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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on has been entered.
Status of Claims
This action is in reply to the claims filed on 07 May 2026. Claims 1-7, 12-18, 23-26, and 28-31 were amended. Claims 27 and 32 were canceled. Claim 33 was newly added. Claims 1-26, 28-31, and 33 currently pending and have been examined.
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 1-26, 28-31, and 33 are rejected under 35 USC § 101
Step 1: Is the claim to a process, machine, manufacture, or composition of matter?
Claims 1-26, 28-31, and 33 fall within one or more statutory categories. Claims 1-11 and 28-31 fall within the category of a process. Claims 12-26 and 33 fall within the category of a machine.
Step 2A Prong One: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Claims 1-26, 28-31, and 33 recite an abstract idea. Representative claim 1 recites:
receiving longitudinal clinical data collected over a plurality of time points for at least one patient having a disease, the clinical data including treatment and/or exposure information and clinical endpoints;
receiving single-cell multiomic immune state data for the at least one patient, the single-cell multiomic immune state data comprising, for each of a plurality of immune cells multiomic measurements including: transcriptomic expression data, protein expression data, T cell receptor sequence data, and B cell receptor sequence data;
constructing a high dimensional immune state representation for the plurality of immune cells by integrating the transcriptomic expression data, the protein expression data, the T cell receptor sequence data, and the B cell receptor sequence data;
based on the high dimensional immune state representation, … learn a graph-based representation of longitudinal immune trajectories that characterize temporal transitions between immune states across the plurality of time points;
inferring intermediate immune states from transitions between immune states represented in the learned graph-based representation of longitudinal immune trajectories, at time points for which clinical outcome data is unavailable;
associating the inferred intermediate immune states with clinical endpoints; and
identifying at least one subset of immune cells exhibiting evolving molecular changes based on the learned graph-based representation of longitudinal immune trajectories and the inferred intermediate immune states.
Therefore, the claim as a whole is directed to “mapping clinical data to immune state data,” which is an abstract idea because it is a method of organizing human activity. “Mapping clinical data to immune state data” is considered to be a method of organizing human activity because it is an example of managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions). The broadest reasonable interpretation of the claims includes the treatment of patients, an activity involving healthcare practitioners and patients.
Step 2A Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application?
This judicial exception is not integrated into a practical application. In particular, claim 1 recites the following additional element(s):
the method is automatically performed with at least one processor connected to at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations, [comprising the above described abstract idea];
using one or more machine learning models to [learn the graph-based representation].
The additional elements individually or in combination do not integrate the exception into a practical application. This additional element merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Claim 1 is directed to an abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
Claim 1 does not include additional elements, considered individually or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element(s), individually and in combination, merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). Accordingly, claim 1 is ineligible.
Dependent claim 2 recites the method of claim 1, further including:
isolating includes developing RNA/protein heatmaps per cell subset.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 2 is considered to be ineligible.
Dependent claim 3 recites the method of claim 1, further including:
mapping longitudinal clinical data to the longitudinal immune trajectories using one or more machine learning models comprising at least a reinforcement learning (RL) and/or deep learning model configured to evaluate the high-dimensional state representation of the immune trajectories against known clinical endpoints,
wherein the mapping includes automated cell type prediction.
The additional elements present in this claim merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 3 is ineligible.
Dependent claim 4 recites the method of claim 3, wherein:
the mapping further includes reducing dimensionality, extracting features, correcting for multiomic batch effect and removing multiomic based multiplets.
The additional elements present in this claim merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 4 is ineligible.
Dependent claim 5 recites the method of claim 1, further including:
separating sub-cell types.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 5 is considered to be ineligible.
Dependent claim 6 recites the method of claim 3, wherein:
the mapping includes cell type-specific matching of clinical signatures with perturbation signatures, including mapping signatures against large scale CRISPR perturbations.
The additional elements present in this claim merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Accordingly, claim 6 is ineligible.
