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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on April 20, 2026, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the Examiner.
Response to Amendment
Applicant’s Amendments filed on February 05, 2026, has been entered and made of record.
Currently pending Claim(s) 76-105
Independent Claim(s) 76 and 91
Amended Claim(s) 76, 80, 90, 91, and 104
Response to Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an Amendment received on February 05, 2026.
In view of amendments filed on February 05, 2026, the Applicant has presented the Abstract on a separate sheet in accordance with 37 C.F.R. § 1.52(b)(4) and 37 C.F.R. § 1.72(b); thus, the objection to the Specification is overcome. Regarding the claims, the Applicant has amended claims 90 and 104 to change their claim dependencies; thus, the rejections under 35 U.S.C. § 112(b) are overcome. Furthermore, the Applicant has amended the independent claims 76 and 91 to include limitations from claim 80.
In view of Applicant Arguments/Remarks filed February 05, 2026, with respect to the claims, the Applicant argued (Remarks pages 9-10) that Udyavar (US 11,881,286 B2) fails to teach the amended limitation in the dependent claims. Specifically, the independent claims now require that the tumor classification model comprises a machine learning feature space that includes the boundaries for a plurality of possible classifications of CD8 localization, and the Applicant argued that Udyavar, at [Col. 6, lines 29-36 and Fig. 3], teaches a classifier which receives gene expression data as input and outputs a phenotype based on correlations between gene expression levels and CD8+ T-cell labels derived from image analysis. Thus, the model does not directly process image analysis results and operate on a machine learning feature space with identified boundaries between classifications.
However, the Examiner respectfully disagrees and argues that although Udyavar teaches a classifier based on gene-expression data [Figs. 1-2], the topology of the CD8+ cells is determined using the same image analysis methods as used by the claimed invention, and a nearly identical feature space is established and used for determining phenotype classification (see the image analysis features labeled “1. Digital pathology” in Fig. 5(a)). For example, in [Col. 23, line 7 – Col. 24, line 12], Udyavar teaches using CD8+ T-cell quantity and spatial distribution features for classifying clusters to an immune phenotype class. As shown in Fig. 2 and this example, the process involves determining a feature space based on the topology of CD8+ cells in the tumor and stroma [Blocks 205-220], performing regression to determine expressed genes based on the topology feature space [Block 225], using clustering to define groups of data based on the expressed genes (which were selected based on the topology feature space) [Block 230], and assigning each cluster to an immune phenotype based on the image analysis results and CD8+ topology features directly [Block 235] ([Col. 24, lines 5-12] “Thus, it will be appreciated that the relationships between the CD8+ T-cell (quantity and spatial-distribution) metrics and immune phenotypes as depicted in FIGS. 6A and 6B may be used in block 235 of process 200 (depicted in FIG. 2 ) to assign each cluster of gene-expression data points to an immune phenotype class.”). Therefore, the final classifications and the expressed genes are both determined directly from the CD8+ T-cell topology features.
Furthermore, the Applicant argued (Remarks page 11) that Guan (US 11,473,151 B2) fails to make up for the deficiencies of Udyavar with regards to the machine learning feature space, and the Examiner finds this argument to be persuasive. Although Guan teaches analyzing histology images to determine a phenotype and explains how each classification is determined [Fig. 3A; Col. 17, lines 7-31], Guan does not teach determining a phenotype using machine learning.
Thus, for the reasons stated above, the Examiner respectfully disagrees with the Applicant’s arguments and maintains the rejections under 35 U.S.C. § 102 applied to claims 76 and 91. Therefore, the rejections applied to the dependent claims are not overcome.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 76-78, 80-87, 89, 91-93, 95-102, and 104 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Udyavar et al. (US 11,881,286 B2), hereafter Udyavar.
