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 .
Status of the Claims
The status of the claims as of the response filed 04 December 2025, is as follows:
Claims 1-8 are pending.
The applicant has amended Claims 1, 7, and 8, which have been considered below.
Response to Applicant’s Arguments Regarding § 101
Claim 8 non-transitory medium amendment, Acknowledged. The transitory-medium issue is resolved. Claim 8 now qualifies as a manufacture under Step 1; non-statutory rejection is withdrawn.
Applicant’s arguments, see pages 5-6, filed date 12/4/2025, with respect to Claims 1-8 have been fully considered and are not persuasive. The Subject matter eligibility rejection is sustained.
Applicant’s amendments to Claims 1, 7, and 8 add the phrases “by analyzing a sample of the target tissue” and “cultured in an in vitro environment.” Applicant contends these amendments introduce “tangible steps” involving “concrete biological inputs” that remove the claims from the mental-process category. Applicant further argues that the claims integrate the alleged exception into a practical application by “improving the drug development process” and reducing the time and cost for developing a new drug.
The Examiner has carefully considered these arguments and respectfully finds them unpersuasive for the reasons set forth below.
The Applicant's amendments, which merely specify the source and origin of the omics data (i.e., analyzing a tissue sample and using in vitro cells) that therefore is evaluated under prong two/step 2b, are unpersuasive because they constitute insignificant pre-solution data gathering or a field-of-use limitation under MPEP § 2106.05(g) and (h). These elements do not integrate the core abstract idea, calculating similarity and synthesizing weighted data, into a practical application or remove from mental process classification, as the entire process remains a cognitive evaluation performable by a human researcher without non-conventional technology.
The Applicant’s argument that the claims are eligible because they improve drug development by reducing time and cost is unpersuasive. This asserted benefit is merely the desired result of applying the abstract idea, which the Examiner respectfully disagrees with as it fails to constitute a technical improvement to a computer or technology under MPEP § 2106.05(a). The claims lack a specific technical mechanism or non-conventional structure, as the specification confirms the invention’s contribution is an abstract analytical methodology ("differentially synthesizing cell-level information...") executed on generic hardware.
Applicant's argument that the cited prior art "fail to describe or even recognize" the claimed estimation approach confuses novelty with eligibility. The Supreme Court has held that the novelty of any element or the process itself is of no relevance in determining subject matter eligibility under 35 U.S.C. § 101 (Diamond v. Diehr). The § 101 inquiry evaluates only whether the claims recite an inventive concept amounting to significantly more than the abstract idea, and the novelty of the abstract method does not satisfy this requirement.
Accordingly, the rejection under 35 U.S.C. § 101 is maintained as set forth in the updated analysis below.
35 U.S.C. § 102 Statutory Rejection
Applicant’s arguments, see pages 7-9, filed December 4, 2025, with respect to Claims 1, 2, and 5-8 have been fully considered and are not persuasive. The 35 U.S.C. § 102(a)(1) rejection is sustained.
The Applicant asserts Szeto fails to describe a "target tissue" because its use of "tissue exposed to a drug" is a general description that does not identify a specific tissue or the analysis of a sample thereof.
The Examiner respectfully disagrees and sustains the rejection because Szeto discloses analyzing a specific patient tissue sample to obtain genomic data. Since Szeto teaches that "biopsy samples to obtain the omics data" are utilized, and data is "collected from individual cancer samples". Because the prior art language is read in the applicant's language BRI, a biopsy of an individual cancer sample constitutes an analysis of a "sample of the target tissue". Refer to Szeto [0026], [0041]; MPEP 2111.
The Applicant asserts that Szeto fails to describe cells "associated with the target tissue," arguing that "Szeto is silent regarding the association between any known cell lines and specific tissues". Applicant claims the reference fails to differentiate between "the use of cells and tissues".
The Examiner respectfully disagrees and maintains the rejection because Szeto explicitly matches specific cell line types to corresponding patient tissue types to ensure predictive accuracy. Refer to Szeto [0044];
The Applicant asserts that Szeto’s "standardized score" represents "how well a pre-trained predictive model statistically fits the patient’s data" rather than a "structural similarity between the omics datasets themselves". Applicant argues that statistical normalization does not reflect "structural similarity.
The Examiner respectfully disagrees and sustains the rejection because Szeto’s scoring system measures the degree of match or conformance between the datasets, which constitutes a calculation of similarity. Szeto expressly states that "where the original patient dataset is more similar to the original dataset... a higher prediction score is observed". A process that calculates a score based on how "similar" one dataset is to another satisfies the broad requirement of "calculating a similarity." Refer to Szeto, par. 0039
The Applicant asserts that Szeto describes "prediction of a drug treatment" which is "completely different from estimating tissue-level drug effect information". Applicant argues the computational approach and form of output are "fundamentally different".
