DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Status
Claims 1-24 are currently pending and under exam herein.
Claims 1-24 are rejected.
Priority
This application is a continuation-in-part of U.S. Application No. 17/750,055, filed 20 May 2022, which is a continuation of U.S. Application No. 16/994,315, filed 14 August 2020, and issued as U.S. Patent No. 11,367,508 on 21 June 2022, which claims the benefit of U.S. Provisional Application No. 62/888,163, filed 16 August 2019, U.S. Provisional Application No. 62/904,300, filed 23 September 2019, and U.S. Provisional Application No. 62/986,201, filed 6 March 2020. Benefit is acknowledged.
Information Disclosure Statement
The information disclosure statement (IDS) filed 15 June 2023 fails to comply with 37 CFR 1.98(a)(2), which requires a legible copy of each cited foreign patent document; each non-patent literature publication or that portion which caused it to be listed; and all other information or that portion which caused it to be listed. It has been placed in the application file, but the information referred to therein has not been considered. Specifically, there is no copy of the non-patent literature publication by Ziemann et al. titled “Gene Name Errors are Widespread in the Scientific Literature.” Therefore, this publications has been lined through on the IDS and has not been considered by the examiner. All other references have been considered.
The information disclosure statements (IDS) submitted on 11 August 2023, 31 October 2024, and 21 March 2025 comply with 37 CFR 1.98. Accordingly, all references listed have been considered by the examiner.
Drawings
The drawings filed on 28 February 2023 have been received and are accepted.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code. Specifically, paragraphs [169], [297], and [315] contain hyperlinks. Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
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 1-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (abstract ideas and natural phenomenon) without significantly more. Under MPEP § 2106, subject matter is patent eligible when the claimed invention is to one of the four statutory categories of invention [Step 1], and the claim is not directed to a judicial exception [Step 2A] unless the claim as a whole includes additional limitations amounting to significantly more than the exception [Step 2B].
Step 1
Claims 1-24 describe inventions that are to one of the statutory categories. In Step 1, a claim must fall within one of the four enumerated categories of statutory subject matter (process, machine, manufacture, or composition of matter); a claim falling outside these categories is ineligible without further analysis. See MPEP § 2106.03. Claims 1-22 are properly to one of the four statutory categories because the claimed invention is a method, which falls into the process category [Step 1: Yes]. Claim 23 is properly to one of the four statutory categories because the claimed invention is a system, which falls into the machine category [Step 1: Yes]. Claim 24 is properly to one of the four statutory categories because the claimed invention is a non-transitory computer-readable storage medium having stored thereon program code instructions, which falls into the manufacture category [Step 1: Yes].
Step 2A
Under Step 2A, a claim is directed to a judicial exception if, under the broadest reasonable interpretation, it recites an abstract idea, law of nature, or natural phenomena [Prong One] without the claim as a whole integrating the exception into a practical application [Prong Two]. Abstract ideas include mathematical concepts, mental processes, and certain methods of organizing human activity. Mathematical concepts encompass mathematical relationships, formulas, equations, and mathematical calculations. See MPEP § 2106.04(a)(2)(I). Mental processes involve concepts that can be performed in the human mind or by a human with the aid of pen and paper, such as observations, evaluations, judgments, or opinions. See MPEP § 2106.04(a)(2)(III). Certain methods of organizing human activity include fundamental economic principles, commercial or legal interactions, and managing personal behavior or relationships. See MPEP § 2106.04(a)(2)(II). Laws of nature and natural phenomena, include naturally occurring principles/relations and nature-based products that are naturally occurring or that do not have markedly different characteristics compared to what occurs in nature. See MPEP § 2106.04(b)-(c).
Prong One
A claim recites a judicial exception when it sets forth or describes a law of nature, natural phenomenon, or abstract idea. Claims 1-24 recite abstract ideas that fall into the groupings of mathematical concepts and mental processes.
Independent claims 1 and 23-24 recite the following limitations, which describe abstract ideas:
training a machine learning model using the positive control group and the negative control group to determine a correlation of the at least one genetic variation condition to a pathway dysregulation score; and
generating a score for the machine learning model, the score indicating a degree of accuracy of the machine learning model, wherein the cellular samples of the negative control group do not include a genetic variation matching the at least one genetic variation condition, and wherein training the machine learning model includes identifying one or more feature genes and determining a weight for each feature gene of the one or more feature genes, the weight being indicative of an impact of the feature gene on the pathway dysregulation score.
The limitation of training a machine learning model involves correlation, regression/weight optimization, and feature selection in vector space, which constitutes an abstract idea within the mathematical concepts grouping. Additionally, the limitation involves analyzing labeled data to find relationships, which constitutes an abstract idea within the mental processes grouping. The limitation of generating a score for the machine learning model involves mathematical evaluation/optimization of model performance, which constitutes an abstract idea within the mathematical concepts grouping.
Dependent claims 3 and 5-22 recite the following limitations, which narrow or describe abstract ideas:
Claim 3 recites determining, within the positive and negative control groups, a first positive confounder group and a first negative confounder group comprising cohorts of patients having a shared confounder type; quantifying a difference between the first positive confounder group and the first negative confounder group; and weighting the first positive confounder group and the first negative confounder group when the difference exceeds a threshold.