Regarding claim 76, Udyavar teaches a computer-implemented method for identifying a human subject suitable for immunotherapy to treat a tumor of the human subject ([Col. 2, lines 32-37] “A machine-learning model (e.g., regression and/or random-forest model) may be used to determine which gene expression levels are related to CD8+ T-cell characteristics. The label identified by the classifier for a given data set can be used to identify a treatment candidate.”), the method executing on data processing hardware that causes the data processing hardware to perform operations ([Col. 4, lines 25-30] “In some embodiments, a system is provided that includes one or more data processors and a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform part or all of one or more methods disclosed herein.”) comprising:
receiving a histology image of a sample of the tumor of the human subject; performing image analysis on the histology image to obtain image analysis results indicating CD8+ T-cell abundance in tumor parenchyma and stroma in the histology image ([Col. 4, lines 5-14] Determining that the tumor corresponds to the immune excluded phenotype may include: accessing one or more digital pathology images corresponding to the subject; determining, based on the one or more digital pathology images, a first quantity of CD8+ cells located in a tumor epithelium in the subject; determining, based on the one or more digital pathology images, a second quantity of CD8+ cells located in a tumor stroma in the subject;” [Col. 5, lines 16-20] “FIGS. 4a-4c illustrate a novel digital image analysis algorithm to quantify the quantity and the spatial distribution of CD8+ T cells in ovarian cancer and exemplary CD8+ T-cell distributions associated with distinct immune phenotypes.”);
processing, using a trained tumor topology classification model that comprises a machine learning feature space that includes boundaries for a plurality of possible classifications of CD8 localization, the image analysis results obtained by performing the image analysis on the histology image to determine, from the boundaries of the machine learning feature space for the plurality of possible classifications of CD8 localization, a classification of CD8 localization in the sample of the tumor ([Col. 6, lines 29-36] “The phenotype prediction can be generated using a machine-learning model, such as a classifier. The gene expression data can identify expression levels of one or more genes in Table 1 (e.g., at least 1, at least 10, at least 50, at least 100 or at least 120 of the genes in Table 1) and/or one or more genes for which expression levels correlate with and/or are predictive of a quantity, spatial distribution and/or locations of CD8+ T cells.” Fig. 2 shows the process of using the classifier. Gene-expression data, which is based directly on the topology of CD8+ cells in the tumor and stroma determined through image analysis, is given as input, and the classifier outputs clusters which can be assigned to an output phenotype based directly on the topology. [Col. 20, lines 3-10] “At block 235, each of the clusters may be assigned to an immune phenotype based on quantity and/or spatial-distribution labels associated with data points (associated with subjects) assigned to the cluster. The immune-phenotype assignment may be based on whether cluster-associated quantity labels were low or high and/or whether cluster-associated spatial-distribution labels were indicative of CD8+ T cell enrichment in the stroma versus in tumors.”);
generating a recommendation for a treatment option for the human subject based on the classification of the CD8 localization in the sample of the tumor ([Col. 3, lines 38-41] “The method may further include selecting one or more treatment candidates based on the particular phenotype, wherein the result identifies the one or more treatment candidates.” [Col. 3, lines 52-57] “In some embodiments, a method of treatment is provided that includes identifying a subject with a tumor; determining that the tumor corresponds to an immune excluded phenotype; and prompting administration of anti-TGFẞ to the subject.”);
Regarding claim 77, Udyavar teaches wherein the plurality of possible classifications of CD8 localization comprises inflamed, desert, excluded, and balanced ([Col. 2, lines 19-22] “The tumor-immune phenotype can include one of: immune-desert phenotype, an immune-excluded phenotype or an inflamed/infiltrated phenotype.”).
Regarding claim 78, Udyavar teaches wherein the classification of CD8 localization in the sample of the tumor comprises excluded ([Col. 2, lines 19-22] “The tumor-immune phenotype can include one of: immune-desert phenotype, an immune-excluded phenotype or an inflamed/infiltrated phenotype.”).
Regarding claim 80, Udyavar teaches wherein the trained tumor topology classification model is trained by a training process (The training process is visualized in Fig. 2 and described in Section III, starting at Col. 18, line 25.) that comprises:
receiving a plurality of training histology images of tumor samples in a plurality of patients ([Col. 18, lines 31-35] “Process 200 begins at block 205 where a training data set corresponding to a set of subjects is received. The training data set may include, for each of a set of subjects, one or more digital pathology images and a set of expression levels of each of a set of genes.”);
for each training histology image in the plurality of training histology images (See the arrow to the left of blocks 210-220 in Fig. 2, showing that the process is repeated for each training image.),
