DETAILED ACTION
The Applicant’s response, received 20 October 2025 has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 1-8, 16-24, 32-34, and 39-44 are pending.
Claims 1-8, 16-24, 32-34, and 39-44 are rejected.
Priority
The effective filing date of the claimed invention is 15 October 2018.
Claim Objections
The objection to claim 17 in the Office action mailed 21 July 2025 is withdrawn in view of the amendment received 20 October 2025.
Claim Rejections - 35 USC § 112
The rejection of claims 35, 36, 37, and 38 under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, in the Office action mailed 21 July 2025 is withdrawn in view of the amendment received 20 October 2025.
The rejection of claims 6-16, 25-32, and 41 under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, in the Office action mailed 21 July 2025 is withdrawn in view of the amendment received 20 October 2025.
The rejection of claims 13 and 29 under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, in the Office action mailed 21 July 2025 is withdrawn in view of the amendment received 20 October 2025.
Claim Rejections - 35 USC § 101
The rejection under 35 U.S.C. 101 in the Office action mailed 21 July 2025 is maintained with modification in view of the amendment received 20 October 2025.
The rejection of claims 9-15, 25-31, and 35-38 in the Office action mailed 21 July 2025 is withdrawn in view of these claims having been cancelled in the amendment received 20 October 2025.
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 1-8, 16-24, 32-34, and 39-44 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea and a law of nature without significantly more. The claims recite: (a) mental processes, i.e., concepts performed in the human mind (e.g., observation, evaluation, judgement, opinion); (b) mathematical concepts (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (c) a law of nature (e.g., naturally occurring relationships).
Subject matter eligibility evaluation in accordance with MPEP 2106.
Eligibility Step 1: Step 1 of the eligibility analysis asks: Is the claim to a process, machine, manufacture or composition of matter?
Claims 1-8, 16, 33, and 39-44 are directed to a method (i.e., a process) for classifying microsatellite instability (MSI) of a tumor specimen; and claims 17-24, 32 and 34 are directed to a computing device (i.e., a machine or manufacture) for executing the method of independent claim 1.
Therefore, these claims are encompassed by the categories of statutory subject matter, and thus, satisfy the subject matter eligibility requirements under step 1.
[Step 1: YES]
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A: Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claim 1 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
training a machine learning model (i.e., mental processes and mathematical concepts) by:
converting the clinically-determined MSI statuses to dependent variables representing an MSI status classification for each cancer sample of the cancer samples (i.e., mental processes);
determining a proportion of unstable microsatellites for each cancer sample of the cancer samples (i.e., mental processes and mathematical concepts);
setting class weights to be inversely proportional to frequencies of MSI status categories in the training dataset to address different numbers of cancer samples across the MSI status categories (i.e., mental processes and mathematical concepts); and
training the machine learning model to predict the MSI status classification using the proportions of unstable microsatellites and the class weights that were set (i.e., mental processes and mathematical concepts);
generating a plurality of groups of reads by associating each read of the genomic sequencing reads with a respective microsatellite locus in the plurality of microsatellite loci based on characteristics of the respective microsatellite locus or characteristics of the genomic sequencing reads (i.e., mental processes);
excluding one or more of the microsatellite loci that fail to meet a threshold number of reads from the plurality of groups of reads (i.e., mental processes and mathematical concepts);
transforming the plurality of groups of reads into a corresponding plurality of feature vectors based at least in part on measured characteristics of repeat lengths in the plurality of microsatellite loci (i.e., mental processes and mathematical concepts);
processing the corresponding plurality of feature vectors using the trained machine learning model to generate a classification indicating a microsatellite instability status of the tumor specimen, the classification being one of microsatellite instability-high (MSI-H), microsatellite stable (MSS), or microsatellite equivocal (MSE) (i.e., mental processes and mathematical concepts);
generating a report based on the classification output and indicating (1) the microsatellite instability status of the tumor specimen and (2) one or more therapeutic options corresponding to the microsatellite instability status (i.e., mental processes).
Independent claim 17 recites a computing device comprising one or more processors configured to execute the judicial exceptions recited in independent claim 1.
Independent claims 1 and 17, and those claims dependent therefrom, further recite a law of nature by correlating genomic instability (i.e., microsatellite instability (MSI)) with a phenotype (i.e., cancer in a tumor specimen), and therefore recite a genotype-phenotype relationship (MPEP 2106.04(b)).