Claim 5 recites wherein the at least one genetic variation condition comprises: a genetic identifier including at least one gene; at least one genetic variation type; and at least one pathogenicity classification.
Claim 6 recites wherein the genetic identifier includes a plurality of genes.
Claim 7 recites wherein the at least one genetic variation type is one of a mutation, a fusion, and a copy number variation.
Claim 8 recites wherein the pathogenicity classification is one of benign, likely benign, malignant, likely malignant, unknown significance, or conflicting evidence.
Claim 9 recites wherein the positive control criteria includes a plurality of genetic variation conditions.
Claim 10 recites further comprising selecting a plurality of feature genes that are downstream of the at least one gene of the genetic identifier within a regulation network.
Claim 11 recites further comprising selecting a plurality of feature genes that are upstream of the at least one gene of the genetic identifier within a regulation network.
Claim 12 recites analyzing, using the machine learning model, genetic information of a cellular sample associated with a patient, classifying, based on the analysis, the cellular sample as having a pathway dysregulation associated with a genetic variation of the patient; and selecting a treatment for the patient, the treatment being based on the classification of the sample.
Claim 13 recites outputting coefficients of the feature genes, based on the correlation of the feature genes with the pathway dysregulation score, wherein the pathway dysregulation score indicates a pathway dysregulation, and wherein a coefficient of a feature gene indicates the feature gene's impact on the pathway dysregulation.
Claim 14 recites evaluating the new cellular sample using the trained machine learning model; based on the evaluation, adding to the new cellular sample a positive label or a negative label , the positive label indicating a potential pathway dysregulation of the sample.
Claim 15 recites generating at least one additional positive control criteria, the at least one additional positive control criteria including at least one additional genetic variation condition that is different from the at least one genetic variation condition; and training an additional machine learning model using the at least one additional positive control group to determine a correlation of the at least one additional genetic variation condition to a pathway dysregulation score for the at least one additional positive control group, wherein training the additional machine learning model includes identifying one or more feature genes corresponding to the at least one additional positive control group and determining a weight for each feature gene of the one or more feature genes, the weight being indicative of an impact of the feature gene on the pathway dysregulation score for the at least one additional positive control group.
Claim 16 recites wherein the genetic identifier of the at least one additional genetic variation condition matches the genetic identifier for the at least one genetic variation condition of the positive control criteria.
Claim 17 recites wherein the one or more feature genes corresponding to the positive control group include a first feature gene and a second feature gene, the second feature gene having a weight that is less than a weight of the first feature gene, wherein a genetic identifier for the additional positive control criteria does not include the second feature gene.
Claim 18 recites receiving a list of genes defining the positive control criteria; defining selection parameters; generating a network of genes related to the list of genes based on the selection parameters; determining a level of influence for each gene in the network of genes; ranking the genes based on the level of influence; identifying a most influential subset of the network of genes; and using expression levels of the most influential subset as features for a feature vector for the machine learning model.
Claim 19 recites refining the positive control criteria based on results of the machine learning model, wherein refining the positive control criteria comprises one or more of excluding biomarkers or variants shown to not be pathogenic or including biomarkers or variants shown to be pathogenic.
Claim 20 recites analyzing, using a decision tree model, a plurality of genetic features for each of the positive and negative control groups; refining, based on the analysis, the seed query to produce the query.
Claim 21 recites wherein analyzing the plurality of genetic features includes refining the seed query to produce an intermediate query and comparing an intermediate RNA signature of cellular samples meeting the intermediate query to a seed RNA signature of cellular samples meeting the seed query; and if a difference between the intermediate RNA signature and the seed RNA signature exceeds a significance threshold, removing, from the seed plurality of samples, cellular samples meeting the intermediate query, and analyzing, using a decision tree model, a plurality of genetic features of the seed plurality of samples.
Claim 22 recites wherein the at least one genetic variation condition includes a threshold genetic expression level and a list of genes and wherein the positive control group includes cellular samples that have expression levels for each gene in the list of genes that equals or exceeds the genetic expression level.
The limitations of claim 3 involve determining confounder groups, quantifying a difference between groups, and weighing the groups, which constitute abstract ideas within the mathematical concepts and mental processes groupings. The limitations of claims 5-9 narrow the abstract ideas of claim 1 by specifying data/information used to describe the genetic variation. The limitation of claims 10-11 narrow the abstract idea of claim 1 by specifying that feature genes are downstream/upstream of the genetic identifier. The limitation of claim 12 involves analyzing a sample, classifying the sample, and selecting a treatment, which are abstract ideas within the mathematical concepts and mental processes groupings. While integration may be demonstrated when the additional elements apply or use the recited judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition, the claim limitation in question must affirmatively recite an action that effects a particular treatment or prophylaxis for a disease or medical condition. The limitation of claim 12 recites selecting a treatment for the patient based on the classification of the sample, which constitutes a mental process when a clinician can analyze the sample classification and select the treatment best suited for that classification.
