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 .
Priority
Applicant claims the benefit of US Provisional Application No. 63615874, filed 12/29/2023. Claims 1-22 have been afforded the benefit of this filing date.
Information Disclosure Statement
The IDS dated 5/02/2024 has been considered and placed in the application file.
Claim Objections
Claims 21 and 22 are objected to because of the following informalities:
Claim 21, should be “ …
Claim 22 depend either directly or indirectly from the objection of claim 21, therefore they are also objected.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and
distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claim 3 recites the limitation "the programmed non-apoptotic cell death comprises …". There is insufficient antecedent basis for this limitation in the claim.
Claim 8 is rejected under 35 U.S.C. 112(b), as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
MPEP 2143.03 (I): “If a claim is subject to more than one interpretation, at least one of which would render the claim unpatentable over the prior art, the examiner should reject the claim as indefinite under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph (see MPEP § 2175) and should reject the claim over the prior art based on the interpretation of the claim that renders the prior art applicable. (Ex parte Ionescu, 222 USPQ 537 (Bd. Pat. App. & Inter. 1984).”
Claim 8 recite “wherein the cells of the second subset of the cells are input to the inlet of the fluidic channel separately from the cells of the first subset of the cells.” It is unclear how the cells can be "pooled" together (as required by parent Claim 7) and simultaneously input "separately" (as required by Claim 8) to the same inlet, creating a contradiction that renders the scope of the claim indefinite. However, for searching for limitations, the interpretation that the subsets of cells are input separately has been used.
1st 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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 5, 11, 12, 13, 15, 16, 17, 21, and 22 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) in view of US Patent Publication 2022 0358646 A1, (Ryan et al.).
Claim 1
Regarding claim 1, Loewke et al. teach a method of processing, the method comprising: using a machine learning encoder to extract respective sets of machine learning (ML)-based features from respective images of cells that are dying and unstained, ("training a machine learning classifier, with a training dataset, to identify each of the set of cell stages of the cell population captured in the set of images, using the set of feature vectors for each image in the set of images," par. 27) wherein cells of a first subset of the cells are at a first state of dying, ("determining one or more cell death-related parameters (e.g., apoptosis-related parameters), from an output of the cell stage classification module of Block S120, that quantify an amount of dead cells in the cell population," par. 43) and wherein cells of a second subset of the cells are at a second state of dying that is different than the first state of dying; ("variations of Block S120 and/or S126, identification of a specific stage of cells (e.g., a single-cell stage, a medium-compaction stage, a full-compaction stage, a dead cell stage, a differentiated cell stage, a debris stage, and a background stage) can motivate additional processing to further classify cell subpopulations of the cell population (e.g., as belonging to multiple classifications) captured in the set of images," par. 31) using a computer vision encoder to extract ("the machine learning algorithm(s) can be characterized by a learning style including any one or more of: … a deep learning algorithm (e.g., a restricted Boltzmann machine, a deep belief network method, a convolution network method, a stacked auto-encoder method, etc.)," par. 32) respective sets of cell morphometric features from the respective images; ("algorithmic modules configured to extract relevant features (e.g., morphological features, features related to cell dynamics) from image data," par. 18) using the respective sets of ML-based features ("algorithmic modules configured to extract relevant features (e.g., morphological features, features related to cell dynamics) from image data," par. 18) and the respective sets of cell morphometric features to the first state of dying or to the second state of dying, ("algorithmic modules configured to extract relevant features (e.g., morphological features, features related to cell dynamics) from image data," par. 18) a phenotypic difference between the cells of the first subset and the cells of the second subset ("processing the feature vector(s) can be performed according to any other suitable image- or non-image-based parameter, in order to generate feature vectors associated with pixels of each image. In Block S126, training the machine learning classifier functions to enable automatic identification of each of the set of cell stages captured in the set of images, by using a training dataset along with the set of feature vectors for each image," par. 29-30).