Dependent claims 2-8, 16, 18-24, 32-34, and 39-44 further recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas, as noted below.
Dependent claims 2 and 18 further recite:
the method of claim 33, wherein the plurality of MSI loci includes at least one locus listed in the table of genomic data (i.e., mental processes).
Dependent claims 3 and 19 further recite:
the method of claim 33, wherein the plurality of MSI loci includes all of the loci listed in the table of genomic data (i.e., mental processes).
Dependent claims 4 and 20 further recite:
the method of claim 33, wherein the plurality of MSI loci includes at least one locus on a chromosome listed in the table of genomic data (i.e., mental processes).
Dependent claims 5 and 21 further recite:
the method of claim 33, wherein each locus in the plurality of MSI loci is positioned on a chromosome listed in the table of genomic data (i.e., mental processes).
Dependent claims 6 and 22 further recite:
mapping reads containing at least 3-6 base pairs from the tumor specimen (i.e., mental processes and mathematical concepts), and
at least 3-6 base pairs from the matched-normal specimen (i.e., mental processes and mathematical concepts).
Dependent claims 7 and 23 further recite:
mapping reads containing at least 30-40 genomic sequencing reads from the tumor specimen (i.e., mental processes and mathematical concepts); and
at least 30-40 genomic sequencing reads from the matched-normal specimen (i.e., mental processes and mathematical concepts).
Dependent claims 8 and 24 further recite:
when mapping reads of the tumor specimen, determining if at least 20-30 microsatellites meet a coverage minimum (i.e., mental processes and mathematical concepts); and
when mapping reads of the matched-normal specimen, determining if at least 20-30 microsatellites meet a coverage minimum (i.e., mental processes and mathematical concepts).
Dependent claims 16 and 32 further recite:
wherein the one or more therapeutic options is selected from the group consisting of fluoropyrimidine, oxaliplatin, irinotecan, Ipilimumab, nivolumab, Pembrolizumab, an anti-PD-L1 antibody (e.g., durvalumab), an anti-CTLA antibody (e.g., tremelimumab), and checkpoint inhibitor (e.g., PD-1 inhibitor, PD-L1 inhibitor, PD-L2 inhibitor, CTLA-4 inhibitor) (i.e., mental processes).
Dependent claims 33 and 34 further recite:
accessing a table of genomic data (i.e., mental processes).
Dependent claim 39 further recites:
wherein the characteristics of the respective microsatellite locus is at least one of a genomic coordinate, a repeat unit structure, or a sequence pattern (i.e., mental processes).
Dependent claim 40 further recites:
wherein the characteristics of the genomic sequencing reads match or align to those of loci in overlapping genomic coordinates; contain repeat units that correspond to structure of the loci; or have flanking sequences that are aligned with the loci (i.e., mental processes).
Dependent claim 41 further recites:
selecting a plurality of tumor genomic sequencing reads from the plurality of genomic sequencing reads and a plurality of matched-normal genomic sequencing reads from the plurality of genomic sequencing reads, wherein the transforming of each group of the grouped reads into the feature vector corresponding to the respective microsatellite locus is based at least in part on comparing measured changes in respective repeat unit counts of the plurality of tumor genomic sequencing reads and the plurality of matched-normal genomic sequencing reads (i.e., mental processes and mathematical concepts).
Dependent claim 42 further recites:
comparing a distribution of repeat units among the groups of reads across loci to measure a deviation or an instability threshold in a repeat unit pattern (i.e., mental processes and mathematical concepts).
Dependent claim 43 further recites:
wherein the comparing uses a Kolmogorov-Smirnov test (i.e., mental processes and mathematical concepts).
Dependent claim 44 further recites:
wherein the transforming includes associating locus-specific characteristics, the locus-specific characteristics including at least one of (1) a flanking sequence; or (2) a repeat unit structure (i.e., mental processes).
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. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pen and paper (e.g., excluding one or more of the microsatellite loci that fail to meet a threshold number of reads from the plurality of groups of reads), and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas (e.g., using the trained machine learning model to generate a classification indicating a microsatellite instability status of the tumor specimen) are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind. Furthermore, a law of nature correlating a genotype-phenotype relationship is identified at Eligibility Step 2A Prong One.
Therefore, claims 1-8, 16-24, 32-34, and 39-44 recite an abstract idea and a law of nature.