The limitations of claim 14 involve analyzing and labeling new samples, which constitutes an abstract idea within the mathematical concepts and mental processes groupings. The limitations of claims 15-17 involve generating additional criteria and training an additional model, which constitute abstract idea within the mathematical concepts and mental processes groupings. The limitations of claim 18 narrows the abstract idea of claim 1 by specifying how feature genes are identified. The limitation 19 involves iterative adjustment to refine control criteria, which is an abstract idea within the mathematical concepts and mental processes groupings. The limitations of claims 20-21 involve seed queries, decision tree refinement, and RNA signature comparison, which constitute abstract ideas within the mathematical concepts and mental processes groupings. The limitation of claim 22 involves imposing a threshold expression level, which constitutes an abstract idea within the mathematical concepts grouping.
Claims 2 and 4 do not recite or narrow judicial exceptions, but inherit the abstract ideas of claim 1. Therefore, claims 1-24 recite abstract ideas – namely mathematical concepts and mental processes [Step 2A, Prong One: Yes].
Prong Two
Claims 1-24 as a whole do not integrate the recited judicial exception into a practical application. A claim that recites a judicial exception [Prong One] is deemed to be directed to a judicial exception [Step 2A] unless the claim as a whole contains additional elements that integrate the exception into a practical application [Prong Two]. A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception, beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. See MPEP §§ 2106.04(d) and 2106.05(e). A claim does not integrate a judicial exception into a practical application by reciting insignificant extra-solution activity, generally linking the exception to a particular technological environment or field of use, merely reciting to apply the exception, merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea. See MPEP § 2106.04(d)(I). Insignificant extra-solution activities are nominal or tangential additions to a claim that are incidental to the primary process or product, including both pre-solution and post-solution activity (e.g. pre-solution data gathering for use in a process). If integrated into a practical application, the claim is eligible; otherwise, it is directed to the judicial exception, necessitating further analysis at Step 2B.
Independent claims 1 and 23-24 recite the following limitations, which are additional elements:
receiving a query including a positive control criteria and a negative control criteria, the positive control criteria including at least one genetic variation condition;
obtaining, in electronic format from within a data store including a plurality of cellular samples: a positive control group, the positive control group including cellular samples having a genetic variation matching the at least one genetic variation condition of the positive control criteria, and a negative control group, the negative control group including cellular samples having genetic attributes matching the negative control criteria, wherein each sample of the plurality of cellular samples includes genetic data for a plurality of genes of the sample, and transcriptomic data comprising RNA expression levels;
Claim 23 recites a computer including a processing device
Claim 24 recites a non-transitory computer-readable storage medium having stored thereon program code instructions that, when executed by a processor
Dependent claims 2, 4, 14-15, and 20 recite the following limitations, which are additional elements:
Claim 2 recites wherein a subset of the plurality of cellular samples is further associated with confounder data for a confounder type, the confounder type comprising at least one of an assay, a match type, a tissue site, a content of the sample, a cancer type, or a purity level of the cellular sample.
Claim 4 recites further comprising receiving a negative control criteria comprising at least one negative genetic variation condition, wherein the samples of the negative control group include the negative genetic variation condition of the negative control criteria.
Claim 14 recites detecting the insertion of a new cellular sample into the data store.
Claim 15 recites obtaining, in electronic format from within the data store including the plurality of cellular samples at least one additional positive control group, the at least one additional positive control group including cellular samples matching the at least one additional genetic variation condition
Claim 20 recites receiving a seed query, the seed query including a positive control group definition and a negative control group definition, the positive control group definition including as least one genetic variation condition; obtaining, in electronic format, a seed plurality of cellular samples including: a seed positive control group including cellular samples meeting the positive control group definition
The limitations of receiving a query and obtaining a positive/negative control group constitute insignificant extra-solution activities that do not integrate the judicial exceptions into a practical application because they are mere data gathering step that do not transform the nature of the claim into a patent-eligible application of the judicial exception. See MPEP § 2106.05(g). Additionally, these limitations are data gathering steps that are limited to a particular type of data, which merely indicates a field of use or technological environment in which to apply a judicial exception and cannot integrate a judicial exception into a practical application. See MPEP § 2106.05(h). These limitations are narrowed by the limitation of claims 2 and 4, which specify that the samples are associated with confounder data and the negative control criteria/group contain a negative genetic variation condition, respectively.
The limitations of claims 23-24 describe generic computer components that amount to nothing more than mere instructions to apply the judicial exceptions, which do not integrate into a practical application. See MPEP §§ 2106.05(b) & (f). The limitation of claims 14-15 and 20 constitute insignificant extra-solution activity that does not integrate the judicial exceptions into a practical application because it is a mere data gathering step that does not transform the nature of the claim into a patent-eligible application of the judicial exception. See MPEP § 2106.05(g). Finally, claims 3, 5-13, 16-19, and 21-22 do not include any additional elements.
The claims as a whole merely recite insignificant extra-solution activities and abstract ideas implemented on generic computer components without meaningful limitations that tie it to a specific technological improvement. Therefore, claims 1-24 do not contain additional elements that integrate the recited abstract ideas into a practical application [Step 2A, Prong Two: No].
