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 .
Status of the Claims
Claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 are pending and under consideration in this action. Claims 1, 5-7, 13-14, 16-17, 20, 23-24, 27, 29, 31-32, 35, and 37-39 were canceled in the amendment filed 10/14/2022
Priority
The instant application is 371 of PCT/US20/55828, filed 10/15/2020, which claims priority to U.S. Provisional Application number 62/916,141, filed 10/16/2019, and U.S. Provisional Application number 62/952,219, filed 12/21/2019, as reflected in the filing receipt mailed 12/22/2022. The claim for domestic benefit for claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 is acknowledged. As such, the effective filing date of claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 is 10/16/2019.
Information Disclosure Statement
The two information disclosure statements (IDS) submitted on 9/22/2023 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS’s have been considered by the examiner.
Drawings
The drawings are objected to because of the following informalities:
The values/labels on the x axis and subplot headings are not legible in Figs. 1 and 3.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code (see Para. [0024], [00115], [00168], [00182], [00187], [00194], [00195], and [00196]). Applicant is required to delete the embedded hyperlink and/or other form of browser-executable code; references to websites should be limited to the top-level domain name without any prefix such as http:// or other browser-executable code. See MPEP § 608.01.
Claim Objections
Claims 3, 12, 19, 33-34, and 36 are objected to because of the following informalities:
Claim 3 recites the phrase “f) classifies the test clinical variant in a pathogenicity category”, which should be corrected to “f) classifying the test clinical variant in a pathogenicity category” for clarity. Claim 3 also recites the phrase “f) optionally providing notification”, which should be corrected to “g) optionally providing notification” for clarity.
Claim 12 recites the phrase “iPSC cells” in line 4 of the claim, which should be corrected to “induced pluripotent stem cell (iPSC) cells” for clarity.
Claims 19, 33, and 34 are missing a comma after the phrase “The method of claim 3” which should be corrected for clarity.
Claim 36 is missing a comma after the phrase “The method of claim 21” which should be corrected for clarity. Claim 36 also recites the phrase “composite euclidean vector magnitudes” in line 4 of the claim, which should be corrected to “composite Euclidean vector magnitudes” for clarity.
Appropriate correction is required.
Claim Rejections - 35 USC § 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 10-12, 15, 19, 22, 30, 34, and 36 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 10 recites the limitation “wherein the phenotype features are selected from pharyngeal pumping duration, inter-pump interval … forward speed, and reverse speed” in lines 1-10 of the claim. The metes and bounds of the claim are rendered indefinite due to the lack of clarity. The claim contains duplicates in the list of phenotype features. It is unclear how the following features are different: (1) curling in lines 4 and 8; (2) length in lines 4 and 7; (3) width in lines 4 and 8; and (4) speed vs. swimming speed in lines 3 and 8. This rejection can be overcome by amendment of claim 10 to clarify duplicates in the list of phenotype features.
Claim 11 and 12 recite the limitation “wherein the first training data comprises” in line 1 of the claims, respectively. There is insufficient antecedent basis for this limitation in the claim, since there is no prior mention of this phrase in claim 3, to which this claim depends. This rejection can be overcome by amendment of claims 11 and 12 to recite “wherein the training data comprises”.
Claim 15 recites the limitations “iteratively regenerating the first classifier model” and “to improve the performance of the first classifier model” in lines 2 and 3-4 of the claim, respectively. There is insufficient antecedent basis for these limitations in the claim, since there is no prior mention of these phrases in claim 3, to which this claim depends. This rejection can be overcome by amendment of claim 15 to recite “iteratively regenerating a first classifier model” and “to improve performance of a first classifier model”.
Claim 19 recites the limitations “replacing the naturally-occurring coding sequence” in line 4 of the claim. There is insufficient antecedent basis for this limitation in the claim, since there is no prior mention of this phrase in claim 3, to which this claim depends. This rejection can be overcome by amendment of claim 19 to recite “replacing a naturally-occurring coding sequence”.
Claim 22 recites the limitation “the method of claim 20” in line 1 of the claim. There is insufficient antecedent basis for this limitation in the claim, since claim 20, to which this claim depends, was canceled. For the purpose of compact prosecution, this claim will be interpreted to be dependent on claim 21; however, correction is respectfully requested.