[Step 2A Prong One: YES]
Eligibility 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); MPEP 2106.05(a-h)). 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 judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
Dependent claims 2-8, 16, 18-21, 30, 32, 33, 39-40, and 42-44 do not recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional elements in independent claims 1 and 17 include:
a computer (claim 1);
one or more processors (claim 1);
a computing device comprising one or more processors (claim 17);
receiving a training dataset comprising genomic sequencing data from cancer samples having clinically-determined MSI statuses (claims 1 and 17);
receiving a plurality of genomic sequencing reads corresponding to a tumor specimen and a matched-normal specimen, wherein the plurality of genomic sequencing reads include a minimum quantity of sequencing reads to map a number of reads at a plurality of microsatellite loci in the tumor specimen and the matched-normal specimen, and wherein each of the minimum quantity of sequencing reads includes a respective sequence of nucleotides spanning a plurality of base pairs (claims 1 and 17);
data output (from the trained machine learning model) (claims 1 and 17); and
generating digital data (claims 1 and 17).
The additional elements in dependent claims 22-24, 34, and 41 include:
one or more processors (claims 22-24, 34, and 41).
The additional elements of a computer and one or more processors (claim 1); a computing device comprising one or more processors (claim 17); one or more processors (claims 22-24, 34, and 41); and generating digital data (claims 1 and 17); invoke a computer and/or computer-related components merely as tools for use in the claimed process, and therefore are not an improvement to computer functionality itself, or an improvement to any other technology or technical field, and thus, do not integrate the judicial exceptions into a practical application (MPEP 2106.04(d)(1)).
The additional elements of receiving and/or inputting and/or outputting data (claims 1 and 17) are insignificant extra-solution activities that are used in the judicial exceptions recited by the claimed process (MPEP 2106.04(d)(1)), and therefore do not integrate the recited judicial exceptions into a practical application (MPEP 2106.05(g)).
Thus, the additionally recited elements merely invoke a computer and/or computer-related components as a tool, and/or amount to insignificant extra-solution activities, and as such, when all limitations in claims 1-8, 16-24, 32-34, and 39-44 have been considered as a whole, the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 1-8, 16-24, 32-34, and 39-44 are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
Dependent claims 2-8, 16, 18-21, 30, 32, 33, 39-40, and 42-44 do not recite any elements in addition to the judicial exception(s).
The additional elements recited in independent claims 1 and 17 and dependent claims 22-24, 34, and 41 are identified above, and carried over from Step 2A: Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at Step 2A: Prong Two was re-evaluated at Step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements were evaluated to determine whether any additional elements or combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional elements of a computer and one or more processors (claim 1); a computing device comprising one or more processors (claim 17); one or more processors (claims 22-24, 34, and 41); generating digital data (claims 1 and 17); and receiving and/or inputting and/or outputting data (claims 1 and 17); are conventional (see MPEP at 2106.05(b) and 2106.05(d)(II) regarding conventionality of computer components and computer processes).
Therefore, when taken alone, all additional elements in claims 1-8, 16-24, 32-34, and 39-44 do not amount to significantly more than the above-identified judicial exception(s). Even when evaluated as a combination, the additional elements fail to transform the exception(s) into a patent-eligible application of that exception. Thus, claims 1-8, 16-24, 32-34, and 39-44 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
Response to Arguments
The Applicant’s arguments/remarks received 20 October 2025 have been fully considered, but are not persuasive.
The Applicant states on page 20 (para. 5) of the Remarks that the claims are not directed to a law of nature, and further, even assuming, arguendo, that the claims are directed to an abstract idea, the claims are not directed to a judicial exception because they integrate the asserted abstract idea into a practical application, and further still, even assuming, arguendo, that the claims are directed to a judicial exception, the claims recite additional elements that amount to significantly more than any judicial exception.
These arguments are not persuasive, for the reasons provided in the above rejection and for the reasons of record as provided in previous responses to Applicant’s arguments (e.g., see the Office action mailed 21 July 2025). Responses to any newly presented arguments will be made of record below, as necessary.
The Applicant provides a discussion of applicable law on pages 20-22 of the Remarks, in particular with regard to the 2019 USPTO Revised Guidance (“Revised Guidance”), the USPTO’s August 2025 Subject Matter Eligibility Memo (“August 2025 Memo”), and Ex parte Desjardins, the USPTO’s Appeals Review Panel (“ARP”).
The Applicant’s foregoing discussion of applicable law is acknowledged, and it is noted that the cited guidance, i.e., the “Revised Guidance” and the “August 2025 Memo” as well as Ex parte Desjardins have been appropriately considered in view of the eligibility analysis guidance provided at MPEP 2106 with regard to the examination of the instant claims in the above rejection.