Dependent claim 7 recites the method of claim 3, wherein:
mapping includes signature mapping to clinical covariates.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 7 is considered to be ineligible.
Dependent claim 8 recites the method of claim 7, wherein:
determining association of complex molecular phenotypes with clinical covariates.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 8 is considered to be ineligible.
Dependent claim 9 recites the method of claim 1, wherein:
validating annotation to group clones of a specific cell type / cell type groups by their trajectories over time.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 9 is considered to be ineligible.
Dependent claim 10 recites the method of claim 8, wherein:
enriching trajectories for response and/or treatment clinical covariates.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 10 is considered to be ineligible.
Dependent claim 11 recites the method of claim 9, wherein:
enriching trajectories in specific molecular phenotypes of interest.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 11 is considered to be ineligible.
Claims 12-22 are parallel in nature to claims 1-11. Accordingly claims 12-22 are rejected as being directed towards ineligible subject matter based upon the same analysis above.
Dependent claim 23 recites the system of claim 12, wherein:
the operations further include inferring secondary immune endpoints trained via inverse reinforcement learning to infer over learned longitudinal immune-state trajectories, and generating a prognosis over a probabilistic prognosis graph.
The additional elements present in this claim merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Therefore, claim 23 is considered to be ineligible.
Dependent claim 24 recites the system of claim 23, wherein:
said reinforcement learning uses a multi-arm bandit or variational autoencoder (VAE) architecture.
The additional elements present in this claim merely recites the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely includes instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). These types of additional elements are not enough to integrate the abstract idea into a practical application, nor do they amount to significantly more than the judicial exception. Therefore, claim 24 is considered to be ineligible.
Dependent claim 25 recites the system of claim 14, wherein:
said mapping includes batch effect correction and multiplet removal across multiomic modalities.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 25 is considered to be ineligible.
Dependent claim 26 recites the system of claim 12, wherein:
the operations further include isolating at least one distinct subset validated by RNA/protein heatmaps per cell subset.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 26 is considered to be ineligible.
Claims 28-31 are parallel in nature to claims 23-26. Accordingly claims 28-31 are rejected as being directed towards ineligible subject matter based upon the same analysis above.
Dependent claim 33 recites the system of claim 12, wherein:
outputting a disease prognosis for the at least one patient.
This merely further limits the abstract idea of claim 1 discussed above and does not provide further additional elements. Therefore, claim 33 is considered to be ineligible.
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.
Claims 1-3, 5, 7-14, 16, 18-22, 26, 31 and 33 are rejected under 35 U.S.C. 103 as being unpatentable over Owen et al. (U.S. 2024/0282453), hereinafter “Owen,” in view of Solomon et al. (U.S. 2021/0057107), hereinafter “Solomon.”