The Examiner respectfully disagrees and sustains the rejection because the "information" estimated in the claims is defined in the specification and dependent claims as a drug effect. Specifically, Claim 6 recites that the estimation "includes: estimating a drug effect on the target tissue." Szeto identifies drugs for which "treatment success or failure can be predicted". Because predicting treatment success is the act of estimating a drug's effect on the target tissue, the reference anticipates this limitation. Refer to Szeto par. 0011
35 U.S.C. § 103 Statutory Rejection
Applicant’s arguments, see pages 9, filed December 4, 2025, with respect to Claims 2-4 have been fully considered and are not persuasive. The 35 U.S.C. § 103 rejection is sustained.
The Applicant asserts that "the cited references fail to disclose all elements" because Newman "merely describes a method to estimate the relative proportions of distinct cell subsets". Applicant argues that because Szeto is allegedly deficient, Newman "fails to remedy" the lack of tissue-level information and similarity features. The evidence cited is Newman's para. [0009] regarding the deconvolution of bulk tissue samples.
The Examiner respectfully disagrees and sustains the rejection because Szeto provides the estimation framework by predicting "treatment success or failure" based on a "patient-specific score". Newman provides the missing mathematical mechanism by defining feature profiles and comparing them using "Euclidean distance" to minimize error.
Integrating Newman's explicit distance-based vector similarity into Szeto’s scoring pipeline is a routine use of a known technique to improve similar methods in the same way (MPEP 2143). This combination achieves the claimed vector-similarity computation between tissue and cell feature vectors with a reasonable expectation of success using standard data-processing steps. Refer to Szeto [0011], [0039]; Newman [0008], [0009], [00150];
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.
Subject Matter Eligibility Rejection – 35 U.S.C. § 101
Claims 1–8 are rejected under 35 U.S.C. § 101 because the claimed subject matter is directed to a judicial exception (an abstract idea) without reciting elements that integrate the exception into a practical application or provide an inventive concept amounting to significantly more than the exception itself.
Step 1: Statutory Categories Analysis
The claims are directed to statutory subject matter, encompassing the following statutory categories:
Process (Claims 1–6): The language reciting “A method for estimating tissue-level information which is performed in a computing device, the method comprising: acquiring… calculating… and estimating” defines a series of acts or steps. This aligns with the definition of a process in MPEP § 2106.03.
Machine (Claim 7): The language reciting “a device… comprising: a memory storing one or more instructions; and a processor configured to execute the stored one or more instructions” describes a concrete thing consisting of parts. This aligns with the definition of a machine in MPEP § 2106.03.
Manufacture (Claim 8): The language reciting “A computer program stored on a non-transitory computer-readable recording medium” describes a tangible article given a new form through artificial efforts. This aligns with the definition of a manufacture in MPEP § 2106.03.
Having confirmed the claims are directed to statutory subject matter, the analysis proceeds to Step 2A, Prong One.
Step 2A, Prong One: Identification of the Abstract Idea
Step 2A, Prong One, determines whether a claim recites a judicial exception or an abstract idea by examining whether the claim's limitations, under their broadest reasonable interpretation, fall within an enumerated abstract idea grouping identified in MPEP § 2106.04(a).
The invention relates to a method and device for estimating tissue-level information from cell-level information by calculating the similarity between a target tissue and a plurality of cells based on omics data, and synthesizing cell-level information weighted by that similarity. The specification states: “it is possible to accurately estimate tissue-level information by differentially synthesizing cell-level information based on the similarity between the target tissue and the cells” (Spec., 0014). Refer to paragraphs 0002–0007 and 0035–0036 for further details regarding the invention concept.
Under MPEP § 2111, Claims 1–8 as a whole recite: (1) acquiring two sets of biological data, omics data from a target tissue sample and omics data from cultured cells; (2) calculating a similarity metric between the tissue and cells based on those two datasets; and (3) estimating tissue-level information by synthesizing (weighting) cell-level information according to the calculated similarity. The core analytical operations in steps (2) and (3), comparing datasets to assess similarity, and weighting information based on the comparison result, describe cognitive evaluations that a person could perform mentally and step (1) describes human activity.
Representative Independent Claim
Independent Claim 1 is reproduced below. Bolded portions represent additional elements evaluated in Prong Two and Step 2B. Non-bolded portions represent the abstract idea.
A method for estimating tissue-level information which is performed in a computing device, the method comprising:
acquiring first omics data for a target tissue by analyzing a sample of the target tissue;
acquiring second omics data for a plurality of cells associated with the target tissue and cultured in an in vitro environment;
calculating a similarity between the target tissue and the plurality of cells based on the first omics data and the second omics data; and
estimating information on the target tissue by synthesizing information on the plurality of cells based on the calculated similarity.
