DETAILED ACTION
This action is responsive to communications filed on May 19, 2023. This action is made Non-Final.
Claims 1-20 are pending in the case.
Claims 1, 8, and 15 are independent claims.
Claims 1-20 are rejected.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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 1-20 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: Independent claims 1, 8, and 15 are directed towards a system, method, and non-transitory medium, respectively. Therefore, these claims, as well as their dependent claims, are directed towards one of the four statutory categories (process, machine (i.e. apparatus), manufacture, or composition of matter.
With respect to claim 1:
2A Prong 1:
Claim 1 recites the following judicial exceptions:
statistically compare the input sequence data and the restored data to identify anomalies in the genome (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomalies).
determine, based on the result of the comparison, whether the genome contains a CRISPR-edited methylation region (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomalies and determine CRSIPR-edited methylation determinations.).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
a system for detecting a CRISPR-edited genome, comprising: one or more processors configured to: receive an input sequence data of a genome (mere instructions to apply the exception or implement the exception on a computer (e.g. – using a computer to receive data and perform particular detections; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
provide the input sequence data to a long short-term memory (LSTM) autoencoder neural network (ANN) having at least one encoder layer and at least one decoder layer, wherein the LSTM ANN was trained using a data sequence of a genome without CRISPR edits; reduce, using the encoder layer of the LSTM-ANN, a dimensionality of the input sequence data to generate reduced data; restore, using the decoder layer of the LSTM-ANN, a dimensionality of the reduced data to generate restored data (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning methods and models to process data and make determinations; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
With respect to claim 2:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
wherein the sequenced data is whole-genome bisulfite sequencing (WGBS) data (mere instructions to apply the exception or implement the exception on a computer (e.g. – using a computer to receive data and perform particular detections; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
With respect to claim 3:
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
wherein the sequenced data comprises of CpG start location data and methylation percentage data (mere instructions to apply the exception or implement the exception on a computer (e.g. – using a computer to receive data and perform particular detections; see MPEP §2106.05(f).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information in memory and performing calculations.).
With respect to claim 4:
2A Prong 1:
Claim 4 recites the following judicial exceptions:
determine whether, based on the identified anomaly in the genome, associated PAM sites have been disrupted and wherein the determination of whether the genome contains a CRISPR-edit is further based on the previous step (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomaly characteristics and determine CRSIPR-edited methylation determinations.).
With respect to claim 5:
2A Prong 1:
Claim 5 recites the following judicial exceptions:
wherein the statistically comparing includes performing a Tukey test on the input sequence data and the restored data (mental process and mathematical computation –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomaly characteristics and determine CRSIPR-edited methylation determinations.).
With respect to claim 6:
2A Prong 1:
Claim 6 recites the following judicial exceptions:
wherein the determining includes determining a methylation location of the CRISPR edit (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomaly characteristics and determine CRSIPR-edited methylation determinations.).
With respect to claim 7:
2A Prong 1:
Claim 7 recites the following judicial exceptions:
determine, ... whether the genome likely contains a CRISPR-edited methylation site, wherein the determining includes weighing the generated score and results ... to determining whether the genome contains a CRISPR edit (mental process –can be performed in the human mind, or by a human using a pen and paper (e.g. a person may statistically compare genome sequence data to detect anomaly characteristics and determine CRSIPR-edited methylation determinations.).
2A Prong 2: The additional elements recited in the claim do not integrate the judicial exception into a practical application.
Additional elements:
using an Convolutional Neural Network (CNN), ... from the CNN ... (generally linking the use of a judicial exception to a particular technological environment or field of use (e.g. using machine learning methods and models to process data and make determinations; see MPEP §2106.05(h).). The additional elements do not effectively integrate the abstract idea into a practical application. 2B: revisiting the additional elements, the additional elements do not amount to significantly more than the judicial exception – recited high level of generality and corresponds to storing and retrieving information and performing calculations.).
