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 .
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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 1-4, 12-13 and 16-18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Hsiao et. al., hereafter Hsiao (Hsiao, Chiaowen Joyce, et al. "Characterizing and inferring quantitative cell cycle phase in single-cell RNA-seq data analysis." Genome research 30.4 (2020): 611.) .
As per claim 1, Hsiao teaches “A computer-implemented method comprising:
receiving sequencing data for a cell sample, the cell sample comprising a plurality of cells; receiving an image of the cell sample;” (See page 2 column 2 paragraph 2 “We collected FUCCI fluorescence images (EGFP-GMNN and mCherry-CDT1)and scRNA-seq data from the same single cells using an automated system designed for the Fluidigm C1 platform (see Methods) (Fig. 1). After image capture, we prepared scRNA seq libraries for sequencing using a SMARTer protocol adapted for iPSCs (Tung et al. 2017).” )
“analyzing the image to determine a plurality of respective cell cycle states for the plurality of cells in the cell sample; and” (See page 3 column 1 section Quantifying continuous cell cycle phase using FUCCI intensities paragraph 1, 3 “Proceeding with the 888 single cells for which we had high-quality RNA-seq data, we turned our attention to the corresponding FUCCI data. For each cell, we defined a fixed cell area (100×100 pixels) for the EGFP-GMNN and mCherry-CDT1 images. This allowed us to account for differences in cell size. We computed two FUCCI scores for each cell to assign cell cycle phase.”. See also column 2 paragraph 1 “With this in mind, we ordered the corrected FUCCI scores by phase and plotted them on a unit circle, using the co-oscillation of mCherry-CDT1 and EGFP-GMNN to infer an angle, or “FUCCI phase,” for each cell (see Methods) (Fig. 2A).” Hsiao)
“integrating the sequencing data with the image using the plurality of respective cell cycle states.” (See pages 3-4 column 2 section Predicting FUCCI phase from gene expression data “Building on these results, we developed a statistical method for predicting continuous cell cycle phase from gene expression data. The intuition behind our approach is that given a set of labeled training data—cells for which we have both FUCCI phase (Y) and scRNA-seq data (X), our trend-filtering approach learns the cyclic trend for each gene (i.e., p(X|Y)). We combine this with a prior for the phase (p(Y)) using the idea of a “naive Bayes” predictor to predict FUCCI phase from gene expression (i.e., p(Y |X)). Given scRNA-seq data, X, on any additional cell without FUCCI data, we can then apply this method to predict its FUCCI phase, Y (for more details, see Methods). Henceforth, our continuous predictor is referred to as peco.” See also pages 8-10 section Methods. Examiner interprets “integrating the sequencing data with the image using the.. cell cycle states” as “learning the cyclic trend for each gene using the fucci phase and scRNA-seq data”. See also fig. 2 and fig. 3. Hsiao)
Claim 16 is rejected under the same analysis as claim 1. (See page 8 column 2 section Image analysis and FUCCI phase quantification, it shows the code to implement on a computer, see also page 10 section Data access, it provides the code and necessary scripts to run the program on the computer. Hsiao)
As per claim 2, Hsiao teaches “The computer-implemented method of claim 1, wherein the step of integrating the sequencing data with the image comprises: mapping each of the plurality of cells in the image to a set of the plurality of cells in the sequencing data using the plurality of respective cell cycle states; and mapping each of the plurality of cells in the sequencing data to a set of the plurality of cells in the image using the plurality of respective cell cycle states.” (See fig. 2, it shows genes mapped to a quantity of cells “(C)Given the FUCCI phase, we ordered cells along the cell cycle to estimate the cyclic trend of gene expression levels for each gene. We identified these five genes as the top five cyclic genes in the data: CDK1, UBE2C, TOP2A, H4C5, and H4C3. Each plot shows the expression levels of 888 single-cell samples and the estimated cyclic trend (orange line). All five genes were