Claim 30 recites the phrase “to improve the performance of the first classifier model” in lines 3-4 of the claim. There is insufficient antecedent basis for this limitation in the claim, since there is no prior mention of this phrase in claim 21, to which this claim depends. This rejection can be overcome by amendment of claim 30 to recite “to improve performance of the first classifier model”.
Claim 34 recites the phrase “wherein the first classifier model classifies the clinical variant” in lines 1-2 of the claim. There is insufficient antecedent basis for this limitation in the claim, since there is no prior mention of this phrase in claim 3, to which this claim depends. This rejection can be overcome by amendment of claim 34 to recite “wherein the classifier model classifies the clinical variant”.
Claim 36 recites the phrase “wherein the redetermined threshold comprises a range of threshold values” in lines 1-2 of the claim. There is insufficient antecedent basis for this limitation in the claim, since there is no prior mention of this phrase in claim 21, to which this claim depends. For the purpose of compact prosecution, this claim will be interpreted to recite “wherein the predetermined threshold comprises a range of threshold values”, as claim 21 contains the phrase “when an output of the first classifier model is above a predetermined threshold”; however, correction is respectfully requested.
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 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite both (1) mathematical concepts (mathematical relationships, formulas or equations, or mathematical calculations) and (2) mental processes, i.e., concepts performed in the human mind (including observations, evaluations, judgements or opinions) (see MPEP § 2106.04(a)).
Step 1:
In the instant application, claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 are directed towards a method, which falls into one of the categories of statutory subject matter (Step 1: YES).
Step 2A, Prong One:
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong One). The following instant claims recite limitations that equate to one or more categories of judicial exceptions:
Claim 2 recites a mathematical concept in “classifying the clinical variant into a pathogenicity category of pathogenic or likely pathogenic using a first classifier model”; a mental process (i.e., an evaluation of a label/diagnostic indicator) in “wherein the clinical variants are labeled with a diagnostic indicator of pathogenic or benign for the human disease”; a mental process (i.e., an evaluation of the output of the classifier to determine if it is above a threshold) in “wherein the first classifier model classifies the clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of the measured phenotype features of a panel of phenotype features from the transgenic organism when an output of the first classifier model is above a threshold value”; a mental process (i.e., an evaluation of the threshold value) in “optionally wherein the threshold value is predetermined”; and a mental process (i.e., an observation of the notification on the computer output display; see specification para. [00122]) in “optionally providing notification to a user for patient testing when the clinical variant is predicted to be pathogenic or likely pathogenic for a human disease”.
Claim 3 recites a mental process (i.e., an evaluation of the phenotype features) in “wherein the phenotype features are from a population of human clinical variants”; a mental process (i.e., an evaluation of the diagnostic indicator for clinical variants) in “wherein the human clinical variants are labeled with a diagnostic indicator of pathogenic or benign for a specific human disease”; a mental process (i.e., an evaluation of the data features to determine a subset) in “selecting a subset of the measured phenotype features for inputs into a machine learning system, wherein the subset includes at least four phenotype features and the diagnostic indicator for the human clinical variants”; a mathematical concept (i.e., dividing the data set) in “randomly partitioning the data set into training data and validation data”; a mental process (i.e., an evaluation of the model input) in “wherein each input has an associated weight”; a mental process (i.e., an evaluation of the model output, and whether it is above/below a threshold) in “wherein the classifier model provides binary outcomes selected from pathogenic or likely pathogenic above a threshold or benign or likely benign below the threshold”; a mental process (i.e., an evaluation of pathogenicity when model output is above a threshold) in “classifies the test clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of the measured phenotype features of a panel of phenotype features from the transgenic organism and the classifier model of d) when an output of the classifier model is above a threshold value”; and a mental process (i.e., an observation of the notification on the computer output display; see specification para. [00122]) in “optionally providing notification to a patient expressing the clinical variant(s) when the clinical variant is predicted to be pathogenic or likely pathogenic for a human disease”.
Claims 4 and 22 recite a mental process (i.e., an evaluation of the diagnostic indicator values) in “wherein the diagnostic indicator is selected from pathogenic, likely pathogenic, likely benign and benign”.