The Applicant reiterates the argument that the claims are not directed to a law of nature on pages 22-24 of the Remarks (previously argued in part at least in the arguments/remarks received 11 March 2025 at pages 27-28 and page 34), in general arguing that because the claims recite active manipulation and transformation of data through computational processes and are not passive observation of natural phenomenon, the claims therefore do not recite correlating genomic instability with cancer or any other phenotype.
This argument is not persuasive, for the reasons made of record, and reiterated here, i.e., at least for the reason that microsatellite instability (MSI) is a genetic hypermutator phenotype caused by deficient DNA mismatch repair (dMMR), which is strongly correlated with specific cancers (i.e., not cancer in general), most notably colorectal, endometrial, and gastric cancers, and further, MSI serves as a vital prognostic marker for better survival in early-stage tumors and also as a predictive biomarker for high responsiveness to immune checkpoint inhibitor therapies.
The Applicant reiterates the argument that the claims are not directed to a judicial exception under Prong Two of Step 2A (pages 24-26) because they integrate the asserted abstract idea into a practical application (previously argued in part at least in the arguments/remarks received 11 March 2025 at page 32, para. 2). The Applicant further attempts to analogize the instant claims to the recent Desjardins decision on page 26 (para. 2) of the Remarks, and states that like the claims in Desjardins, the present claims recite active training steps that configure a machine learning model with specific technical improvements to address a known problem in the field, and further states that the Desjardins decision recognized that a specific improvement to how a machine learning model operates constitutes patent-eligible subject matter, and further states that the present claims similarly recite specific improvements to the machine learning model training process: converting clinically-determined MSI statuses to dependent variables, determining proportions of unstable microsatellites, setting class weights inversely proportional to class frequencies to address class imbalance, and training the model using both the proportions and the class weights.
The arguments are not persuasive, at least in part for the reasons of record, i.e., the instants claims do not recite any additional elements that apply, rely on, or use the recited judicial exceptions in a manner that imposes a meaningful limit on the judicial exceptions, and further because the instant claims do not provide an improvement to computer functionality itself, or an improvement to another technology or technical field. With regard to the Applicant’s attempt to analogize the instant claims to the claims in Desjardins, these arguments are not persuasive at least because the fact patterns differ between the claims at issued in Desjardins and the instant claims, not least in that the “ARP” in Desjardins notes that the Federal Circuit held that the eligibility determination should turn on whether “the claims are directed to an improvement to computer functionality versus being directed to an abstract idea” (citing Enfish), prior to the “ARP” finding that the improvement to how the machine learning model operates allows artificial intelligence (AI) systems to use less of their storage capacity and enables reduced system complexity, as supported by the Specification. This fact pattern contrasts with the fact pattern of the training steps recited in the instant claims, which are steps of optimizing a classifier for the purpose of outputting an inference, i.e., the most probably class (of data) for a given input.
The Applicant reiterates the argument that the claims recite additional elements that amount to significantly more than any judicial exception at Step 2B (pages 26-28) because they include specific limitations that amount to an inventive concept (previously argued in part at least in the arguments/remarks received 11 March 2025 at page 34, bottom). The Applicant further states that the active training steps recited in the instant claims are not well-understood, routine, or conventional in the field (page 26, para., bottom) and that the specific combination of steps of the training process represents a non-conventional approach to training machine learning models for genomic classification, and it addresses the inherent class imbalance problem outlined in the specification.
These arguments are not persuasive, at least in part for the reasons of record, i.e., the instants claims do not recite any additional elements that amount to significantly more than the judicial exceptions, and therefore do not provide an inventive concept, and further because the limitations that recite the steps of training the model comprise the judicial exceptions identified at Eligibility Step 2A Prong One in the above rejection, and as such, the limitations that recite the steps of training the model are not limitations that are carried over to Step 2B for further analysis (i.e., they are not additional elements), and thus, the limitations that recite the steps of training the model cannot amount to significantly more than the recited judicial exceptions, and therefore cannot provide the inventive concept at Step 2B.
Claim Rejections - 35 USC § 103
The rejection of claims 1-13, 15-24, 26-29, and 31-44 under 35 U.S.C. 103 as being unpatentable over Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. in view of Xiao et al. in the Office action mailed 21 July 2025, is maintained with modification in view of the amendment received 20 October 2025, as noted below:
The rejection of claims 9-13, 15, 26-29, 31, and 35-38 is withdrawn in view of these claims having been cancelled in the amendment received 20 October 2025.