previously identified as related to cell cycle regulation. The vertical lines correspond to phase boundaries derived from the PAM-based classification.” See also fig. 3 on page 5, it shows “(C)Estimated cyclic trend of top five cyclic genes for samples from cell line NA18511. The rows correspond to prediction results from peco of five genes, Oscope and reCAT. For the Oscope/reCAT results, we ordered the single-cell samples from NA18511 using the Oscope/reCAT-based predicted phase (based on 888 samples in the data) and used trendfilter to estimate cyclic trend of gene expression. For the peco results, we ordered the samples according to the predicted phase and used trend filter to estimate cyclic trend of gene expression.” Examiner points out that they are mapped to each other and therefore covers the BRI (broadest reasonable interpretation) of the claim. See also page 9 section Filtering and normalization of gene expression data “We then used data from the empty wells to determine filtering criteria for the non empty wells (see Supplemental Fig.S2 ): number of mapped reads, percentage of unmapped reads, percentage of ERCC reads, and percentage of genes detected to have at least one read. Second, we determined the number of cells captured in each C1 well using linear discriminant analysis (LDA) (for our previous work for the rationale, see Tung et al. 2017). We fitted two LDA models: (1) number of cells per well∼ gene molecule count + con centration of cDNA amplicons, and (2) number of cells per well∼ read-to-molecule conversion efficiency of ERCC spike-in controls +read-to-molecule conversion efficiency of endogenous genes. We used DAPI staining results to determine the number of cells captured in each well… In total, we collected 20,327 genes from 1536 scRNA-seq samples after read mapping. After the quality filtering steps described above, we were left with 888 samples and 11,040 genes. We standardized the molecule counts to CPM using per-sample total molecule count prefiltering from the 20,327 genes.” See also pages 9-10 section Predicting quantitative cell cycle phase of single cells: a supervised learning approach. Hsiao)
As per claim 3, Hsiao teaches “The computer-implemented method of claim 1, wherein the image is a brightfield image.” (See page 8 column 2 paragraph 1 “For each cell capture site, four images were captured, including bright field, DAPI, EGFP, and mCherry. The total imaging time, together with the setup time, was ∼45 min for one 96-well C1 IFC.” Hsiao)
Claim 17 is rejected under the same analysis as claim 3.
As per claim 4, Hsiao teaches “The computer-implemented method of claim 3, wherein analyzing the image to determine the plurality of respective cell cycle states for the plurality of cells in the cell sample comprises using a trained machine learning model.” (See also pages 9-10 section Predicting quantitative cell cycle phase of single cells: a supervised learning approach. “Our goal was to build a statistical method to predict continuous cell cycle phase from gene expression data. We implemented the method in a two-step algorithm. In the first step, we trained our predictor on data from five individuals and learned the cyclic trend for each gene using trendfilter.” See also the subsections Notations and Methods on page 10 which show a learning process. See also page 3 section Predicting FUCCI phase from gene expression data, which shows a supervised learning approach (a well known machine learning method) “Building on these results, we developed a statistical method for predicting continuous cell cycle phase from gene expression data. The intuition behind our approach is that given a set of labeled training data—cells for which we have both FUCCI phase (Y) and scRNA-seq data (X), our trend-filtering approach learns the cyclic trend for each gene (i.e., p(X|Y)). We combine this with a prior for the phase (p(Y)) using the idea of a “naive Bayes” predictor to predict FUCCI phase from gene expression (i.e., p(Y |X)). Given scRNA-seqdata, X, on any additional cell with out FUCCI data, we can then apply this method to predict its FUCCI phase, Y (for more details, see Methods). Henceforth, our continuous predictor is referred to as peco.” Hsiao)
Claim 18 is rejected under the same analysis as claim 4.