Regarding claim 1, Owen discloses a method automatically performed by at least one processor connected to at least one memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations, the method comprising:
receiving longitudinal clinical data collected over a plurality of time points for at least one patient having a disease (See Owen [0326] Multiple samples may be obtained from a subject to monitor the effects of the treatment over time. [0251] the system can receive multiple different sets of records and apply classifiers to connect the data sets based on phenotypes.), the clinical data including treatment and/or exposure information and clinical endpoints (See Owen [0326] samples may be obtained from a subject during a treatment or a treatment regime. Multiple samples may be obtained from a subject to monitor the effects of the treatment over time. The sample may be taken from a subject known or suspected of having a disease or disorder for which a definitive positive or negative diagnosis is not available via clinical tests. The sample may be taken from a subject suspected of having a disease or disorder. The sample may be taken from a subject experiencing unexplained symptoms, such as fatigue, nausea, weight loss, aches and pains, weakness, or bleeding. The sample may be taken from a subject having explained symptoms. [0327] the progression of a disease can be tracked before treatment, after treatment, or during the course of treatment, to determine the treatment's effectiveness.);
receiving single-cell multiomic immune state data for the at least one patient (See Owen [0252] The data used by the system can include nucleic acid sequencing data, transcriptome data, genome data, epigenome data, proteome data, metabolome data, virome data, metabolome data, methylome data, lipidomic data, lineage-ome data, nucleosomal occupancy data, a genetic variant, a gene fusion, an insertion or deletion (indel), or any combination thereof. This means the data is multi-omic. [0318] the system can perform analysis of data sets including, for example, mRNA gene expression or transcriptome data, DNA genomic data, proteomic data, metabolomic data, other types of “-omic” data, or a combination thereof. [0327] a sample can be taken at a first time point and assayed, and then another sample can be taken at a subsequent time point and assayed. See also [0333].), the single-cell multiomic immune state data comprising, for each of a plurality of immune cells multiomic measurements including: transcriptomic expression data (See Owen [0318] the system can perform analysis of data sets including, for example, mRNA gene expression or transcriptome data, DNA genomic data, proteomic data, metabolomic data, other types of “-omic” data, or a combination thereof.), protein expression data (See Owen [0318] the system can perform analysis of data sets including, for example, mRNA gene expression or transcriptome data, DNA genomic data, proteomic data, metabolomic data, other types of “-omic” data, or a combination thereof.), T cell receptor sequence data, and B cell receptor sequence data (See Owen [0277] the records include RNA transcription information (i.e. RNA marker data). [0336] the records can include T Cell and B Cell categories included in the data (i.e. T Cell and B Cell receptor marker data). [0186] the system can measure B cell receptor signaling. [0222] the system can perform linear regression relating individual cell types including B cells and T Cells. [0254] the records can be associated with purified cell populations.);
constructing a high dimensional immune state representation for the plurality of immune cells by integrating the transcriptomic expression data, the protein expression data, the T cell receptor sequence data, and the B cell receptor sequence data (See Owen [0252] The records used by the system may comprise nucleic acid sequencing data, transcriptome data, genome data, epigenome data, proteome data, metabolome data, virome data, metabolome data, methylome data, lipidomic data, lineage-ome data, nucleosomal occupancy data, a genetic variant, a gene fusion, an insertion or deletion (indel), or any combination thereof. This meets the broadest reasonable interpretation of “high-dimensional immune state representation.”);
based on the high dimensional immune state representation, using one or more machine learning models to learn a graph-based representation of longitudinal immune trajectories that characterize temporal transitions between immune states across the plurality of time points (See Owen [0249] the disclosed data analytical techniques such as machine learning enable proper correlation between genetic records and phenotypes. [0406] a difference in the feature sets (e.g., quantitative measures of a panel of condition-associated genomic loci) determined between the two or more time points may be indicative of one or more clinical indications. [0269] the system can use graphical exploratory analysis.);
inferring … immune states from transitions between immune states represented in the learned graph-based representation of longitudinal immune trajectories, at time points for which clinical outcome data is unavailable (See Owen Fig. 1 and [0251] the system trains a classifier using records of gene expression data with known phenotypes in order to apply that classifier to records without a known phenotype. [00256]-[0258] the phenotypes are disease states. Therefore the system is using the classifier to infer clinical outcomes where no outcome was already known.);
associating the inferred … immune states with clinical endpoints (See Solomon [0202] the system can use machine learning to predict outcome, survival, and disease progression milestones and disease progression timelines. This meets the broadest reasonable interpretation of inferring intermediate immune states and connects to them to clinical endpoints.); and
identifying at least one subset of immune cells exhibiting evolving molecular changes based on the learned graph-based representation of longitudinal immune trajectories and the inferred … immune states (See Owen [0274] Differential expression (DE) analysis and WGCNA may then be carried out on data sets. [0269] Significant genes within each study may be filtered to retain DE genes. [0353] the system can identify receptor-ligand interactions and subsequent signaling pathways. [0185] the system can identify those molecules and pathways highly associated with disease. [0249] the disclosed data analytical techniques enable proper correlation between genetic records and phenotypes. [0287] the system can determine the most important genes such as interferon signaling, pattern recognition receptor signaling, and control of survival and proliferation.).
