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
Claims 1-10,15-23 and 26 are pending and under consideration in this action. Claims 11-14, and 24-25 were canceled in the amendment filed 3/3/2023.
Priority
The instant application is a 371 of PCT/GB2021/050342, filed 2/12/2021, which claims priority to United Kingdom Application Number 2002586.2, filed 2/24/2020, as reflected in the filing receipt mailed on 10/19/2023. Acknowledgment is made of applicant' s claim for foreign priority under 35 U.S.C. 119 (a)-(d). Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. The claims to the benefit of priority are acknowledged and the effective filing date of claims 1-10, 15-23, and 26 is 2/24/2020.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 11/21/2022, 9/2/2025, and 12/15/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS’s have been considered by the examiner.
Claim Rejections - 35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 8, 15, 18-19, and 21-23 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 8 recites the phrase “removing from consideration the one or more latent variables not sufficiently associated with a biological mechanism”. The term “sufficiently” in claim 8 is a relative term which renders the claim indefinite. The term “sufficiently” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The Specification (see Para. [0048]) reiterates the claim language, disclosing that for the purpose of ignoring noise, the interpretation module may be configured to remove from consideration latent variables not sufficiently associated with a biological mechanism. However, the Specification does not provide, for example, any parameters defining whether or not a latent variable is associated with a biological mechanism.
Claim 15 recites the phrase “mapping a latent variable to a cell line if one or more features in the cell line sufficiently match the one or more features encoded in the latent variable” in lines 2-3 of the claim. The term “sufficiently” in claim 15 is a relative term which renders the claim indefinite. The term “sufficiently” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The Specification (see Para. [0051]) reiterates the claim language, disclosing that if the pattern associated with features in the cell line sufficiently match one or more features encoded in the latent variable, then a latent variable is mapped to a cell line. However, the Specification does not provide, for example, any parameters defining whether or not an encoded feature matches a cell line.
Claim 18 recites the phrase “an extent to which the target regulates one or more of the genes encoded in the latent variable” in lines 2-3 of the claim. There is insufficient antecedent basis for “one or more of the genes” in the claim, since there is no prior mention of this phrase in claim 16, to which this claim depends. This rejection can be overcome by amendment of claim 18 to recite “an extent to which the target regulates one or more genes encoded in the latent variable”. Claims 21-23 are also rejected due to their dependence from claim 18.
Claim 19 recites the phrase “annotating a respective latent variable with targets that sufficiently regulate one or more of the features encoded in the respective latent variable” in lines 2-3 of the claim. The term “sufficiently” in claim 19 is a relative term which renders the claim indefinite. The term “sufficiently” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. The Specification (see Para. [0057]) reiterates the claim language, disclosing that the target relevance module may additionally or alternatively be configured to annotate each latent variable with targets that sufficiently regulate one or more of the features it encodes. However, the Specification does not provide, for example, any parameters or values defining whether or not the target regulates features in a respective latent variable.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10, 15-23, and 26 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite both (1) mathematical concepts (mathematical relationships, formulas or equations, or mathematical calculations) and (2) mental processes, i.e., concepts performed in the human mind (including observations, evaluations, judgements or opinions) (see MPEP § 2106.04(a)).
Step 1:
In the instant application, claims 1-10 and 15-23 are directed towards a process, and claim 26 is directed towards a system, which falls into one of the categories of statutory subject matter (Step 1: YES).
Step 2A, Prong One:
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong One). The following instant claims recite limitations that equate to one or more categories of judicial exceptions:
Claim 1 recites a mathematical concept (i.e., encoding data) in “encoding data, which is comprised of one or more features, as one or more latent variables”; a mental process (i.e., evaluating latent variable to determine features) in “identifying the one or more features encoded in the latent variables”; a mental process (i.e., an evaluation of features in comparison to cell lines) in “mapping the one or more latent variables to cell lines based on the one or more features”; a mathematical concept and a mental process (i.e., scoring, ranking, or weighting targets to determine a relevance score, see Specification Para. [0056]) in “determining a relevance of one or more targets to each of one or more of the one or more latent variables”; and a mental process (i.e., comparing data) in “matching the one or more targets to the cell lines via the one or more latent variables”.