As per claim 12, Hsiao teaches “The computer-implemented method of claim 1, wherein the image is a fluorescently-labeled image.” (See page 2 column 2 paragraph 2 “We collected FUCCI fluorescence images (EGFP-GMNN and mCherry-CDT1) and scRNA-seq data from the same single cells using an automated system designed for the Fluidigm C1 platform (see Methods) (Fig. 1).” See also fig. 1 and fig. 2. Hsiao)
As per claim 13, Hsiao teaches “The computer-implemented method of claim 1, wherein the plurality of respective cell cycle states comprise one or more of G1 Phase, S Phase, G2 Phase, M Phase, and G0 Phase.” (See page 4 fig. 2 “(B) We ordered FUCCI scores of EGFP and mCherry by FUCCI phase to visualize the co-oscillation of EGFP and mCherry along the cell cycle.Red and green points correspond to EGFP and mCherry scores, respectively. The vertical lines correspond to phase boundaries derived from the PAM based classification (G1, 384 cells; S, 172 cells; G2/M, 332 cells).” See also page 1 column 2 paragraph 2 “Regardless of whether or not cells are sorted, all single-cell studies to date have accounted for cell cycle by using the standard classification of cell cycle phases, which is based on the notion that a cell passes through a consecutive series of distinct phases (G1, S, G2, M, and G0) marked by irreversible abrupt transitions.” See also page 6 paragraph 2. Hsiao)
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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 5-7, 11, 14, 15 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Hsiao in view of Masaeli et. al., hereafter Masaeli (US Pub. No. 20240153289 A1).
As per claim 5, Hsiao already teaches “The computer-implemented method of claim 4, wherein using the trained machine learning model comprises: inputting the brightfield image into the trained machine learning model;” (See page 8 column 2 paragraph 1 “After the cell sorting step on the C1 machine, the C1 IFC microfluidic chip was immediately transferred to JuLI stage (NanoEnTek)for imaging. The JuLI stage was specifically designed as an automated single-cell observation system for C1 IFC vessel. For each cell capture site, four images were captured, including bright field, DAPI, EGFP, andmCherry… Then, the camera proceeds to capture images of each C1 well.” and Page 3 column 2 subsection Our supervised approach, see also pages 9 column 2 and page 10 column 1 section Predicting quantitative cell cycle phase of single cells: a supervised learning approach along with Notations and Methods. Hsiao) , however Hsiao does not teach “and outputting a spatial distribution of organelles of the plurality of cells in a simulated image of the cell sample from the trained machine learning model.”
Masaeli teaches “and outputting a spatial distribution of organelles of the plurality of cells in a simulated image of the cell sample from the trained machine learning model.” (Examiner interprets “simulated image” as the cell morphology map as seen in paragraphs 53, 55, 56, 87, 88. See also paragraph 98 “[0098] Any one of the methods and platforms disclosed herein can be capable of processing image data of one or more cells to generate one or more morphometric maps of the one or more cells. Non-limiting examples of morphometric models can be utilized to analyze one or more images of single cells (or cell clusters) can include, e.g., simple morphometrics (e.g., based on lengths, widths, masses, angles, ratios, areas, etc.), landmark-based geometric morphometrics (e.g., spatial information, intersections, etc. of one or more components of a cell), procrustes-based geometric morphometrics (e.g., by removing non-shape information that is altered by translation, scaling, and/or rotation from the image data), Euclidean distance matrix analysis, diffeomorphometry, and outline analysis. The morphometric map(s) can be multi-dimensional (e.g., 2D, 3D, etc.). The morphometric map(s) can be reported to the user via the GUI.” The components contain the organelles as seen in paragraph 53 “Non-limiting examples of one or more morphological properties of a cell, as disclosed herein, that can be extracted from one or more images of the cell can include, but are not limited to (i) shape, curvature, size (e.g., diameter, length, width, circumference), area, volume, texture, thickness, roundness, etc. of the cell or one or more components of the cell (e.g., cell membrane, nucleus, mitochondria, etc.), (ii) number or positioning of one or more contents (e.g., nucleus, mitochondria, etc.) of the cell within the cell (e.g., center, off-centered, etc.),” See also paragraph 6 and 41. Masaeli )
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao with the teachings of Masaeli to output a spatial distribution of organelles in a simulated image. The modification would have been motivated by the desire to identify a disease state in order to provide preferable therapy, therefore it is an improvement, as suggested by Masaeli (See paragraph 99 “[0099] Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples). The two or more samples can each be analyzed to determine a morphological profile (e.g., a cell morphology map) of each sample. For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest. In another example, the morphological profiles of the two or more samples can be compared to monitor a progress of a condition of a subject, e.g., comparing first image data of a first set of cells from a subject before a treatment (e.g., a test drug candidate, chemotherapy, surgical resection of solid tumors, etc.) and second image data of a second set of cells from the subject after the treatment... In a different example, the morphological profiles of the two or more samples can be compared to monitor effects of two or more different treatment options (e.g., different test drugs) in two or more different cohorts (e.g., human subjects, animal subjects, or cells being tested in vitro/ex vivo). Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value).” Masaeli)
Claim 19 is rejected under the same analysis as claim 5.