Claims 8 and 26 recite a mental process (i.e., an observation/evaluation of the type of transgenic organism) in “wherein the transgenic organism is a nematode or zebrafish”.
Claim 10 recites a mental process (i.e., an evaluation of phenotype features for inclusion in the model) in “wherein the phenotype features are selected from pharyngeal pumping duration, inter-pump interval, pumping frequency, peak amplitude of different pump components, speed, forward vs. reverse travel, curling, length, width, lethality, attenuation, bending angle-mid-point asymmetry, maximum amplitude (um), self-contact distance, mean amplitude (um), body wave number, area, dynamic amplitude (stretch), center point speed (um/s), center point trajectory/time, peristaltic speed (um/s), absolute peristaltic track length/time, activity, brush stroke, length, reverse swim, curling, fit, swimming speed, wave initiation rate, wavelength, width, proportion time forward, proportion time reverse, straight-line speed, forward speed, and reverse speed”.
Claim 11 recites a mental process (i.e., an evaluation of the components of the first training data) in “wherein the first training data comprises values from a panel of at least five phenotype features”.
Claim 12 recites a mental process (i.e., an evaluation of the components of the training data) in “wherein the first training data further comprises patient phenotype, patient drug response, or phenotype in a second transgenic organism expressing the human clinical variant”; and a mental process (i.e., an observation of the type of transgenic organism) in “wherein the second transgenic organism is selected from frog oocyte, nematode or zebrafish, fly or rodent or iPSC cells”.
Claim 18 recites a mental process (i.e., an evaluation of how the threshold was determined) in “wherein the threshold is determined using performance of the classifier model as measured by sensitivity and specificity, optionally wherein the threshold value is determined based on a specificity of at least about 0.70”.
Claim 21 recites a mathematical concept in “classifying the clinical variant into a pathogenicity category of pathogenic or likely pathogenic using a first classifier model”; a mental process (i.e., an evaluation of a label/diagnostic indicator) in “wherein the clinical variants are labeled with a diagnostic indicator of pathogenic or benign for the human disease”; a mental process (i.e., an evaluation of the output of the classifier to determine if it is above a threshold) in “wherein the first classifier model classifies the clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of the measured transcriptome features of a panel of transcriptome features from the transgenic organism when an output of the first classifier model is above a predetermined threshold”; and a mental process (i.e., an observation of the notification on the computer output display; see specification para. [00122]) in “providing notification to a user for patient testing when the clinical variant is predicted to be pathogenic or likely pathogenic for a human disease”.
Claim 25 recites a mental process (i.e., an evaluation of clinical variant) in “wherein the clinical variant is a variant of unknown or uncertain significance or unassigned”.
Claim 28 recites a mental process (i.e., an evaluation of the training set data components) in “wherein the first training data set further comprises patient transcriptome features, patient drug response, or transcriptome features in a second transgenic organism expressing the human clinical variant”; and a mental process (i.e., an observation of the type of transgenic organism) in “wherein the second transgenic organism is selected from frog oocyte, fly, nematode, zebrafish or rodent”.
Claim 34 recites a mathematical concept in “wherein the first classifier model classifies the clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of measured phenotype features and measured transcriptome features”.
Claim 36 recites a mental process (i.e., an evaluation of how the predetermined threshold was determined) in “wherein the redetermined threshold comprises a range of threshold values selected from the group consisting of direct outputs from either a radial or linear classifier, cartesian coordinates from an origin on dimension reduced plots, and composite Euclidean vector magnitudes from multidimensional feature sets”.
These recitations are similar to the concepts of collecting information, and displaying certain results of the collection and analysis is Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)), and organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships.
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification, and are determined to be directed to mental processes that in the simplest embodiments are not too complex to practically perform in the human mind. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind. The instant claims must therefore be examined further to determine whether they integrate the abstract idea into a practical application (Step 2A, Prong One: YES).
Step 2A, Prong Two:
In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP § 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP § 2106.04(d)(I)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP § 2106.04(d)(III)). The following claims recite limitations that equate to additional elements:
Claim 2 recites “a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models”; “obtaining measured phenotype features of a transgenic organism expressing the human clinical variant”; and “wherein the first classifier model is generated by a machine learning system using a first training data set that comprises phenotype features from the transgenic organism of a panel of at least four phenotype features from a population of clinical variants”.