Claim 2 recites a mental process (i.e., a judgement of data to include) in “wherein the data comprises at least one of genomics data, transcriptomics data, methylation data, clinical data applied to genes, and biological mechanisms associated with multiple features”.
Claim 3 recites a mathematical concept in “encoding the data as the one or more latent variables using linear and non-linear machine learning models”.
Claim 4 recites a mathematical concept in “encoding the data as the one or more latent variables using a matrix factorization approach”.
Claim 5 recites a mathematical concept in “encoding the data as the one or more latent variables using a clustering algorithm”.
Claim 6 recites a mental process (i.e., comparing data to make an association) in “associating a biological mechanism with each latent variable based on the one or more features that the latent variable encodes”.
Claim 7 recites a mathematical concept (i.e., determining a measure of confidence the association between a latent variable and a biological mechanism; see Specification Para. [0048]) in “determining an extent to which each latent variable is associated with a respective biological mechanism”.
Claim 8 recites a mental process (i.e., removing a variable based on a comparison of data) in “removing from consideration the one or more latent variables not sufficiently associated with a biological mechanism”.
Claim 9 recites a mental process (i.e., an evaluation of whether a variable is correlated to a disease) in “assessing the one or more latent variables for relevance to a disease”.
Claim 10 recites a mental process (i.e., an evaluation of whether a mechanism is associated with disease) in “determining an extent to which a respective biological mechanism associated with a latent variable is associated with the disease”.
Claim 15 recites a mental process (i.e., a comparison of data to determine correlation) in “mapping a latent variable to a cell line if one or more features in the cell line sufficiently match the one or more features encoded in the latent variable”.
Claim 16 recites a mathematical concept (i.e., determining a mapping value as a measure of confidence or other similarity metrics; see Specification Para. [0055]) in “assigning a mapping value to each latent variable and cell line pair based on a relevance of the cell line to the latent variable”.
Claim 17 recites a mental process (i.e., an evaluation of how well the features in the cell line match the features in the latent variable) in “wherein the relevance of the cell line to the latent variable is based on an extent to which one or more features in the cell line matches the one or more features encoded in the latent variable”.
Claim 18 recites a mathematical concept (i.e., calculating a relevance score; see Specification Para. [0056]) in “determining a relevance score of each target to each latent variable based on an extent to which the target regulates one or more of the genes encoded in the latent variable”.
Claim 19 recites a mental process (i.e., an evaluation of whether a target is regulated based on encoded features in order to annotate a variable) in “annotating a respective latent variable with targets that sufficiently regulate one or more of the features encoded in the respective latent variable”.
Claim 20 recites a mental process (i.e., a comparison of data to match targets) in “matching targets to cell lines by comparing the mapping of the one or more latent variables to the cell lines and the relevance of the targets to the one or more latent variables”.
Claim 21 recites a mathematical concept (i.e., calculating a metric, for example by summing, multiplying or aggregating data; see Specification Para, [0060]) in “for each latent variable, determining a metric between each target and each cell line based on: the mapping value of the latent variable and the cell line; and the relevance score of the target and the latent variable”.
Claim 22 recites a mathematical concept (i.e., calculating a metric, as in claim 21) in “wherein the metric is also based on the relevance of the latent variable to a disease”.
Claim 26 recites a mathematical concept (i.e., encoding data) in “an encoder configured to encoded data as one or more latent variables”; a mental process (i.e., evaluating latent variable to determine features) in “an interpretation module configured to identify one or more features encoded in the one or more latent variables”; a mental process (i.e., an evaluation of latent variables in comparison to cell lines) in “a cell line mapping module configured to map the one or more latent variables to cell lines”; a mathematical concept and a mental process (i.e., scoring, ranking, or weighting targets to determine a relevance score, see Specification Para. [0056]) in “a target relevance module configured to determine a relevance of one or more targets to each of one or more of the one or more latent variables”; and a mental process (i.e., comparing data) in “a matching module configured to match the one or more targets to the cell lines via the one or more latent variables”.
These recitations are similar to the concepts of collecting information, and displaying certain results of the collection and analysis is Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)), and organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships.