Step 2B
Claims 1-24 do not include additional elements, whether considered individually or in combination, that are sufficient to amount to significantly more than the judicial exception itself. Under Step 2B, the claim is analyzed to determine whether there are any additional elements that, individually or in combination, constitute an “inventive concept" sufficient to ensure that the claim, as a whole, amounts to significantly more than the judicial exception itself. See MPEP § 2106.05; and Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 217-18, 110 USPQ2d 1976, 1981 (2014).
Independent claims 1 and 23-24 recite the following limitations, which are additional elements:
receiving a query including a positive control criteria and a negative control criteria, the positive control criteria including at least one genetic variation condition;
obtaining, in electronic format from within a data store including a plurality of cellular samples: a positive control group, the positive control group including cellular samples having a genetic variation matching the at least one genetic variation condition of the positive control criteria, and a negative control group, the negative control group including cellular samples having genetic attributes matching the negative control criteria, wherein each sample of the plurality of cellular samples includes genetic data for a plurality of genes of the sample, and transcriptomic data comprising RNA expression levels;
Claim 23 recites a computer including a processing device
Claim 24 recites a non-transitory computer-readable storage medium having stored thereon program code instructions that, when executed by a processor
Dependent claims 2, 4-9, 14-15, 18, and 20 recite the following limitations, which are additional elements:
Claim 2 recites wherein a subset of the plurality of cellular samples is further associated with confounder data for a confounder type, the confounder type comprising at least one of an assay, a match type, a tissue site, a content of the sample, a cancer type, or a purity level of the cellular sample.
Claim 4 recites further comprising receiving a negative control criteria comprising at least one negative genetic variation condition, wherein the samples of the negative control group include the negative genetic variation condition of the negative control criteria.
Claim 14 recites detecting the insertion of a new cellular sample into the data store.
Claim 15 recites obtaining, in electronic format from within the data store including the plurality of cellular samples at least one additional positive control group, the at least one additional positive control group including cellular samples matching the at least one additional genetic variation condition
Claim 20 recites receiving a seed query, the seed query including a positive control group definition and a negative control group definition, the positive control group definition including as least one genetic variation condition; obtaining, in electronic format, a seed plurality of cellular samples including: a seed positive control group including cellular samples meeting the positive control group definition
The independent claim limitations and the limitation of claims of claims 15 and 20 reciting receiving a query and obtaining a positive/negative control group constitute conventional insignificant extra-solution data gathering steps that are limited to a particular type of data, which merely indicate a field of use or technological environment in which to apply a judicial exception and do not amount to significantly more than the exception itself. See MPEP §§ 2106.04(g)-(h); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); and Xiao Liu et al., Combining data from TCGA and GEO databases and reverse transcription quantitative PCR validation to identify gene prognostic markers in lung cancer, 12 Onco Targets Ther. 709, Abstract § Materials and methods (21 January 2019) (receiving query and obtaining data for analysis from Gene Expression Omnibus and The Cancer Genome Atlas databases using R language). These limitations are narrowed by the limitations of claims 2 and 4, which specify that the samples are associated with confounder data and the negative control criteria/group contain a negative genetic variation condition, respectively. See Xiao Liu, at 710 col.1 para.2.
The independent claim limitations of claims 23-24 are generic and conventional computer components that amount to nothing more than mere instructions to apply the judicial exceptions, which does not constitute an inventive concept sufficient to amount to significantly more than the judicial exception itself. See MPEP §§ 2106.05(b) and (f); and Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 573 U.S. 208, 225, 110 USPQ2d 1976, 1984 (2014). The limitation of claim 14 recites conventional insignificant extra-solution activity of detecting the addition of a sample to a dataset for analysis, which does not constitute an inventive concept sufficient to amount to significantly more than the judicial exception itself. See MPEP § 2106.05 (f); and Ethan Cerami et al., The cBio Cancer Genomics Portal: An Open Platform for Exploring Multidimensional Cancer Genomics Data, 2(5) Cancer Discov. 401-04 (9 May 2012).
Overall, claims 1-24 amount to no more than conventional insignificant extra-solution activities and implementing the abstract ideas on conventional computers in a routine way. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception itself because the claims recite additional elements that equate to insignificant extra-solution activity and mere instructions to apply the recited abstract ideas in a generic way or in a generic computing environment. Therefore, claims 1-24 are rejected for failing to set forth patent eligible subject matter under 35 U.S.C. 101 because the claimed invention recites abstract ideas [Step 2A, Prong One: Yes] and the additional elements do not integrate the judicial exception into a practical application [Step 2A, Prong Two: No] and do not amount to claiming significantly more than the recited exception [Step 2B: No].
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 4-10, 18, and 22-24 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Gregory P. Way et al., Machine Learning Detects Pan-cancer Ras Pathway Activation in The Cancer Genome Atlas, 23 Cell Reports 172-80 (3 April 2018) (hereinafter “Way”).