Loewke et al. do not explicitly teach all of to generate respective multi-dimensional feature vectors that represent respective cell phenotypes; and using the respective multi-dimensional feature vectors to correlate.
However, Ryan et al. teach to generate respective multi-dimensional feature vectors that represent respective cell phenotypes; ("Mapping the action potential features of the diseased neurons and healthy cells provides a phenotype for the disease, which can be described using a vector on a multidimensional space," par. 107) and using the respective multi-dimensional feature vectors to correlate ("˜300 features/parameters are identified and mapped onto a ˜300 dimensional space as vectors. The vectors thus describe the disease phenotype and/or compound effects on the cells as indicated by the measured action potential features," par. 102).
Therefore, taking the teachings of Loewke et al. and Ryan et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. to use dimensional feature mapping as taught by Ryan et al. The suggestion/motivation for doing so would have been that, “reducing the optical signals from raw video, to action potentials (e.g., as voltage traces), action potential features and patterns, and finally, functional phenotypes, allows the systems and methods of the invention to significantly reduce the data footprint required to derive meaningful and multidimensional measurements of cellular behavior. In conjunction with data compression methods described below, this allows cellular behaviors to be efficiently stored and manipulated in a database, which allows high-throughput analyses of, for example, cell type, cell states, disease phenotype, and pharmacological response” as noted by the Ryan et al. disclosure in paragraph [0009], which also motivates combination because the combination would predictably have a higher optimization as there is a reasonable expectation that the combination would result in a faster, more accurate, and more efficient method for classifying cell populations, reducing data storage requirements while improving the ability to distinguish between functional phenotypes; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 5
Regarding claim 5, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach wherein the cells further comprise a plurality of additional subsets of cells that are at different states of dying than one another ("determining one or more cell death-related parameters (e.g., apoptosis-related parameters), from an output of the cell stage classification module of Block S120, that quantify an amount of dead cells in the cell population," par. 43).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 11
Regarding claim 11, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach the first state of dying to a feature in the multi-dimensional feature vectors that is present in the cells of the first subset and is not present in the cells of the second subset ("variations of Block S120 and/or S126, identification of a specific stage of cells (e.g., a single-cell stage, a medium-compaction stage, a full-compaction stage, a dead cell stage, a differentiated cell stage, a debris stage, and a background stage) can motivate additional processing to further classify cell subpopulations of the cell population (e.g., as belonging to multiple classifications) captured in the set of images," par. 31).
Loewke et al. do not explicitly teach all of wherein the correlating comprises informatically linking.
However, Ryan et al. teach wherein the correlating comprises informatically linking ("Mapping the action potential features of the diseased neurons and healthy cells provides a phenotype for the disease, which can be described using a vector on a multidimensional space," par. 107).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 12
Regarding claim 12, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach wherein the images are brightfield cell images ("the image data can comprise images derived from any one or more of: phase contrast microscopy (e.g., low-light phase contrast microscopy), fluorescent microscopy, darkfield microscopy, brightfield microscopy," par. 22).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 13
Regarding claim 13, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach wherein the machine learning encoder uses a convolutional neural network or a vision transformer ("the machine learning algorithm(s) can be characterized by a learning style including any one or more of: … a deep learning algorithm (e.g., a restricted Boltzmann machine, a deep belief network method, a convolution network method, a stacked auto-encoder method, etc.)," par. 32).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 15
Regarding claim 15, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach wherein the machine learning encoder extracts n ML-based features, ("training a machine learning classifier, with a training dataset, to identify each of the set of cell stages of the cell population captured in the set of images, using the set of feature vectors for each image in the set of images," par. 27) the computer-vision encoder extracts m cell morphometric features ("algorithmic modules configured to extract relevant features (e.g., morphological features, features related to cell dynamics) from image data," par. 18).
Loewke et al. do not explicitly teach all of wherein the feature vectors have n+m dimensions, and wherein n and m are positive integers.
