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 .
Claim Status
Claims 1-21 are pending and examined herein.
Claims 1-21 are rejected.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. Claims 1-21 are granted the claim to the benefit of priority to foreign application JP2021-103918 filed 23 June 2021. Thus, the effective filling date of claims 1-21 is 23 June 2021.
Information Disclosure Statement
The information disclosure statements (IDS) were received on 14 December 2023 and 14 February 2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements have been considered by the examiner.
Drawings
The drawings received on 14 December 2023 are accepted.
Claim Interpretation
112/f
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier.
Such claim limitations are:
“a light receiving unit configured to receive light emitted from a biologically derived particle” in claims 1 and 15.
“a dimensional compression unit configured to generate dimensionally compressed data…” in claims 1 and 14.
“a learning unit configured to construct a machine learning model based on the dimensionally compressed data and the multidimensional data” in claims 1 and 14.
“an analysis unit configured to estimate another dimensionally compressed data corresponding to another multidimensional data using the machine learning model constructed by the learning unit” in claim 8.
“a sorting unit configured to sort the biologically derived particle as a sorting target” in claim 10.
“a determination unit configured to determine whether the biologically derived particle is the sorting target based on the dimensionally compressed data…” in claim 11.
“an output unit configure to present, in real time and within two-dimensional or three-dimensional coordinate space, to a user, the dimensionally compressed data…” in claim 13.
“the determination unit is configured to determine whether the biologically derived particle is the sorting target based on whether the two-dimensional or three-dimensional…” in claim 13.
“an information processing apparatus configured to: access multidimensional data… and generate, with a machine learning model, coordinate information…” in claim 15.
“the information processing apparatus is further configured to: access second multidimensional data…, generate, with the machine learning model, second coordinate information of a second dimensionally… and comparing the second dimensionally compressed map…” in claim 17.
“the information processing apparatus is further configured to identify a cell population in the first biologically derived particle…” in claim 19.
The instant disclosure provides the corresponding structure of the information processing apparatus which encompasses a device with a processor and memory for performing the recited functions (instant disclosure [0124]-[0125] and Fig. 17). The “dimensional compression unit”, “learning unit”, “analysis unit”, and “determination unit” is interpreted as being software which is implemented with the computer hardware of the information processing apparatus. The corresponding algorithm for the “dimensional compression unit” is shown in [0034]-[0036] of the disclosure. The corresponding algorithm for the learning unit is shown in [0040]-[0045] of the disclosure. The corresponding algorithm for the “analysis unit” is shown in [0049]-[0050] of the disclosure. The corresponding algorithm for the “determination unit” is shown in [0108] of the instant disclosure. The instant disclosure provides the corresponding structure of the output unit as a device capable of presenting the dimensionally compressed data estimated as a display device (see instant disclosure [0050]). The instant disclosure provides the corresponding structure of the sorting unit (see instant disclosure [0099]). The instant disclosure provides the corresponding structure for the light receiving unit as a photodetector (see instant disclosure [0015]-[0016]).
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 112
112/b
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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 13 and 14 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 13 recites “present, in real time and within two-dimensional or three-dimensional coordinate space, to a user…” which renders the metes and bounds of the claim indefinite. The indefiniteness arises because it is unclear what amount of time or timeframe is encompassed by the limitation of “in real time”. The specification does not provide a clear and precise definition of the limitation, nor would one skilled in the art recognize the metes and bounds of said limitation. For the sake of furthering examination this limitation will be interpreted as “present, within two-dimensional or three-dimensional coordinate space, to a user…”.
Claim 14 recites “the multidimensional” in line 7 of the claim. There is insufficient antecedent basis for this limitation in the claim. The indefiniteness arises because the claim does not make clear what “the multidimensional” is referring to in the claim. This rejection could be overcome by amendment of this limitation to “the multidimensional data”. For the sake of furthering examination this limitation will be interpreted as “the multidimensional data”.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10 and 14-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
(Step 1)
Claims 1-10 and 14-21 fall under the statutory category of a machine.