The rejection of claim 25 under 35 U.S.C. 103 as being unpatentable over Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. in view of Xiao et al. as applied to claims 1-13, 15-24, 26-29, and 31-44 above, and further in view of Zhang et al. in the Office action mailed 21 July 2025, is withdrawn in view of this claim having been cancelled in the amendment received 20 October 2025.
The rejection of claims 14 and 30 under 35 U.S.C. 103 as being unpatentable over Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. in view of Xiao et al. as applied to claims 1-13, 15-24, 26-29, and 31-44 above, and further in view of Jenkins et al. in the Office action mailed 21 July 2025, are withdrawn in view of these claims having been cancelled in the amendment received 20 October 2025.
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 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.
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.
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.
Claims 1-8, 16-24, 32-34, and 39-44 are rejected under 35 U.S.C. 103 as being unpatentable over Kautto et al. (Oncotarget, 2017, Vol. 8, No. 5, pp. 7452-7463; and Supplementary Material, pp. 1-11; as cited in the Office action mailed 21 July 2025) in view of Hause et al. (Nature Medicine. 2016. Vol. 22(11), pp. 1342-1350; Supplementary Material: Online Methods pp. 1-2; as cited in the Office action mailed 15 December 2022) in view of Cortes-Ciriano et al. (as cited in the Information Disclosure Statement received 31 March 2020) in view of Xiao et al. (International Publication Number WO 2018/175501 (27 September 2018), as cited in the Office action mailed 11 October 2024).
The Applicant’s amendment received 20 October 2025 is acknowledged. It is noted that the new amended limitations are substantially related to generally recognized core steps of training a classifier, e.g., data collection and preparation, data splitting, feature engineering and scaling, model selection, model training, hyperparameter tuning, evaluation, and deployment and monitoring. It is further noted that the rejection of record includes at least one reference showing the training of a classifier model (i.e., Cortes-Ciriano et al., as noted below) that at least suggests that the newly amended limitations would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, as discussed below.
Regarding claims 1 and 17, Kautto et al. shows:
a microsatellite instability (MSI) detection tool for classifying samples by MSI-status (Abstract);
detecting MSI status from next-generation sequencing (NGS) data (page 7453, col. 1, para. 3);
sequencing reads generated from matched normal and tumor patient samples (page 7459, col. 1, para. 1; and FIG. 1);
for each targeted loci, ensuring the reads are of sufficient sequence length, meet a minimum average base quality score, and cover the entire targeted locus (page 7459, col. 1, para. 2);
determining the starting position of the microsatellite motif within a read’s sequence and determining the total number of repeats by pattern matching the continuous motif pattern from the starting point (page 7459, col. 1, para. 2);
each locus is checked for a total number of supporting reads to ensure there is sufficient support to generate a statistically significant distribution (page 7459, col. 1, para. 3) for both the normal and tumor files, and loci with substandard coverage are discarded (page 7459, col. 2, para. 1); and
outputting an instability classification score ranging from 0.0 (entirely stable) to 2.0 (entirely unstable) (page 7459, col. 2, para. 3; and FIG. 1) with thresholds and scores for classifications of microsatellite instability high (MSI-H) or microsatellite stable (MSS) (FIG. 2).
Regarding claims 1 and 17, Kautto et al. does not show:
the steps of training a machine learning model;
using a trained machine learning model;
a threshold number for sufficient read coverage of microsatellite loci;
transforming the plurality of groups of reads into a corresponding plurality of feature vectors based at least in part on measured characteristics of repeat lengths in the plurality of microsatellite loci;
processing the corresponding plurality of feature vectors using the trained machine learning model to generate a classification output indicating a microsatellite instability status of the tumor specimen, the classification output being one of microsatellite instability-high (MSI-H), microsatellite stable (MSS), or microsatellite equivocal (MSE); and
generating a digital report based on the classification output and indicating
(1) the microsatellite instability status of the tumor specimen and
(2) one or more therapeutic options corresponding to the microsatellite instability status.
Regarding claims 1 and 17, Hause et al. shows:
that insufficient sequencing read depth precluded interrogation of all microsatellites for every specimen (p. 1342, col. 2, para. 4), and
sufficient coverage at a loci was considered ≥30 reads (p. 1342, col. 2, para. 4).