Claim 3 recites “obtaining, by one or more processors, a data set comprising measured phenotype features of a transgenic organism expressing a human clinical variant”; “generating a classifier model using a machine learning system based on the training data and the subset of inputs”; “obtaining at least four measured phenotype features of a transgenic organism expressing at least one test human clinical variant”.
Claim 9 further recites “wherein the phenotype features are measured in an electropharyngeogram (EPG) assay, morphology and/or movement phenotype assay, or a gene expression profile, lethality, incidence of males, axonal outgrowth, or synaptic transmission assay”.
Claims 15 and 30 further recites “iteratively regenerating the first classifier model by training the first classifier model with new training data to improve the performance of the first classifier model”.
Claim 19 further recites “wherein the transgenic organism expresses the human clinical variant following modification to create the human clinical variant in the genome of the transgenic organism, optionally using CRISPR, and/or replacing the naturally-occurring coding sequence of the transgenic organism with a modified coding sequence” and “wherein the presence of the clinical variant in the transgenic organism(s) is confirmed by nucleotide sequencing”.
Claim 21 recites “a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models”; “obtaining measured transcriptome features of a transgenic organism expressing the human clinical variant”; and “wherein the first classifier model is generated by a machine learning system using a first training data set that comprises transcriptome features from the transgenic organism of a panel of transcriptome features from a population of clinical variants”.
Claim 33 recites “wherein the classifier model is generated using a machine learning system based on the training data and the subset of inputs, each of which include measured phenotype features and measured transcriptome features”.
Regarding the above cited limitations in claims 2-3 and 21 of (i) a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models (claim 2); (ii) one or more processors (claim 3); and (iii) a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models (claim 21). These limitations require only a generic computer component, which does not improve computer technology. Therefore, these limitations equate to mere instructions to implement an abstract idea on a generic computer, which the courts have established does not render an abstract idea eligible in Alice Corp. 573 U.S. at 223, 110 USPQ2d at 1983.
Regarding the above cited limitations in claims 2-3, 9, 15, 19, 21, 30, and 33 of (iv) obtaining measured phenotype features of a transgenic organism expressing the human clinical variant (claims 2 and 3); (v) wherein the first classifier model is generated by a machine learning system using a first training data set that comprises phenotype features from the transgenic organism of a panel of at least four phenotype features from a population of clinical variants (claim 2); (vi) generating a classifier model using a machine learning system based on the training data and the subset of inputs (claim 3); (vii) obtaining at least four measured phenotype features of a transgenic organism expressing at least one test human clinical variant (claim 3); (viii) wherein the phenotype features are measured in an electropharyngeogram (EPG) assay, morphology and/or movement phenotype assay, or a gene expression profile, lethality, incidence of males, axonal outgrowth, or synaptic transmission assay (claim 9); (ix) iteratively regenerating the first classifier model by training the first classifier model with new training data to improve the performance of the first classifier model (claims 15 and 30); (x) wherein the transgenic organism expresses the human clinical variant following modification to create the human clinical variant in the genome of the transgenic organism, optionally using CRISPR, and/or replacing the naturally-occurring coding sequence of the transgenic organism with a modified coding sequence (claim 19); (xi) wherein the presence of the clinical variant in the transgenic organism(s) is confirmed by nucleotide sequencing (claim 19); (xii) obtaining measured transcriptome features of a transgenic organism expressing the human clinical variant (claim 21); (xiii) wherein the first classifier model is generated by a machine learning system using a first training data set that comprises transcriptome features from the transgenic organism of a panel of transcriptome features from a population of clinical variants (claim 21); and (xiv) wherein the classifier model is generated using a machine learning system based on the training data and the subset of inputs, each of which include measured phenotype features and measured transcriptome features (claim 33). These limitations equate to insignificant, extra-solution activity of mere data gathering because these limitations gather data before or after the recited judicial exceptions of classifying the clinical variant into a pathogenicity category using a classifier model (see MPEP § 2106.04(d)). As such, claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 are directed to an abstract idea (Step 2A, Prong Two: NO).
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 claims recite additional elements that equate to well-understood, routine and conventional (WURC) limitations (MPEP § 2106.05(d)). The instant claims recite same additional elements described in Step 2A, Prong Two above.