However, Ryan et al. teach wherein the feature vectors have n+m dimensions, and wherein n and m are positive integers ("˜300 features/parameters are identified and mapped onto a ˜300 dimensional space as vectors. The vectors thus describe the disease phenotype and/or compound effects on the cells as indicated by the measured action potential features," par. 102).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 16
Regarding claim 16, Loewke et al. and Ryan et al. teach the method of claim 15 as noted above.
Loewke et al. do not explicitly teach all of wherein within each of the feature vectors, each dimension of the n+m dimensions is an element of that feature vector.
However, Ryan et al. teach wherein within each of the feature vectors, each dimension of the n+m dimensions is an element of that feature vector ("In some embodiments, ˜300 features/parameters are identified and mapped onto a ˜300 dimensional space as vectors," par. 109).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 17
Regarding claim 17, Loewke et al. and Ryan et al. teach the method of claim 15 as noted above.
Loewke et al. do not explicitly teach all of wherein the element is a numeric value.
However, Ryan et al. teach wherein the element is a numeric value ("In some embodiments, ˜300 features/parameters are identified and mapped onto a ˜300 dimensional space as vectors," par. 109).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 21
Regarding claim 21, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach to the first state of dying or the second state of dying, ("determining one or more cell death-related parameters (e.g., apoptosis-related parameters), from an output of the cell stage classification module of Block S120, that quantify an amount of dead cells in the cell population," par. 43) the phenotypic difference between the cells of the first subset and the cells of the second subset ("determination of parameters related to any one or more of: … differentiated cell morphology state as determined from an output of a cell cluster segmentation module configured to identify morphological features (e.g., roundedness, flatness, dendritic phenotype, etc.) of individual and clustered cells; … and any other suitable parameters related to normal or abnormal cell phenotype," par. 45).
Loewke et al. do not explicitly teach all of reducing dimensionalities of the multi-dimensional feature vectors to generate lower- dimensional vectors, wherein the lower-dimensional vectors are used to correlate .
However, Ryan et al. teach further comprising reducing dimensionalities of the multi-dimensional feature vectors to generate lower- dimensional vectors, wherein the lower-dimensional vectors are used to correlate ("With high dimensional data, the number of features may far exceed the number of observations. High-dimensional readouts tend to perform poorly in many clustering, matching, and classification tasks, because high-dimensional spaces are sparse and most vectors are orthogonal. Some embodiments reduce a total number of features to a limited subset, a smaller number of the features, that are actually presented to the machine learning system," par. 112).
Loewke et al. and Ryan et al. are combined as per claim 1.
Claim 22
Regarding claim 22, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach that is present in the cells of the first subset and is not present in the cells of the second subset ("determining one or more cell death-related parameters (e.g., apoptosis-related parameters), from an output of the cell stage classification module of Block S120, that quantify an amount of dead cells in the cell population," par. 43) ("variations of Block S120 and/or S126, identification of a specific stage of cells (e.g., a single-cell stage, a medium-compaction stage, a full-compaction stage, a dead cell stage, a differentiated cell stage, a debris stage, and a background stage) can motivate additional processing to further classify cell subpopulations of the cell population (e.g., as belonging to multiple classifications) captured in the set of images," par. 31).
Loewke et al. do not explicitly teach all of wherein the correlating comprises informatically linking the first state of dying to a feature cluster in a space defined by the lower-dimensional vectors
However, Ryan et al. teach wherein the correlating comprises informatically linking the first state of dying to a feature cluster in a space defined by the lower-dimensional vectors ("With high dimensional data, the number of features may far exceed the number of observations. High-dimensional readouts tend to perform poorly in many clustering, matching, and classification tasks, because high-dimensional spaces are sparse and most vectors are orthogonal. Some embodiments reduce a total number of features to a limited subset, a smaller number of the features, that are actually presented to the machine learning system," par. 112).
Loewke et al. and Ryan et al. are combined as per claim 1.