Regarding independent claims 1 and 23-24, Way discloses developing a machine-learning approach to detect aberrant pathway activity in tumors. At 173 col.2 para.2 (a computer-implemented method/system of training a machine-learning model for detecting dysregulation in a cellular pathway). Way defines positive controls as tumors with Ras pathway mutations and negative controls as wild-type samples. At 173 col.2 para.2; 174 col.1 para.1 (receiving a query including a positive control criteria and a negative control criteria, the positive control criteria including at least one genetic variation condition). Way obtains multi-omic data from The Cancer Genome Atlas (TCGA) PanCancerAtlas, with the positive control group being samples with Ras mutations/alterations and the negative control group being Ras wild-type cell lines. At 172 col.2 para.2; 174 col.1 paras.1-2 (obtaining, in electronic format from within a data store including a plurality of cellular samples: a positive control group, the positive control group including cellular samples having a genetic variation matching the at least one genetic variation condition of the positive control criteria, and a negative control group, the negative control group including cellular samples having genetic attributes matching the negative control criteria; wherein the cellular samples of the negative control group do not include a genetic variation matching the at least one genetic variation condition). TCGA provides DNA mutation data and RNA-seq gene expression data for thousands of tumors from various cancer types. At 173 col.2 para.2 (wherein each sample of the plurality of cellular samples includes genetic data for a plurality of genes of the sample, and transcriptomic data comprising RNA expression levels).
Way trains the machine learning model using the positive and negative control groups to determine the impact of Ras mutations on aberrant pathway activity. At 173 col.2 para.2; 174 col.1 para.1 (training a machine learning model using the positive control group and the negative control group to determine a correlation of the at least one genetic variation condition to a pathway dysregulation score). Way evaluates the model using the area under the receiver operating characteristic (AUROC) curve, which describes the overall trade-off between true positive and false positive rates, and area under the precision recall (AUPR) curve, which measures precision against recall for the model. At e2 para.5; e3 para.6 (generating a score for the machine learning model, the score indicating a degree of accuracy of the machine learning model). Way teaches that the model detects Ras mutations and determines weights for each gene, with the weight indicating the importance of the gene on aberrant pathway activity. At 174 col.2 paras.1-2 (wherein training the machine learning model includes identifying one or more feature genes and determining a weight for each feature gene of the one or more feature genes, the weight being indicative of an impact of the feature gene on the pathway dysregulation score).
Way discloses using sci-kit learn with python 3.5.2 to perform the model training, testing, and evaluations, which necessarily involves a computer and a processing device. At e3 para.6; see also Habib, § Different Types of Python Implementations (a computer including a processing device). Way also discloses that the software is available as code for download. At e3 para.7 (a non-transitory computer-readable storage medium having stored thereon program code instructions).
Regarding claim 2, Way discloses using cancer type variables as covariates. At e1 para.3 (the method of claim 1, wherein a subset of the plurality of cellular samples is further associated with confounder data for a confounder type, the confounder type comprising at least one of an assay, a match type, a tissue site, a content of the sample, a cancer type, or a purity level of the cellular sample).
Regarding claim 4, Way defines negative controls as wild-type samples and obtains multi-omic data from TCGA PanCancerAtlas, with the negative control group being Ras wild-type cell lines. At 172 col.2 para.2; 173 col.2 para.2; 174 col.1 paras.1-2 (the method of claim 1, further comprising receiving a negative control criteria comprising at least one negative genetic variation condition, wherein the samples of the negative control group include the negative genetic variation condition of the negative control criteria).
Regarding claims 5-8, Way discloses that the Ras pathway mutations have a genetic identifier indicating the various genes impacted, a genetic variation of mutation or copy number gain/loss, and a classification of Ras variants, which are highly likely to be malignant. At 173 col.2 para.2; 174 col.1 para.1 (the method of claim 1 wherein the at least one genetic variation condition comprises: a genetic identifier including at least one gene; at least one genetic variation type; and at least one pathogenicity classification; the method of claim 5, wherein the genetic identifier includes a plurality of genes; the method of claim 5, wherein the at least one genetic variation type is one of a mutation, a fusion, and a copy number variation; the method of claim 5, wherein the pathogenicity classification is one of benign, likely benign, malignant, likely malignant, unknown significance, or conflicting evidence).
Regarding claim 9, Way defines positive controls as tumors with Ras pathway mutations, which can arise from KRAS, NRAS, or HRAS mutations or through NF1 loss-of-function events. At 173 col.1 para.2 & col.2 para.2 (the method of claim 5, wherein the positive control criteria includes a plurality of genetic variation conditions).
Regarding claim 10, Way discloses that the model is trained to detect downstream gene expression patterns consistent with aberrant pathway activity. At 173 col.2 para.2 (the method of claim 5, further comprising selecting a plurality of feature genes that are downstream of the at least one gene of the genetic identifier within a regulation network).