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification, and are determined to be directed to mental processes that in the simplest embodiments are not too complex to practically perform in the human mind. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Specifically, the steps recited in independent claims 1 and 26 involve nothing more than encoding data, identifying features, mapping features to cell lines, correlating targets with latent variables, and matching targets to cell lines. The step of encoding data, under the BRI, is performed using mathematical operations. The instant specification (see Para. [0064]) discloses that the encoding may be performed using an autoencoder, matrix factorization, and/or clustering algorithms. Additionally, since there are no specifics in the methodology, the steps of identifying features, mapping features to cell lines, correlating targets with latent variables, and matching targets to cell lines, is something that under BRI, one could perform mentally. Therefore, the claimed steps are not further defined beyond something that reads on performing a calculation (encoding) using the computer as a tool, and merely analyzing the data to make determinations or correlations. As such, said steps are directed to judicial exceptions. The instant claims must therefore be examined further to determine whether they integrate the abstract idea into a practical application (Step 2A, Prong One: YES).
Step 2A, Prong Two:
In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP § 2106.04(d)). 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. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP § 2106.04(d)(I)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP § 2106.04(d)(III)). The following independent claims recite limitations that equate to additional elements:
Claim 1 recites a “computer-implemented” method.
Regarding the above cited limitations in claim 1 of (i) a computer-implemented method. This limitation requires only a generic computer component, which does not improve computer technology. Therefore, this limitation equates to mere instructions to implement an abstract idea on a generic computer, which the courts have established does not render an abstract idea eligible in Alice Corp. 573 U.S. at 223, 110 USPQ2d at 1983.
Additionally, none of the recited dependent claims recite additional elements which would integrate the judicial exception into a practical application. Specifically, claim 23 recites an extra-solution activity of outputting a list of cell lines, which is incidental to the primary process of matching cell lines to targets using the latent variables (see MPEP § 2106.05(g)). As such, claims 1-10, 15-23, and 26 are directed to an abstract idea (Step 2A, Prong Two: NO).
Step 2B:
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The instant independent claims recite the same additional elements described in Step 2A, Prong Two above.
Regarding the above cited limitations in claim 1 of (i) a computer-implemented method. This limitation equates to instructions to implement an abstract idea on a generic computing environment, which the courts have established does not provide an inventive concept (see MPEP § 2106.05(d) and MPEP § 2106.05(f)).
These additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the instant claims do not amount to significantly more than the judicial exception itself (Step 2B: NO). As such, claims 1-10, 15-23 and 26 are not patent eligible.
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 1-10, 15, 19-20, and 26 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Ronen et al. (Evaluation of colorectal cancer subtypes and cell lines using deep learning. Life Sci Alliance. 2(6):e201900517 (2019); published 12/2/2019; cited in the IDS dated 9/2/2025).
Regarding claim 1, Ronen et al. teaches a deep learning-based method to measure the similarity between tumors and disease models such as cancer cell lines. The findings are relevant to patient stratification and selection of cell lines for early-stage drug discovery pipelines, biomarker discovery and target identification (i.e., a computer-implemented method of selecting a cell line for an assay) (Abstract). Ronen et al. further teaches the development of an autoencoder-based method, called maui, that integrates data from multiomics experiments. They used it to infer latent factors that summarize molecular patterns, from data sets made up of RNA-seq, single nucleotide polymorphisms, and copy number variants (CNVs) (i.e., encoding data, which is comprised of one or more features, as one or more latent variables) (Pg. 10, Col. 1, Para. 3). Ronen et al. further teaches the association of latent factors with genomic features. The stacked variational autoencoder model described above computes latent