2nd Claim Rejections - 35 USC § 103
Claims 2, 3, and 4 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2026 0017958 A1, (Takeuchi et al.).
Claim 2
Regarding claim 2, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the first and second states of dying are independently selected from the group consisting of non-programmed cell death, non-apoptotic cell death, necroptosis, or programmed apoptotic cell death.
However, Takeuchi et al. teach wherein the first and second states of dying are independently selected from the group consisting of non-programmed cell death, non-apoptotic cell death, necroptosis, or programmed apoptotic cell death ("there are cell deaths called programmed cell deaths, which are represented by apoptosis, in addition to cell deaths incidentally caused by external factors, which are represented by necrosis," par. 2) ("the cells that have undergone programmed cell death include cells that have undergone one or more cell deaths selected from the group consisting of apoptosis, necroptosis, ferroptosis, pyroptosis, parthanatos, entosis, NETosis, and autophagic cell death," par. 21).
Therefore, taking the teachings of Loewke et al., Ryan et al., and Takeuchi et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use a variety of states/types of cell death as taught by Takeuchi et al. The suggestion/motivation for doing so would have been that, “wherein the cells that have undergone programmed cell death include cells that have undergone one or more cell deaths selected from the group consisting of apoptosis, ferroptosis, pyroptosis, parthanatos, entosis, NETosis, and autophagic cell death” as noted by the Takeuchi et al. disclosure in paragraph [0030], which also motivates combination because the combination would predictably have a greater utility as there is a reasonable expectation that the system could be used to classify a much wider, more heterogeneous, and complex range of pathological states and cellular processes; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 3
Regarding claim 3, Loewke et al., Ryan et al., and Takeuchi et al. teach the method of claim 2 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the programmed non-apoptotic cell death comprises at least one selected from the group consisting of vacuole-presenting cell death, mitochondrial-dependent cell death, iron-dependent cell death, and immune-reactive cell death.
However, Takeuchi et al. teach wherein the programmed non-apoptotic cell death comprises at least one selected from the group consisting of vacuole-presenting cell death, mitochondrial-dependent cell death, iron-dependent cell death, and immune-reactive cell death ("the cells that have undergone programmed cell death include cells that have undergone one or more cell deaths selected from the group consisting of apoptosis, necroptosis, ferroptosis, pyroptosis, parthanatos, entosis, NETosis, and autophagic cell death," par. 21).
Loewke et al., Ryan et al., and Takeuchi et al. are combined as per claim 2.
Claim 4
Regarding claim 4, Loewke et al., Ryan et al., and Takeuchi et al. teach the method of claim 2 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the programmed apoptotic cell death comprises at least one of apoptosis and anoikis.
However, Takeuchi et al. teach wherein the programmed apoptotic cell death comprises at least one of apoptosis and anoikis ("there are cell deaths called programmed cell deaths, which are represented by apoptosis, in addition to cell deaths incidentally caused by external factors, which are represented by necrosis," par. 2).
Loewke et al., Ryan et al., and Takeuchi et al. are combined as per claim 2.
3rd Claim Rejections - 35 USC § 103
Claims 6, 7, 9, and 10 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2025 0153190 A1, (Chiu et al.).
Claim 6
Regarding claim 6, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach inputting the cells of the first subset of the cells to an inlet ("In some instances, the fluid sample includes cells," par. 49) of a fluidic channel; ("the channel 202 includes an inlet 2022 and an outlet 2024. The inlet 2022 is configured to introduce the sample into the channel," par. 163) flowing the cells of the first subset of the cells from the inlet through the fluidic channel; the first subset of the cells within the fluidic channel ("the channel 202 includes an inlet 2022 and an outlet 2024. The inlet 2022 is configured to introduce the sample into the channel," par. 163).
Loewke et al. and Ryan et al. do not explicitly teach all of generating the respective images of the cells.
However, Chiu et al. teach generating the respective images of the cells ("receiving image data corresponding to a set of images of the cell population," par. 17).