(Step 2A Prong 1)
Under the BRI, the instant claims recite judicial exceptions that are an abstract idea of the type that is in the grouping of a “mental process”, such as procedures for evaluating, analyzing or organizing information, and forming judgement or an opinion. The instant claims further recite judicial exceptions that are an abstract idea of the type that is in the grouping of a “mathematical concept”, such as mathematical relationships and mathematical equations.
Claims 1 and 14 recite a mathematical concept of “generate dimensionally compressed data by dimensionally compressing multidimensional data from the light receiving compressing multidimensional data… wherein the multidimensional data corresponds to light output from a biologically derived particle”.
Claim 15 recites a mathematical concept of “generate coordinate information of a dimensionally compressed map based on the multidimensional data”.
Dependent claim 8 recites a mathematical concept of “estimate another dimensionally compressed data…”. Dependent claim 17 recites a mathematical concept of “generate second coordinate information of a second…”. Dependent claim 17 recites a mental process of “comparing the second dimensionally compressed map with the first dimensionally compressed map”. Dependent claim 18 recites a mental process of “determine whether the second biologically derived particle differs…”. Dependent claim 19 recites a mental process of “wherein the first biologically derived particle is from a patient, and the second biologically derived particle is from a healthy person” and “identify a cell population in the first biologically derived particle rather than in the second biologically derived particle based on comparison results…”.
The claims recite mathematical concepts of mathematical calculations as generating dimensionally compressed data by dimensionally compressing multidimensional data, estimating dimensionally compressed data, and generate coordinate information of a dimensionally compressed map based on the multidimensional data (which encompasses a mathematical calculation using a function that maps numerical data from a high-dimensional representation into a lower dimensional representation see instant disclosure [0037]).
The claims recite mental processes of analyzing/evaluating data and making judgments as determine whether the biologically derived particle is the sorting target based on criteria, comparing the second and the first dimensionally compressed maps, and identifying cell populations within the data. The human mind is capable of performing these analyses because they encompass abstract data analysis, performing comparisons, and making judgments based on criteria. Dependent claims 2- 4, 9, 20, and 21 further limit the mental process/mathematical concept recited in the independent claim but do not change their nature as a mental process/mathematical concept. Thus, claims 1-10 and 14-21 recite abstract ideas.
(Step 2A Prong 2)
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). Integration into a practical application is evaluated by identifying whether there are any additional elements recited in the claim and evaluating those additional elements to determine whether they integrate the exception into a practical application.
The additional element in claim 1 and claim 15 of a particle analysis apparatus comprising a light receiving unit configured to receive light emitted from a biologically derived particle and the additional elements in claims 15 and 17 of accessing this data in a computer environment does not integrate the judicial exceptions to a practical application because this additional element constitutes as insignificant extra solution activity of data gathering (see MPEP 2106.05(g)). This constitutes as insignificant extra solution activity because this only interacts with the judicial exception by providing data to be analyzed by the judicial exceptions.
The additional element in claims 1, 5, 8, 14, and 15 of an information processing apparatus, a dimensional compression unit, a learning unit, an analysis unit (which is interpreted as a general purpose computer including a processor and memory) to perform judicial exceptions does not integrate the judicial exceptions into a practical application because this is applying the judicial exceptions to a generic computer without an improvement to computer technology (see MPEP 2106.04(d)(1)). The generic computer only interacts with the recited judicial exceptions in a manner by being invoked as a tool to perform the judicial exceptions.
The additional element in claims 1 and 14 of constructing a machine learning model, the additional element in claims 5-7 which limits the constructing to using a neural network (comprising an input layer, two intermediate layers, and an output layer) with a certain amount of nodes and being optimized using the training data, the additional element in claims 8, 15, and 17 of using the machine learning model, the additional element in claim 16 which limits how the machine learning model was trained does not integrate the judicial exceptions into a practical application because this is generally linking the recited judicial exceptions of performing dimensionality reduction on collected from multidimensional data from a biologically derived particle to machine learning/neural network technology (see MPEP 2106.05(h)). It is noted that the abstract data being used to train the neural network/machine learning model falls under the judicial exception itself (i.e., the additional element is constructing and using the neural network and the performance of dimensionality reduction falls under the abstract idea).