Owen does not disclose:
[the inferred immune states are] intermediate immune states.
Solomon teaches:
[the inferred immune states are] intermediate immune states (See Solomon [0202] the system can use machine learning to predict outcome, survival, and disease progression milestones and disease progression timelines. This meets the broadest reasonable interpretation of inferring intermediate immune states and connects to them to clinical endpoints. [0124] the trained models may impute genetic information differently due to changes the underlying disease or changes in the disease state, immune state, or condition, which improve the overall accuracy of the results.).
The system of Solomon is applicable to the disclosure of Owen as they both share characteristics and capabilities, namely, they are directed to using machine learning for multiomic analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Owen to include intermediate milestone analysis as taught by Solomon. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Owen in order to improve the accuracy with which a physician can select an immunotherapy treatment for a specific patient, in which the selected treatment is more likely than not to be effective, and according to which the patient outcomes can be monitored to quickly determine if the treatment is having a beneficial effect on disease progression or if an alternative treatment might be indicated instead (see Solomon [0009]).
Regarding claim 2, Owen in view of Solomon discloses the method of claim 1 as discussed above. Owen further discloses a method, including:
developing RNA/protein heatmaps per immune cell subset (See Owen [0345] the system can analyze datasets using DE analysis (as shown by a differential expression heatmap).).
Regarding claim 3, Owen in view of Solomon discloses the method of claim 1 as discussed above. Owen further discloses a method, including:
mapping longitudinal clinical data to the longitudinal immune trajectories (See Owen [0249] the disclosed data analytical techniques enable proper correlation between genetic records and phenotypes. [0251] the system can use a classifier to map third record set to a first or second record set with a known phenotype.) using one or more machine learning models comprising at least a reinforcement learning (RL) and/or deep learning model (See Owen [0058] the machine learning used by the system can include a deep learning algorithm.) configured to evaluate the high-dimensional state representation of the immune trajectories against known clinical endpoints (See Owen [0249] the disclosed data analytical techniques enable proper correlation between genetic records and phenotypes. [0251] the system can use a classifier to map third record set to a first or second record set with a known phenotype. [0252] The records used by the system may comprise nucleic acid sequencing data, transcriptome data, genome data, epigenome data, proteome data, metabolome data, virome data, metabolome data, methylome data, lipidomic data, lineage-ome data, nucleosomal occupancy data, a genetic variant, a gene fusion, an insertion or deletion (indel), or any combination thereof. This meets the broadest reasonable interpretation of “high-dimensional immune state representation.”),
wherein the mapping includes automated cell type prediction (See Owen [0347] the system has tools for identifying cell types through iterative search. See also [0222].).
Regarding claim 5, Owen in view of Solomon discloses the method of claim 1 as discussed above. Owen further discloses a method, including:
separating sub-cell types (See Owen [0357] the system can categorize cell sub-categories.).
Regarding claim 7, Owen in view of Solomon discloses the method of claim 3 as discussed above. Owen further discloses a method, wherein:
mapping includes signature mapping to clinical covariates (See Owen [0360] the system has a tool for mapping molecular signature to potential drugs for therapeutic intervention.).
Regarding claim 8, Owen in view of Solomon discloses the method of claim 7 as discussed above. Owen further discloses a method, including:
determining association of complex molecular phenotypes with clinical covariates (See Owen [0185] the system can identify those molecules and pathways highly associated with disease. [0249] the disclosed data analytical techniques enable proper correlation between genetic records and phenotypes. [0287] the system can determine the most important genes such as interferon signaling, pattern recognition receptor signaling, and control of survival and proliferation.).