As per claim 6, Hsiao in view of Masaeli already teaches “The computer-implemented method of claim 5,”, however Masaeli also teaches “further comprising segmenting one or more organelles of the plurality of cells in the simulated image of the cell sample.” (The morphometrics map can be generated bases on the outline and geometric properties of cell components (organelles), and See paragraph 98 “[0098] Any one of the methods and platforms disclosed herein can be capable of processing image data of one or more cells to generate one or more morphometric maps of the one or more cells. Non-limiting examples of morphometric models can be utilized to analyze one or more images of single cells (or cell clusters) can include, e.g., simple morphometrics (e.g., based on lengths, widths, masses, angles, ratios, areas, etc.), landmark-based geometric morphometrics (e.g., spatial information, intersections, etc. of one or more components of a cell), procrustes-based geometric morphometrics (e.g., by removing non-shape information that is altered by translation, scaling, and/or rotation from the image data), Euclidean distance matrix analysis, diffeomorphometry, and outline analysis. The morphometric map(s) can be multi-dimensional (e.g., 2D, 3D, etc.). The morphometric map(s) can be reported to the user via the GUI.” The components contain the organelles as seen in paragraph 53 “Non-limiting examples of one or more morphological properties of a cell, as disclosed herein, that can be extracted from one or more images of the cell can include, but are not limited to (i) shape, curvature, size (e.g., diameter, length, width, circumference), area, volume, texture, thickness, roundness, etc. of the cell or one or more components of the cell (e.g., cell membrane, nucleus, mitochondria, etc.), (ii) number or positioning of one or more contents (e.g., nucleus, mitochondria, etc.) of the cell within the cell (e.g., center, off-centered, etc.),” It utilizes the same combination rationale as the segmentation is directly used in the comparison of samples. Masaeli)
As per claim 7, Hsiao in view of Masaeli already teaches “The computer-implemented method of claim 6, further comprising quantifying a plurality of cell features of the plurality of cells in the simulated image of the cell sample.” (See paragraph 53 “[0053] The cell morphology map can be generated based on one or more morphological features (e.g., characteristics, profiles, fingerprints, etc.) from the processed image data. Non-limiting examples of one or more morphological properties of a cell, as disclosed herein, that can be extracted from one or more images of the cell can include, but are not limited to (i) shape, curvature, size (e.g., diameter, length, width, circumference), area, volume, texture, thickness, roundness, etc. of the cell or one or more components of the cell (e.g., cell membrane, nucleus, mitochondria, etc.), (ii) number or positioning of one or more contents (e.g., nucleus, mitochondria, etc.) of the cell within the cell (e.g., center, off-centered, etc.), and (iii) optical characteristics of a region of the image(s) (e.g., unique groups of pixels within the image(s)) that correspond to the cell or a portion thereof (e.g., light emission, transmission, reflectance, absorbance, fluorescence, luminescence, etc.).” See also paragraph 57 “[0057] In some cases of the hierarchical clustering as disclosed herein, an initial set of clusters can be generated based on an initial morphological feature that is extracted from the image data, and one or more clusters of the initial set of clusters can comprise a plurality of sub-clusters based on second morphological features or sub-features of the initial morphological feature. For example, the initial morphological feature can be stem cells (or not), and the sub-features can be different types of stem cells (e.g., embryonic stem cells, induced pluripotent stem cells, mesenchymal stem cells, muscle stem cells, etc.)”. See also paragraphs 86, 87, Masaeli.)