Claim 8:
Claim 8 substantially corresponds to claim 1 and is rejected under the same rationale.
Claim 9:
Claim 9 substantially corresponds to claim 2 and is rejected under the same rationale.
Claim 10:
Claim 10 substantially corresponds to claim 3 and is rejected under the same rationale.
Claim 11:
Claim 11 substantially corresponds to claim 4 and is rejected under the same rationale.
Claim 12:
Claim 12 substantially corresponds to claim 5 and is rejected under the same rationale.
Claim 13:
Claim 13 substantially corresponds to claim 6 and is rejected under the same rationale.
Claim 14:
Claim 14 substantially corresponds to claim 7 and is rejected under the same rationale.
Claim 15:
Claim 15 substantially corresponds to claim 1 and is rejected under the same rationale.
Claim 16:
Claim 16 substantially corresponds to claim 2 and is rejected under the same rationale.
Claim 17:
Claim 17 substantially corresponds to claim 3 and is rejected under the same rationale.
Claim 18:
Claim 18 substantially corresponds to claim 4 and is rejected under the same rationale.
Claim 19:
Claim 19 substantially corresponds to claim 6 and is rejected under the same rationale.
Claim 20:
Claim 20 substantially corresponds to claim 7 and is rejected under the same rationale.
2B concluded: After considering all claim elements individually and as an ordered combination, it is determined that the claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4, 6-11, and 13-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Farris, M. Heath, et al. "Detection of CRISPR-mediated genome modifications through altered methylation patterns of CpG islands." BMC genomics 21.1 (2020): 856 (“Farris”), in view of Karaletsos et al., US Publication 2024/0386990 (“Karaletsos”), and further in view of Knight et al., US Publication 2022/0254440 (“Knight”).
Claim 1:
Farris teaches or suggests a system for detecting a CRISPR-edited genome, comprising:
recieve an input sequence data of a genome (see Fig. 1; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Visualizing methylation calls and variance - variance at the known genomic edit sites were observedin comparisons of the sequenced methylomes of edited animals and control animals at their respective edit locations.);
provide the input sequence data ... sequence of a genome without CRISPR edits (see Fig. 1; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Visualizing methylation calls and variance - variance at the known genomic edit sites were observed in comparisons of the sequenced methylomes of edited animals and control animals at their respective edit locations.);
statistically compare the input sequence data ... to identify anomalies in the genome (see Fig. 1, 4, 5, 6a-d, 7a-c, 8a-c; Table 2; §Background – statistical methodology for the detection of CGI methylation variance as a result of CRIS PR-mediated genomic editing; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Statistical selection of CGIs - statistical filters (Fig. 4) were empirically selected and applied to the epigenetic profiles of CGIs across the mouse genome to identify CGIs with statistically significant positive change from the control animal; §CRISPR edits mediated by HDR - observation of the methylome at the edited CGI locations for the edited animals as compared to the control demonstrates the significant deviation in the methylation patterns Case 1 CGIs within the statistical workflow. observations were reproduced in comparisons of the edited CGIs of modified animals to the unedited CGIs of Control 2 Animal ; §CGIs with statistically relevant – CGIs containing statistically significant change from that of the control animal and containing changes beyond those considered biological noise were categorized as; §Statistical methods - two-step evaluation approach was adopted to determine significant differences in increased methylation levels between the CRISPR-edited and control animals; §Visualizing methylation calls and variance - variance at the known genomic edit sites were observed in comparisons of the sequenced methylomes of edited animals and control animals at their respective edit locations.); and
determine, based on a result of the statistical comparison, whether the genome contains a CRISPR-edited methylation region (see §Abstract - method described here locates the directed modification of the mouse epigenome that persists over generations. While this observance would require supporting molecular observations such as direct sequence changes or gene expression changes, the observation of epigenetic modification provides an indicator that intentionally directed genomic edits can lead to collateral, unintentional epigenomic changes post modification with generational persistence; §Background - observation of these CGI methylation changes represents one mechanism to detect applications of CRISPR technology to induce site-directed edits, leaving genomic scars that echo through generations orthogonal to naturally occurring methylation patterns. Further, leveraging the multiplexing abilities of CRISPR technology, modification of one or many CGIs in this manner provides a tool for tracking the functional influence of CGI disruptions. statistical methodology for the detection of CGI methylation variance as a result of CRISPR-mediated genomic editing; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Discussion - methodology described here represents one approach to detecting genomic scars left behind during the application of CRISPR.).