Regarding claim 15, Way discloses training machine learning models to predict Ras mutations and Ras copy number gains separately. At e2 para.7. Way uses the same procedure used to train the combined model, with the positive control being defined as Ras mutations or Ras copy number gains. At 173 col.2 para.2; e2 para.7. While the rejection of claim 5 refers to the combined model, the procedure for the separate models is the same such that the Ras mutations model could be substituted for the combined model, rendering the Ras copy number gains an additional positive control that is different. (generating at least one additional positive control criteria, the at least one additional positive control criteria including at least one additional genetic variation condition that is different from the at least one genetic variation condition). Way obtains multi-omic data from TCGA PanCancerAtlas, with the positive control group being samples with Ras copy number gains for oncogenes. At 172 col.2 para.2; 173 col.2 para.2 (obtaining, in electronic format from within the data store including the plurality of cellular samples at least one additional positive control group, the at least one additional positive control group including cellular samples matching the at least one additional genetic variation condition). Way trains a copy number machine learning model using the positive control group to determine the impact of Ras copy number gains on aberrant pathway activity. At 173 col.2 para.2; 174 col.1 para.1 (training an additional machine learning model using the at least one additional positive control group to determine a correlation of the at least one additional genetic variation condition to a pathway dysregulation score for the at least one additional positive control group). Way teaches that the model detects Ras copy number gains and determines weights for each gene, with the weight indicating the importance of the gene on aberrant pathway activity. At 174 col.2 paras.1-2 (wherein training the additional machine learning model includes identifying one or more feature genes corresponding to the at least one additional positive control group and determining a weight for each feature gene of the one or more feature genes, the weight being indicative of an impact of the feature gene on the pathway dysregulation score for the at least one additional positive control group).
Regarding claim 16, Way discloses that both Ras mutations and Ras copy number gains involve abnormalities in Ras genes KRAS, NRAS, or HRAS. At 173 col.1 para.2 (the method of claim 15, wherein the genetic identifier of the at least one additional genetic variation condition matches the genetic identifier for the at least one genetic variation condition of the positive control criteria).
Regarding claim 17, Way discloses that the model produces feature genes with different weights. At 174 col.2 para.2; Data S2 (the method of claim 16, wherein the one or more feature genes corresponding to the positive control group include a first feature gene and a second feature gene, the second feature gene having a weight that is less than a weight of the first feature gene). Figure 2 demonstrates that some cancer types contain mutations but lack copy number gains (wherein a genetic identifier for the additional positive control criteria does not include the second feature gene).
Regarding claim 18, Way defines positive controls as tumors with Ras pathway mutations, which can arise from KRAS, NRAS, or HRAS mutations or through NF1 loss-of-function events. At 173 col.1 para.2 & col.2 para.2 (receiving a list of genes defining the positive control criteria). Way discloses quality control filtering to generate a set of samples with greater than 15 target gene events related to the Ras pathway mutations. At e1 para.2 (defining selection parameters; generating a network of genes related to the list of genes based on the selection parameters). Way teaches that the model determines weights for each gene, with a higher weight indicating the gene has an influence on aberrant pathway activity and a lower weight indicating the gene is characteristic of wild-type Ras. At 174 col.2 para.2 (determining a level of influence for each gene in the network of genes; ranking the genes based on the level of influence). Way discloses that the model learns a vector of coefficients or gene-specific weights that optimize the penalized logistic function. At e2 para.2 (identifying a most influential subset of the network of genes; and using expression levels of the most influential subset as features for a feature vector for the machine learning model).
Regarding claim 19, Way discloses refining the input criteria based on the results of the model by excluding BRAF dominated cancer types because BRAF V600E mutations were predicted to be Ras wild-type. At 177 col.1 para.2 (the method of claim 1, further comprising: refining the positive control criteria based on results of the machine learning model, wherein refining the positive control criteria comprises one or more of excluding biomarkers or variants shown to not be pathogenic or including biomarkers or variants shown to be pathogenic).
Regarding claim 22, Way performs differential expression analysis on 9,074 samples and 20,500 genes using the limma Bioconductor package to select positive control group samples, which involves analyzing expression levels to ensure they meet a threshold. At e1 para.2; e3 para.2 (the method of claim 1, wherein the at least one genetic variation condition includes a threshold genetic expression level and a list of genes and wherein the positive control group includes cellular samples that have expression levels for each gene in the list of genes that equals or exceeds the genetic expression level).
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.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Way in view of Katherine A. Hoadley et al., Cell-of-Origin Patterns Dominate the Molecular Classification of 10,000 Tumors from 33 Types of Cancer, 173(2) Cell 291-304.e6 (5 April 2018) (hereinafter “Hoadley”).
Regarding claim 3, Way discloses the method of claim 2 (see 102 rejection above), including training an elastic net machine learning model on positive and negative control groups of TCGA tumor samples labeled by genetic variations using transcriptomic data to generate a pathway activation/dysregulation score with feature gene weights. Way teaches confounder handling at a high level, but does not expressly detail determining, within the positive and negative control groups, a first positive confounder group and a first negative confounder group comprising cohorts of patients having a shared confounder type; quantifying a difference between the first positive confounder group and the first negative confounder group; and weighting the first positive confounder group and the first negative confounder group when the difference exceeds a threshold. However, Hoadley determines confounder-based subgroups within large TCGA cohorts. At abstract. Hoadley determines positive and negative confounder groups stratified by shared confounder types such as cancer type, tissue site, and molecular subtypes. At abstract; 292 col.1 para.3; e4 para.9 (determining, within the positive and negative control groups, a first positive confounder group and a first negative confounder group comprising cohorts of patients having a shared confounder type). Hoadley quantifies differences between identified subgroups. At 294 col.1 para.5; Figure 2; e5 paras.2-4 (quantifying a difference between the first positive confounder group and the first negative confounder group). Hoadley discusses adjustments/weighing for confounders such as purity and batch effect when differences are significant. At Figure 3 legend; e5 paras.2-4 (weighting the first positive confounder group and the first negative confounder group when the difference exceeds a threshold). Hoadley notes that the disclosed clustering technique has potential clinical utility, and suggests that this technique may improve basket-trial design by considering both mutations and oncogenic signaling pathways along with consideration of each tumor’s tissue-specific or cell-of-origin context. At 301 col.1 para.3; 302 col.1 para.1.