Regarding claims 1 and 17, Kautto et al. in view of Hause et al. does not show:
the steps of training a machine learning model;
using a trained machine learning model;
processing the corresponding plurality of feature vectors using the trained machine learning model to generate a classification output indicating a microsatellite instability status of the tumor specimen, the classification output being one of microsatellite instability-high (MSI-H), microsatellite stable (MSS), or microsatellite equivocal (MSE); and
generating a digital report based on the classification output and indicating
(1) the microsatellite instability status of the tumor specimen and
(2) one or more therapeutic options corresponding to the microsatellite instability status.
Regarding claims 1 and 17, Cortes-Ciriano et al. shows:
using training sets of data from the different MSI classes to train a model (e.g., Figure 5(e)-(f); and page 11, col. 1, paras. 4-5 (i.e., MSI status prediction model generation));
a classifier for the prediction of MSI status as MSI-H, MSS (microsatellite stable) and uncertain (i.e., equivocal) (page 9, FIG. 5(g));
a model training dataset (page 9, FIG. 5(e) & (f); and page 11, col. 1, para. 5);
encoding the number of MSI events and the presence or absence of MSI events in a vector (page 11, col. 1, para. 4);
obtaining the distribution of the allelic repeat length at each MS locus by collecting the lengths of all intra-read MS repeats mapped to that locus (page 10, col. 2, para. 4); and
using the MSI-based predictive model to classify patients into MSI-H and MSS categories (page 10, col. 1, para. 3);
Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. does not show generating a digital report based on the classification output and indicating (1) the microsatellite instability status of the tumor specimen and (2) one or more therapeutic options corresponding to the microsatellite instability status.
Xiao et al. shows:
methods and systems of molecular profiling of diseases such as cancer, wherein some embodiments can be used to identify treatments for the disease, and can further include biomarkers for immune checkpoint therapy, including microsatellite instability (Abstract).
Xiao et al. further shows classifying samples as MSI-H or microsatellite stable (MSS; page 222, para. [00479] and Table 17), and
further shows generating a molecular profiling report that can be computer generated and comprise the type of testing and results, and also potential therapies (p. 143, para. [00396], and at least Figures 27A-BR and Example 3).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. by incorporating a method step of excluding loci with an insufficient number of sequence reads as disclosed by Hause et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. with the Hause et al. because Hause et al. shows that insufficient sequencing read depth would preclude interrogation of microsatellite loci, and that ≥30 reads per locus would provide sufficient coverage, as discussed above. This modification would have had a reasonable expectation of success given that both Kautto et al. and Hause et al. disclose machine learning classifiers for MSI detection and classification.
It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. in view of Hause et al. by incorporating steps for encoding the number of MSI events and the presence or absence of MSI events in a vector, and training a classifier for MSI prediction as disclosed by Cortes-Ciriano et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. in view of Hause et al. with Cortes-Ciriano et al. because Cortes-Ciriano et al. shows using sequencing data to examine the molecular fingerprints of MSI in great detail (Abstract), including the distribution of allelic repeat length at each MS locus. This modification would have had a reasonable expectation of success given that both Kautto et al. in view of Hause et al. and Cortes-Ciriano et al. disclose using MSI-based predictive models to classify patient samples according to MSI status.
It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. by incorporating methods for generating a molecular profiling report that can be computer generated and comprise the type of testing and results, and also potential therapies as disclosed by Xiao et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. with Xiao et al. because Xiao et al. shows molecular profiling of diseases such as cancer, wherein some embodiments can be used to identify treatments for the disease, and can further include biomarkers for immune checkpoint therapy, including microsatellite instability (Abstract). This modification would have had a reasonable expectation of success given that both Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. and Xiao et al. disclose classifying samples as MSI-H or microsatellite stable (MSS).
Regarding claim 41, Kautto et al. further shows the counts at each locus are normalized separately for the normal and tumor sample and the stepwise difference between each distribution is calculated, and then the average of all difference scores is taken to generate the instability score for the normal-tumor sample pair (FIG. 1).