The additional element in claim 10 of the particle analysis apparatus further comprises a sorting unit configured to sort the biologically derived particle as a sorting target does not integrate the judicial exceptions into a practical application because this additional element constitutes as generally linking the judicial exceptions to the particle technological environment of particle analysis apparatus configured to sort biologically derived particles (see MPEP 2106.05(h)).
Thus, the additional elements do not integrate the judicial exceptions into a practical application and claims 1-10 and 14-21 are directed to the abstract idea.
(Step 2B)
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because:
The additional element in claim 1 and claim 15 of a particle analysis apparatus comprising a light receiving unit configured to receive light emitted from a biologically derived particle and the additional elements in claims 15 and 17 of accessing this data in a computer environment is conventional as shown by Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023) and Lin and Owsley et al. (US 20200333236 A1).
The additional elements in claims 1, 5, 8, 14, and 15 of an information processing apparatus, a dimensional compression unit, a learning unit, an analysis unit (which is interpreted as a general purpose computer including a processor and memory) to perform judicial exceptions is conventional as shown by MPEP 2106.05(b) and MPEP 2106.05(d)(II).
The additional element in claim 10 of the particle analysis apparatus further comprises a sorting unit configured to sort the biologically derived particle as a sorting target is conventional as shown by Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023) and Lin and Owsley et al. (US 20200333236 A1).
The additional element in claims 1 and 14 of constructing a machine learning model, the additional element in claims 5-7 which limits the constructing to using a neural network (comprising an input layer, two intermediate layers, and an output layer) with a certain amount of nodes and being optimized using the training data, the additional element in claims 8, 15, and 17 of using the machine learning model, the additional element in claim 16 which limits how the machine learning model was trained is conventional as shown by which shows constructing and using a neural network for to dimensionally compress data from a high dimensional space to a low dimensional space Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023) and page 338 of Roman-Rangel (Engineering Applications of Artificial Intelligence 81 (2019): 336-345).
Thus, the additional elements are not sufficient to amount to significantly more than the judicial exception because they are conventional.
Examiner Comment
It is noted that claims 11-13 are not rejected under 35 U.S.C. 101 because these claims integrate the judicial exception of performing dimensionality reduction by constructing the machine learning model which is used to determine the sorting target which the sorting unit is configured to physically sort. Thus, the combination of the additional elements of constructing the machine learning model, the sorting unit configured to sort the biologically derived particle as a sorting target integrates the judicial exceptions of performing dimensionality reduction and determining a sorting target based on the dimensionally compressed data because these claims provide a particular machine imposes meaningful limits on the recited judicial exceptions (i.e., the judicial exceptions are tied to the machine operation of physically sorting the particles). It is noted that claims 12 and 13 are not rejected due to including all the limitations of claim 11 due to their dependency on claim 11.
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.
Claims 1, 2, 5-12, and 14-16 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023).
Claim 1 is directed to a particle analysis system comprising a particle analysis apparatus comprising a light receiving unit configured to receive light emitted from a biologically derived particle
Lin et al. shows systems having a light detection system for characterizing particles of a sample in a flow stream (such as cells in a biological sample) with a photodetector configured to generate data signals from light detected from the particles in the flow stream (Lin et al. [0058]).
and an information processing apparatus comprising a dimensional compression unit configured to generate dimensionally compressed data by dimensionally compressing multi-dimensional data corresponding to light output from a biologically derived particle
Lin et al. shows systems including one or more processing devices and computer readable storage medium comprising instructions that receives measurement data from a particle analyzer and converts the measurements using a non-parametric transformation into initial transformation measurements (Lin et al. [0021]). Lin et al. shows that the non-parametric transformation includes a t-distributed stochastic neighbor embedding (t-SNE) which is a nonlinear dimensionality reduction technique (Lin et al. [0039] and [0040]).
and a learning unit configured to construct a machine learning model based on the dimensionally compressed data and the multidimensional data.