performing image analysis on the training histology image to obtain a CD8+ T-cell abundance in the tumor parenchyma and stroma in the training histology image (Blocks 210-220 of Fig. 2 show that image analysis is performed to identify CD8+ T-cells in a training image and identify whether the cells are in the “stroma” or “tumor” class. [Col. 18, lines 52-65] “Each image may be filtered using a frequency corresponding to the CD8+ IHC staining and further processed to identify substantial signals (e.g., via thresholding, peak detection, local averaging and thresholding, etc.). In some instances, an image is first filtered based on a counterstain frequency and processed for cell segmentation to identify cell boundaries. Within each boundary, signals at the CD8+ IHC staining frequency may then be (for example) averaged, summed or processed to identify a median value, and the result may be compared to a threshold to predict whether the cell is a CD8+ T cell. At block 215, each detected CD8+ T cell is assigned to a category to indicate whether it is within a tumor region or a stroma region.”);
training the tumor topology classification model using results of the image analysis and the CD8+ T-cell abundance in the tumor parenchyma and stroma in each of the plurality of training histology images ([Col 19, lines 61-67 – Col. 20, lines 1-10] “At block 230, a cluster analysis is performed using expression values for genes determined to be sufficiently specific. The cluster analysis may include using a component analysis, such as principal component analysis or independent component analysis. The cluster analysis may limit a number of clusters (e.g., to 3, 4, 5, 6, 7, 8, etc.). The cluster analysis may be unsupervised and/or performed only based on quantity and spatial-distribution values. At block 235, each of the clusters may be assigned to an immune phenotype based on quantity and/or spatial-distribution labels associated with data points (associated with subjects) assigned to the cluster. The immune-phenotype assignment may be based on whether cluster-associated quantity labels were low or high and/or whether cluster-associated spatial distribution labels were indicative of CD8+ T cell enrichment in the stroma versus in tumors.”);
generating the machine learning feature space comprising the plurality of classifications based on the training; and identifying boundaries between the plurality of possible classifications of CD8 localization ([Col. 67, lines 51-58] “The 6 clusters were reduced to 3 immune phenotypes that optimally reflected the distribution of CD8+ T cells while capturing unique biological features. The immune phenotypes were labeled, “infiltrated”, “excluded”, and “desert”, given their association with low vs. high CD8 quantity, and with CD8+ T cell enrichment in stroma vs. tumor epithelial cells.” The topology features of the CD8+ T-cells are directly used for determining which phenotype a cluster belongs to.).
Regarding claim 81, Udyavar teaches wherein the CD8+ T-cell abundance comprises a graphical representation of a relationship between percentages of stromal CD8+ T-cells and percentage of parenchymal CD8+ T-cells with respect to a total number of T-cells present in the histology image ([Col. 22, lines 4-11] “Metrics were defined to include a total CD8+ T cell count, a CD8+ T cell count per tumor epithelium and/or a CD8+ T cell count stroma area (See FIG. 4 a ). To better capture and quantify the CD8 infiltration patterns, the CD8 scores were converted into polar coordinates defining two new quantitative metrics: 1) the quantity of CD8+ T cells (R=squareroot [(CD8 tumor)2+(CD8 stroma)2]) and 2) the spatial distribution of CD8+ T cells (θ=atan(CD8 stroma/CD8 tumor)).”).
Regarding claim 82 Udyavar teaches wherein the operations further comprise:
applying a polar coordinate transformation on the graphical representation, resulting in a polar plot, wherein training the tumor topology classification model is further based on using the polar plot ([Col. 22, lines 4-11] “Metrics were defined to include a total CD8+ T cell count, a CD8+ T cell count per tumor epithelium and/or a CD8+ T cell count stroma area (See FIG. 4 a ). To better capture and quantify the CD8 infiltration patterns, the CD8 scores were converted into polar coordinates defining two new quantitative metrics: 1) the quantity of CD8+ T cells (R=squareroot [(CD8 tumor)2+(CD8 stroma)2]) and 2) the spatial distribution of CD8+ T cells (θ=atan(CD8 stroma/CD8 tumor)).”).
Regarding claim 83, Udyavar teaches wherein: each training histology image of the plurality of training histology images comprises a label obtained by at least one pathologist to provide a classification for CD8 localization in the training histology image; and training the tumor topology classification model comprises validating results from the machine learning feature space by comparing the labels of the plurality of training histology images ([Col. 50, lines 40-53] “The two-dimensional metrics defining CD8+ T cell quantities and distribution for these 122 samples confirmed that the classifier assigned them to a sensible immune phenotype (FIG. 5 d , right panel). A subset of 39 samples were also selected from the testing set and compared the tumor-immune phenotypes predicted by the 157-gene molecular classifier with those manually annotated by a pathologist… The results were concordant even with the subjectivity of phenotypes as assigned by pathologists (FIGS. 7 c and 7 d ).”).
Regarding claim 84, Udyavar teaches wherein the treatment option comprises immunotherapy ([Col. 3, lines 5-14] “In some embodiments, a method of treatment is provided that includes targeting the TGFβ pathway… Thus, targeting the TGFβ pathway may overcome T cell exclusion from tumors and improve subjects' response to cancer immunotherapy.”).