Regarding claims 2-8, 16, 18-24, and 32-34, 39, 40, and 42-44, Kautto et al. further does not show:
wherein the plurality of MSI loci includes at least one locus listed in the table of genomic data (claims 2 and 18);
wherein the plurality of MSI loci includes all of the loci listed in the table of genomic data (claims 3 and 19);
wherein the plurality of MSI loci includes at least one locus on a chromosome listed in the table of genomic data (claims 4 and 20);
wherein each locus in the plurality of MSI loci is positioned on a chromosome listed in the table of genomic data (claims 5 and 21);
wherein mapping the genomic sequencing data comprises mapping reads containing at least 3-6 base pairs from the tumor sample, and at least 3-6 base pairs from the matched-normal sample (claims 6 and 22);
wherein mapping the genomic sequencing reads comprises mapping at least 30-40 genomic sequencing reads from the tumor sample; and at least 30-40 genomic sequencing reads from the matched-normal sample (claims 7 and 23);
when mapping the genomic sequencing reads of the tumor sample, determining if at least 20-30 microsatellites meet a coverage minimum; and when mapping the genomic sequencing reads of the matched-normal sample, determining if at least 20-30 microsatellites meet a coverage minimum (claims 8 and 24);
wherein the therapeutic is selected from the group consisting of fluoropyrimidine, oxaliplatin, irinotecan, Ipilimumab, nivolumab, Pembrolizumab, an anti-PD-L1 antibody (e.g., durvalumab), an anti-CTLA antibody (e.g., tremelimumab), and checkpoint inhibitor (e.g., PD-1 inhibitor, PD-L1 inhibitor, PD-L2 inhibitor, CTLA-4 inhibitor) (claims 16 and 32);
accessing a table of genomic data (claims 33 and 34);
wherein the characteristics of the respective microsatellite locus is at least one of a genomic coordinate, a repeat unit structure, or a sequence pattern (claim 39);
wherein the characteristics of the genomic sequencing reads match or align to those of loci in overlapping genomic coordinates; contain repeat units that correspond to structure of the loci; or have flanking sequences that are aligned with the loci (claim 40);
comparing a distribution of repeat units among the groups of reads across loci to measure a deviation or an instability threshold in a repeat unit pattern (claim 42);
wherein the comparing uses a Kolmogorov-Smirnov test (claim 43); and
wherein the transforming includes associating locus-specific characteristics, the locus-specific characteristics including at least one of (1) a flanking sequence; or (2) a repeat unit structure (claim 44).
Regarding claims 6 and 22, Hause et al. further shows evaluating MSI using exome-sequencing data wherein the size of the instability event in base pairs (bp) is at least 3 and less than 6 base pairs (FIG. 1(d)).
Regarding claims 7 and 23, Hause et al. further shows that sufficient coverage in both tumor and normal tissue for instability status to be inferred is ≥30 reads (page 1342, col. 2, para. 4).
Regarding claims 8 and 24, Hause et al. further shows that 223,082 microsatellite loci had sufficient read coverage (page 1342, col. 2, para. 4).
Therefore, it would have been further prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. by incorporating the method of evaluating MSI using exome-sequencing data as disclosed by Hause et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. with the Hause et al. because Hause et al. shows identifying microsatellite loci that are disproportionately located in intronic and coding regions compared to distributions observed genome-wide (FIG. 1(d)), and aligned reads from exome files that show the number of microsatellites with instability events that are at least 3-6 based pairs (FIG. 1(a) and (d)), as discussed above. This modification would have had a reasonable expectation of success given that both Kautto et al. and Hause et al. disclose machine learning classifiers for MSI detection and classification.
Regarding claims 2, 3, 4, 5, and 18, 19, 20, 21, 33, and 34, Cortes-Ciriano et al. further shows the genomic coordinates indicating the location of the MSI repeats in the hg19 assembly of the human genome (FIG. 4 (a-b)).
Regarding claim 39, Cortes-Ciriano et al. further shows the genomic coordinates indicating the location of the MSI repeats in the hg19 assembly of the human genome (FIG. 4 (a-b)).
Regarding claim 40, Cortes-Ciriano et al. further shows sequencing reads spanning each MS repeat and at least 2 base pairs at each flanking side (FIG. 1(a)); and identifying MS loci in sequence reads using flanking sequences (page 10, col. 2, para. 2).
Regarding claims 42 and 43, Cortes-Ciriano et al. further shows the distribution of MS lengths from tumor and matched-normal genomes at each locus was compared using the Kolmogorov-Smirnov statistic (page 10, col. 2, para. 4).
Regarding claim 44, Cortes-Ciriano et al. further shows sequencing reads spanning each MS repeat and at least 2 base pairs at each flanking side (FIG. 1(a)); and identifying MS loci in sequence reads using flanking sequences (page 10, col. 2, para. 2).