Lin et al. shows the system is configured to generate a parametric model to receive as input raw measurements for the first portion of particles and generate as an output the initial transformed measurements (Lin et al. [0021]). Lin et al. shows that this parametric model includes a neural network which is generated/trained to approximate the non-parametric transformation based on the dimensionally compressed data and the multi-dimensional data (Lin et al. [0039] – [0041]). Lin et al. further shows that the pre- and post-t-SNE data may be used to train a neural network that learns the transformation between the original data space and the dimensionality reduced space (Lin et al. [0046]).
Claim 2 is directed to wherein the dimensional compression unit is configured to dimensionally compress the multidimensional data using a nonlinear method.
Lin et al. shows that the non-parametric transformation includes a t-distributed stochastic neighbor embedding (t-SNE) which is a nonlinear dimensionality reduction technique (Lin et al. [0039] and [0040]).
Claim 5 is directed to wherein the learning unit is configured to construct the machine learning model using a neural network comprising an input layer, two or more intermediate layers, and an output layer.
Lin et al. shows the neural network can consist of an entry layer with a number of nodes equivalent to the dimensionality of the untransformed data, four fully connected layers, and an output layer of two nodes (Lin et al. [0041]).
Claim 6 is directed to wherein a number of nodes of the input layer is same as a number of dimensions of the multidimensional data, and a number of nodes of the output layer is same as a number of dimensions of the dimensionally compressed data.
Lin et al. shows the neural network can consist of an entry layer with a number of nodes equivalent to the dimensionality of the untransformed data, four fully connected layers, and an output layer of two nodes (Lin et al. [0041]). Lin et al. further shows that the neural network represents a transformation between the space occupied by the original, untransformed data and the space occupied by the transformed data which is interpreted that the output layer is the same as a number of dimensions in the dimensionally compressed data (Lin et al. [0042]).
Claim 7 is directed to wherein a network structure and weighting of the neural network are optimized by applying the multidimensional data to the input layer and applying the dimensionally compressed data to the output layer.
Lin et al. shows the pre- and post tSNE data is used to train a neural network that learns the transformation between the original data space and the dimensionality reduced space by optimizing the weighting and structure of the network to produce the desired results (Lin et al. [0041], [0046], and [0049])
Claim 8 is directed to wherein the information processing apparatus further comprises an analysis unit configured to estimate another dimensionally compressed data corresponding to another multidimensional data using the machine learning model constructed by the learning unit.
Lin et al. shows after training, the neural network approximated the transformation that was originally used to transform the small training dataset and the neural network can be used to transform new observations by feeding new data to the entry layer and collecting the resulting transformed data from the output layer which can be using for downstream applications such as cell sorting decisions (Lin et al. [0042]).
Claim 9 is directed to wherein the multi-dimensional data comprises data corresponding to light intensity of fluorescence emitted from the biologically derived particle.
Lin et al. shows the light detection systems include a plurality of fluorescence detectors (Lin et al. [0071]). Lin et al. further shows that the data measure includes intensity of the fluorescence from a particle (Lin et al. [0054]).
Claim 10 is directed to wherein the particle analysis apparatus further comprises a sorting unit configured to sort the biologically derived particle as a sorting target.
Lin et al. shows the system includes a particle sorting component for sorting particles (such as cells) of the sample (Lin et al. [0022] and [0085]).
Claim 11 is directed to wherein the particle analysis apparatus further comprises a determination unit configured to determine whether the biologically derived particle is the sorting target based on the dimensionally compressed data corresponding to the multidimensional data estimated by the machine learning model.
Lin et al. shows the particle analyzer is configured to identify a target vessel for a particle based at least in part on the convert measurement (Lin et al. [0021]-[0022]). Lin et al. shows that the converted measurements are generated from the parametric neural network model (Lin et al. [0021]-[0022] and [0046]).
