregnancy due to prolonged contribution to cfDNA by a demised… cotwin,” i.e., a vanishing-twin-driven complex phenotype directly analogous to and predictive of a vanishing-twin-driven complex sex phenotype. Rabinowitz, in turn, already discloses and defines mosaicism generally (“Mosaicism may refer to a set of cells in an embryo, or other individual that are heterogeneous with respect to their ploidy state,” Definitions, column 9, lines 35-60) and discloses detecting a segmented/partial monosomy condition through its segmentation algorithm: “if one of the minority segments has confidence greater than a threshold, that chromosome may be flagged as being segmented” and “this chromosome may be flagged as ‘segmented monosomy’” (Detailed Description, “Segmentation”, column 27, lines 45-70), which Rabinowitz applies to the sex chromosomes per claim 9. It is further well known in the art that sex-chromosome mosaicism (e.g., 45, X/46, XX or 45, X/46, XY mosaic Turner-syndrome genotypes) is among the most clinically significant and commonly encountered complex sex-chromosome phenotypes in prenatal and postnatal genetic testing (see, e.g., Skuse, D. ScienceDirect, “Sex Chromosome Aneuploidies – an overview,” noting that “failing to correctly assess sex chromosome ploidy will result in faulty assumptions during… variant calling”).
A PHOSITA would have been motivated to configure the Rabinowitz/Hill/Norwitz sex-chromosome classifier to flag both of these known, clinically significant confounding phenotypes – vanishing twins (Hochstenbach) and mosaic monosomy (Rabinowitz’s own segmentation/mosaicism disclosure, applied to the sex chromosomes) – because both were well-known sources of discordant or ambiguous sex-chromosome NIPT results at the time of the invention, and a classifier that fails to account for them risks clinically significant misclassification. Combining these known solutions to known, recognized problems in the same field of endeavor is precisely the type of combination KSR identifies as “obvious to try” among “a finite number of identified, predictable solutions,” MPEP § 2143(I)(E), and simultaneously an application of a known technique (confound-flagging) to a known device/method (the sex-chromosome classifier) to yield predictable results, MPEP § 2143(I)(D).
Regarding claim 7 and 29:
Claims 7 and 29 recite that the method/system “provides a negative result where the respective sex-chromosome status is determined to be anomalous.”
Hochstenbach discloses exactly this practice in the NIPT context: when the measured data present an internal discrepancy consistent with an anomalous confound (there, a vanishing co-twin), the result is withheld/flagged rather than reported as a positive or negative call – “the result was reported to be indecisive for chromosome 21 and the conflicting data was reported to the responsible physician” (case report narrative).
A PHOSITA implementing the combined Rabinowitz/Hill classifier would have been motivated by Hochstenbach’s teaching to configure the classifier to output a negative/no-call result whenever its confidence-scored hypothesis output (which Rabinowitz already computes, e.g., “a hypothesis may be determined to be the most likely, and the ploidy state… may be called if the normalized probability is greater than a threshold,” Detailed Description, “Hypotheses”, column 15, lines 15-55) fails to clear a reliability threshold, i.e., is anomalous – an application of Rabinowitz’s own known confidence-thresholding technique to the known clinical problem (identified by Hochstenbach) of anomalous/discordant NIPT sex-chromosome data, yielding the predictable result of a safer, more clinically reliable negative/no-call output. MPEP § 2143(I)(D).
Claims 24–32 recite system limitations that parallel, respectively, the method limitations of claims 2-10). For the reasons given above with respect to claim 23, each of these system claims is rejected on the same combinations of references and the same rationales applied to its corresponding method claim, because a programmed computer system executing the corresponding combined method (Rabinowitz’s own “on a computer” claim language) satisfies the “system adapted to…” claim language under MPEP § 2114(II).
Conclusion
No claims are allowed.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ARSHAD KHAN whose telephone number is (571)272-9812. The examiner can normally be reached Mon-Fri-7:30-5:00 PM.
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 Riggs can be reached at 5712703062. 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.
/A.H.K./Examiner, Art Unit 1686
/MARY K ZEMAN/Primary Examiner, Art Unit 1686
Prosecution Insights