Way discloses a base method of a Ras classifier, and Hoadley discloses a clustering technique for confounder handling. A person having ordinary skill in the art would recognize that applying Hoadley’s technique to the method of Way would predictably result in an improved method of pan-cancer classification by accounting for important confounders such as tumor type or cell-of-origin. Additionally, a person having ordinary skill in the art would be motivated to modify Way’s Ras pathway classifier by incorporating Hoadley’s clustering technique because Hoadley demonstrates that cell-of-origin and cancer-type patterns dominate the molecular classification of TCGA tumors. One of ordinary skill in the art would reasonably expect success in this combination because both references operate on TCGA PanCancer data, and combining a proven pathway classifier (Way) with a proven confounder mitigation technique (Hoadley) would predictably yield a more accurate and less biased model for pathway dysregulation scoring. Applying a known technique to a known device (method, or product) ready for improvement to yield predictable results is likely to be obvious. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, USPQ2d 1385, 1395 – 97 (2007); and MPEP § 2143, D.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Way in view of Charles J. Vaske et al., Inference of patient-specific pathway activities from multi-dimensional cancer genomics data using PARADIGM, 26(12) Bioinformatics 237-45 (1 June 2010) (hereinafter “Vaske”).
Regarding claim 11, Way teaches the method of claim 5 (see 102 rejection above). Way does not expressly disclose selecting a plurality of feature genes that are upstream of the at least one gene of the genetic identifier within a regulation network. However, Vaske teaches using directed regulatory networks (PARADIGM) to infer and select upstream pathway components based on integrated patient data. At 239 col.2 para.2; Figs. 1-2. Vaske demonstrates that integrating directed regulatory networks improves pathway activity inference and provides mechanistic insight into how genetic alterations drive downstream expression changes. At 239 col.2 para.4.
Way discloses a method of elastic net feature selection on RNA expression, and Vaske discloses a style of network modeling to analyze upstream genes in pathway analysis. A person having ordinary skill in the art would recognize that Vaske’s technique could be applied to Way’s classifier to improve mechanistic understanding of how genetic alterations drive pathway dysregulation. One of ordinary skill in the art would recognize that the combination would predicably yield a more interpretable model without unexpected difficulties. Applying a known technique to a known device (method, or product) ready for improvement to yield predictable results is likely to be obvious. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, USPQ2d 1385, 1395 – 97 (2007); and MPEP § 2143, D.
Claims 12-13 are rejected under 35 U.S.C. 103 as being unpatentable over Way.
Regarding claim 12, Way discloses using the machine learning model to analyze genetic information of a cellular sample, and classify the sample as having Ras pathway mutations. At 173 col.2 para.2. While Way does not use the model to analyze and classify a patient sample, Way notes that the model may sidestep requirements to profile multiple genomic measurements to detect Ras activation and identify more patients with activated Ras. At 177 col.2 para.4. A person having ordinary skill in the art would be motivated to use the model disclosed by Way to analyze and classify a patient sample because it would reduce requirements to profile multiple genomic measurements and identify more patient with activated Ras. One of ordinary skill in the art would reasonably expect success in this application because the model is generally sensitive and specific overall, is generalizable to cell-line data, largely aligns with curated variant oncogenicity, and identifies phenocopying events leading to activated Ras. At 177 col.1 para.4. Additionally, Way discloses that selumetinib has shown promising results in treating children with NF1 mutant plexiform neurofibromas, while PD 0325901 has shown efficacy in treating NF1 mutant neurofibromas in mouse- and human-derived malignant peripheral nerve sheath xenografts. At 177 col.1 para.5 – col.1 para.1. Way notes that as data increases in scale and algorithms are better constructed to model disease heterogeneity, the ability to research downstream responses of pathway misregulation and identify multi-model therapies targeting various vulnerabilities of individual tumors will improve. At 177 col.2 para.4. In applying the model to patient samples, a person having ordinary skill in the art would be motivated to select a treatment for the patient based on the classification of the sample. One of ordinary skill in the art would reasonably expect success in targeting vulnerabilities of individual tumors based on the classification because treatments have been shown to be effective/ineffective based on the underlying pathway dysregulation. Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention is likely to be obvious. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, USPQ2d 1385, 1395 – 97 (2007); and MPEP § 2143, G.