Claim Abstract Classification Rationale
Under their Broadest Reasonable Interpretation (MPEP § 2111), independent Claims 1, 7, and 8 recite a process of comparing biological datasets to quantify similarity between a tissue and cells, then weighting cell-level information by that similarity to estimate tissue-level information. This process aligns with the following abstract idea categories:
Mental Process (MPEP § 2106.04(a)(2)(III)): A mental process includes concepts performed in the human mind, encompassing observation, evaluation, judgment, and opinion, with or without the aid of pen and paper. Independent Claims 1, 7, and 8 recite “calculating a similarity between the target tissue and the plurality of cells based on the first omics data and the second omics data” and “estimating information on the target tissue by synthesizing information on the plurality of cells based on the calculated similarity.” Under MPEP § 2111, “calculating a similarity” covers any comparison of two datasets, and “synthesizing… based on the calculated similarity” covers weighting and combining information. These operations involve evaluation and judgment: comparing data to assess similarity, then drawing a weighted conclusion. The specification supports this interpretation, stating: “the estimation device 10 may estimate the drug effect score 24 for the target tissue by synthesizing (e.g. weight sum) cell-level drug effect scores 21 to 23 using the similarity between the target tissue and the cells Cell-1 to Cell-3 as weights w1 to w3” (Spec., 0053). This paragraph confirms that the core operations are weighting and summation, mathematical/cognitive judgments that a person could replicate. A human researcher with printed gene-expression tables could visually compare values across columns, identify which cell lines have expression profiles closest to the tissue, mentally assign greater weight to more similar cell lines, and compute a weighted average of drug-effect scores on paper.
Certain Method of Organizing Human Activity (MPEP § 2106.04(a)(2)(II)): This category encompasses managing personal behavior or relationships or interactions between people, including following rules or instructions. Independent Claims 1, 7, and 8 recite “acquiring first omics data for a target tissue …” and “acquiring second omics data for a plurality of cells associated with the target tissue ...” These data-acquisition steps describe a managed laboratory workflow collecting biological samples, performing assays, and gathering experimental results from cultured cell lines, which falls under the sub-category of managing personal behavior or relationships (following established research protocols and instructions). The specification supports this, stating: “the cell-level drug effect information may include drug effect information on the cell line. Such information may be easily obtained from a disclosed database (DB), or may be obtained at a low experimental cost” (Spec., 0039). This paragraph confirms that the data-acquisition steps describe laboratory data collection activities conducted in accordance with established experimental procedures. A laboratory team routinely collects tissue samples, cultures cell lines in vitro, runs assays, and records the resulting omics data in databases, all standard human interactions in drug development research.
Manual Replication Scenario (Human Equivalence)
The abstract nature of the claims is reinforced because the entire process is analogous to fundamental human activities:
Although a computer executes these operations faster, speed and efficiency do not transform an otherwise abstract process into a non-abstract one. Consider the following scenario in the context of the applicant’s disclosure: A pharmacology researcher receives a printed gene-expression report from a lung-cancer tissue biopsy (obtaining first omics data by analyzing a sample). The researcher has also published expression data sheets for five laboratory cell lines associated with lung cancer that were cultured in an in vitro environment (acquiring second omics data). Using a ruler and pen, the researcher lines up corresponding gene-expression values from the tissue report and each cell-line sheet, mentally noting which cell lines have profiles closest to the tissue (i.e., calculating similarity). Finally, the researcher multiplies each cell line’s known drug-effect score by its similarity ranking, sums the weighted scores across the paper, and reports the result as the estimated drug effect for the tissue (estimating information synthesized from the calculated similarity). No computer, software, or specialized hardware was needed at any step.
Dependent Claims Analysis (Prong One)
The dependent Claims 2–6 are also directed to an abstract idea:
Claim 2: Recites that “the second omics data include omics data for cell lines cultured in an in vitro environment, and the information on the plurality of cells includes information on the cell line.” Under BRI, this narrows the type of data and cell source. This is a mental process because it merely specifies the biological context of the data being compared; a person can mentally evaluate cell-line data the same way regardless of its in vitro origin. This is also a field-of-use limitation under MPEP § 2106.05(h).
Claim 3: Recites “generating a first feature vector from the first omics data; generating a second feature vector from the second omics data; and calculating the similarity based on a vector similarity between the first feature vector and the second feature vector.” Under BRI, generating a feature vector means extracting numerical representations from data, a mathematical concept (MPEP § 2106.04(a)(2)(I)). Calculating vector similarity is a mathematical computation. A person could tabulate gene expression values in columns (vectors) and compare them with pen and paper.
Claim 4: Recites that “the vector similarity is calculated based on a distance between the first feature vector and the second feature vector in a vector space.” Under BRI, this specifies a distance metric, Euclidean distance, for example (Spec., 0062). Computing the distance between two vectors is a mathematical calculation (MPEP § 2106.04(a)(2)(I)) that a person can perform with paper and a calculator.