Regarding claim 85, Udyavar teaches wherein the immunotherapy comprises an anti-PD-1/PD-L1 antagonist therapy ([Col. 2, lines 36-41] “The label identified by the classifier for a given data set can be used to identify a treatment candidate. For example, the treatment candidate may include anti-TGFβ (and potentially also a checkpoint inhibitor, such as anti-PD-L1) when the phenotype is identified as an immune-excluded phenotype.” [Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 86, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an antibody or antigen-binding fragment thereof that specifically binds a target protein selected from programmed death 1 (PD-1; an "anti-PD-1 antibody") or programmed death ligand 1 (PD-L1; an "anti-PD-L1 antibody”) ([Col. 12, lines 22-29] “A tumor-immune phenotype can be used to inform treatment decisions and/or generate predictions as to whether and/or a degree to which a particular subject will respond to a particular treatment. For example: an immune checkpoint inhibitor therapy may be recommended, more likely to be recommended and/or predicted to be more effective for the inflamed/infiltrated phenotype (e.g., relative to the other phenotypes);” [Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 87, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an anti- PD-1 antibody ([Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 89, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an anti- PD-L1 antibody ([Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 91, Udyavar teaches a system comprising:
data processing hardware; and memory hardware in communication with the data processing hardware and storing instructions that when executed on the data processing hardware causes the data processing hardware to perform operations ([Col. 4, lines 25-30] “In some embodiments, a system is provided that includes one or more data processors and a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform part or all of one or more methods disclosed herein.”)
for identifying a human subject suitable for immunotherapy to treat a tumor of the human subject ([Col. 2, lines 32-37] “A machine-learning model (e.g., regression and/or random-forest model) may be used to determine which gene expression levels are related to CD8+ T-cell characteristics. The label identified by the classifier for a given data set can be used to identify a treatment candidate.”), the operations comprising:
receiving a histology image of a sample of the tumor of the human subject; performing image analysis on the histology image to obtain image analysis results indicating CD8+ T-cell abundance in tumor parenchyma and stroma in the histology image ([Col. 4, lines 5-14] Determining that the tumor corresponds to the immune excluded phenotype may include: accessing one or more digital pathology images corresponding to the subject; determining, based on the one or more digital pathology images, a first quantity of CD8+ cells located in a tumor epithelium in the subject; determining, based on the one or more digital pathology images, a second quantity of CD8+ cells located in a tumor stroma in the subject;” [Col. 5, lines 16-20] “FIGS. 4a-4c illustrate a novel digital image analysis algorithm to quantify the quantity and the spatial distribution of CD8+ T cells in ovarian cancer and exemplary CD8+ T-cell distributions associated with distinct immune phenotypes.”);
processing, using a trained tumor topology classification model that comprises a machine learning feature space that includes boundaries for a plurality of possible classifications of CD8 localization, the image analysis results obtained by performing the image analysis on the histology image to determine, from the boundaries of the machine learning feature space for the plurality of possible classifications of CD8 localization, a classification of CD8 localization in the sample of the tumor ([Col. 6, lines 29-36] “The phenotype prediction can be generated using a machine-learning model, such as a classifier. The gene expression data can identify expression levels of one or more genes in Table 1 (e.g., at least 1, at least 10, at least 50, at least 100 or at least 120 of the genes in Table 1) and/or one or more genes for which expression levels correlate with and/or are predictive of a quantity, spatial distribution and/or locations of CD8+ T cells.” Fig. 2 shows the process of using the classifier. Gene-expression data, which is based directly on the topology of CD8+ cells in the tumor and stroma determined through image analysis, is given as input, and the classifier outputs clusters which can be assigned to an output phenotype based directly on the topology. [Col. 20, lines 3-10] “At block 235, each of the clusters may be assigned to an immune phenotype based on quantity and/or spatial-distribution labels associated with data points (associated with subjects) assigned to the cluster. The immune-phenotype assignment may be based on whether cluster-associated quantity labels were low or high and/or whether cluster-associated spatial-distribution labels were indicative of CD8+ T cell enrichment in the stroma versus in tumors.”); and
generating a recommendation for a treatment option for the human subject based on the classification of the CD8 localization in the sample of the tumor ([Col. 3, lines 38-41] “The method may further include selecting one or more treatment candidates based on the particular phenotype, wherein the result identifies the one or more treatment candidates.” [Col. 3, lines 52-57] “In some embodiments, a method of treatment is provided that includes identifying a subject with a tumor; determining that the tumor corresponds to an immune excluded phenotype; and prompting administration of anti-TGFẞ to the subject.”).