Therefore, taking the teachings of Loewke et al., Ryan et al., and Chiu et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use the microfluidic chamber configuration as taught by Chiu et al. The suggestion/motivation for doing so would have been that, “The at least one array of electrodes is configured to apply dielectrophoretic (DEP) forces to the fluid flowing through the microfluidic chamber 102. DEP refers to a force which can act upon particles in a non-uniform electric field. As a result of differing particle properties, DEP can sort/separate particles in static or flowing fluids” as noted by the Chiu et al. disclosure in paragraph [0099], which also motivates combination because the combination would predictably have a higher optimization as there is a reasonable expectation that the resulting device would achieve high-selectivity, label-free sorting of cell samples by effectively combining precise electrical manipulation (DEP) of cells; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 7
Regarding claim 7, Loewke et al., Ryan et al., and Chiu et al. teach the method of claim 6 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the cells of the first subset of cells are pooled with the second subset of cells, such that inputting the cells of the first subset of the cells to the inlet of the fluidic channel further comprises inputting the cells of the second subset of the cells to the inlet of the fluidic channel.
However, Chiu et al. teach wherein the cells of the first subset of cells are pooled with the second subset of cells, ("and a plurality of outlets configured to collect a plurality of types of particles in the sample," par. 11) such that inputting the cells of the first subset of the cells to the inlet of the fluidic channel further comprises inputting the cells of the second subset of the cells to the inlet of the fluidic channel ("the channel 202 includes an inlet 2022 and an outlet 2024. The inlet 2022 is configured to introduce the sample into the channel," par. 163).
Loewke et al., Ryan et al., and Chiu et al. are combined as per claim 6.
Claim 9
Regarding claim 9, Loewke et al., Ryan et al., and Chiu et al. teach the method of claim 6 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of further comprising collecting the cells of the first subset of the cells at an outlet of the fluidic channel.
However, Chiu et al. teach further comprising collecting the cells of the first subset of the cells at an outlet of the fluidic channel ("and a plurality of outlets configured to collect a plurality of types of particles in the sample," par. 11).
Loewke et al., Ryan et al., and Chiu et al. are combined as per claim 6.
Claim 10
Regarding claim 10, Loewke et al., Ryan et al., and Chiu et al. teach the method of claim 9 as noted above.
Loewke et al. also teach using the phenotypic difference between the cells of the first subset and the cells of the second subset ("determination of parameters related to any one or more of: … differentiated cell morphology state as determined from an output of a cell cluster segmentation module configured to identify morphological features (e.g., roundedness, flatness, dendritic phenotype, etc.) of individual and clustered cells; … and any other suitable parameters related to normal or abnormal cell phenotype," par. 45).
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the outlet comprises a first and a second reservoirs, the method further comprising sorting the cells into the first reservoir or into the second reservoir.
[AltContent: textbox (Figure 1B shows the edge configuration for sorting particles in a sample.)]
PNG
media_image1.png
472
544
media_image1.png
Greyscale
However, Chiu et al. teach wherein the outlet comprises a first and a second reservoirs, ("Referring to FIG. 1B, bubble 154 shows an expanded view of the edge configuration of the first array 104 of electrodes near the sidewall 156 of the microfluidic chamber," par. 130) the method further comprising sorting the cells into the first reservoir or into the second reservoir ("configured to operate based on different sets of parameters to apply different DEP forces to the fluid flowing through the microfluidic chamber 102 so as to sort/separate different types of particles in the sample. For example, the first array 104 of electrodes is configured to apply DEP forces to sort/separate a first type of particle in the sample; the second array 106 of electrodes is configured to sort/separate a second type of particle in the sample," par. 115).
Loewke et al., Ryan et al., and Chiu et al. are combined as per claim 6.
4th Claim Rejections - 35 USC § 103
Claim 8 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2025 0153190 A1, (Chiu et al.) and US Patent Publication 2021 0387186 A1, (Hayden et al.).