As per claim 11, Hsiao already teaches “The computer-implemented method of claim 4, further comprising: providing a training dataset comprising brightfield images and corresponding fluorescent images;” (See page 8 column 2 paragraph 1 “After the cell sorting step on the C1 machine, the C1 IFC microfluidic chip was immediately transferred to JuLI stage (NanoEnTek)for imaging. The JuLI stage was specifically designed as an automated single-cell observation system for C1 IFC vessel. For each cell capture site, four images were captured, including bright field, DAPI, EGFP, andmCherry… Then, the camera proceeds to capture images of each C1 well.” and Page 3 column 2 subsection Our supervised approach, see also pages 9 column 2 and page 10 column 1 section Predicting quantitative cell cycle phase of single cells: a supervised learning approach along with Notations and Methods. The training data set has labeled. See also page 9 subsection Filtering and normalization of gene expression data and Data access on page 10. Hsiao), however Hsiao does not teach “and training a machine learning model to predict spatial distributions of organelles of cells in simulated images using the training dataset.”
Masaeli teaches “and training a machine learning model to predict spatial distributions of organelles of cells in simulated images using the training dataset.” ([0049] FIG. 1 schematically illustrates an example method for classifying a cell. The method can comprise processing image data 110 comprising tag-free images/videos of single cells (e.g., image data 110 consisting of tag-free images/videos of single cells). Various clustering analysis models 120 as disclosed herein can be used to process the image data 110 to extract one or more morphological properties of the cells from the image data 110, and generate a cell morphology map 130A based on the extracted one or more morphological properties. For example, the cell morphology map 130A can be generated based on two morphological properties as dimension 1 and dimension 2. The cell morphology map 130A can comprise one or more clusters (e.g., clusters A, B, and C) of datapoints, each datapoint representing an individual cell from the image data 110. The cell morphology map 130A and the clusters A-C therein can be used to train classifier(s) 150. Subsequently, a new image 140 of a new cell can be obtained and processed by the trained classifier(s) 150 to automatically extract and analyze one or more morphological features from the cellular image 140 and plot it as a datapoint on the cell morphology map 130A… For example, the classifier(s) 150 can determine and report that the cell in the new image data 140 has a 95% probability of belonging to cluster C, 1% probability of belonging to cluster B, and 4% probability of belong to cluster A, solely based on analysis of the tag-free image 140 and one or more morphological features of the cell extracted therefrom.” See also paragraphs 52 “[0052] The cell morphology map can be a visual (e.g., graphical) representation of one or more clusters of datapoints. The cell morphology map can be… For example, a heatmap can be used as colorimetric scale to represent the classifier prediction percentages for each cell against a cell class, cell type, or cell state.”. See also paragraphs 45, 53, 55, 56, 57, 58 and 66-69. See also paragraph 88 “For example, upon the user's selection, the classifier can be trained to identify one or more common morphological features within the selected datapoints (e.g., features that distinguish the selected datapoints from the unselected data). ”. See also paragraph 90, 91 and 93. Masaeli )
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao with the teachings of Masaeli to predict spatial distributions of organelles in simulated images. The modification would have been motivated by the desire to identify a disease state in order to provide preferable therapy, therefore it is an improvement, as suggested by Masaeli (See paragraph 99 “[0099] Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples). The two or more samples can each be analyzed to determine a morphological profile (e.g., a cell morphology map) of each sample. For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest. In another example, the morphological profiles of the two or more samples can be compared to monitor a progress of a condition of a subject, e.g., comparing first image data of a first set of cells from a subject before a treatment (e.g., a test drug candidate, chemotherapy, surgical resection of solid tumors, etc.) and second image data of a second set of cells from the subject after the treatment... In a different example, the morphological profiles of the two or more samples can be compared to monitor effects of two or more different treatment options (e.g., different test drugs) in two or more different cohorts (e.g., human subjects, animal subjects, or cells being tested in vitro/ex vivo). Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value).” Masaeli)
As per claim 14, Hsiao already teaches “A method comprising: integrating sequencing data for a cell sample with an image of the cell sample according to the computer-implemented method of claim 1;… based on the integrated sequencing data and image of the cell sample”, however Hsiao does not teach “and providing a diagnosis, prognosis, or treatment recommendation for a subject.”