Regarding the above cited limitations in claims 2-3 and 21 of (i) a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models; (ii) one or more processors; and (iii) a computer implemented system comprising at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement one or more models. These limitations equate to instructions to implement an abstract idea on a generic computing environment, which the courts have established does not provide an inventive concept (see MPEP § 2106.05(d) and MPEP § 2106.05(f)).
Regarding the above cited limitations in claims 2-3 and 21 of (iv) obtaining measured phenotype features of a transgenic organism expressing the human clinical variant (claims 2 and 3); (vii) obtaining at least four measured phenotype features of a transgenic organism expressing at least one test human clinical variant (claim 3); and (xii) obtaining measured transcriptome features of a transgenic organism expressing the human clinical variant (claim 21). These limitations equate to receiving/transmitting data over a network, which the courts have established as a WURC limitation of a generic computer in buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014).
Regarding the above cited limitations in claim 9 of (viii) wherein the phenotype features are measured in an electropharyngeogram (EPG) assay, morphology and/or movement phenotype assay, or a gene expression profile, lethality, incidence of males, axonal outgrowth, or synaptic transmission assay (claim 9). This limitation is considered to be insignificant extra-solution activity of mere data gathering. This step is incidental to the primary process of classifying the clinical variant into a pathogenicity category using the classifier model, wherein the data measured in the assays are merely inputs for the classifier model (see MPEP § 2106.05(g)).
Regarding the above cited limitations in claims 2-3, 15, 19, 21, 30, and 33 of (v) wherein the first classifier model is generated by a machine learning system using a first training data set that comprises phenotype features from the transgenic organism of a panel of at least four phenotype features from a population of clinical variants (claim 2); (vi) generating a classifier model using a machine learning system based on the training data and the subset of inputs (claim 3); (ix) iteratively regenerating the first classifier model by training the first classifier model with new training data to improve the performance of the first classifier model (claims 15 and 30); (x) wherein the transgenic organism expresses the human clinical variant following modification to create the human clinical variant in the genome of the transgenic organism, optionally using CRISPR, and/or replacing the naturally-occurring coding sequence of the transgenic organism with a modified coding sequence (claim 19); (xi) wherein the presence of the clinical variant in the transgenic organism(s) is confirmed by nucleotide sequencing (claim 19); (xiii) wherein the first classifier model is generated by a machine learning system using a first training data set that comprises transcriptome features from the transgenic organism of a panel of transcriptome features from a population of clinical variants (claim 21); and (xiv) wherein the classifier model is generated using a machine learning system based on the training data and the subset of inputs, each of which include measured phenotype features and measured transcriptome features (claim 33). These limitations when viewed individually and in combination, are WURC limitations as taught by McDiarmid et al. (CRISPR-Cas9 human gene replacement and phenomic characterization in Caenorhabditis elegans to understand the functional conservation of human genes and decipher variants of uncertain significance. Dis Model Mech. 11(12): dmm036517 (2018)), Ioannidis et al. (REVEL: An Ensemble Method for Predicting the Pathogenicity of Rare Missense Variants. Am J Hum Genet. 99(4): 877-885 (2016)), Hakim et al. (WorMachine: machine learning-based phenotypic analysis tool for worms. BMC Biol. 16(1): 8 (2018)), and Smith et al. (Deep learning of representations for transcriptomics-based phenotype prediction. bioRxiv 574723 (2019). https://doi.org/10.1101/574723). McDiarmid et al. discloses the framework for in vivo functional analysis of human genetic variation using C. elegans. A human gene and/or variant of uncertain significance is implicated in disease etiology through clinical sequencing (limitation (xi)) (Pg. 10, Fig. 8). McDiarmid et al. further discloses that targeted CRISPR-Cas9 human gene replacement is used to generate a library of knockout, human wild-type and variant transgenic strains (limitation (x)) (Pg. 10, Fig. 8).
Ioannidis et al. discloses a method for predicting the pathogenicity of rare coding variants in humans using REVEL (rare exome variant ensemble learner) using a random forest classifier (Abstract and Pg. 878, Col. 2, Para. 1). The random forest was trained on a set of variants with 1,000 binary classification trees (limitation (vi)) (Pg. 878, Col. 2, Para. 1).