Claim 5: Recites “inputting the first omics data into a classification model that receives omics data and outputs classes of cells to obtain a confidence score for each class; and calculating the similarity based on the obtained confidence score.” Under BRI, the classification model outputs a confidence score (probability) for each cell class (Spec., ¶0075). The claim describes applying data to a model and using the output for comparison. This is a mathematical concept and mental process, evaluating model output and using scores to assess similarity.
Claim 6: Recites “estimating a drug effect on the target tissue by synthesizing drug effect information on the plurality of cells.” Under BRI, this narrows the type of information being synthesized to drug effects. This is a mental process—a researcher synthesizes drug effect data by weighting and combining, and a field-of-use limitation restricting the abstract idea to drug development.
Having identified the abstract ideas recited in Claims 1–8, the analysis proceeds to Step 2A, Prong Two, to determine whether the additional elements integrate the judicial exception into a practical application.
Step 2A, Prong Two: Integration into a Practical Application
Step 2A, Prong Two evaluates whether the claim as a whole integrates the recited judicial exception into a practical application by examining whether the additional elements, individually and in combination, impose a meaningful limit on the abstract idea beyond merely applying it. The additional elements identified in Claims 1, 7, and 8 do not integrate the abstract idea into a practical application because they amount to generic computing components, pre-solution data-gathering activity, and field-of-use limitations that serve only to implement the abstract idea in a computing environment.
Evaluation of Independent Claims 1, 7, and 8 Additional Elements
Computing Device (Claim 1), Memory and Processor (Claim 7), Non-Transitory Computer-Readable Recording Medium (Claim 8): The recitation of “a computing device” (Claim 1), “a memory storing one or more instructions; and a processor configured to execute the stored one or more instructions” (Claim 7), and “a non-transitory computer-readable recording medium” (Claim 8) does not integrate the abstract idea into a practical application because it amounts to mere instructions to apply the exception using generic computer components under MPEP § 2106.05(f).
The specification describes these components in entirely generic terms: “The computing device may be a notebook, a desktop, a laptop, or the like, but may include any type of device equipped with a computing function” (Spec., 0037). The processor is described as “at least one of a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art” (Spec., 0084). The memory “may be implemented as a volatile memory such as RAM” (Spec., 0085). These passages confirm that the claimed computing elements are recited at the highest level of generality, invoked merely as tools to perform the abstract idea, without any particular configuration, architecture, or interaction that would reflect a technological improvement under MPEP § 2106.05(a).
“By analyzing a sample of the target tissue” (Claims 1, 7, 8): The recitation of “by analyzing a sample of the target tissue” does not integrate the abstract idea into a practical application because it constitutes insignificant extra-solution activity under MPEP § 2106.05(g).
This phrase specifies how the first omics data is obtained, by analyzing a physical tissue sample. This is a pre-solution data-gathering step: it collects input data for the abstract idea (calculating similarity and synthesizing information), which is then processed. The specification confirms: “the genetic expression data of the target tissue can be acquired, for example, by analyzing a sample of the target tissue, but is not limited thereto” (Spec., 0047). The phrase “but is not limited thereto” reveals the data-acquisition step is broadly recited and not tied to any specific analytical technique, instrument, or methodology. It does not describe a particular improvement to any technology or a specific technical mechanism under MPEP § 2106.05(a).
“Cultured in an in vitro environment” (Claims 1, 7, 8): The recitation of “cultured in an in vitro environment” does not integrate the abstract idea into a practical application because it constitutes a field-of-use limitation under MPEP § 2106.05(h).
This phrase limits the source of the second omics data to cells that were laboratory-cultured, restricting the abstract idea to a particular biological context without adding a meaningful structural or functional limitation. The specification confirms: “the cell-level drug effect information may include drug effect information on the cell line. Such information may be easily obtained from a disclosed database (DB), or may be obtained at a low experimental cost” (Spec., ¶0039). Data from in vitro cell lines are readily available in public databases, specifying this origin does not transform the claim’s analytical method into a practical application.
When viewed as a whole, the combination of these additional elements, generic computing hardware executing a data comparison and synthesis process, with input data sourced from tissue sample analysis and in vitro cell lines, describes a general computing environment receiving biological data and performing the abstract analytical steps. The combination does not recite a specific technical mechanism, a non-standard hardware configuration, or a particular data-processing architecture that would render the claim practical. Each element serves its ordinary, expected function, and together they implement the abstract idea on a generic computer using conventionally obtained biological inputs.
Dependent Claims Analysis (Prong Two)
The dependent claims do not add additional elements that integrate the abstract idea into a practical application.
Claim 2: Specifies that the second omics data includes data for cell lines cultured in an in vitro environment and that the cell information includes information on the cell line. This adds no new additional element, it merely narrows the abstract idea by specifying the biological data type. This is a field-of-use limitation under MPEP § 2106.05(h).