Masaeli teaches “and providing a diagnosis, prognosis, or treatment recommendation for a subject.” (See paragraphs 241 “[0241] In some embodiments, the system and methods disclosed herein are used for cancer diagnosis in a subject…” See also paragraph 256, 267. See also paragraph 99 “Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples)… For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest… Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value). ”. See also paragraphs 276. Masaeli)
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao with the teachings of Masaeli to provide a diagnosis, prognosis or treatment to a subject according to the sequential data and image of the cell. The modification would have been motivated by the desire to identify a disease state in order to provide preferable therapy, therefore it is an improvement, as suggested by Masaeli (See paragraph 99 “[0099] Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples). The two or more samples can each be analyzed to determine a morphological profile (e.g., a cell morphology map) of each sample. For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest. In another example, the morphological profiles of the two or more samples can be compared to monitor a progress of a condition of a subject, e.g., comparing first image data of a first set of cells from a subject before a treatment (e.g., a test drug candidate, chemotherapy, surgical resection of solid tumors, etc.) and second image data of a second set of cells from the subject after the treatment... In a different example, the morphological profiles of the two or more samples can be compared to monitor effects of two or more different treatment options (e.g., different test drugs) in two or more different cohorts (e.g., human subjects, animal subjects, or cells being tested in vitro/ex vivo). Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value).” Masaeli)
As per claim 15, Hsiao already teaches “A method comprising: integrating sequencing data for a cell sample with an image of the cell sample according to the computer-implemented method of claim 1;… based on the integrated sequencing data and image of the cell sample”, however Hsiao does not teach “and administering a treatment to a subject.”
Masaeli teaches “and administering a treatment to a subject.” (See paragraph 99 “Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples)… For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest… Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value). ” See also paragraphs 276. Masaeli)
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao with the teachings of Masaeli to provide a treatment to a subject using the sequential data and image of the cell. The modification would have been motivated by the desire to identify a disease state in order to provide preferable therapy, therefore it is an improvement, as suggested by Masaeli (See paragraph 99 “[0099] Any of the methods or platforms disclosed herein (e.g., the analysis module) can be used to process, analyze, classify, and/or compare two or more samples (e.g., at least 2, 3, 4, 5, 6, 7, 8, 9, 10, or more test samples). The two or more samples can each be analyzed to determine a morphological profile (e.g., a cell morphology map) of each sample. For example, the morphological profiles of the two or more samples can be compared for identifying a disease state of a patient's sample in comparison to a health cohort's sample or a sample of image data representative of a disease of interest. In another example, the morphological profiles of the two or more samples can be compared to monitor a progress of a condition of a subject, e.g., comparing first image data of a first set of cells from a subject before a treatment (e.g., a test drug candidate, chemotherapy, surgical resection of solid tumors, etc.) and second image data of a second set of cells from the subject after the treatment... In a different example, the morphological profiles of the two or more samples can be compared to monitor effects of two or more different treatment options (e.g., different test drugs) in two or more different cohorts (e.g., human subjects, animal subjects, or cells being tested in vitro/ex vivo). Accordingly, the systems and methods disclosed herein can be utilized (e.g., via sorting or enrichment of a cell type of interest or a cell exhibiting a characteristic of interest) to select a drug and/or a therapy that yields a desired effect (e.g., a therapeutic effect greater than equal to a threshold value).” Masaeli)
Claims 8-10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Hsiao in view of Masaeli, also in view of Li et. al., hearafter Li (CN Pub. No. 112184696 B), further in view of Mukhopadhyay et. al. (US Pub. No. 20180315506 A1) and Takagi et. al. (US Pub. No. 20160350915 A1)