Regarding claim 13, Way discloses that the model outputs a coefficient for the genes based on its impact on aberrant pathway activity indicating the importance of the gene on aberrant pathway activity. At 173 col.2 para.2; 174 col.2 paras.1-2 (the method of claim 12, further comprising, outputting coefficients of the feature genes, based on the correlation of the feature genes with the pathway dysregulation score, wherein the pathway dysregulation score indicates a pathway dysregulation, and wherein a coefficient of a feature gene indicates the feature gene's impact on the pathway dysregulation).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Way in view of Ethan Cerami et al., The cBio Cancer Genomics Portal: An Open Platform for Exploring Multidimensional Cancer Genomics Data, 2(5) Cancer Discov. 401-04 (9 May 2012) (hereinafter “Cerami”).
Regarding claim 14, Way discloses using the machine learning model to evaluate a cellular sample not used to train the model. At 174 col.2 para.2 (evaluating the new cellular sample using the trained machine learning model). Based on the evaluation, the cellular sample is labeled as wild-type or Ras mutant. At 175 col.2 para.3 (based on the evaluation, adding to the new cellular sample a positive label or a negative label , the positive label indicating a potential pathway dysregulation of the sample). Way fails to disclose detecting the insertion of a new cellular sample into the data store. However, Cerami discloses a database system that supports detecting insertion of new samples and running analyses on the new samples. At 401 col.1 para.2 & col.2 para.2. Cerami notes that the portal includes TCGA data sets. At 401 col.1 para.2.
A person having ordinary skill in the art could combine Way’s classifier for labeling new samples with Cerami’s portal for detecting new sample insertions. Each element would merely perform the same function as it does separately, with Cerami’s portal detecting new sample insertions into the TCGA database and Way’s classifier analyzing and labeling the new samples. One of ordinary skill in the art would recognize that the combination would yield the predictable result of automatically evaluating and labeling newly inserted samples. Combining prior art elements according to known methods to yield predicable results is likely to be obvious. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, USPQ2d 1385, 1395 – 97 (2007); and MPEP § 2143, A.
Claims 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over Way in view of Xiang Chen et al., The use of classification trees for bioinformatics, 1(1) Wiley Interdiscip Rev Data Min Knowl Discov. 55-63 (18 April 2012) (hereinafter “Chen”).
Regarding claim 20, Way teaches the method of claim 1 (see 102 rejection above). Way discloses defining positive and negative control criteria with the positive including a genetic variation, and obtaining TCGA data matching the positive and negative criteria. At 172 col.2 para.2; 173 col.2 para.2; 174 col.1 paras.1-2 (a positive control group definition and a negative control group definition, the positive control group definition including as least one genetic variation condition; obtaining, in electronic format, a seed plurality of cellular samples including: a seed positive control group including cellular samples meeting the positive control group definition; and a seed negative control group including cellular samples meeting the negative control group definition). Way discloses that the machine learning model is an elastic net penalized logistic regression classifier. At 172 col.2 para.2. Way does not explicitly disclose iterative seed query refinement using a decision tree analysis.
However, Chen discloses starting with an initial labeled training dataset for tree-based analysis. At 2 para.1; 4 para.1 (receiving a seed query). Chen teaches that decision tree models are used to analyze high-dimensional genomic features. At 3 para.4 (analyzing, using a decision tree model, a plurality of genetic features for each of the positive and negative control groups). Chen discloses that splits are selected based on a randomly selected subset of features. At 2 para.2; 4 para.2 (refining, based on the analysis, the seed query to produce the query). Chen notes that decision trees identify informative features, which can reduce downstream computation time/cost. At 5 para.2; 7 para.7.
A person having ordinary skill in the art could combine the classifier of Way with the decision tree of Chen with each element merely performing the same function as it does separately such that the decision tree is used to refine the input for the classifier of Way. One of ordinary skill in the art would recognize that the results of the combination are predictably an improved method of detecting aberrant pathway activity in tumors because refining the input by identifying informative features leads to a quicker and more robust elastic net model for pathway detection. Combining prior art elements according to known methods to yield predicable results is likely to be obvious. See KSR International Co. v. Teleflex Inc., 550 U.S. 398, 415-421, USPQ2d 1385, 1395 – 97 (2007); and MPEP § 2143, A.
Regarding claim 21, Chen discloses comparing the classification accuracy between intermediate subsets and the full sample set. At 5 para.4; 6 para.3 (the method of claim 20, wherein analyzing the plurality of genetic features includes refining the seed query to produce an intermediate query and comparing an intermediate RNA signature of cellular samples meeting the intermediate query to a seed RNA signature of cellular samples meeting the seed query). Chen teaches that samples are pruned when differences in performance exceed thresholds during iterative tree-building and validation. At 2 paras.1 & 4; 6 para.3 (if a difference between the intermediate RNA signature and the seed RNA signature exceeds a significance threshold, removing, from the seed plurality of samples, cellular samples meeting the intermediate query, and analyzing, using a decision tree model, a plurality of genetic features of the seed plurality of samples).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Emily A Darrigrand whose telephone number is (571) 272-1098. The examiner can normally be reached Monday-Thursday 7:00AM-4:00PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Larry Riggs, can be reached at (571) 270-3062. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/E.A.D./ Examiner, Art Unit 1686
/OLIVIA M. WISE/ Supervisory Patent Examiner, Art Unit 1685
Prosecution Insights