Claims 3–4: Specify generating feature vectors and calculating vector similarity based on distance. These claims add no tangible additional elements—they further detail the mathematical technique for the similarity calculation, narrowing the abstract idea without introducing a technical improvement. This fails to improve computer functionality under MPEP § 2106.05(a).
Claim 5: Recites “inputting the first omics data into a classification model.” The classification model is an arguably additional element. However, the specification describes it generically as implementable via “a neural network, … a decision tree, a support vector machine, or logistic regression” (Spec., 0072), listing standard machine learning approaches without identifying any particular architecture, training regimen, or processing constraint tied to a technological improvement. This amounts to mere instructions to apply the exception using a generic analytical model under MPEP § 2106.05(f).
Claim 6: Specifies that the estimation includes “estimating a drug effect on the target tissue by synthesizing drug effect information.” This adds no new element; it narrows the type of information being synthesized to drug effects. This is a field-of-use limitation under MPEP § 2106.05(h).
When viewed as a whole, the combination of the additional elements in the independent and dependent claims does not integrate the abstract idea into a practical application. The dependent claims refine the mathematical and analytical methods but do not recite any structural or non-conventional computer configuration or technical improvement as required by MPEP § 2106.05(a) and (h).
Because the claims’ additional elements, individually and in combination, do not integrate the abstract idea into a practical application, the analysis proceeds to Step 2B.
Step 2B: Inventive Concept Analysis
Step 2B evaluates whether any additional element, individually or in combination, provides an inventive concept amounting to “significantly more” than the judicial exception (MPEP § 2106.05). The additional elements identified in Prong Two, generic computing components, data-gathering steps specifying tissue sample analysis, and the in vitro field-of-use qualifier, do not supply an inventive concept because the specification describes each as conventional and does not attribute any inventive significance to their configuration or interaction.
Evaluation of Independent Claims 1, 7, and 8 Additional Elements
The following additional elements are evaluated consistent with the Prong Two analysis above:
Computing Device / Memory and Processor / Non-Transitory CRM: The specification admits that the computing device is any general-purpose computer: “The computing device may be a notebook, a desktop, a laptop, or the like, but may include any type of device equipped with a computing function” (Spec., 0037). The processor is described as “any type of processor well known in the art” (Spec., 0084). The storage is described as “a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, and the like, a hard disk, a removable disk, or any computer-readable recording medium well-known in the art” (Spec., 0088). These admissions confirm that the claimed computing elements are well-understood, routine, and conventional per MPEP § 2106.05(d)(II). The specification’s use of “well known in the art” and listing of standard hardware categories constitutes an admission of conventionality. Neither the claims nor the specification identify any change to processor architecture, memory structure, data-path, or execution semantics. These elements function as instructions to apply the judicial exception on generic hardware under MPEP § 2106.05(f) and represent insignificant extra-solution activity by merely placing the abstract steps in a computing environment under MPEP § 2106.05(g).
“By analyzing a sample of the target tissue”: The specification states: “the genetic expression data of the target tissue can be acquired, for example, by analyzing a sample of the target tissue, but is not limited thereto” (Spec., 0047). The phrase “but is not limited thereto” indicates this data-acquisition method is generic and non-specific. Analyzing a tissue sample to obtain gene expression data is a standard laboratory procedure in genomics research. Refer to MPEP 2106.05(d)(II). Under MPEP § 2106.05(g), this pre-solution data-gathering step is an insignificant extra-solution activity that does not amount to significantly more. The step does not recite a particular assay, instrument, protocol, or technique that would distinguish it from conventional biological sample analysis.
“Cultured in an in vitro environment”: The specification confirms that cell-level information from in vitro cell lines is standard research data: “Such information may be easily obtained from a disclosed database (DB), or may be obtained at a low experimental cost” (Spec., 0039). Culturing cells in vitro and collecting their omics data is a well-understood, routine practice in pharmaceutical research. This field-of-use limitation under MPEP § 2106.05(h) merely restricts the abstract idea to a particular biological data source and does not contribute an inventive concept. Refer US20190085324A1, par. 0522, US20190262399A1, par. 0770, US20200362334A1, par. 0661
As a whole, the combination of the additional elements—generic computing hardware receiving conventionally obtained biological data—does not provide an inventive concept. The elements are arranged in a conventional manner (input data → process → output result) to execute the abstract idea without adding any unconventional steps, specialized architecture, or technical improvement that would amount to significantly more.
Dependent Claims Analysis (Step 2B)
The following dependent claims are evaluated for additional elements beyond those in the independent claims:
Claim 2: Does not add a new additional element. It merely narrows the abstract idea by specifying the data type and cell source. No Step 2B evaluation is required—the claim inherits the rejection of Claim 1 as explained in Prong One.
Claims 3–4: Do not add new additional elements. They further specify the mathematical technique (feature vectors, vector distance) for calculating similarity. These are the narrowing of the abstract mathematical concept. No Step 2B evaluation is required—the claims inherit the rejection of Claim 1 as explained in Prong One.