factors. The architecture and depth of the neural network also makes it nontrivial to associate the input genomic features (gene expression, mutations, etc.) with the different latent factors. However, to make biological sense of the latent factors, it is necessary to make that association. To do that, they computed Spearman’s ρ for each latent factor with each input feature and called a latent factor associated with an input feature if P < 0.001 (i.e., identifying the one or more features encoded in the latent variables) (Pg. 14, Col. 1, Para. 4). Ronen et al. further teaches that they examined 54 cancer cell lines derived from tumors of the colon from the Cancer Cell Line Encyclopedia (CCLE). They used maui to infer latent factor values for the cell lines to permit their characterization using the same latent factors as the tumors. As cell lines may develop adaptations specific to cell culture, their molecular profiles are often more similar to other cell lines than to those of primary tumors. They compiled a list of nearest neighbors for each cell line and, then, counted how many of its nearest neighbors are cell lines (as opposed to tumors). They used Euclidean distance in the space defined by the latent factors to determine similarity and found that about half of the colorectal cancer (CRC) cell lines they investigated belong to a “cell line cluster,” meaning that most of their neighbors were other cell lines. They eliminated cell lines where this proportion is above half and found among them a mislabeled cell line: COLO741, which has been shown to derive from melanoma and not from CRC (in more recent versions of the CCLE annotations, this has been fixed). This finding indicates the merit of using this method to flag cell lines as poor models for tumors (i.e., mapping the one or more latent variables to cell lines based on the one or more features) (Pg. 7, Col. 1, Para. 1 – Col. 2, Para. 1). Ronen et al. further teaches a closer examination reveals the degree to which maui clusters resemble the consensus molecular subtypes (CMS) and where they diverge. The CMS labels for TCGA tumors are shown in Table 1. CMS1 is captured by cluster 2, CMS2 is split between clusters 3 and 5, CMS3 is captured by cluster 0, CMS4 overlaps with cluster 4, and cluster 1 is mixed. They also exhibit similar mutation rates among TP53, APC, KRAS, and BRAF, a set of genes commonly mutated in CRCs (i.e., determining a relevance of one or more targets to each of one or more of the one or more latent variables) (Pg. 3, Table 1; Pg. 6, Fig. 2; and Pg. 5, Col. 1, Para. 2). Ronen et al. further teaches that the CRC cell lines CL40, SW1417, and CW2 are deemed most suitable as models for CRC tumors. Using the same criteria, the cell line COLO320 ranked among the lowest. COLO320 lacks mutations in major CRC driver genes such as BRAF, KRAS, PIK3CA, and PTEN, and it is actually of a neuroendocrine origin. This very likely makes COLO320 a poor model for CRC (i.e., matching the one or more targets to the cell lines via the one or more latent variables) (Pg. 8, Col. 2, Para. 2).
Regarding claim 2, Ronen et al. teaches that the data includes data from tumors from The Cancer Genome Atlas (TCGA), gene expression data (mRNA), mutations, clinical metadata for the patients with tumors from the TCGA, and cancer cell line encyclopedia (CCLE) data. They considered only tumors (from TCGA) and cancer cell lines (from CCLE) that have complete data, that is all available measurements in all three assays: gene expression, SNVs and CNVs (i.e., wherein the data comprises at least one of genomics data, transcriptomics data, methylation data, clinical data applied to genes, and biological mechanisms associated with multiple features) (Pg. 11, Col. 2, Para. 1-3).
Regarding claim 3, Ronen et al. teaches that they fit an autoencoder using all TCGA samples, both with and without a (CMS) label, as well as colon-derived cancer cell lines (i.e., encoding the data as one or more latent variables using linear and non-linear machine learning models) (Pg. 11, Col. 2, Para. 7).
Regarding claim 4, Ronen et al. teaches that they used maui to extract latent factors from data on gene expression, point mutations and copy number alterations, and did the same thing using the linear matrix factorization approach, MOFA (i.e., encoding the data as the one or more latent variables using a matrix factorization approach) (Pg. 3, Col. 1, Para. 2 and Pg. 5, Col. 2, Para. 3).
Regarding claim 5, Ronen et al. teaches that they used maui to extract latent factors from data on gene expression, point mutations and copy number alterations, and did the same thing using the clustering approach iCluster+ (i.e., comprising encoding the data as the one or more latent variables using a clustering algorithm) (Pg. 3, Col. 1, Para. 2).