Hakim et al. discloses a machine learning-based phenotypic analysis of nematodes (Title, Abstract). Morphological and fluorescent features, including area, length, thickness, midwidth, head and tail diameter ratios, etc., were used to train the model (limitation (v)) (Pg. 3, Table 1 and Pg. 3, Col. 2, Para. 2). Hakim et al. further discloses that the features are used in classification models (limitation (xiv)) (Pg. 3, Col. 2, Para. 1). Hakim et al. further discloses that the model allows users to retrain the network on their own labeled data, to further improve and fit the network (limitation (ix)) (Pg. 8, Col. 2, Para. 1).
Smith et al. discloses an analysis of phenotype prediction from transcriptomics data. Twelve different datasets are created, each with a different gene set, used for training supervised and unsupervised models, including classifier models (limitations (xiii) and (xiv)) (Pg. 7, Fig. 1).
These additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the instant claims do not amount to significantly more than the judicial exception itself (Step 2B: NO). As such, claims 2-4, 8-12, 15, 18-19, 21-22, 25-26, 28, 30, 33-34, and 36 are not patent eligible.
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 2-4, 8-12, 15, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over Ioannidis et al. (REVEL: An Ensemble Method for Predicting the Pathogenicity of Rare Missense Variants. Am J Hum Genet. 99(4): 877-885 (2016); published 9/22/2016) in view of McDiarmid et al. (CRISPR-Cas9 human gene replacement and phenomic characterization in Caenorhabditis elegans to understand the functional conservation of human genes and decipher variants of uncertain significance. Dis Model Mech. 11(12): dmm036517 (2018); published 11/26/2018) and Hakim et al. (WorMachine: machine learning-based phenotypic analysis tool for worms. BMC Biol. 16(1): 8 (2018); published 1/16/2018).
Regarding claim 2, Ioannidis et al. teaches a method for predicting the pathogenicity of rare coding variants in humans using REVEL (rare exome variant ensemble learner) (i.e., a method to predict pathogenicity for a clinical variant of a human disease) (Abstract). Ioannidis et al. further teaches that the random forest model was run using R (i.e., on a computing device containing at least one processor and at least one memory, the at least one memory comprising instructions executed by the at least one processor to cause the at least one processor to implement classifier models) (Pg. 878, Col. 2, Para. 1). Ioannidis et al. further teaches that test set 2 consisted of 1,953 pathogenic or likely pathogenic and 2,406 benign or likely benign variants (i.e., wherein the clinical variants are labeled with a diagnostic indicator of pathogenic or benign for the human disease) (Pg. 879, Col. 1, Para. 2). In test set 2, they confirmed that REVEL had the best performance among the ensemble methods both overall and for neutral variants within all allele frequencies (AFs) ranges up to 3% and that the improvement in AUC was greatest for rare neutral variants (i.e., classifying the clinical variant into a pathogenicity category of pathogenic or likely pathogenic using a first classifier model) (Pg. 880, Col. 1, Para. 2). Ioannidis et al. further teaches that they trained a random forest on a set of variants (i.e., wherein the first classifier model is generated by a machine learning system using a first training data set) (Pg. 878, Col. 2, Para. 1). Ioannidis et al. further teaches that REVEL was trained with putative rare neutral and disease missense variants. Missense exome sequencing variants (ESVs) were obtained from the Exome Sequencing Project (ESP) European-American and African-American populations, the Atherosclerosis Risk in Communities (ARIC) study European-American and African American populations, and the 1000 Genomes Project (KGP) European, Yoruban, and Asian populations (i.e., features from a population of clinical variants) (Pg. 878, Col. 2, Para. 2). Ioannidis et al. further teaches that the sensitivity and specificity varies at different REVEL score thresholds, above which a variant would be classified as pathogenic (i.e., wherein the first classifier model classifies the clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of the measured phenotype features of a panel of phenotype features from the transgenic organism when an output of the first classifier model is above a threshold value) (Pg. 880, Col. 2, Para. 2). Ioannidis et al. further teaches that current tools are often trained on predominantly common neutral variants and some explicitly impose a minimum AF threshold for defining neutral training variants (i.e., optionally wherein the threshold value is predetermined) (Pg. 878, Col. 1, Para. 2).