Claim 5: Adds the additional element of a “classification model.” The specification describes this model generically: “the classification model 55 may be implemented based on a neural network… the classification model 55 may be implemented based on a traditional machine learning model, such as a decision tree, a support vector machine, or logistic regression” (Spec., 0072). This lists conventional, well-known machine learning architectures without identifying any specialized configuration. The specification’s enumeration of standard model types is an admission of conventionality under MPEP § 2106.05(d). This amounts to mere instructions to apply the exception using a generic analytical tool under MPEP § 2106.05(f) and does not provide significantly more.
Claim 6: Does not add a new additional element. It specifies drug effect estimation as the application of the synthesis step. This is a field-of-use limitation under MPEP § 2106.05(h) that narrows the abstract idea to the drug-development context and does not provide significantly more.
As a whole, the combination of dependent claims and their additional elements does not provide an inventive concept. The dependent claims refine the abstract methodology with conventional mathematical techniques and a generic classification model, without introducing any non-conventional element or arrangement that would amount to significantly more than the judicial exception.
The claims are directed to an abstract idea, calculating similarity between biological datasets and synthesizing weighted information, and lack an inventive concept that would supply significantly more than the exception itself. Therefore, Claims 1–8 are rejected under 35 U.S.C. § 101.
Claim Rejections – 35 U.S.C. § 102
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, 6-8 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Szeto (US 2018/0190381 A1).
Claim 1. Szeto teaches, A method for estimating tissue-level information which is performed in a computing device, the method comprising: (Szeto, par. 0002-0005)
acquiring first omics data for a target tissue by analyzing a sample of the target tissue; (Szeto, par. 0011-0012, 0043, 0026-0027 “ biopsy samples to obtain the omics data“, 0041, “Collected from individual cancer samples “)
Szeto describes a system and method that uses known cell line genomics and drug-response data. Szeto teaches collecting patient genomic-scale data from individual cancer samples (i.e., analyzing a sample of the cancer/tumor tissue using microarray or sequencing) and using that patient omics/pathway model data as input to the drug-response prediction pipeline.
acquiring second omics data for a plurality of cells associated with the target tissue and cultured in an in vitro environment; (Szeto, par. 0011-0012, 0043, 0026-0027, 0036, 0041, 0044, abstract “cell line genomics”)
Szeto describes a system and method that uses known cell line genomics and drug-response data. Szeto expressly treats the cell-culture/tissue omics/pathway models as the inputs used to build the predictor library and then evaluate patient data (e.g., cell-line pathway models → response predictors; patient pathway model → test models).
calculating a similarity between the target tissue and the plurality of cells based on the first omics data and the second omics data; (Szato, par. 0026-0027, 0039)
Szato, describe systems and methods that match patient pathway models with response predictors to identify effective drugs and higher "standardized score" in drug response prediction indicates a better chance of a patient responding well to a specific drug, especially when their data closely matches the data used to create the prediction model.
and estimating information on the target tissue by synthesizing information on the plurality of cells based on the calculated similarity. (Szeto, par. 0011-0012, 0026-0027, 0039, Figure 1A-1c, Figure 2A)
Szeto describes, drug response in patients for prediction using omics data and biological processes derived from omics data.
Claim 2. Szeto teaches, The method of claim 1, wherein the second omics data include omics data for cell lines cultured in an in vitro environment, and the information on the plurality of cells includes information on the cell line. (Szeto, par. 0036, 0043)
Claim 6. Szeto teaches, The method of claim 1, wherein the estimating of the information on the target tissue includes: estimating a drug effect on the target tissue by synthesizing drug effect information on the plurality of cells. (Szeto, See at least, fig, 5-6, par. 0011-0012, 0036, 0039, 0042, Abstract)
Szeto discloses estimating a drug effect on the patient's target tissue by synthesizing drug effect information from multiple cell lines.
Note: Claims 7-8 are rejected with the same analysis above to being very similar to claim 1.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 3-4 is/are rejected under 35 U.S.C. 103 as being unpatentable over Szeto – US 20180190381A1 with Newman - WO2016118860A1.
Claim 3. Szeto teaches, The method of claim 1, wherein the calculating of the similarity includes: generating a first feature vector from the first omics data; par. 0027, 0013, 0038, 0040, 0043, Figure 2A)
generating a second feature vector from the second omics data; par. 0027, 0013, 0038, 0040, 0043, Figure 2A)
and
calculating the similarity based on a vector similarity between the first feature vector and the second feature vector. (par. 0016, 0020-0021, 0027, 0013-0014, 0038-0039, 0040, 0043, Figure 2A)
Szeto teaches calculating the similarity (under BRI, a patient-specific score indicative of closeness) between patient omics/pathway data and pre-built response predictors by computing null-model standardized scores and ranking the predictors: Generate large library of response predictors … using multiple distinct machine learning algorithms … Generate null models … Standardize raw data … obtain normalized results … rank results…Szeto further explains that the system “uses a patient pathway model to generate respective test models … [and] ranks the respective test models by their respective gain” and that “the difference in standardized score is then used for ranking … where the original patient dataset is more similar … a higher prediction score is observed”.