Claim 12 is directed to wherein the machine learning model is implemented in hardware in the particle analysis apparatus.
Lin et al. shows the neural network is constrained to an architecture to facilitate translation of the neural network to a configuration for the sorting electronics included in an analytical instrument which is interpreted that the neural network model is implemented in hardware of the particle analysis apparatus (Lin et al. [0041]). Lin et al. shows that the trained neural network can then be programmed into a FPGA and used to sort cells (or other particles) for the actual sort experiments (Lin et al. [0046]).
Claim 14 is directed to an information processing apparatus comprising: a dimensional compression unit configured to generate dimensionally compressed data by dimensionally compressing multidimensional data corresponding to light emitted from a biologically derived particle
Lin et al. shows a system including one or more processing devices and a computer-readable storage medium comprising instructions that, when executed by the processing devices, causes the system to convert measurements for a first portion of particles associated with an experiment received from a particle analyzer using a non-parametric transformation into initial transformed measurements (Lin et al. [0021]). Lin et al. shows that the non-parametric transformation includes a t-distributed stochastic neighbor embedding (t-SNE) which is a nonlinear dimensionality reduction technique (Lin et al. [0039] and [0040]).
and a learning unit configured to construct a machine learning model based on the dimensionally compressed data and the multidimensional data.
Lin et al. shows the system is configured to generate a parametric model to receive as input raw measurements for the first portion of particles and generate as an output the initial transformed measurements (Lin et al. [0021]). Lin et al. shows that this parametric model includes a neural network which is generated/trained to approximate the non-parametric transformation based on the dimensionally compressed data and the multi-dimensional data (Lin et al. [0039] – [0041] and [0046]).
Claim 15 is directed to a particle analysis system comprising: a particle analysis apparatus comprising a light receiving unit configured to receive light emitted from a biologically derived particle,
Lin et al. shows systems having a light detection system for characterizing particles of a sample in a flow stream (such as cells in a biological sample) with a photodetector configured to generate data signals from light detected from the particles in the flow stream (Lin et al. [0058] and Fig. 1).
and an information processing apparatus configured to: access multidimensional data corresponding to the light emitted from the biologically derived particle, and generate, with a machine learning model, coordinate information of a dimensionally compressed map based on the multidimensional data.
Lin et al. shows the system includes a processor configured to apply a generated transformation model to a set of data signals from the light detection system (Lin et al. [0058]). Lin et al. shows that the transformation model is a machine learning model such as a neural network model which is trained to transform the data signals (Lin et al. [0047]-[0049]). Lin et al. further shows that the neural network is trained on pre- and post- tSNE data to learn the transformation between the original data space and the dimensionality reduced space which is used to transform new observations by feeding new data to the entry layer and collecting the resulting transformed data from the output layer which can be used in downstream applications (Lin et al. [0042]).
Claim 16 is directed to wherein the machine learning model is trained with another multidimensional data regarding previously measured light emitted from another biologically derived particle and another dimensionally compressed data from the another multidimensional data.
Lin et al. further shows that the neural network is trained on pre- and post- tSNE data to learn the transformation between the original data space and the dimensionality reduced space which is used to transform new observations by feeding new data to the entry layer and collecting the resulting transformed data from the output layer (Lin et al. [0042]). Lin et al. shows that the transformation model is generated using data based on a first set of data signals from the light detection system and compressed multidimensional data of a first set of data signals (Lin et al. [0058]). These limitations show that the neural network transformation model is applied to new observations which are different from the observations used to train the transformation model.
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.
Claims 3, 4, and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023) as applied to claims 1 and 11 under 35 U.S.C. 102 above, and further in view of Pe’er et al. (US 20180046755 A1).
Claims 3 is directed to wherein the dimensional compression unit dimensionally compresses the multidimensional data to two dimensions or three dimensions. Claim 4 is directed to wherein the dimensionally compressed data comprises coordinate data in a two-dimensional or three- dimensional coordinate space.