Regarding claim 92, Udyavar teaches wherein the plurality of possible classifications of CD8 localization comprises inflamed, desert, excluded, and balanced ([Col. 2, lines 19-22] “The tumor-immune phenotype can include one of: immune-desert phenotype, an immune-excluded phenotype or an inflamed/infiltrated phenotype.”).
Regarding claim 93, Udyavar teaches wherein the classification of CD8 localization in the sample of the tumor comprises excluded ([Col. 2, lines 19-22] “The tumor-immune phenotype can include one of: immune-desert phenotype, an immune-excluded phenotype or an inflamed/infiltrated phenotype.”).
Regarding claim 95, Udyavar teaches wherein the trained tumor topology classification model is trained by a training process (The training process is visualized in Fig. 2 and described in Section III, starting at Col. 18, line 25.) that comprises:
receiving a plurality of training histology images of tumor samples in a plurality of patients ([Col. 18, lines 31-35] “Process 200 begins at block 205 where a training data set corresponding to a set of subjects is received. The training data set may include, for each of a set of subjects, one or more digital pathology images and a set of expression levels of each of a set of genes.”);
for each training histology image in the plurality of training histology images (See the arrow to the left of blocks 210-220 in Fig. 2, showing that the process is repeated for each training image.),
performing image analysis on the training histology image to obtain a CD8+ T-cell abundance in the tumor parenchyma and stroma in the training histology image (Blocks 210-220 of Fig. 2 show that image analysis is performed to identify CD8+ T-cells in a training image and identify whether the cells are in the “stroma” or “tumor” class. [Col. 18, lines 52-65] “Each image may be filtered using a frequency corresponding to the CD8+ IHC staining and further processed to identify substantial signals (e.g., via thresholding, peak detection, local averaging and thresholding, etc.). In some instances, an image is first filtered based on a counterstain frequency and processed for cell segmentation to identify cell boundaries. Within each boundary, signals at the CD8+ IHC staining frequency may then be (for example) averaged, summed or processed to identify a median value, and the result may be compared to a threshold to predict whether the cell is a CD8+ T cell. At block 215, each detected CD8+ T cell is assigned to a category to indicate whether it is within a tumor region or a stroma region.”);
training the tumor topology classification model using results of the image analysis and the CD8+ T-cell abundance in the tumor parenchyma and stroma in each of the plurality of training histology images ([Col 19, lines 61-67 – Col. 20, lines 1-10] “At block 230, a cluster analysis is performed using expression values for genes determined to be sufficiently specific. The cluster analysis may include using a component analysis, such as principal component analysis or independent component analysis. The cluster analysis may limit a number of clusters (e.g., to 3, 4, 5, 6, 7, 8, etc.). The cluster analysis may be unsupervised and/or performed only based on quantity and spatial-distribution values. At block 235, each of the clusters may be assigned to an immune phenotype based on quantity and/or spatial-distribution labels associated with data points (associated with subjects) assigned to the cluster. The immune-phenotype assignment may be based on whether cluster-associated quantity labels were low or high and/or whether cluster-associated spatial distribution labels were indicative of CD8+ T cell enrichment in the stroma versus in tumors.”);
generating the machine learning feature space comprising the plurality of classifications based on the training; and identifying boundaries between the plurality of possible classifications of CD8 localization (([Col. 67, lines 51-58] “The 6 clusters were reduced to 3 immune phenotypes that optimally reflected the distribution of CD8+ T cells while capturing unique biological features. The immune phenotypes were labeled, “infiltrated”, “excluded”, and “desert”, given their association with low vs. high CD8 quantity, and with CD8+ T cell enrichment in stroma vs. tumor epithelial cells.” The topology features of the CD8+ T-cells are directly used for determining which phenotype a cluster belongs to.).
Regarding claim 96, Udyavar teaches wherein the CD8+ T-cell abundance comprises a graphical representation of a relationship between percentages of stromal CD8+ T-cells and percentage of parenchymal CD8+ T-cells with respect to a total number of T-cells present in the histology image ([Col. 22, lines 4-11] “Metrics were defined to include a total CD8+ T cell count, a CD8+ T cell count per tumor epithelium and/or a CD8+ T cell count stroma area (See FIG. 4 a ). To better capture and quantify the CD8 infiltration patterns, the CD8 scores were converted into polar coordinates defining two new quantitative metrics: 1) the quantity of CD8+ T cells (R=squareroot [(CD8 tumor)2+(CD8 stroma)2]) and 2) the spatial distribution of CD8+ T cells (θ=atan(CD8 stroma/CD8 tumor)).”).