Regarding claim 9, Owen in view of Solomon discloses the method of claim 1 as discussed above. Owen further discloses a method, including:
validating annotation to group clones of a specific cell type / cell type groups by their trajectories over time (See Owen [0345] expressed genes are annotated using publicly available databases and then cross-referenced using purified single-cell microarray datasets and RNAseq experiments. [0368] samples used to train the classifier can be samples and associated datasets and outputs obtained at a plurality of different time points from the same subject as part of a longitudinal monitoring of a subject before, during, and after a course of treatment for one or more conditions of the subject. [0404] the feature sets, including conditioned-associated genomic loci, can be analyzed and assessed for a duration of time.).
Regarding claim 10, Owen in view of Solomon discloses the method of claim 8 as discussed above. Owen further discloses a method, including:
enriching trajectories for response and/or treatment clinical covariates (See Owen [0258] the system uses Gene Set Enrichment Analysis for enrichment of phenotype-associated cell-specific modules. [0345] analysis is used to determine enriched categories of interest. Enriched categories are cross-examined with GO and KEGG terms to derive key insights for further analysis.).
Regarding claim 11, Owen in view of Solomon discloses the method of claim 9 as discussed above. Owen further discloses a method, including:
enriching trajectories in specific molecular phenotypes of interest (See Owen [0258] the system uses Gene Set Enrichment Analysis for enrichment of phenotype-associated cell-specific modules. [0345] analysis is used to determine enriched categories of interest. Enriched categories are cross-examined with GO and KEGG terms to derive key insights for further analysis.).
Regarding claim 12-14, 16, and 18-22, Owen in view of Solomon discloses the method of claims 1-3, 5, and 7-11 as discussed above. Claims 12-14, 16, and 18-22 recite a system that performs a method substantially similar to the method of claims 1-3, 5, and 7-11. Accordingly, claims 12-14, 16, and 18-22 are rejected based on the same analysis.
Regarding claim 26, Owen in view of Solomon discloses the system of claim 12 as discussed above. Owen further discloses a system, including:
the operations further include isolating at least one distinct subset validated by RNA/protein heatmaps per cell subset (See Owen [0345] the system can analyze datasets using DE analysis (as shown by a differential expression heatmap).).
Regarding claim 31, Owen in view of Solomon discloses the system of claim 26 as discussed above. Claim 31 recites a method that is substantially similar to the method performed by the system of claim 26. Accordingly, claim 31 is rejected based on the same analysis.
Regarding claim 33, Owen in view of Solomon discloses the system of claim 12 as discussed above. Owen further discloses a system, including:
outputting a disease prognosis for the at least one patient (See Owen [0022] the system can electronically output a report indicative of the disease state. [0376] The trained algorithm may comprise a classifier configured to accept as input a plurality of input variables or features (e.g., condition-associated genomic loci) and to produce or output one or more output values based on the plurality of input variables or features (e.g., condition-associated genomic loci). [0063] In some embodiments, a difference in the assessment of the disease state of the subject among the plurality of time points is indicative of one or more clinical indications selected from the group consisting of: (i) a diagnosis of the disease state of the subject, (ii) a prognosis of the disease state of the subject, and (iii) an efficacy or non-efficacy of a course of treatment for treating the disease state of the subject.).
Claims 4, 15, 25, and 30 are rejected under 35 U.S.C. 103 as being unpatentable over Owen et al. (U.S. 2024/0282453), hereinafter “Owen,” in view of Solomon et al. (U.S. 2021/0057107), hereinafter “Solomon,” and further in view of Baryawno et al. (U.S. 2020/0208114), hereinafter “Baryawno.”
Regarding Claim 4, Owen in view of Solomon discloses the method of claim 3 as discussed above. Owen further discloses a method, wherein:
the mapping further includes reducing dimensionality, extracting features (See Owen [0268] the system can perform dimensionality reduction. [0262] the system can use LASSO for feature selection.), correcting for multiomic batch effect (See Owen [0275] the system uses ssGSEA, which scores single samples in isolation and may be thus shielded from technical variation within and among data sets. This is understood to be used for addressing the batch effect problem inherent in single-cell RNA-sequencing data.).