Lin et al. does not explicitly show that the dimensionality reduction operation compresses the multi-dimensional data to two dimensions or three dimensions.
Like Lin et al., Pe’er et al. shows mapping high-dimensional data collected from a flow cytometry experiment to a low-dimensional space using a t-SNE algorithm. Pe’er et al. shows converting high-dimensional data collected from a flow cytometry experiment to a low dimensional space by mapping a point from high-dimensional space (the point representing a cell) to two-dimensional space or three-dimensional space using a t-SNE algorithm (Pe’er et al. [0042]-[0046]).
Claim 13 is directed to the particle analysis system further comprising an output unit configured to present, within two-dimensional or three-dimensional coordinate space, to a user, the dimensionally compressed data corresponding to the multidimensional data estimated by the machine learning model,
Lin et al. shows that the system is configured to convert a measurement for a particle based at least in part on the parametric model (Lin et al. [0021]). Lin et al. shows the system can include a transformation control system for analyzing and displaying the biological events on a graphical display configured to present biological event data as a plot (Lin et al. [0090]-[0094]).
wherein the determination unit is configured to determine whether the biologically derived particle is the sorting target based on whether the two-dimensional or three-dimensional coordinate space is within a range predetermined as the sorting target.
Lin et al. shows that the particle analyzer may be further configured to identify a target vessel for a particle based at least in part on the converted measurement corresponding a sort criterion associated with the target vessel (Lin et al. [0022]). Lin et al. shows the system is configured to transform raw event data and apply specific sorting criteria such as gate information which identifies a range of measurements for classifying the particle which is specified using measurements in the transformed space (Lin et al. [0127] and [0128]).
Lin et al. does not explicitly show that the dimensionality reduction operation compresses the multi-dimensional data to two dimensions or three dimensions.
Like Lin et al., Pe’er et al. shows mapping high-dimensional data collected from a flow cytometry experiment to a low-dimensional space using a t-SNE algorithm. Pe’er et al. shows converting high-dimensional data collected from a flow cytometry experiment to a low dimensional space by mapping a point from high-dimensional space (the point representing a cell) to two-dimensional space or three-dimensional space using a t-SNE algorithm (Pe’er et al. [0042]-[0046]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have substituted the t-SNE dimensionality reduction algorithm to convert the data into a low-dimensional representation which is then used to train the neural network model to predict this transformation of Lin et al. with the t-SNE dimensionality reduction algorithm which maps high-dimensional data to two-dimensional space or three dimensional space of Pe’er et al. because both Lin et al. and Pe’er et al. shows dimensional reduction algorithms for representing high-dimensional cytometric data into a low dimensional space and would lead to predictable results of producing data in two-dimensional or three-dimensional space which is used to train the neural network model to learn the mapping produced by the dimensionality reduction algorithm.
Claims 15-18 are rejected under 35 U.S.C. 103 as being unpatentable over Lin and Owsley et al. (US 20200333236 A1) in view of Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023).
Claim 15 is directed to a particle analysis system comprising: a particle analysis apparatus comprising a light receiving unit configured to receive light emitted from a biologically derived particle,
Lin and Owsley et al. shows particle analyzers can comprise means for recording the measured data and analyzing the data and provides that data storage and analysis can be carried out using a computer connected to the detection electronics (Lin and Owsley et al. [0028] and [0029]).
and an information processing apparatus configured to: access multidimensional data corresponding to the light emitted from the biologically derived particle, and generate, with a machine learning model, coordinate information of a dimensionally compressed map based on the multidimensional data.
Lin and Owsley et al. shows a system including a processor configured to access a first cytometric event data associated with a first event and transform this first event data from a high-dimensional space to a low dimensional space and that the transformed first event data is associated with a first bin within the low-dimensional space (Lin and Owsley et al. [0040]). Lin and Owsley et al. shows that the event data is fluorescence detected from the particle such as intensity of the fluorescence (Lin and Owsley et al. [0043]).