Regarding claim 97, Udyavar teaches wherein the operations further comprise:
applying a polar coordinate transformation on the graphical representation, resulting in a polar plot, wherein training the tumor topology classification model is further based on using the polar plot ([Col. 22, lines 4-11] “Metrics were defined to include a total CD8+ T cell count, a CD8+ T cell count per tumor epithelium and/or a CD8+ T cell count stroma area (See FIG. 4 a ). To better capture and quantify the CD8 infiltration patterns, the CD8 scores were converted into polar coordinates defining two new quantitative metrics: 1) the quantity of CD8+ T cells (R=squareroot [(CD8 tumor)2+(CD8 stroma)2]) and 2) the spatial distribution of CD8+ T cells (θ=atan(CD8 stroma/CD8 tumor)).”).
Regarding claim 98, Udyavar teaches wherein: each training histology image of the plurality of training histology images comprises a label obtained by at least one pathologist to provide a classification for CD8 localization in the training histology image; and training the tumor topology classification model comprises validating results from the machine learning feature space by comparing the labels of the plurality of training histology images ([Col. 50, lines 40-53] “The two-dimensional metrics defining CD8+ T cell quantities and distribution for these 122 samples confirmed that the classifier assigned them to a sensible immune phenotype (FIG. 5 d , right panel). A subset of 39 samples were also selected from the testing set and compared the tumor-immune phenotypes predicted by the 157-gene molecular classifier with those manually annotated by a pathologist… The results were concordant even with the subjectivity of phenotypes as assigned by pathologists (FIGS. 7 c and 7 d ).”).
Regarding claim 99, Udyavar teaches wherein the treatment option comprises immunotherapy ([Col. 3, lines 5-14] “In some embodiments, a method of treatment is provided that includes targeting the TGFβ pathway… Thus, targeting the TGFβ pathway may overcome T cell exclusion from tumors and improve subjects' response to cancer immunotherapy.”).
Regarding claim 100, Udyavar teaches wherein the immunotherapy comprises an anti-PD-1/PD-L1 antagonist therapy ([Col. 2, lines 36-41] “The label identified by the classifier for a given data set can be used to identify a treatment candidate. For example, the treatment candidate may include anti-TGFβ (and potentially also a checkpoint inhibitor, such as anti-PD-L1) when the phenotype is identified as an immune-excluded phenotype.” [Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 101, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an antibody or antigen-binding fragment thereof that specifically binds a target protein selected from programmed death 1 (PD-1; an "anti-PD-1 antibody") or programmed death ligand 1 (PD-L1; an "anti-PD-L1 antibody”) ([Col. 12, lines 22-29] “A tumor-immune phenotype can be used to inform treatment decisions and/or generate predictions as to whether and/or a degree to which a particular subject will respond to a particular treatment. For example: an immune checkpoint inhibitor therapy may be recommended, more likely to be recommended and/or predicted to be more effective for the inflamed/infiltrated phenotype (e.g., relative to the other phenotypes);” [Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 102, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an anti- PD-1 antibody ([Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
Regarding claim 104, Udyavar teaches wherein the anti-PD-1/PD-L1 antagonist comprises an anti- PD-L1 antibody ([Col. 4, line 5] “The checkpoint inhibitor includes anti-PD-L1.”).
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.
Claims 79, 88, 90, 94, 103, and 105 are rejected under 35 U.S.C. 103 as being unpatentable over Udyavar (US 11,881,286 B2), further in view of Guan et al. (US 11,473,151 B2), hereafter Guan.
Regarding claim 79, Udyavar fails to teach wherein the operations further comprise: determining that the sample of the tumor exhibits a negative PD-L1 expression status, wherein generating the recommendation for the treatment option is further based on the determination that the sample of the tumor exhibits the negative PD-L1 expression status.
However, Guan teaches wherein the operations further comprise:
determining that the sample of the tumor exhibits a negative PD-L1 expression status ([Col. 148, lines 66-67 – Col. 149, lines 1-4]“Samples were scored for PD-L1 expression on tumor-infiltrating immune cells, which included macrophages, dendritic cells, and lymphocytes…. An exploratory analysis of PD-L1 expression on tumor cells (TC) was conducted. Specimens were scored as immunohistochemistry TC0, TC1, TC2, or TC3 if <1%, ≥1% but <5%, ≥5% but <50%, or ≥50% of tumor cells were PD-L1-positive, respectively.”),
wherein generating the recommendation for the treatment option is further based on the determination that the sample of the tumor exhibits the negative PD-L1 expression status ([Col. 149, lines 4-8] “PD-L1 scores in patients with multiple specimens from different time points or samples were based on the highest score. This assay was validated for investigational use in clinical trials at the IC1 and IC2 cutoff.” [Col. 162, lines 18-21] “Assessment of the association of PD-L1 expression on tumor-infiltrating immune cells (IC) on baseline tumors with response (objective response rate) was a co-primary endpoint.” [Col. 162, lines 25-31] “As found previously in a smaller cohort of patients, PD-L1 expression on IC was significantly associated with response, and tumors with high PD-L1 expression (IC2+) displayed the highest CR rate (FIG. 1A). Improved OS benefit from atezolizumab was observed in patients with high PD-L1 IC scores (IC2/3) relative to patients with lower PD-L1 IC scores (IC0/1) (FIG. 8A).”)).