Regarding claim 3, Ioannidis et al. teaches a method for predicting the pathogenicity of rare coding variants in humans using REVEL (rare exome variant ensemble learner) using a random forest classifier (i.e., a computer-implemented method for using a classifier model to predict pathogenicity for a clinical variant of a human disease) (Abstract and Pg. 878, Col. 2, Para. 1). Ioannidis et al. further teaches the limitation of one or more processors as described for claim 2 above. Ioannidis et al. further teaches that missense exome sequencing variants (ESVs) were obtained from the Exome Sequencing Project (ESP) European-American and African-American populations, the Atherosclerosis Risk in Communities (ARIC) study European-American and African American populations, and the 1000 Genomes Project (KGP) European, Yoruban, and Asian populations (i.e., wherein the phenotype features are from a population of human clinical variants) (Pg. 878, Col. 2, Para. 2). Ioannidis et al. further teaches that the test set consisted of 1,953 pathogenic or likely pathogenic and 2,406 benign or likely benign variants (i.e., wherein the human clinical variants are labeled with a diagnostic indicator of pathogenic or benign for a specific human disease and wherein the subset includes the diagnostic indicator for the human clinical variant) (Pg. 879, Col. 1, Para. 2). Ioannidis et al. further teaches that they randomly selected approximately half (n = 140,921) of the putatively neutral exome sequencing variants (ESVs), of which 123,706 rare ESVs (with a maximum alternate AF between 0.1% and 1% across the seven study populations) were used for training, and 17,215 ESVs with an AF >1% were used for initial evaluation of performance across a range of AFs. The remaining half of ESVs were held out for use as independent test variants as described below. Thus, the final training set consisted of 6,182 HGMD disease variants and 123,706 rare neutral ESVs (i.e., randomly partitioning the data set into training data and validation data) (Pg. 878, Col. 2, Para. 2). Ioannidis et al. further teaches that they trained a random forest on the set of variants with 1,000 binary classification trees. They selected the number of trees to be sufficiently large for the out-of-bag (OOB) error rate to plateau. The OOB prediction for a given training variant is the proportion of trees that classified the variant as pathogenic across only those trees in the forest that excluded the variant from their bootstrapped training sample. The importance of each predictive feature was measured by the total decrease in the Gini index (improvement in node purity) for all splits on that feature, averaged over all trees in the forest (i.e., generating a classifier model using a machine learning system based on the training data and the subset of inputs, wherein each input has an associated weight) (Pg. 878, Col. 2, Para. 1). Ioannidis et al. further teaches that a variant would be classified as pathogenic above a threshold (i.e., wherein the classifier model provides binary outcomes selected from pathogenic or likely pathogenic above a threshold or benign or likely benign below the threshold) (Pg. 880, Col. 2, Para. 2 and Supporting Information, Fig. S1). Ioannidis et al. further teaches that the sensitivity and specificity varies at different REVEL score thresholds, above which a variant would be classified as pathogenic (i.e., classifies the test clinical variant in a pathogenicity category of pathogenic or likely pathogenic using input variables of the measured phenotype features of a panel of phenotype features from the transgenic organism and the classifier model of d) when an output of the classifier model is above a threshold value) (Pg. 880, Col. 2, Para. 2).
Regarding claim 4, Ioannidis et al. teaches that the set consisted of 1,953 pathogenic or likely pathogenic and 2,406 benign or likely benign variants (i.e., wherein the diagnostic indicator is selected from pathogenic, likely pathogenic, likely benign and benign) (Pg. 879, Col. 1, Para. 2).
Regarding claim 18, Ioannidis et al. teaches that the sensitivity and specificity corresponding to different REVEL score thresholds in Fig. S1. The variant is classified as pathogenic above the threshold. For example, 75.4% of disease mutations but only 10.9% of neutral variants (and 12.4% of all ESVs) have a REVEL score above 0.5, corresponding to a sensitivity of 0.754 and specificity of 0.891. Selecting a more stringent REVEL score threshold of 0.75 would result in higher specificity but lower sensitivity, with 52.1% of disease mutations, 3.3% of neutral variants, and 4.1% of all ESVs being classified as pathogenic (i.e., wherein the threshold is determined using performance of the classifier model as measured by sensitivity and specificity, optionally wherein the threshold value is determined based on a specificity of at least about 0.70) (Pg. 880, Col. 2, Para. 2 and Supplemental Data, Fig. S1).