Like Lin and Owsley et al., Lin et al. shows the system includes a processor configured to apply a transformation to a set of data signals from the light detection system. Lin et al. shows that the transformation model is a machine learning model such as a neural network model which is trained to transform the data signals (Lin et al. [0047]-[0049]). Lin et al. further shows that the neural network is trained on pre- and post- tSNE data to learn the transformation between the original data space and the dimensionality reduced space which is used to transform new observations by feeding new data to the entry layer and collecting the resulting transformed data from the output layer which can be used in downstream applications (Lin et al. [0042]).
Claim 16 is directed to wherein the machine learning model is trained with another multidimensional data regarding previously measured light emitted from another biologically derived particle and another dimensionally compressed data from the another multidimensional data.
Lin et al. further shows that the neural network is trained on pre- and post- tSNE data to learn the transformation between the original data space and the dimensionality reduced space which is used to transform new observations by feeding new data to the entry layer and collecting the resulting transformed data from the output layer (Lin et al. [0042]). Lin et al. shows that the transformation model is generated using data based on a first set of data signals from the light detection system and compressed multidimensional data of a first set of data signals (Lin et al. [0058]). These limitations show that the neural network transformation model is applied to new observations which are different from the observations used to train the transformation model.
Claim 17 is directed to wherein: the multidimensional data is first multidimensional data corresponding to light emitted from a first biologically derived particle, the coordinate information of a dimensionally compressed map is first coordinate information of a first dimensionally compressed map
Lin and Owsley et al. shows that the multidimensional data is a first data corresponding to a first biologically derived particle and that the coordinate information of this first data corresponding to a first biologically derived particle is the low-dimensional representation of the high-dimensional data associated with the first biologically derived particle (Lin and Owsley et al. [0040]).
the information processing apparatus is further configured to: access second multidimensional data corresponding to light emitted from a second biologically derived particle, generate, with the machine learning model, second coordinate information of a second dimensionally compressed map based on the second multidimensional data,
Lin and Owsley et al. further shows accessing and transforming second multidimensional data from a second biologically derived particle into a low-dimensional representation of the high-dimensional data associated with the second biologically derived particle and that the low-dimensional representation is associated with a second bin (Lin and Owsley et al. [0040])
and comparing the second dimensionally compressed map with the first dimensionally compressed map.
Lin and Owsley et al. shows comparing the second dimensionally compressed map with the first dimensionally compressed map as the operation that determines the first bin associated with the first transformed flow cytometric event data and the second bin associated with the second transformed flow cytometric event data are different (Lin and Owsley et al. [0040]).
Lin and Owsley et al. does not show a machine learning model that performs the dimensionality reduction process.
Like Lin and Owsley et al., Lin et al. shows the system includes a processor configured to apply a transformation to a set of data signals from the light detection system. Lin et al. shows using a neural network transformation model to generate dimensionally compressed multidimensional data corresponding to biologically derived particles by learning the non-parametric transformation using pre- and post- tSNE data (Lin et al. [0042]).
Claim 18 is directed to wherein the information processing apparatus is further configured to: determine whether the second biologically derived particle differs from the first biologically derived particle based on comparison results of the second dimensionally compressed map and the first dimensionally compressed map.
Lin and Owsley et al. shows the system determines that the first bin associated with the first transformed flow cytometric event data and the second bin associated with the second transformed flow cytometric event data are different (Lin and Owsley et al. [0040]).
An invention would have been obvious to one or ordinary skill in the art if some motivation in the prior art would have led that person to modify reference teachings to arrive at the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the operation of transforming the multi-dimensional to a low-dimensional representation to perform a comparison of a first and second particle low-dimensional map of Lin and Owsley et al. to be implemented with the neural network model trained to perform this transformation from high-dimensional space to low dimensional space of Lin et al. because this would allow for a system that is capable of transforming new observations using a parametric neural network model that learns this transformation without the need to recalculate the transformation with the addition of new observations as required by non-parametric transforms like t-SNE (Lin et al. [0039] and [0043]). One would have a reasonable expectation of success because the transformation applied in Lin and Owsley et al. is a t-SNE dimensionality reduction transformation while Lin et al. utilizes a parametric neural network model to learn the mapping produced by a t-SNE dimensionality reduction transformation.