Udyavar and Guan are analogous to the claimed invention, because both teach methods of determining the localization and spatial distribution of CD8+ cells for classifying tumors into phenotype groups and determining treatment plans. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by considering the PD-L1 expression status when determining potential treatment options. This modification would allow for PD-L1 expression to impact the decision-making process, which is important since PD-L1 expression levels impact a patient’s complete response rate to treatments proposed by the claimed invention, such as atezolizumab (Guan [Col. 162, lines 25-31] “As found previously in a smaller cohort of patients, PD-L1 expression on IC was significantly associated with response, and tumors with high PD-L1 expression (IC2+) displayed the highest CR rate (FIG. 1A). Improved OS benefit from atezolizumab was observed in patients with high PD-L1 IC scores (IC2/3) relative to patients with lower PD-L1 IC scores (IC0/1) (FIG. 8A).”).
Regarding claim 88, Udyavar fails to teach wherein the anti-PD-1 antibody comprises nivolumab or pembrolizumab. However, Guan teaches wherein the anti-PD-1 antibody comprises nivolumab or pembrolizumab ([Col. 40, lines 24-27] “In a specific aspect, a PD-1 binding antagonist is MDX-1106 (nivolumab). In another specific aspect, a PD-1 binding antagonist is MK-3475 (pembrolizumab).”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by using nivolumab or pembrolizumab as the anti-PD-1 antibody. This modification allow for the use an antibody which is sufficiently capable of binding PD-L1 (Guan [Col. 40, lines 35-40] “The terms “anti-PD-L1 antibody” and “an antibody that binds to PD-L1” refer to an antibody that is capable of binding PD-L1 with sufficient affinity such that the antibody is useful as a diagnostic and/or therapeutic agent in targeting PD-L1.”).
Regarding claim 90, Udyvar fails to teach wherein the anti-PD-L1 antibody comprises avelumab, atezolizumab, or durvalumab. However, Guan teaches wherein the anti-PD-L1 antibody comprises avelumab, atezolizumab, or durvalumab ([Col. 10, lines 25-28] “In some embodiments, the anti-PD-L1 antibody is selected from the group consisting of: MPDL3280A (atezolizumab), YW243.55.S70, MDX-1105, MED14736 (durvalumab), and MSB0010718C (avelumab).”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by using avelumab, atezolizumab, or durvalumab as the anti-PD-1 antibody. This modification allow for the use an antibody which is sufficiently capable of binding PD-L1 (Guan [Col. 40, lines 35-40] “The terms “anti-PD-L1 antibody” and “an antibody that binds to PD-L1” refer to an antibody that is capable of binding PD-L1 with sufficient affinity such that the antibody is useful as a diagnostic and/or therapeutic agent in targeting PD-L1.”).
Regarding claim 94, Udyavar fails to teach wherein the operations further comprise: determining that the sample of the tumor exhibits a negative PD-L1 expression status, wherein generating the recommendation for the treatment option is further based on the determination that the sample of the tumor exhibits the negative PD-L1 expression status.