Farris does not explicitly disclose one or more processors configured to: ... to a long short-term memory (LSTM) autoencoder neural network (ANN) having at least one encoder layer and at least one decoder layer, wherein the LSTM ANN was trained using a training data ...; reduce, using the encoder layer of the LSTM-ANN, a dimensionality of the input sequence data to generate reduced data; restore, using the decoder layer of the LSTM-ANN, a dimensionality of the reduced data to generate restored data; and the restored data.
Karaletsos teaches or suggests one or more processors configured to: ... provide input the input sequence data to ... autoencoder neural network having at least one encoder layer and at least one decoder layer, wherein the ... ANN was trained using a training data sequence of genome ...; reduce, using the encoder layer of the ... ANN, a dimensionality of the input sequence data to generate reduced data; restore, using the decoder layer of the ... ANN, a dimensionality of the reduced data to generate restored data; and the restored data (see para. 0008 - In various embodiments, the perturbation is ... genetic editing agent. In various embodiments, the genetic editing agent comprises a CRISPR system. In various embodiments, the plurality of disentangled representations in the latent space are generated using phenotypic assay data captured from one or more cells. In various embodiments, the phenotypic assay data comprises one or more of cell sequencing data, protein expression data, gene expression data; para. 0108 - machine learning models disclosed herein can be any one of ... autoencoder neural networks; para. 0109 - machine learning model can refer to the decoder of an autoencoder architecture. Thus, the machine learning model decodes information from the latent space. In various embodiments, an autoencoder further includes an encoder which serves to encode information into the latent space; para. 0110 - involving the autoencoder architecture, the encoder is a neural network that includes a first set of layers and the decoder is a neural network that includes a second set of layers; para. 0111 - trained using any one of ... dimensionality reduction; para. 0114 – the autoencoder architecture may employ an encoder that encodes information into the latent space. The encoder is configured to analyze a phenotypic output of a cell to generate one or more corresponding representations in the latent space. employs the trained machine learning model that decodes the representation in the latent space; para. 0117 – encoder may generate a latent representation of a perturbed cell (e.g., perturbed cell 110B shown in FIG. 1) by encoding phenotypic assay data captured from the perturbed cell. Here, the training process can further involve disentangling the latent representation; para. 0125 - machine learning model 320 decodes information in the latent space 305 to generate the prediction 550; para. 0126 - the prediction is combined with the reference ground truth data of the phenotypic assay data 510 by determining a difference between the prediction and the reference ground truth data of the phenotypic assay data 510. The difference represents a value, such as a loss value, that is useful for training at least the machine learning model 320. As shown in FIG. 5, the value can be backpropagated for training each of the encoder 520 and the machine learning model 320.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Farris, to include one or more processors configured to: ... provide input the input sequence data to ... autoencoder neural network having at least one encoder layer and at least one decoder layer, wherein the ... ANN was trained using a training data sequence of genome ...; reduce, using the encoder layer of the ... ANN, a dimensionality of the input sequence data to generate reduced data; restore, using the decoder layer of the ... ANN, a dimensionality of the reduced data to generate restored data; and the restored data for the purpose of efficiently implementing an autoencoder neural network to encode sequence data to a latent space and decode the encoded sequence data to make a prediction regarding a perturbation, improving cellular response analysis, as taught by Karaletsos (see 0003, 0008, and 0126).