Claim 8
Regarding claim 8, Loewke et al., Ryan et al., and Chiu et al. teach the method of claim 7 as noted above.
Loewke et al., Ryan et al., and Chiu et al. do not explicitly teach all of wherein the cells of the second subset of the cells are input to the inlet of the fluidic channel separately from the cells of the first subset of the cells.
However, Hayden et al. teach wherein the cells of the second subset of the cells are input to the inlet of the fluidic channel separately from the cells of the first subset of the cells ("the channel comprises separate inlets for the first type of particles and for the second type of particles to independently introduce the first type of particles and the second type of particles into the fluid stream in the fluid guiding section," par. 90).
Therefore, taking the teachings of Loewke et al., Ryan et al., Chiu et al., and Hayden et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use the microfluidic chamber configuration as taught by Chiu et al. and separately inputting different types of particles as taught by Hayden et al. The suggestion/motivation for doing so would have been that, “particles of at least one type comprise a first type of particles and a second type of particles and the method further comprises controlling a supply of the first type of particles and of the second type of particles into the fluid stream, such that said current cluster constitution approaches said target cluster constitution” as noted by the Hayden et al. disclosure in paragraph [0089], which also motivates combination because the combination would predictably have a reduced flow distance as there is a reasonable expectation that incorporating a controlled, multi-type particle supply into the specified microfluidic chamber configuration would permit precise, real-time adjustments of particle cluster populations within the fluid stream, thereby optimizing the desired cluster constitution at the point of analysis; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
5th Claim Rejections - 35 USC § 103
Claim 14 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2022 0293272 A1, (Pang et al.).
Claim 14
Regarding claim 14, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach wherein the computer-vision encoder ("the machine learning algorithm(s) can be characterized by a learning style including any one or more of: … a deep learning algorithm (e.g., a restricted Boltzmann machine, a deep belief network method, a convolution network method, a stacked auto-encoder method, etc.)," par. 32).
Loewke et al. and Ryan et al. do not explicitly teach all of uses a human-constructed algorithm.
However, Pang et al. teach uses a human-constructed algorithm ("at least part of this process is automated, requiring computation through an ETL pipeline with rule-based algorithms and/or neural networks," par. 25).
Therefore, taking the teachings of Loewke et al., Ryan et al., and Pang et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use the rule-based algorithm as taught by Pang et al. The suggestion/motivation for doing so would have been that, “at least part of this process is automated, requiring computation through an ETL pipeline with rule-based algorithms and/or neural networks” as noted by the Pang et al. disclosure in paragraph [0025], which also motivates combination because the combination would predictably have a higher accuracy as there is a reasonable expectation that the automated, rule-based algorithm would reliably analyze large datasets for cell population classifications with increased accuracy, efficiency, and robustness; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
6th Claim Rejections - 35 USC § 103
Claims 18 and 19 are rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2020 0167914 A1, (Stamatoyannopoulos et al.).
Claim 18
Regarding claim 18, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the ML-based features are orthogonal to one another.
However, Stamatoyannopoulos et al. teach wherein the ML-based features are orthogonal to one another ("a set of eigenvectors (also known as characteristic vectors, proper vectors, or latent vectors) that form an orthogonal basis set of unit vectors (each denoting an orthogonal axis of a multi-dimensional space) which, in combination with a corresponding set of eigenvalues (or scalar values) may be used to describe a multi-dimensional input data set (or input data vector)," par. 81).