Ioannidis et al. does not teach obtaining measured phenotype features of a transgenic organism expressing the human clinical variant; a first training data set that comprises phenotype features from the organism of a panel of at least four phenotype features; selecting a subset of the measured phenotype features for inputs into a machine learning system, wherein the subset includes at least four phenotype features; obtaining at least four measured phenotype features of a transgenic organism expressing at least one test human clinical variant; wherein the transgenic organism is a nematode or zebrafish; wherein the phenotype features are measured in an electropharyngeogram (EPG) assay, morphology and/or movement phenotype assay, or a gene expression profile, lethality, incidence of males, axonal outgrowth, or synaptic transmission assay; wherein the phenotype features are selected from pharyngeal pumping duration, inter-pump interval … proportion time forward, proportion time reverse, straight-line speed, forward speed, and reverse speed; wherein the first training data comprises values from a panel of at least five phenotype features; wherein the first training data further comprises patient phenotype, patient drug response, or phenotype in a second transgenic organism expressing the human clinical variant, wherein the second transgenic organism is selected from frog oocyte, nematode or zebrafish, fly or rodent or iPSC cells; wherein the machine learning system further comprises iteratively regenerating the first classifier model by training the first classifier model with new training data to improve the performance of the first classifier model; and wherein the transgenic organism expresses the human clinical variant following modification to create the human clinical variant in the genome of the transgenic organism, optionally using CRISPR, and/or replacing the naturally-occurring coding sequence of the transgenic organism with a modified coding sequence; optionally wherein the presence of the clinical variant in the transgenic organism(s) is confirmed by nucleotide sequencing.
Regarding claim 2, McDiarmid et al. teaches a strategy for targeted human gene replacement and phenomic characterization based on CRISPR-Cas9 genome engineering in the genetic model organism Caenorhabditis elegans, that will facilitate assessment of the functional conservation of human genes and structure-function analysis of disease-associated variants with unprecedented precision (Abstract). McDiarmid et al. further teaches that the framework involves targeted CRISPR-Cas9 human gene replacement or analogous methods to generate a library of knockout, human wild-type and variant transgenic strains. Large isogenic synchronous colonies of these transgenic worms are grown, and their morphology, baseline locomotion and sensory phenotypes are rapidly characterized using machine vision to establish novel functional assays and interpret variant effects. In vivo functional data can be used to probe epistatic network disruptions and cluster variants based on multi-parametric phenotypic profiles (i.e., obtaining measured phenotype features of a transgenic organism expressing the human clinical variant) (Pg. 10, Fig. 8).
Regarding claim 2, Hakim et al. teaches a machine learning-based phenotypic analysis of nematodes (Title, Abstract). Morphological and fluorescent features, including area, length, thickness, midwidth, head and tail diameter ratios, etc., were used to train the model (i.e., wherein the first classifier model is generated by a machine learning system using a first training data set that comprises phenotype features from the organism of a panel of at least four phenotype features) (Pg. 3, Table 1 and Pg. 3, Col. 2, Para. 2).
Regarding claim 3, McDiarmid et al. teaches the limitation of obtaining a data set comprising measured phenotype features of a transgenic organism expressing the human clinical variant as described for claim 2 above. McDiarmid et al. further teaches that in addition to morphology, baseline locomotion and sensory phenotypes, metrics for initial and final reversal responses, habituation difference scores or chemotaxis indices from all plates were pooled, and metrics were compared across strains (i.e., obtaining at least four measured phenotype features of a transgenic organism expressing at least one clinical variant) (Pg. 12, Col. 2, Para. 2).
Regarding claim 3, Hakim et al. teaches that for the feature extractor, all morphological and fluorescent measurements currently available in WorMachine are detailed in Table 1 (Pg. 3, Table 1). Objects which deviate in area size, length, or skeleton disfigurement are flagged for manual inspection, together with images identified as “noise” by the deep learning network (Pg. 2, Col. 2, Para. 2 – Pg. 3, Col. 1, Para. 1). Hakim et al. further teac