Though Karaletsos teaches the use of autoencoder neural networks and long-short term memory networks, Farris and Karaletsos do not explicitly disclose a long-short-term memory (LSTM) auto-encoder neural network .... LSTM ANN; LSTM-ANN; LSTM-ANN.
Knight teaches or suggests a long-short-term memory (LSTM) auto-encoder neural network .... LSTM ANN; LSTM-ANN; LSTM-ANN (see para. 0086 - CRISPRa system, an RNAi system, or an shRNA system) may be used to edit a respective genomic region to facilitate the re-programming of a cell of the cell type between the first phenotypic state and the second phenotypic state. After the editing, an anomaly detection algorithm may be used to measure a quantity of a shift in the latent space of the cell as a result of using the genomic editing unit to edit the respective genomic region. anomaly detection algorithm may comprise one or more of: ... a neural network (e.g., replicator neural network, autoencoder, long short-term memory (LSTM) neural network). Measuring the quantities of shifts in the latent space of the cell as a result of using the genomic editing unit to edit the respective genomic region, the one or more genes may be ranked; para. 0087 - mapping ( e.g., using a UMAP algorithm or a supervised dimensionality reduction algorithm) the singlecell RNA sequence (scRNA-seq) data for the plurality of diseased cells and the plurality of normal cells into a latent space corresponding to a plurality of phenotypic states of the cell type.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Farris and Karaletsos, to include a long-short-term memory (LSTM) auto-encoder neural network .... LSTM ANN; LSTM-ANN; LSTM-ANN for the purpose of efficiently implementing a LSTM and an autoencoder neural network to analyze edited genomic sequence regions, improving cellular anomaly analysis, as taught by Knight (0086 and 0087).
Claim(s) 8 and 15:
Claim(s) 8 and 15 correspond to Claim 1, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 8 and 15 as well.
Claim 2:
Farris further teaches or suggests wherein the sequenced data is a whole-genome bisulfite sequencing (WGBS) data (see Fig. 2; § Whole genome bisulfite sequencing for a genome-wide evaluation of CpG and CGI methylation patterns - To determine differential methylation of CpG islands across the genomes of the evaluated animals, we sequenced the genome-wide methylation patterns of CpGs using whole genome bisulfite sequencing (WGBS).).
Claim(s) 9 and 16:
Claim(s) 9 and 16 correspond to Claim 2, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 9 and 16 as well.
Claim 3:
Farris further teaches or suggests wherein the input sequence data comprises of CpG state location data and methylation percentage data (see Tables 3-6; § Visualizing methylation calls and variance - For each given edited CGI, the chromosome, the CGI start location coordinate, and the CGI end location coordinate were defined to bound the data and resulting plot to the CRIS PR-targeted CGI genomic location for the comparisons. The bounded data for each animal consisted of a genomic start location coordinate, a genomic end location coordinate, and observed percent methylation at the location for qualifying CpG locations within the bounded CGI genomic range.).
Claim(s) 10 and 17:
Claim(s) 10 and 17 correspond to Claim 3, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 10 and 17 as well.
Claim 4:
Farris further teaches or suggests wherein one or more processors are further configured to determine whether, based on the identified anomaly in the genome, associated PAM sites have been disrupted (Fig. 1, 5, 6, 7; § CRISPR edits mediated by HDR display methylation profiles at CGIs with distinctive increases in methylation – this edit, the CRISPR-targeted PAM site (dashed line) is located upstream of the affected CGI. border of methylation inflection at the interaction site of the terminus of the downstream homology arm.) and wherein the determination of whether the genome contains a CRISP-edit is further based on the previous step (see Abstract - method described here locates the directed modification of the mouse epigenome that persists over generations. While this observance would require supporting molecular observations such as direct sequence changes or gene expression changes, the observation of epigenetic modification provides an indicator that intentionally directed genomic edits can lead to collateral, unintentional epigenomic changes post modification with generational persistence; §Background - observation of these CGI methylation changes represents one mechanism to detect applications of CRISPR technology to induce site-directed edits, leaving genomic scars that echo through generations orthogonal to naturally occurring methylation patterns. Further, leveraging the multiplexing abilities of CRISPR technology, modification of one or many CGIs in this manner provides a tool for tracking the functional influence of CGI disruptions. statistical methodology for the detection of CGI methylation variance as a result of CRISPR-mediated genomic editing; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Discussion - methodology described here represents one approach to detecting genomic scars left behind during the application of CRISPR.).