Therefore, taking the teachings of Loewke et al., Ryan et al., and Stamatoyannopoulos et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use orthogonal latent vectors as taught by Stamatoyannopoulos et al. The suggestion/motivation for doing so would have been that, “The transformation is defined in such a way that the first principal component has the largest possible variance (i.e., accounts for as much of the variability in the input data set as possible), and each succeeding component in turn has the highest variance possible under the constraint that it is orthogonal to the preceding components” as noted by the Stamatoyannopoulos et al. disclosure in paragraph [0082], which also motivates combination because the combination would predictably have a higher success rate in capturing the maximum variance within the cell image data as there is a reasonable expectation that maximizing variance through orthogonal transformation (e.g., principal component analysis) would provide a more optimized, compact, and descriptive set of features for classifying cell populations; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Claim 19
Regarding claim 19, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. also teach the cell morphometric features ("algorithmic modules configured to extract relevant features (e.g., morphological features, features related to cell dynamics) from image data," par. 18).
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the ML-based features are orthogonal.
However, Stamatoyannopoulos et al. teach wherein the ML-based features are orthogonal ("a set of eigenvectors (also known as characteristic vectors, proper vectors, or latent vectors) that form an orthogonal basis set of unit vectors (each denoting an orthogonal axis of a multi-dimensional space) which, in combination with a corresponding set of eigenvalues (or scalar values) may be used to describe a multi-dimensional input data set (or input data vector)," par. 81).
Loewke et al., Ryan et al., and Stamatoyannopoulos et al. are combined as per claim 18.
7th Claim Rejections - 35 USC § 103
Claim 20 is rejected under 35 U.S.C. 103 as obvious over US Patent Publication 2015 0087240 A1, (Loewke et al.) and US Patent Publication 2022 0358646 A1, (Ryan et al.) in view of US Patent Publication 2025 0251388 A1, (Champetier et al.).
Claim 20
Regarding claim 20, Loewke et al. and Ryan et al. teach the method of claim 1 as noted above.
Loewke et al. and Ryan et al. do not explicitly teach all of wherein the cell morphometric features are selected from the group consisting of position features, cell shape features, pixel intensity features, texture features, and focus features.
However, Champetier et al. teach wherein the cell morphometric features are selected from the group consisting of position features, cell shape features, pixel intensity features, texture features, and focus features ("said extracted phenotypic features are selected from the group consisting of intensity features, granularity features, intensity distribution features, texture features, size and shape features, colocalization features, run-length grey level matrix-based features, wavelet transform based features and combinations thereof, preferably selected from the group consisting of intensity features, granularity features, intensity distribution features, texture features, and any combinations thereof," par. 59).
Therefore, taking the teachings of Loewke et al., Ryan et al., and Champetier et al. as a whole, it would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify imaging and classifying cell populations as taught by Loewke et al. and dimensional feature mapping as taught by Ryan et al. to use a variety of morphometric features as taught by Champetier et al. The suggestion/motivation for doing so would have been that, “phenotypic features are selected from the group consisting of intensity features, granularity features, intensity distribution features, texture features, size and shape features, colocalization features, run-length grey level matrix-based features, wavelet transform based features and combinations thereof, preferably selected from the group consisting of intensity features, granularity features, intensity distribution features, texture features, and any combinations thereof.” as noted by the Champetier et al. disclosure in paragraph [0059], which also motivates combination because the combination would predictably have a higher utility as there is a reasonable expectation that a broader, more comprehensive analysis of the cellular phenotype—derived from combining multiple independent feature sets—will yield a more robust and accurate classification of cell types, developmental stages, or functional states compared to using any single class of features alone; and/or because doing so merely combines prior art elements according to known methods to yield predictable results.
Reference Cited
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure.
US Patent Publication 2020 0402628 A1 to Victors et al. discloses evaluating cell-based assay query perturbations by computing composite vectors that represent the difference in central tendency measurements between control cell aliquots and, respectively, test aliquots and query perturbation aliquots.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KARSTEN F LANTZ whose telephone number is (571) 272-4564. The examiner can normally be reached Monday-Friday 8:00-4:00.
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, Ms. Jennifer Mehmood can be reached on 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.
/Karsten F. Lantz/Examiner, Art Unit 2664
Date: 4/10/2026
/NANCY BITAR/Primary Examiner, Art Unit 2664
Prosecution Insights