Regarding claim 6, Ronen et al. teaches that when they associated clinically relevant latent factors with gene ids, they observed an enrichment of pathways such as Wnt signaling and other APC-mediated processes known to play a role in CRC. One of the factors most significantly associated with survival is enriched in neuronal growth factor (NGF) signaling. NGF signaling, which controls neurogenesis, has been associated with aggressive colorectal tumors. Thus, in addition to exposing latent factor biomarkers with the prognostic value, maui sheds light on underlying biological processes that merit study in search for new drug targets (i.e., associating a biological mechanism with each latent variable based on the one or more features that the latent variable encodes) (Pg. 5, Col. 2, Para. 4).
Regarding claim 7, Ronen et al. teaches that pathway enrichment scores for genes associated with the latent factors which carry the prognostic value (have significant effects in Cox regression). Clinically relevant factors are factors with a coefficient in a fitted Cox model controlling for age, sex, and tumor stage, which are statistically significantly nonzero (Padj < 0.05). Examples of the mechanisms in Fig. 3C include signaling my EGFR, signaling by PDFT, and signaling by Wnt (i.e., determining an extent to which each latent variable is associated with a respective biological mechanism) (Pg. 7, Fig. 3C).
Regarding claim 8, Ronen et al. teaches that they first selected a subset of latent factors which are individually predictive of patient survival, calling those clinically relevant latent factors. This was carried out by fitting univariate Cox proportional hazards regression models, one per latent factor, and selecting ones for which the coefficient is nonzero with P < 0.05 (i.e., removing from consideration the one or more latent variables not sufficiently associated with a biological mechanism) (Pg. 3, Col. 2, Para. 3).
Regarding claims 9 and 10, Ronen et al. teaches that the superior computational efficiency of maui enables it to infer a large number of latent factors from multiomics data. This provides an opportunity to select those that are most interesting and might serve as biomarkers for colorectal cancer. To demonstrate this, they fitted Cox proportional hazards models, fitting one regression model for each factor, as above, selecting clinically relevant latent factors. Fig 3B shows the 95% confidence interval of coefficients for these latent factors, showing that high values for some of these latent factors are predictive of a poor prognosis (β > 0), whereas others are predictive of more favorable outcomes (β < 0). This lends a significant prognostic value to such latent factors (i.e., assessing the one or more latent variables for relevance to a disease and determining an extent to which a respective biological mechanism associated with a latent variable is associated with the disease) (Pg. 5, Col. 2, Para. 1 and Pg. 7, Fig. 3).
Regarding claim 15, Ronen et al. teaches that they artificially contaminated the data set by adding a random sample of 60 non-colon cell lines, assuming that these would be ill suited to the study of CRC tumors. They used this to repeat the exercise of counting the nearest neighboring cell lines. With the introduction of these true positives (non-colon cancer cell lines are considered true positives in the task of predicting which cell lines are poor models for CRC tumors), they found that more of the cell lines could be assigned to a “cell line cluster” in which most of their neighbors are other cell lines. For nearly all non-colon derived cell lines, the five nearest neighbors were other cell lines, whereas this was not the case for colon-derived cell lines. As a result, they designated cell lines whose five nearest neighbors are other cell lines, as less suitable for the study of colorectal tumors (“rejected”), as they more closely resemble other cell lines, even those derived from other tissues. They retain cell lines with at least one tumor among their five nearest neighbors as more likely to be suitable models (i.e., mapping a latent variable to a cell line if one or more features in the cell line sufficiently match the one or more features encoded in the latent variable) (Pg. 7, Col. 2, Para. 2 – Pg. 8, Col. 1, Para. 1).
Regarding claim 19, Ronen et al. teaches that the CMS scheme is incomplete because it is unable to classify many tumors. They used maui to assign the remaining non-CMS tumors to subtypes by repeating the clustering analysis while including both tumors that do not have a CMS designation and cancer cell lines. In this process, they included the cancer cell lines deemed to be suitable models to assign the cell lines to CRC subtypes. They present a novel subtyping scheme for CRC, which covers the whole TCGA cohort and includes tumors without a CMS designation. They also associate CRC cell lines with these subtypes. The tumors without a CMS label are distributed roughly according to the cluster size, as is to be expected for samples that lack a consensus definition, and each cluster is associated with at least one cell line. Cluster 2 (CMS1, MSI) is associated with the most cell lines; it comprises hypermutated tumors with low CIN. The cell lines that matched to cluster 2 show the same characteristics, another indication that latent factors capture patterns which are important to cancer biology. Cluster 2 has mutations in TP53, APC, KRAS, and BRAF genes (i.e., annotating a respective latent variable with targets that sufficiently regulate one or more of the features encoded in the respective latent variable) (Pg. 9, Col. 1, Para. 1 – Col. 2, Para. 1 and Pg. 5, Col. 1, Para. 2).