As per claim 8, Hsiao in view of Masaeli already teaches “The computer-implemented method of claim 7, wherein the plurality of cell features comprise, area of cell, area of nucleus… volume of cell, and volume of nucleus” (See paragraphs 38 and 53 “[0053]… Non-limiting examples of one or more morphological properties of a cell, as disclosed herein, that can be extracted from one or more images of the cell can include, but are not limited to (i) shape, curvature, size (e.g., diameter, length, width, circumference), area, volume, texture, thickness, roundness, etc. of the cell or one or more components of the cell (e.g., cell membrane, nucleus, mitochondria, etc.),” Masaeli), “number of cytoplasm, density-based clustering algorithm (DBSCAN) clusters, number of mitochondria DBSCAN clusters,” (See paragraphs 51-56 (shows that clustering can be based on morphological features which includes a number of mitochondria), paragraph 82 shows a number of clusters and paragraph 71 shows that the clustering algorithms utilized is density based spatial clustering of applications with noise (DB SCAN). Masaeli implicitly teaches a number of cytoplasm dbscan clusters, in the case of cancer cell, the cell population is analyzed by the using the clustering methods disclosed, see paragraph “[0243] In some embodiments, the system and methods disclosed herein are used to identify cancer cells from biological samples acquired from mammalian subjects, wherein the cell population is analyzed by nuclear detail, nuclear contour, presence or absence of nucleoli, quality of cytoplasm, quantity of cytoplasm, nuclear aspect ratio, cytoplasmic aspect ratio, or nuclear to cytoplasmic ratio. In some aspects, the cancer cells that are identified indicate the presence of cancer in the mammalian sample,”, it is shown over a BRI since it shows that Masaeli provides a number of clusters analyzed from a cell population. In the case of mammal, the quantity of cytoplasm is added as an option. See also paragraphs 236-249. See also paragraphs 293, 362 and 38.Masaeli ), however Hsiao in view of Maseli does not teach
“maximum area of available cross sections of the nucleus, ratio of nuclear volume to nuclear area, total pixel count of cell, total pixel count of mitochondria, total pixel count of nucleus,”
Li teaches “total pixel count of cell, total pixel count of mitochondria, total pixel count of nucleus” (See page 5 paragraphs 2 “… counting the total number of pixels of the morphological processed image, magnifying and observing the single regular organelles in the image, counting the pixels occupied by the single regular organelles, and dividing the total number of the pixels by the pixels occupied by the single regular organelles to obtain the total number of the organelles.” See also page 9 last paragraph and page 10 first paragraph “The method for calculating the cell area in step S5 includes: as shown in fig. 5, the image after morphological processing is returned to the binary image matrix, the Z value of the pixel where the cell exists is 1, the pixel where the cell does not exist is 0, the whole binary image matrix is traversed, and the number of pixels is counted.”, since Z is 1 when a cell exists and 0 when it does not, the count presents the cell pixel total before performing the RGB sampling. Li)
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao and Masaeli with the teachings of Li to count the total cell pixel and total organelles pixels. The modification would have been motivated by the desire to simplify the procedure and improve the efficiency and accuracy of cell counting, therefore it is an improvement, as suggested by Li (See page 1 paragraphs 1-5 “In view of the above problems, an object of the present invention is to provide a method and a system for counting cell nuclei and organelles and calculating the area thereof, which simplify the procedure for calculating the number and area of cells and improve the efficiency and accuracy of cell counting” Li)
Mukhopadhyay teaches “ratio of nuclear volume to nuclear area” (See paragraph 7 “(iv) for each of the one or more cells, extracting, by the processor, an information surface value associated with a nuclear contrast feature (e.g., temperature difference between the nucleus area and the cellular area, e.g., contrast difference between the nucleus area and the cellular area), and a nuclear area feature (e.g., a ratio of a nucleus area to a nuclear volume projection),” Mukhopadhyay)
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao and Masaeli, Li with the teachings of Mukhopadhyay to include a ratio of a nuclear volume and nuclear area. The modification would have been motivated by the desire to detect cancer and provide treatment, therefore it is an improvement, as suggested by Mukhopadhyay ( Step (iv) which contains the nuclear area to volume ratio, has the end purpose to treat cancer. See paragraphs 19-21 “[0019] In certain embodiments, the method further comprises selecting an area to be analyzed in the image, wherein the area comprises at least two adjacent sections, repeating the steps of (i)-(v) for each of the at least two adjacent sections; and deciding if the area comprises a cancer boundary by comparing normality statuses of the two adjacent sections (e.g., wherein two adjacent sections of the cancer boundary have different stages of cancer).
[0020] In certain embodiments, the method comprises providing one or more therapeutic treatments to a subject or a sample (e.g., cell culture from a subject), repeating steps (i)-(v); and comparing the normality status before the one or more therapeutic treatments and the normality status after the one or more therapeutic treatments.