Owen does not disclose:
removing multiomic based multiplets.
Baryawno teaches:
removing multiomic based multiplets (See Baryawno [1300] the system removed multiplets and doublets from the analysis.).
The system of Baryawno is applicable to the disclosure of Owen in view of Solomon as they both share characteristics and capabilities, namely, they are directed to gene expression and disease analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Owen in view of Solomon to include addressing multiplets data as taught by Baryawno. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Owen in view of Solomon in order to prospectively isolate and functionally characterize niche cells (see Baryawno [0008]).
Regarding claim 15, Owen in view of Solomon and Baryawno discloses the method of claim 4 as discussed above. Claim 15 recites a system that performs a method substantially similar to the method of claim 4. Accordingly, claim 15 is rejected based on the same analysis.
Regarding Claim 25, Owen in view of Solomon discloses the system claim 14 as discussed above. Owen further discloses a method, wherein:
said mapping includes batch effect correction (See Owen [0275] the system uses ssGSEA, which scores single samples in isolation and may be thus shielded from technical variation within and among data sets. This is understood to be used for addressing the batch effect problem inherent in single-cell RNA-sequencing data.).
Owen does not disclose:
said mapping includes … multiplet removal across multiomic modalities.
Baryawno teaches:
said mapping includes … multiplet removal across multiomic modalities (See Baryawno [1300] the system removed multiplets and doublets from the analysis.).
The system of Baryawno is applicable to the disclosure of Owen in view of Solomon as they both share characteristics and capabilities, namely, they are directed to gene expression and disease analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Owen in view of Solomon to include addressing multiplets data as taught by Baryawno. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Owen in view of Solomon in order to prospectively isolate and functionally characterize niche cells (see Baryawno [0008]).
Regarding claim 30, Owen in view of Solomon and Baryawno discloses the system of claim 25 as discussed above. Claim 30 recites a method that is substantially similar to the method performed by the system of claim 25. Accordingly, claim 30 is rejected based on the same analysis.
Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Owen et al. (U.S. 2024/0282453), hereinafter “Owen,” in view of Solomon et al. (U.S. 2021/0057107), hereinafter “Solomon,” and further in view of Zhang et al. (U.S. 2016/0153005), hereinafter “Zhang.”
Regarding Claim 6, Owen in view of Solomon discloses the method of claim 3 as discussed above. Owen further discloses a method, wherein:
the mapping includes cell type-specific matching of clinical signatures with perturbation signatures (See Owen [0730] system can be used to provide novel insights into the totality of perturbations in molecular pathways predicted by GWAS results, the possible differences in pathologic mechanisms in different ancestral groups, and also identify novel therapeutic targets.).
Owen does not disclose:
including mapping signatures against large scale CRISPR perturbations.
Zhang teaches:
including mapping signatures against large scale CRISPR perturbations (See Zhang [0293] system includes the integration of CRISPR techniques with phenotypic assays to determine the phenotypic changes, if any, resulting from gene perturbations. The use of the CRISPR-Cas9 systems (to provide Cas9-mediated genomic perturbations) can be combined with biochemical, sequencing, electrophysiological, and behavioral analysis to study the function of the targeted genomic element.).
The system of Zhang is applicable to the disclosure of Owen in view of Solomon as they both share characteristics and capabilities, namely, they are directed to gene expression and disease analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Owen in view of Solomon to include CRISPR perturbation analysis as taught by Zhang. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Owen in view of Solomon in order to provide methods that are affordable, easy to set up, scalable, and amenable to targeting multiple positions within the eukaryotic genome (see Zhang [0006]).
Regarding claim 17, Owen in view of Solomon and Zhang discloses the method of claim 6 as discussed above. Claim 17 recites a system that performs a method substantially similar to the method of claim 6. Accordingly, claim 17 is rejected based on the same analysis.