Claim(s) 11 and 18:
Claim(s) 11 and 18 correspond to Claim 4, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 11 and 18 as well.
Claim 6:
Farris further teaches or suggests wherein the determining includes determining a methylation location of the CRISPR edit (see Fig. 1, 5, 6, 7; §Abstract - describes a statistically based workflow for indicating locations of modified CGIs and provides a mechanism for evaluating the directed modification of the methylome of the affected CGI at the CpG-level. method described here locates the directed modification of the mouse epigenome that persists over generations. While this observance would require supporting molecular observations such as direct sequence changes or gene expression changes, the observation of epigenetic modification provides an indicator that intentionally directed genomic edits can lead to collateral, unintentional epigenomic changes post modification with generational persistence; §Background - observation of these CGI methylation changes represents one mechanism to detect applications of CRISPR technology to induce site-directed edits, leaving genomic scars that echo through generations orthogonal to naturally occurring methylation patterns. Further, leveraging the multiplexing abilities of CRISPR technology, modification of one or many CGIs in this manner provides a tool for tracking the functional influence of CGI disruptions. statistical methodology for the detection of CGI methylation variance as a result of CRISPR-mediated genomic editing; §CRISPR edits mediated by HDR display methylation profiles at CGIs with distinctive increases in methylation - observation of the methylome at the edited CGI locations for the edited animals as compared to the control demonstrates the significant deviation in the methylation patterns; §CGIs with statistically relevant methylation changes – demonstrates an increase of methylation toward complete methylation change at modified CpG locations; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Discussion -evaluations focused on CGIs with an increased methylation profile at their CpG locations as compared to control animals. marked increase of methylation is observed within the affected CGIs for the CpG locations spanning the range of genomic incorporation of the donor DNA. methodology described here represents one approach to detecting genomic scars left behind during the application of CRISPR.).
Claim(s) 13 and 19:
Claim(s) 13 and 19 correspond to Claim 6, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 13 and 19 as well.
Claim 7:
Farris further teaches or suggests determine ... whether the genome likely contains a CRISPR-edited methylation site ... to determine whether the genome contains a CRISPR edit (see Fig. 1, 5, 6, 7; §Abstract - describes a statistically based workflow for indicating locations of modified CGIs and provides a mechanism for evaluating the directed modification of the methylome of the affected CGI at the CpG-level. method described here locates the directed modification of the mouse epigenome that persists over generations. While this observance would require supporting molecular observations such as direct sequence changes or gene expression changes, the observation of epigenetic modification provides an indicator that intentionally directed genomic edits can lead to collateral, unintentional epigenomic changes post modification with generational persistence; §Background - observation of these CGI methylation changes represents one mechanism to detect applications of CRISPR technology to induce site-directed edits, leaving genomic scars that echo through generations orthogonal to naturally occurring methylation patterns. Further, leveraging the multiplexing abilities of CRISPR technology, modification of one or many CGIs in this manner provides a tool for tracking the functional influence of CGI disruptions. statistical methodology for the detection of CGI methylation variance as a result of CRISPR-mediated genomic editing; §CRISPR edits mediated by HDR display methylation profiles at CGIs with distinctive increases in methylation - observation of the methylome at the edited CGI locations for the edited animals as compared to the control demonstrates the significant deviation in the methylation patterns; §CGIs with statistically relevant methylation changes – demonstrates an increase of methylation toward complete methylation change at modified CpG locations; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Discussion -evaluations focused on CGIs with an increased methylation profile at their CpG locations as compared to control animals. marked increase of methylation is observed within the affected CGIs for the CpG locations spanning the range of genomic incorporation of the donor DNA. methodology described here represents one approach to detecting genomic scars left behind during the application of CRISPR.).