Regarding claim 20, Ronen et al. teaches the mapping of the one or more latent variables to the cell lines and the relevance of targets to the one or more latent variables as described for claim 1 above. Ronen et al. further teaches that the fact that a particular cell line more closely resembles non-colon-derived cancer cell lines than CRC tumors is an indication that it might not be suitable as a model for CRCs. That this method successfully rejects almost all known contaminants is another indication that rejected colon cancer cell lines are likely to be poor models for CRC as well. The CRC cell lines CL40, SW1417, and CW2 are deemed most suitable as models for CRC tumors. Using the same criteria, the cell line COLO320 ranked among the lowest. COLO320 lacks mutations in major CRC driver genes such as BRAF, KRAS, PIK3CA, and PTEN, and it is actually of a neuroendocrine origin. This very likely makes COLO320 a poor model for CRC (i.e., matching targets to cell lines by comparing the mapping of the one or more latent variables to the cell lines and the relevance of the targets to the one or more latent variables) (Pg. 8, Col. 2, Para. 1).
Regarding claim 26, Ronen et al. teaches the limitations of an encoder configured to encode data as one or more latent variables; an interpretation module configured to identify one or more features encoded in the one or more latent variables; a cell line mapping module configured to map the one or more latent variables to cell lines; a target relevance module configured to determine a relevance of one or more targets to each of one or more of the one or more latent variables; and a matching module configured to match the one or more targets to the cell lines via the one or more latent variables as described for claim 1 above.
Therefore, Ronen et al. teaches all the limitations in claims 1-10, 15, 19-20, and 26.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 16-18 and 21-23 are rejected under 35 U.S.C. 103 as being unpatentable over Ronen et al. as applied to claims 1-10, 15, 19-20, and 26 above, and further in view of Mo et al. (Pattern discovery and cancer gene identification in integrated cancer genomic data. Proc Natl Acad Sci USA. 110(11): 4245-50 (2013); published 2/21/2013).
Regarding claim 23, Ronen et al. teaches that the CRC cell lines CL40, SW1417, and CW2 are deemed most suitable as models for CRC tumors. Using the same criteria, the cell line COLO320 ranked among the lowest. COLO320 lacks mutations in major CRC driver genes such as BRAF, KRAS, PIK3CA, and PTEN, and it is actually of a neuroendocrine origin. This very likely makes COLO320 a poor model for CRC. The ranked cell lines are shown in Fig. 5 (i.e., outputting a ranked list of cell lines for each target based on the metrics) (Pg. 8, Col. 2, Para. 1 and Pg. 9, Fig. 5).
Ronen et al., as applied to claims 1-10, 15, 19-20, and 26 above, does not teach assigning a mapping value to each latent variable and cell line pair based on a relevance of the cell line to the latent variable (claim 16); wherein the relevance of the cell line to the latent variable is based on an extent to which one or more features in the cell line matches the one or more features encoded in the latent variable (claim 17); determining a relevance score of each target to each latent variable based on an extent to which the target regulates one or more of the genes encoded in the latent variable (claim 18); for each latent variable, determining a metric between each target and each cell line based on: the mapping value of the latent variable and the cell line; and the relevance score of the target and the latent variable (claim 21); wherein the metric is also based on the relevance of the latent variable to a disease (claim 22).