[0021] In certain embodiments, the steps of repeating and comparing are performed periodically to monitor an effect of the one or more therapeutic treatments.” See also paragraphs 23 and 27. Mukhopadhyay)
Takagi teaches “maximum area of available cross sections of the nucleus” (See paragraphs 17 and 25. “[0017] In the labeling step S1, a chemical substance, such as a fluorescent dye or a fluorescent protein, is supplied to the cell clump X, thereby labeling a specific component in cells. The components in a cell include a cell nucleus, a cell membrane, cell cytoplasm, a particular organ such as mitochondria, DNA, RNA, and so forth.” “[0025] In the center-of-gravity determining step S5, for example, as shown in FIG. 4, the 3D image of the whole cell clump X, which is created in the 3D-image creating step S4, is sliced along a plurality of planes P parallel to each other in a particular direction, cross sections A of the cell clump X in the planes P are compared to extract the cross section A that has the maximum area, and the center-of-gravity position O in the extracted cross section A is obtained, thus determining the center-of-gravity position O of the cell clump X.”. See also paragraph 60. Takagi)
It would have been obvious to one of ordinary skill in the art before the effective filing
date of the claimed invention to combine the teachings of Hsiao and Masaeli, Li and Mukhopadhyay with the teachings of Takagi to include the maximum area of cross section of the nucleus. The modification would have been motivated by the desire to have better accuracy when estimating the volume and better accuracy at estimating effectiveness, therefore it is an improvement, as suggested by Takagi (See paragraph 3 “ In such three-dimensional culturing, there is a known calibration method in which, in order to observe the culture conditions of a cell clump in which a plurality of cells are aggregated in three dimensions, the accuracy of estimating the volume of the cell clump from an image including the cell clump is improved (for example, see PTL 1).” See also paragraph 32 ” [0032] For example, when a chemical substance is supplied to the cell clump X for drug screening, cells Y that are located lower are more affected by the gravitational force. Therefore, by organizing the evaluation results according to the distance in the direction of the gravitational force, the effectiveness of the chemical substance can be accurately evaluated.” Takagi)
Claim 20 is rejected under the same analysis as claim 8.
As per claim 9, Hsiao in view of Masaeli, Li, Mukhopadhyay and Takagi already teaches “The computer-implemented method of claim 8, further comprising”, however Masaeli teaches “correlating the plurality of cell features with a cell cycle state.” (See paragraph 7 “[0007]… a cell morphology atlas (CMA) comprising a database having a plurality of annotated single cell images that are grouped into morphologically-distinct clusters corresponding to a plurality of predefined cell classes; a modeling library comprising a plurality of models that are trained and validated using datasets from the CMA, to identify different cell types and/or states based at least on morphological features;” See also paragraph 38, 41, 52, 53 and 67. Masaeli)
As per claim 10, Hsiao in view of Masaeli, Li, Mukhopadhyay and Takagi already teaches “The computer-implemented method of claim 9,”, however only Hsiao and Masaeli teaches “wherein correlating the plurality of cell features with the cell cycle state comprises inferring a cell cycle pseudotime for a cell using one or more of the plurality of cell features, wherein the plurality of cell features are correlated with the cell cycle state using the cell cycle pseudotime.” (Masaeli already teaches cell features as stated in the prior rejections.) (See page 10 column 1 subsections Notations and Methods, it shows a pseudotime based on the cell cycle “For each cell m in the test data, (Ytest 1m, ...,Ytest Gm)′ denotes the log2 normalized gene expression vector. The method estimates… the cell cycle phase for reach single-cell sample m… By using the training data, we estimate a function fg for each gene describing the cyclic trend of gene expression levels in FUCCI phase . f is a cyclic function assumed to be continuous at zero and 2π.” See also the steps provided in Methods. Hsiao.)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DYLAN J MENDEZ MUNIZ whose telephone number is (703)756-5672. The examiner can normally be reached M-F, 8AM - 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, Andrew Moyer can be reached at (571) 272-9523. 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.
/DYLAN JOHN MENDEZ MUNIZ/Examiner, Art Unit 2675
/ANDREW M MOYER/Supervisory Patent Examiner, Art Unit 2675
Prosecution Insights