Karaletsos further teaches or suggests determine, using a Convolutional Neural Network ... wherein the determining includes weighting the generated score and results from the CNN (see para. 0008 - In various embodiments, the perturbation is ... genetic editing agent. In various embodiments, the genetic editing agent comprises a CRISPR system. In various embodiments, the plurality of disentangled representations in the latent space are generated using phenotypic assay data captured from one or more cells. In various embodiments, the phenotypic assay data comprises one or more of cell sequencing data, protein expression data, gene expression data; para. 0108 - machine learning models disclosed herein can be any one of ... convolutional neural networks(CNN); para. 0109 - machine learning model can refer to the decoder of an autoencoder architecture. Thus, the machine learning model decodes information from the latent space. In various embodiments, an autoencoder further includes an encoder which serves to encode information into the latent space; para. 0110 - involving the autoencoder architecture, the encoder is a neural network that includes a first set of layers and the decoder is a neural network that includes a second set of layers; para. 0111 - trained using any one of ... dimensionality reduction; para. 0114 – the autoencoder architecture may employ an encoder that encodes information into the latent space. The encoder is configured to analyze a phenotypic output of a cell to generate one or more corresponding representations in the latent space. employs the trained machine learning model that decodes the representation in the latent space; para. 0117 – encoder may generate a latent representation of a perturbed cell (e.g., perturbed cell 110B shown in FIG. 1) by encoding phenotypic assay data captured from the perturbed cell. Here, the training process can further involve disentangling the latent representation; para. 0125 - machine learning model 320 decodes information in the latent space 305 to generate the prediction 550; para. 0126 - the prediction is combined with the reference ground truth data of the phenotypic assay data 510 by determining a difference between the prediction and the reference ground truth data of the phenotypic assay data 510. The difference represents a value, such as a loss value, that is useful for training at least the machine learning model 320. As shown in FIG. 5, the value can be backpropagated for training each of the encoder 520 and the machine learning model 320.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Farris, to include determine, using a Convolutional Neural Network ... wherein the determining includes weighting the generated score and results from the CNN for the purpose of efficiently implementing a trained convolutional neural network to make a prediction regarding a perturbation, improving cellular response analysis, as taught by Karaletsos (see 0003, 0008, and 0126).
Claim(s) 14 and 20:
Claim(s) 14 and 20 correspond to Claim 7, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 14 and 20 as well.
Claim(s) 5 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Farris, in view of Karaletsos, in view of Knight, and further in view of Gersbach et al., US Publication 2016/0201089 (“Gersbach”).
Claim 5:
Farris further teaches or suggests wherein statistically comparing includes performing ... on the input sequence data ... (see Fig. 1, 4, 5, 6a-d, 7a-c, 8a-c; Table 2; §Background – statistical methodology for the detection of CGI methylation variance as a result of CRIS PR-mediated genomic editing; §Results - methylomes of CRISPR edited mice were evaluated using whole genome bisulfite sequencing to determine the modifications induced within the methylome by the CRISPR editing process; §Statistical selection of CGIs - statistical filters (Fig. 4) were empirically selected and applied to the epigenetic profiles of CGIs across the mouse genome to identify CGIs with statistically significant positive change from the control animal; §CRISPR edits mediated by HDR - observation of the methylome at the edited CGI locations for the edited animals as compared to the control demonstrates the significant deviation in the methylation patterns Case 1 CGIs within the statistical workflow. observations were reproduced in comparisons of the edited CGIs of modified animals to the unedited CGIs of Control 2 Animal ; §CGIs with statistically relevant – CGIs containing statistically significant change from that of the control animal and containing changes beyond those considered biological noise were categorized as; §Statistical methods - two-step evaluation approach was adopted to determine significant differences in increased methylation levels between the CRISPR-edited and control animals; §Visualizing methylation calls and variance - variance at the known genomic edit sites were observed in comparisons of the sequenced methylomes of edited animals and control animals at their respective edit locations.).