However, Szeto fails to disclose generating a first feature vector from the first omics data; generating a second feature vector from the second omics data; and calculating the similarity based on the vector similarity between the first feature vector and the second feature vector.
Newman (WO 2016/118860 A1) teaches the Missing Element in bold, describing explicit vector-to-vector similarity/distance between omics-derived feature vectors: Newman defines a feature profile m and compares profiles using a difference measurement that “may be a correlation coefficient … Euclidean distance” (para. [00150]); related claims teach that the “lowest error is obtained using a Pearson … Spearman … Euclidean distance” (para. [0008]/claim 9). Newman also normalizes vector norms when constructing nulls—“wherein m and m have the same Euclidean norm (|m|=|m*|)”* (para. [0009])—confirming standard vector-space operations on omics feature vectors.
It would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to combine the teachings of Szeto with Newman because both references address the shared purpose of quantifying how a sample’s omics profile relates to known cellular signatures/models to drive downstream decisions. Szeto (paras. [0038]–[0039], Newman (para. [0008-0009],[00150]), a POSITA would obtain the claimed calculating the similarity … based on the vector similarity between the first feature vector and the second feature vector, using well-specified correlation or Euclidean metrics that directly quantify vector closeness while retaining Szeto’s overall scoring/ranking pipeline. (Newman paras. [00150], [0008]).
A person of ordinary skill in the art would have been motivated to integrate the vector-similarity between first and second feature vectors from Newman into the system of Szeto to achieve the benefit of “ lowest error is obtained using a Pearson … Spearman … Euclidean distance” (para. [0008]), and identifies correlation/Euclidean difference measurements for profile comparison (para. [00150]).
Furthermore, the proposed combination is obvious because use of known technique to improve similar methods in the same way. The technique of vector-space similarity (e.g., Pearson correlation, Euclidean distance) between omics feature vectors is known in the art (as evidenced by Newman, paras. [0008], [0009], [00150]) for improving omics-based inference by quantifying profile closeness with standard distance/similarity metrics. Applying this known technique to the analogous Szeto framework (patient omics → scoring → ranking) predictably improves it in the same manner to achieve the claimed vector-similarity computation between the first and second feature vectors a direct, quantitative similarity measure feeding Szeto’s selection/ranking step.
A PHOSITA would have had a reasonable expectation of success in combining the references because the modification requires only routine data-processing: Szeto already ingests patient omics/pathway data and computes scores against a library (Fig. 2A) (para. [0021]); swapping-in or adding Newman’s vector similarity (correlation/Euclidean) merely requires forming two feature vectors (tissue, cell) and computing a standard metric that Newman specifies and norm-controls (paras. [0009], [00150]). Both references provide enabling detail for their respective steps, and their data types (gene-expression/omics) and computational context align.
Claim 4. Szeto with Newman teaches, The method of claim 3, wherein the vector similarity is calculated based on a distance between the first feature vector and the second feature vector in a vector space. (Newman, par. 0008)
Claim(s) 5 is rejected under 35 U.S.C. 103 as being unpatentable over Szeto – US 20180190381A1 with Tan, Y., & Cahan, P. (2018). SingleCellNet: a computational tool to classify single cell RNA-Seq data across platforms and across species. Posted on bioRxiv. https://doi.org/10.1101/508085, PTO-892-U.
Claim 5. Szeto teaches, The method of claim 1, wherein the calculating of the similarity includes: inputting the first omics data into a classification model that receives omics data (Szeto, par. 0027 “machine learning algorithm that uses omics data and/or pathway models generated from a cell culture or tissue” par. 0038 “actual patient data using null models for each of the response predictors in the database”, par. 0031 “patient dataset (omics data or pathway model)” par. 0013 “ machine learning system may uses various classifiers”)
and Szeto, par. 0024 “representation of dasatinib sensitivity sorted by cell line type”, par. 0025“representation of dasatinib sensitivity sorted by human TCGA tumor type”, fig.5-fig.6)
and calculating the similarity .(Szeto, par. 0039 “here the original patient dataset is more similar to the original dataset used in the calculation of a prediction model, a higher prediction score is observed (as the prediction model is optimized for predicting a response to a specific drug).”)