Therefore, it would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. in view of Hause et al. by incorporating the genomic coordinates for the microsatellite repeats that are known to be recurrently altered by MSI, as disclosed by Cortes-Ciriano et al. (e.g., FIG. 4), and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. in view of Hause et al. with Cortes-Ciriano et al. because Cortes-Ciriano et al. shows the genomic coordinates indicating the location of the MSI repeats in the hg19 assembly of the human genome (FIG. 4 (a-b)) and after filtering reads with low mapping quality, the distribution of MS lengths from tumor and matched-normal genomes at each locus was compared using the Kolmogorov-Smirnov statistic with a minimum of 5 tumor and 5 matched normal reads (page 10, col. 2, para. 4). This modification would have had a reasonable expectation of success given that both Kautto et al. in view of Hause et al. and Cortes-Ciriano et al. disclose using MSI-based predictive models to classify patient samples according to MSI status.
Regarding claims 16 and 32, Xiao et al. further shows identifying potential benefit from an immune checkpoint inhibitor therapy when the biological sample is MSI-H, including without limitation ipilimumab, nivolumab, pembrolizumab, or durvalumab (par. [0393]).
Therefore, it would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the methods shown by Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. by incorporating a method for identifying at least one therapy of potential benefit for an individual with cancer, using a molecular profile generated by performing the method for determining MSI, as disclosed by Xiao et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. with Xiao et al. because Xiao et al. shows identifying potential benefit from an immune checkpoint inhibitor therapy when the biological sample is MSI-H, including without limitation ipilimumab, nivolumab, pembrolizumab, or durvalumab (par. [0393]). This modification would have had a reasonable expectation of success given that both Kautto et al. in view of Hause et al. in view of Cortes-Ciriano et al. and Xiao et al. disclose classifying samples as MSI-H or microsatellite stable (MSS).
Thus, the claims are prima facie obvious.
Response to Arguments
The Applicant’s arguments/remarks received 20 October 2025 have been fully considered, but are not persuasive.
The Applicant states on page 28 of the Remarks that the combination of Kuatto, Hause, Cortes-Cirianao, and Xiao fails to teach or suggest each and every element of the claims. The Applicant highlights the newly amended limitations to claims 1 and 17, and further states (page 29, para. 1) that none of Kuatto, Hause, Cortes-Cirianao, and Xiao teaches or suggests at least this combination of elements. The Applicant further states (para. 2) that the Office action mailed 21 July 2025 (page 50) acknowledges that neither Kuatto nor Hause disclose using a trained machine learning model, and that Xiao is silent on a machine learning model, let alone training a machine learning model as recited in amended claims 1 and 17, and further states (para. 3) that Cortes-Ciriano, either alone or in combination with Kuatto, Hause, and Xiao, fails to correct these deficiencies. The Applicant further states (para. 4) that while Cortes-Ciriano generally discloses training data and random forest classifier to distinguish between MSI-H and MSS cases, the reference does not train its classifier using the claimed steps of amended claims 1 and 17 (para. 5, and page 30, para. 1), and therefore the proposed combination of Kuatto, Hause, Cortes-Ciriano, and Xiao fails to teach or suggest each and every elements of these claims.
These arguments are not persuasive, because the newly amended limitations reciting steps of training a classifier model in claims 1 and 17 comprise steps that would be understood by one of skill in the art before the effective filing date of the claimed invention to be steps that are generally performed in training a classifier to predict MSI status, in view of conventional steps of training a model (e.g., data collection and preparation, data splitting, feature engineering and scaling, model selection, model training, hyperparameter tuning, evaluation, and deployment and monitoring) and further in view of the Cotes-Ciriano reference disclosing using training sets of data from the different MSI classes to train a model (e.g., Figure 5(e)-(f); and page 11, col. 1, paras. 4-5 (i.e., MSI status prediction model generation)) and using the trained classifier model for the prediction of MSI status as MSI-H, MSS (microsatellite stable) and uncertain (i.e., equivocal) (page 9, FIG. 5(g)). Thus, Cortes-Ciriano et al. at least suggests that the newly amended limitations would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, and therefore the combination of references used in the above rejection show that the claims would have been prima facie obvious.
Conclusion
No claims are allowed.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN W. BAILEY whose telephone number is (571)272-8170. The examiner can normally be reached Mon - Fri. 1000 - 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, 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.
/S.W.B./Examiner, Art Unit 1687
/Joseph Woitach/Primary Examiner, Art Unit 1687