Further, Karaletsos further teaches or suggests and the restored data (see para. 0008 - In various embodiments, the perturbation is ... genetic editing agent. In various embodiments, the genetic editing agent comprises a CRISPR system. In various embodiments, the plurality of disentangled representations in the latent space are generated using phenotypic assay data captured from one or more cells. In various embodiments, the phenotypic assay data comprises one or more of cell sequencing data, protein expression data, gene expression data; para. 0108 - machine learning models disclosed herein can be any one of ... autoencoder neural networks; para. 0109 - machine learning model can refer to the decoder of an autoencoder architecture. Thus, the machine learning model decodes information from the latent space. In various embodiments, an autoencoder further includes an encoder which serves to encode information into the latent space; para. 0110 - involving the autoencoder architecture, the encoder is a neural network that includes a first set of layers and the decoder is a neural network that includes a second set of layers; para. 0111 - trained using any one of ... dimensionality reduction; para. 0114 – the autoencoder architecture may employ an encoder that encodes information into the latent space. The encoder is configured to analyze a phenotypic output of a cell to generate one or more corresponding representations in the latent space. employs the trained machine learning model that decodes the representation in the latent space; para. 0117 – encoder may generate a latent representation of a perturbed cell (e.g., perturbed cell 110B shown in FIG. 1) by encoding phenotypic assay data captured from the perturbed cell. Here, the training process can further involve disentangling the latent representation; para. 0125 - machine learning model 320 decodes information in the latent space 305 to generate the prediction 550; para. 0126 - the prediction is combined with the reference ground truth data of the phenotypic assay data 510 by determining a difference between the prediction and the reference ground truth data of the phenotypic assay data 510. The difference represents a value, such as a loss value, that is useful for training at least the machine learning model 320. As shown in FIG. 5, the value can be backpropagated for training each of the encoder 520 and the machine learning model 320.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Farris, to include and the restored data for the purpose of efficiently implementing an autoencoder neural network to encode sequence data to a latent space and decode the encoded sequence data to make a prediction regarding a perturbation, improving cellular response analysis, as taught by Karaletsos (see 0003, 0008, and 0126).
Gersbach further teaches or suggests a Tukey test (see para. 0035 – Treatment with the combination of gRNAs was statistically different than all other treatments (*Ps0.02) by Tukey's test; para. 0036 - Treatment with the combination of gRNAs was statistically different than all other treatments (*P<0.05) by Tukey's test; para. 0042 – gRNA 75/25 is significantly different than gRNA 50/50 and control (*P<0.01, Tukey's test); para. 0328 - Statistical analysis was performed by Tukey's test with alpha equal to 0.05 in JMP 10 Pro.).
Accordingly, it would have been obvious to one having ordinary skill before the effective filing date of the claimed invention to modify the system and method, taught in Farris, to include a Tukey test for the purpose of efficiently performing statistical comparison, improving statistical analysis, as taught by Gersbach (0035 and 0328).
Claim(s) 12:
Claim(s) 12 correspond to Claim 5, and thus, Farris, Karaletsos, and Knight teach or suggest the limitations of claim(s) 12 as well.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Andrew T McIntosh whose telephone number is (571)270-7790. The examiner can normally be reached M-Th 8:00am-5:30pm.
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, Tamara Kyle can be reached at 571-272-4241. 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.
/ANDREW T MCINTOSH/Primary Examiner, Art Unit 2144