Szeto teaches inputting the first omics data into a classification model that receives omics data and obtaining a score, of the Claim 5, the method of claim 1, wherein the calculating of the similarity includes: inputting the first omics data into a classification model that receives omics data and outputs classes of cells to obtain a confidence score for each class; and calculating the similarity based on the obtained confidence score, Szeto describes inputting patient omics data into machine learning classifiers built from cell-line data to generate prediction scores, and teaches that higher scores indicate greater similarity between the patient's data and the cell-line data underlying the model. However, Szeto does not describe a classification model that outputs classes of cells to obtain a confidence score for each class or calculating the similarity based on the obtained confidence score.
Tan & Cahan teaches a classification model that receives omics data and outputs classes of cells to obtain a confidence score for each class and calculating the similarity based on the obtained confidence score of the Claim 5. Under MPEP 2111, a confidence score for each class is reasonably interpreted as any numerical value a classifier produces for each output category indicating the degree of match between the input and that category. Tan & Cahan describes a multi-class Random Forest classifier trained on cell-type-annotated single cell RNA-Seq data that takes query omics data as input, classifies each cell against all reference cell types, and outputs a per-class classification score summing to one quantitative value for each cell-type class that directly measures the degree of match. These per-class scores then serve as the quantitative measure of similarity, which the authors expressly describe as more informative than binary categorical assignment. (Tan & Cahan, See at least, Summary, page 2: SingleCellNet, which addresses these issues and enables the classification of query single cell RNA-Seq data in comparison to reference single cell RNA-Seq data; Discussion, pag. 7: a multi-class Random Forest classifier is then trained with the transformed training data; a classification score is generated for each query cell; Figure 2, page 8 description: The classification score for each column/cell sums up to 1, with a range from 0 black to 1 yellow; Discussion, page 7: a quantitative, rather than a binary, metric of identity is informative).
The combination of Szeto + Tan & Cahan makes obvious the full limitation under inputting the first omics data into a classification model that receives omics data and outputs classes of cells to obtain a confidence score for each class; and calculating the similarity based on the obtained confidence score because Szeto seeks to quantify how similar a patient's omics profile is to reference cell-line data and already inputs patient omics data into trained classifiers for this purpose. Tan & Cahan teaches a multi-class Random Forest cell-type classifier that takes omics data and produces per-class confidence scores a known technique that directly measures the tissue-to-cell similarity Szeto's system requires. A person of ordinary skill would implement Tan & Cahan's classifier within Szeto's pipeline as the similarity calculation step, and the predictable result is per-class confidence scores quantifying how closely the patient tissue matches each reference cell type. (See at least, Szeto, par. 0039: where the original patient dataset is more similar to the original dataset used in the calculation of a prediction model, a higher prediction score is observed; par. 0013: contemplated machine learning system may use various classifiers, including...random forest algorithms; Tan & Cahan, Discussion page 7: a multi-class Random Forest classifier is then trained with the transformed training data; a classification score is generated for each query cell; Discussion, page 7: a quantitative, rather than a binary, metric of identity is informative).
A skilled artisan who read Szeto's application would combine Tan & Cahan with Szeto because both references are in the same field of endeavor under MPEP § 2141.01(a), computational analysis of omics data from cells and tissues using machine learning classifiers and Szeto expressly relies on similarity between patient omics data and cell-line reference data as the mechanism driving accurate drug prediction, directly pointing toward the need for a quantitative cell-type classification method that Tan & Cahan provides. (See at least, Szeto, par. 0002: the field of the invention is systems and methods of predicting drug responses using omics information; par. 0039: where the original patient dataset is more similar to the original dataset used in the calculation of a prediction model, a higher prediction score is observed; Tan & Cahan, Summary, page 2: SingleCellNet, which addresses these issues and enables the classification of query single cell RNA-Seq data in comparison to reference single cell RNA-Seq data).
Integrating Tan & Cahan's cell-type classification into Szeto's pipeline solves the problem of quantifying which cell types in the reference library are most similar to the patient's tissue, replacing Szeto's indirect similarity measurement, based on drug-response prediction score magnitude with a direct, multi-class cell-type classification that produces explicit per-class confidence scores. The benefit is a more precise and interpretable similarity assessment, and the result is predictable because both systems already process gene-level omics data through machine learning classifiers to produce quantitative scores. (See at least, Szeto, par. 0039: a higher prediction score for a response predictor using a patient dataset pathway model or omics data indicates that the patient's response to treatment with the drug used in the response predictor may also be accurately predicted; Tan & Cahan, Discussion, page. 7: a quantitative, rather than a binary, metric of identity is informative, or when the presence of shared cell types across datasets is unclear).
A person of ordinary skill would have a reasonable expectation of success because both references process gene-level omics data through machine learning classifiers. Szeto explicitly teaches using expression data and copy number data as omics inputs, and Tan & Cahan's classifier operates on gene expression data the same category of input.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSHUA DAMIAN RUIZ whose telephone number is (571)272-0409. The examiner can normally be reached 0800-1800.
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, Shahid Merchant can be reached at (571) 270-1360. 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.
/JOSHUA DAMIAN RUIZ/Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684