However, Guan teaches wherein the operations further comprise:
determining that the sample of the tumor exhibits a negative PD-L1 expression status ([Col. 148, lines 66-67 – Col. 149, lines 1-4] “Samples were scored for PD-L1 expression on tumor-infiltrating immune cells, which included macrophages, dendritic cells, and lymphocytes…. An exploratory analysis of PD-L1 expression on tumor cells (TC) was conducted. Specimens were scored as immunohistochemistry TC0, TC1, TC2, or TC3 if <1%, ≥1% but <5%, ≥5% but <50%, or ≥50% of tumor cells were PD-L1-positive, respectively.”),
wherein generating the recommendation for the treatment option is further based on the determination that the sample of the tumor exhibits the negative PD-L1 expression status ([Col. 149, lines 4-8] “PD-L1 scores in patients with multiple specimens from different time points or samples were based on the highest score. This assay was validated for investigational use in clinical trials at the IC1 and IC2 cutoff.” [Col. 162, lines 18-21] “Assessment of the association of PD-L1 expression on tumor-infiltrating immune cells (IC) on baseline tumors with response (objective response rate) was a co-primary endpoint.” [Col. 162, lines 25-31] “As found previously in a smaller cohort of patients, PD-L1 expression on IC was significantly associated with response, and tumors with high PD-L1 expression (IC2+) displayed the highest CR rate (FIG. 1A). Improved OS benefit from atezolizumab was observed in patients with high PD-L1 IC scores (IC2/3) relative to patients with lower PD-L1 IC scores (IC0/1) (FIG. 8A).”)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by considering the PD-L1 expression status when determining potential treatment options. This modification would allow for PD-L1 expression to impact the decision making process, which is important since PD-L1 expression levels impact a patient’s complete response rate to treatments proposed by the claimed invention, such as atezolizumab (Guan [Col. 162, lines 25-31] “As found previously in a smaller cohort of patients, PD-L1 expression on IC was significantly associated with response, and tumors with high PD-L1 expression (IC2+) displayed the highest CR rate (FIG. 1A). Improved OS benefit from atezolizumab was observed in patients with high PD-L1 IC scores (IC2/3) relative to patients with lower PD-L1 IC scores (IC0/1) (FIG. 8A).”).
Regarding claim 103, Udyavar fails to teach wherein the anti-PD-1 antibody comprises nivolumab or pembrolizumab. However, Guan teaches wherein the anti-PD-1 antibody comprises nivolumab or pembrolizumab ([Col. 40, lines 24-27] “In a specific aspect, a PD-1 binding antagonist is MDX-1106 (nivolumab). In another specific aspect, a PD-1 binding antagonist is MK-3475 (pembrolizumab).”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by using nivolumab or pembrolizumab as the anti-PD-1 antibody. This modification allow for the use an antibody which is sufficiently capable of binding PD-L1 (Guan [Col. 40, lines 35-40] “The terms “anti-PD-L1 antibody” and “an antibody that binds to PD-L1” refer to an antibody that is capable of binding PD-L1 with sufficient affinity such that the antibody is useful as a diagnostic and/or therapeutic agent in targeting PD-L1.”).
Regarding claim 105, Udyavar fails to teach wherein the anti-PD-L1 antibody comprises avelumab, atezolizumab, or durvalumab. However, Guan teaches wherein the anti-PD-L1 antibody comprises avelumab, atezolizumab, or durvalumab ([Col. 10, lines 25-28] “In some embodiments, the anti-PD-L1 antibody is selected from the group consisting of: MPDL3280A (atezolizumab), YW243.55.S70, MDX-1105, MED14736 (durvalumab), and MSB0010718C (avelumab).”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Udyavar’s invention by using avelumab, atezolizumab, or durvalumab as the anti-PD-1 antibody. This modification allow for the use an antibody which is sufficiently capable of binding PD-L1 (Guan [Col. 40, lines 35-40] “The terms “anti-PD-L1 antibody” and “an antibody that binds to PD-L1” refer to an antibody that is capable of binding PD-L1 with sufficient affinity such that the antibody is useful as a diagnostic and/or therapeutic agent in targeting PD-L1.”).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Gaire et al. (US 12,031,988 B2) teaches image analysis methods for analyzing the topology of A-type cells and B-type cells by determining a proximity score based on a reference distribution and determining a combined score based on the proximity score and the density of A-type cells and/or B-type cells. The combined score is used to output the state of the sample in the image and can be used for determining a tumor phenotype.
Binnig et al. (US 2018/0364240 A1) teaches methods of using image analysis using tumor and immune cell markers and gene expression to characterize lung cancer images. Binnig also teaches using models, such as a random forest, for predicting a patient’s response to durvalumab based on the observed changes in T-cell topology and the PD-L1 response by the tumor cells.
Klaushen et al. (Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning. Seminars in Cancer Biology. 52(2), 151-157.) teaches methods for tumor-infiltrating lymphocyte (TIL) scoring and discusses machine learning methods compared to human performed methods. Klaushen also teaches interpretable machine learning applied to TIL scoring.
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.
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to ERIC JAMES SHOEMAKER whose telephone number is (571)272-6605. The examiner can normally be reached Monday through Friday from 8am to 5pm ET.
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, JENNIFER MEHMOOD, can be reached at (571)272-2976. 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.
/Eric Shoemaker/
Patent Examiner
/JENNIFER MEHMOOD/ Supervisory Patent Examiner, Art Unit 2664
Prosecution Insights