Claims 19-21 are rejected under 35 U.S.C. 103 as being unpatentable over Lin and Owsley et al. (US 20200333236 A1) in view of Lin et al. (WO 2020/047468 A1; cited in IDS received 14 December 2023) as applied to claim 17 above, and further in view of Pe’er et al. (US 20180046755 A1).
Claim 19 is directed to wherein: the first biologically derived particle is from a patient, and the second biologically derived particle is from a healthy person and the information processing apparatus is further configured to identify a cell population in the first biologically derived particle rather than in the second biologically derived particle based on comparison results of the second dimensionally compressed map and the first dimensionally compressed map.
Lin and Owsley et al. in view of Lin et al. shows transforming high-dimensional data of biologically derived particles into a low dimensional space that is associated with bins and that the binning can be based on automated population detection (Lin and Owsley et al. [0040] and [0073]).
Lin and Owsley et al. in view of Lin et al. does not show that the first biologically derived particle is from a patient and the second biologically derived particle is from a healthy person or identifying a cell population in the first biological derived particle rather than in the second biologically derived particle based on comparison results.
Like Lin and Owsley et al. in view of Lin et al., Pe’er et al. shows analyzing biological particle data collected from a flow cytometer that measures parameters of cells. Pe’er et al. shows a system configured for mapping healthy and cancerous bone marrow samples, as well as other types of cancerous tissue, including solid tumors and shows that healthy bone marrow automatically maps into a consistent shape, whereas leukemia samples map into malformed shapes that are distinct from healthy bone marrow and from each other (Pe’er et al [0008]). This is interpreted as analyzing biological particles from a patient (such as a leukemia patient) and a health person to identify cell populations (represented as clusters in the low dimensional space) that differ between samples.
Claim 20 is directed to wherein: the first biologically derived particle is from a patient at a first time, and the second biologically derived particle is from the patient at a second time different from the first time.
Pe’er et al. shows the biologically derived particle is from a patient at a first time and the second biologically derived particle is from the patient at a second time different than the first as applying the analysis on a matched diagnosis and relapse pair from a patient with AML: one sample taken before chemotherapy and another after a relapse of the disease (Pe’er et al. [0088]).
Claim 21 is directed to the first biologically derived particle and the second biologically derived particle are cultured under different conditions.
Pe’er et al. shows the systems can be used to identify drug resistant subsets of cells by treating a collection of cells with a drug and then mapped to low dimensional space to identify drug resistant cells (Pe’er et al. [0057], [0081], and Fig. 23). It would have been obvious to one of ordinary skill in the art to have biologically derived particles cultured in different drugs to identify differing cell populations resulting from the differing drugs.
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the system configured to transform high-dimensional event data of cells into a low-dimensional representation utilizing a parametric neural network model of Lin and Owsley et al. in view of Lin et al. to incorporate the identification of populations which differ from healthy persons, patients, matched diagnosis and relapse sample, and drug cultured samples of Pe’er et al. because this would allow for a compressive system capable of performing a dimensionality reduction procedure on new observations of high-dimensional data from cells and utilize the low dimensional representation produced to identify cell populations that differ between different biologically derived and cultured particles (Pe’er et al. [0008]). One would have a reasonable expectation of success because Lin and Owsley et al. in view of Lin et al. shows transforming high-dimensional cytometric data into a low dimensional space while Pe’er et al. shows analyzing the low-dimensional space to identify cell populations that differ between heathy persons, patients, matched samples of a patient from different time points, and different samples cultured with different drugs.
Conclusion
No claims are allowed.
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN EDWARD HAYES whose telephone number is (571)272-6165. The examiner can normally be reached M-F 9am-5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Olivia Wise can be reached at 571-272-2249. 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.
/JONATHAN EDWARD HAYES/Examiner, Art Unit 1685
Prosecution Insights