Regarding claim 16, Mo et al. teaches a framework for joint modeling of discrete and continuous variables that arise from integrated genomic, epigenomic, and transcriptomic profiling data. The core idea is motivated by the hypothesis that diverse molecular phenotypes can be predicted by a set of orthogonal latent variables that represent distinct molecular drivers, and thus can reveal tumor subgroups of biological and clinical importance. The method (iCluster+) can accurately group cell lines by their cell-of-origin for several cancer types, and precisely pinpoint their known and potential cancer driver genes (Abstract). Mo et al. further teaches the clustering of 729 cancer cell lines using iCluster+ to reveal 12 cell line clusters characterized by distinct mutational, copy number, and gene expression profiles (i.e., the latent variables). Known and candidate cancer genes associated with each integrated cluster (and thereby, the cell lines), determined by gene-wise Fisher’s combined probability test to identify genes with strongly concordant copy number and expression changes. The y axis is the
χ
2
=
-
2
(
log
P
c
n
+
log
P
e
x
p
)
statistic in each cluster where
P
c
n
,
P
e
x
p
denote
P
values for cluster-specific copy number and expression alterations, respectively. The most significant genes that show concordant amplification / overexpression (red) or loss / underexpression (blue) in the corresponding cluster are highlighted (i.e., assigning a mapping value to each latent variable and cell line pair based on a relevance of the cell line to the latent variable) (Pg. 4247, Fig. 2).
Regarding claim 17, Mo et al. teaches that the 12 cell line clusters have similar histological composition in each integrated cluster (i.e., one or more features in the cell line). For example, cluster 5 is associated with bone and CNS, whereas cluster 10 is associated with skin and CNS. The cell lines were cluster based on the latent variables representing the distinct mutational, copy number, and gene expression profiles (i.e., wherein the relevance of the cell line to the latent variable is based on an extent to which one or more features in the cell line matches the one or more features encoded in the latent variable) (Pg. 4247, Fig. 2B).
Regarding claim 18, Mo et al. teaches that the 12 cell line clusters characterized by distinct mutational, copy number, and gene expression profiles in Fig. 2B. Known and candidate cancer genes associated with each integrated cluster, determined by gene-wise Fisher’s combined probability test were calculated. For example, in Cluster 10, MITF, LRGUK, CREB3L2 were amplified/overexpressed (shown in red), while PPA1, CCDC6, and PNP were underexpressed (shown in blue) (i.e., determining a relevance score of each target to each latent variable based on an extent to which the target regulates one or more of the genes encoded in the latent variable) (Pg. 4247, Fig. 2).
Regarding claim 21, Mo et al. teaches that the gene-wise Fisher’s combined probability test to identify genes with strongly concordant copy number and expression changes was calculated for each integrated cluster (i.e., for each latent variable, determining a metric between each target and each cell line). The statistic is based on cluster-specific copy number and expression alterations (i.e., the latent variables) for an integrated cluster. The statistic also shows that the most significant genes that show concordant amplification/overexpression (red) or loss/underexpression (blue) in the corresponding cluster (i.e., based on the mapping value of the latent variable and the cell line; and based on the relevance score of the target and the latent variable) (Pg. 4247, Fig. 2).
Regarding claim 22, Mo et al. teaches that the 12 cell line clusters have similar histological composition in each integrated cluster. For example, cluster 4 is related to disease in breast tissue (i.e., wherein the metric is also based on the relevance of the latent variable to a disease) (Pg. 4247, Fig. 2B).
Therefore, regarding claims 16-18 and 21-23, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the deep learning based method for selecting cell lines for early-stage drug discovery pipelines of Ronen et al. with the analysis of Mo et al. because the method of Mo et al. uses latent variables to represent the underlying disease driving factors in a variety of different cancer genomes, thereby augmenting the analysis of colorectal cancer subtypes of Ronen et al. The analysis of Mo et al. across a variety of cancer genomes can also provide insights for developing targeted therapeutics and informative biomarkers (Mo et al., Pg. 4249, Col. 2, Para. 3 and Pg. 4250, Col. 1, Para. 2). One of ordinary skill in the art would be able to combine the teachings of Ronen et al. with Mo et al. with reasonable expectation of success due to the same nature of the problem to be solved, since both incorporate a method for linking cell lines to cancer associated genes. Therefore, regarding claims 16-18 and 21-23, the instant invention is prima facie obvious (MPEP § 2142).
Conclusion
No claims allowed.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DIANA P SANFORD whose telephone number is (571)272-6504. The examiner can normally be reached Mon-Fri 8am-5pm EST.
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, Karlheinz Skowronek can be reached at (571)272-9047. 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.
/D.P.S./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687