Claims 23-24 and 28-29 are rejected under 35 U.S.C. 103 as being unpatentable over Owen et al. (U.S. 2024/0282453), hereinafter “Owen,” in view of Solomon et al. (U.S. 2021/0057107), hereinafter “Solomon,” and further in view of Eckardt et al. (“Reinforcement Learning for Precision Oncology,” Cancers 13(18), 4624 (Sep 2021), hereinafter “Eckardt.”
Regarding Claim 23, Owen discloses the method of claim 1 as discussed above. Owen further discloses a method, wherein:
inferring secondary immune endpoints is trained … to infer over immune-state trajectories from observed clinical endpoints (See Owen Fig. 1 and [0251] the system trains a classifier using records of gene expression data with known phenotypes in order to apply that classifier to records without a known phenotype. [00256]-[0258] the phenotypes are disease states. Therefore the system is using the classifier to infer clinical outcomes where no outcome was already known.), and a prognosis is generated over a probabilistic prognosis graph (See Owen [0063] In some embodiments, a difference in the assessment of the disease state of the subject among the plurality of time points is indicative of one or more clinical indications selected from the group consisting of: (i) a diagnosis of the disease state of the subject, (ii) a prognosis of the disease state of the subject, and (iii) an efficacy or non-efficacy of a course of treatment for treating the disease state of the subject.).
Owen does not disclose:
[the model] is trained via inverse reinforcement learning.
Zhang teaches:
[the model] is trained via inverse reinforcement learning (See Eckardt Fig. 3, page 7; multimodal data, including genetic assays, serve as input for the reinforcement learning framework. See also Section 4.Discussion, page 10; another possibility is to first train the reinforcement learning agent by expert demonstration, inverse learning, transfer learning or a combination thereof.).
The system of Eckardt is applicable to the disclosure of Owen in view of Solomon as they both share characteristics and capabilities, namely, they are directed to using machine learning for genetic data analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Owen in view of Solomon to include inverse reinforcement learning as taught by Eckardt. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Owen in view of Solomon in order to address sequential tasks by exploring the underlying dynamics of an environment and shaping it by taking actions in order to maximize cumulative rewards over time, thereby achieving optimal long-term outcomes (see Eckardt Abstract).
Regarding claim 24, Owen in view of Solomon and Eckardt discloses the system of claim 23 as discussed above. Owen further discloses a system, including:
said reinforcement learning uses a multi-arm bandit or variational autoencoder (VAE) architecture (See Owen [0610] the system can use a particular kind of autoencoder, termed a Gaussian mixture variational autoencoder (GMVAE).).
Regarding claims 28-29, Owen in view of Solomon and Eckardt discloses the system of claims 23-24 as discussed above. Claims 28-29 recite a method that is substantially similar to the method performed by the system of claims 23-24. Accordingly, claims 28-29 are rejected based on the same analysis.
Response to Arguments
Applicant's arguments filed 07 May 2026, with respect to the 35 U.S.C. §101 rejection of the claims, have been fully considered but they are not persuasive. Applicant argues that the claims recite a technical solution to a technical problem and are therefore integrated into a practical application (see Applicant Remarks pages 12-15). This is not persuasive. The additional elements, individually or in combination. do not integrate the exception into a practical application. These additional elements, included the broadly recited use of machine learning, merely amounts to reciting the words ‘‘apply it’’ (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea (see MPEP 2106.05(f)). Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore, the claims remain rejected as being directed to ineligible subject matter.
Applicant's arguments filed 07 May 2026, with respect to the 35 U.S.C. §103 rejection of the claims, have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of the Solomon reference.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Solomon et al. (U.S. 2021/0057107) discloses a system for predicting treatment outcomes based on genetic imputation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BENJAMIN L HANKS whose telephone number is (571)270-5080. The examiner can normally be reached Monday-Friday 8am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shahid Merchant can be reached at (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/B.L.H./Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights