DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. 202110648180.4, filed on 06/10/2021.
Status of Claims
Claims 1-20 are currently pending and examined on the merits.
Information Disclosure Statement
The information disclosure statements filed 06/03/2022 is/are acknowledged. A signed copy of the corresponding 1449 form has been included with this Office action.
Drawings
Figure 1 contains color. Color photographs and color drawings are not accepted in utility applications unless a petition filed under 37 CFR 1.84(a)(2) is granted. Any such petition must be accompanied by the appropriate fee set forth in 37 CFR 1.17(h), one set of color drawings or color photographs, as appropriate, if submitted via the USPTO patent electronic filing system or three sets of color drawings or color photographs, as appropriate, if not submitted via the via USPTO patent electronic filing system, and, unless already present, an amendment to include the following language as the first paragraph of the brief description of the drawings section of the specification:
The patent or application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.
Color photographs will be accepted if the conditions for accepting color drawings and black and white photographs have been satisfied. See 37 CFR 1.84(b)(2).
Figures 1, 6-7, are unclear. The drawings are objected to under 37 CFR 1.83(a) because they fail to show:
106, Genetic sequence collection terminal (Fig. 1)
108, To-be-processed genetic sequence (Fig. 1)
116, Gene signature (Fig. 1)
120, Enhanced signature (Fig. 1)
as described in the specification. Any structural detail that is essential for a proper understanding of the disclosed invention should be shown in the drawing. MPEP § 608.02(d). 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.
Nucleotide and/or Amino Acid Sequence Disclosures
Figure 4 and the specification, paragraph 113, contain sequences.
REQUIREMENTS FOR PATENT APPLICATIONS CONTAINING NUCLEOTIDE AND/OR AMINO ACID SEQUENCE DISCLOSURES
Items 1) and 2) provide general guidance related to requirements for sequence disclosures.
37 CFR 1.821(c) requires that patent applications which contain disclosures of nucleotide and/or amino acid sequences that fall within the definitions of 37 CFR 1.821(a) must contain a "Sequence Listing," as a separate part of the disclosure, which presents the nucleotide and/or amino acid sequences and associated information using the symbols and format in accordance with the requirements of 37 CFR 1.821 - 1.825. This "Sequence Listing" part of the disclosure may be submitted:
In accordance with 37 CFR 1.821(c)(1) via the USPTO patent electronic filing system (see Section I.1 of the Legal Framework for Patent Electronic System (https://www.uspto.gov/PatentLegalFramework), hereinafter "Legal Framework") as an ASCII text file, together with an incorporation-by-reference of the material in the ASCII text file in a separate paragraph of the specification as required by 37 CFR 1.823(b)(1) identifying:
the name of the ASCII text file;
ii) the date of creation; and
iii) the size of the ASCII text file in bytes;
In accordance with 37 CFR 1.821(c)(1) on read-only optical disc(s) as permitted by 37 CFR 1.52(e)(1)(ii), labeled according to 37 CFR 1.52(e)(5), with an incorporation-by-reference of the material in the ASCII text file according to 37 CFR 1.52(e)(8) and 37 CFR 1.823(b)(1) in a separate paragraph of the specification identifying:
the name of the ASCII text file;
the date of creation; and
the size of the ASCII text file in bytes;
In accordance with 37 CFR 1.821(c)(2) via the USPTO patent electronic filing system as a PDF file (not recommended); or
In accordance with 37 CFR 1.821(c)(3) on physical sheets of paper (not recommended).
When a “Sequence Listing” has been submitted as a PDF file as in 1(c) above (37 CFR 1.821(c)(2)) or on physical sheets of paper as in 1(d) above (37 CFR 1.821(c)(3)), 37 CFR 1.821(e)(1) requires a computer readable form (CRF) of the “Sequence Listing” in accordance with the requirements of 37 CFR 1.824.
If the "Sequence Listing" required by 37 CFR 1.821(c) is filed via the USPTO patent electronic filing system as a PDF, then 37 CFR 1.821(e)(1)(ii) or 1.821(e)(2)(ii) requires submission of a statement that the "Sequence Listing" content of the PDF copy and the CRF copy (the ASCII text file copy) are identical.
If the "Sequence Listing" required by 37 CFR 1.821(c) is filed on paper or read-only optical disc, then 37 CFR 1.821(e)(1)(ii) or 1.821(e)(2)(ii) requires submission of a statement that the "Sequence Listing" content of the paper or read-only optical disc copy and the CRF are identical.
Specific deficiencies and the required response to this Office Action are as follows:
Specific deficiency - This application fails to comply with the requirements of 37 CFR 1.821 - 1.825 because it does not contain a "Sequence Listing" as a separate part of the disclosure or a CRF of the “Sequence Listing.”.
Required response - Applicant must provide:
A "Sequence Listing" part of the disclosure; together with
An amendment specifically directing its entry into the application in accordance with 37 CFR 1.825(a)(2);
A statement that the "Sequence Listing" includes no new matter as required by 37 CFR 1.821(a)(4); and
A statement that indicates support for the amendment in the application, as filed, as required by 37 CFR 1.825(a)(3).
If the "Sequence Listing" part of the disclosure is submitted according to item 1) a) or b) above, Applicant must also provide:
A substitute specification in compliance with 37 CFR 1.52, 1.121(b)(3) and 1.125 inserting the required incorporation-by-reference paragraph, consisting of:
A copy of the previously-submitted specification, with deletions shown with strikethrough or brackets and insertions shown with underlining (marked-up version);
A copy of the amended specification without markings (clean version); and
A statement that the substitute specification contains no new matter.
If the "Sequence Listing" part of the disclosure is submitted according to item 1) c) or d) above, applicant must also provide:
A CRF in accordance with 37 CFR 1.821(e)(1) or 1.821(e)(2) as required by 1.825(a)(5); and
A statement according to item 2) a) or b) above.
Specific deficiency – Nucleotide and/or amino acid sequences appearing in the specification are not identified by sequence identifiers in accordance with 37 CFR 1.821(d).
Required response – Applicant must provide:
A substitute specification in compliance with 37 CFR 1.52, 1.121(b)(3) and 1.125 inserting the required sequence identifiers, consisting of:
A copy of the previously-submitted specification, with deletions shown with strikethrough or brackets and insertions shown with underlining (marked-up version);
A copy of the amended specification without markings (clean version); and
A statement that the substitute specification contains no new matter.
Specific deficiency – Nucleotide and/or amino acid sequences appearing in the drawings are not identified by sequence identifiers in accordance with 37 CFR 1.821(d). Sequence identifiers for nucleotide and/or amino acid sequences must appear either in the drawings or in the Brief Description of the Drawings.
Required response – Applicant must provide:
Replacement and annotated drawings in accordance with 37 CFR 1.121(d) inserting the required sequence identifiers;
AND/OR
A substitute specification in compliance with 37 CFR 1.52, 1.121(b)(3) and 1.125 inserting the required sequence identifiers into the Brief Description of the Drawings, consisting of:
A copy of the previously-submitted specification, with deletions shown with strikethrough or brackets and insertions shown with underlining (marked-up version);
A copy of the amended specification without markings (clean version); and
A statement that the substitute specification contains no new matter.
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 an abstract idea of mental steps, mathematic concepts, organizing human activity, or a natural law without significantly more.
Step 2A, Prong 1
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 1). In the instant application, the claims recite the following limitations that equate to an abstract idea/law of nature/natural phenomenon:
Claim 1 recites, “A method comprising:
obtaining a genetic sequence... performing signature extraction on the genetic sequence… enhancing the gene signature…and, testing the genetic sequence…” (lines 1-3), which is a mental step, i.e. can be performed with pen and paper, and is a claim directed to a law of nature, i.e. correlating a naturally occurring genetic element with an identifier.
Claim 3 recites, “…performing signature extraction…” (line 1), “…determining…a gene fragment …” (line 2) & “…performing signature extraction…” (Iine 3); mental step; natural law
Claim 4 recites, “…performing matching…” (line 4); mental step
Claim 6 recites, “determining…a confidence level” (line 3) & “…performing signature extraction…” (line 4); mental step
Claim 13 recites, “…performing signature extraction…” (line 5); mental step
Claim 14 recites, “…performing signature extraction…” (line 3); mental step
Claim 15 recites, “…performing matching…” (line 3); mental step
Claim 17 recites, “determining…a confidence level” (line 3) & “…performing signature extraction…” (line 4); mental step
Claim 20 recites, “…performing signature extraction…” (line 6) & “…testing the genetic sequence…” (line 8); mental step; natural law (testing genetic sequences)
The claims recite an abstract idea of analyzing human genetic sequences (See MPEP 2106.07(a)).
These recitations are similar to the concepts of collecting information, analyzing it and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), 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)) and 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)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas.
While claims 7, 12 and 18 recite performing some aspects of the analysis using a “model”, there are no additional limitations that indicate that this model requires anything other than carrying out the recited mental process or mathematical concept in a generic computer environment. Merely reciting that a mental process is being performed in a generic computer environment does not preclude the steps from being performed practically in the human mind or with pen and paper as claimed. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then if falls within the “Mental processes” grouping of abstract ideas. As such, claim(s) 1-10 recite(s) an abstract idea/law of nature/natural phenomenon (Step 2A, Prong 1: YES).
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). This judicial exception is not integrated into a practical application because the claims do not recite an additional element that reflects an improvement to technology or applies or uses the recited judicial exception to affect a particular treatment for a condition. Rather, the instant claims recite additional elements that amount to mere instructions to implement the abstract idea in a generic computing environment or mere instructions to apply the recited judicial exception via a generic treatment. Specifically, the claims recite the following additional elements:
Claim 13 recites “one or more processors” (line 2) and “…one or more memories” (line 3)
Claim 20 recites “...one or more memories …” (line 1)
There are no limitations that indicate that the claimed analysis engine or the formats of the provided data require anything other than generic computing systems. As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. As such, claims 1-10 is/are directed to an abstract idea/law of nature/natural phenomenon (Step 2A, Prong 2: NO).
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 mere instructions to apply the recited exception in a generic way or in a generic computing environment. The instant claims recite the following additional elements:
Claim 1 recites “…obtaining a genetic sequence…” (line 1)
Claim 2 recites “…obtaining a testing result” (line 1)
Claim 3 recites “…obtaining the gene signature.” (line 4)
Claim 4 recites “…obtaining reference data…” (line 2)
Claim 6 recites “…obtaining a base quality…” (line 2)
Claim 7 recites “…obtaining a convolutional neural network model…” (line 2-3) & “…obtaining the enhanced signature…” (line 4-5)
Claim 10 recites “…obtaining…mutation reference information…” (line 2-3)
Claim 11 recites “…obtaining a mutation testing result…” (line 2)
Claim 12 recites “…inputting the enhanced signature into a three-dimensional network model…” (lines 2-3)
Claim 13 recites “…enhancing the gene signature to obtain an enhanced signature…” (line 12)
Claim 14 recites “…obtaining the gene signature…” (line 4)
Claim 15 recites “…obtaining reference data…” (line 2)
Claim 17 recites “…obtaining a base quality…” (line 2)
Claim 18 recites “…obtaining a convolutional neural network model…” (line 2-3) & “…obtaining the enhanced signature…” (line 4-5)
Claim 19 recites “…obtaining…mutation reference information…” (line 2-3)
Claim 20 recites “…performing sample collection…” (line 4), “performing signature extraction on the genetic sequence to obtain a gene signature…” (lines 11-12), and
“…enhancing the gene signature to obtain an enhanced signature corresponding to the gene signature…” (lines 13-14)
Regarding claims 1-20, The steps of obtaining sequencing data and performing sample collection do not integrate the abstract idea into a practical application and constitutes an insignificant extra-solution activity (i.e., data gathering and presentation), which does not impose a meaningful limit on the abstract idea. As discussed above, there are no additional limitations to indicate that the claimed analysis engine requires anything other than generic computer components in order to carry out the recited abstract idea in the claims. Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. MPEP 2106.05(f) discloses that mere instructions to apply the judicial exception cannot provide an inventive concept to the claims.
Furthermore, the additional elements recited in the claims amount to well-understood, routine and conventional activity, as evidenced by Koumakis (Computational and Structural Biotechnology Journal Volume 18, 2020, Pages 1466-1473), Poplin, et al. (Nature Biotechnology, Vol. 36, No. 10, pages 983-990), Lal et al. (bioRxiv preprint, November 4, 2019, pages 1-18), Hong, et al. (PLOS Computational Biology, February 21, 2020, pages 1-25) and Koo, et al (PLOS Computational Biology, December 19, 2019, pages 1-17).
Koumakis discloses a review of deep learning models and their application in genomics, and covers several applications, noting that convolutional neural networks (CNNs, a type of deep learning model) are commonly used for feature extraction, selection, and reduction (pg. 1467, sec 1.1; performing signature extraction on the genetic sequence to obtain a gene signature), but also have several applications for enriching sequencing analysis, such as predicting sequence motifs, classifying gene expression targets, and optimizing synthetic gene sequences (Table 1, pg. 1469, “List of deep learning methodologies in genomics” ; performing signature extraction on the genetic sequence to obtain a gene signature; enhancing the gene signature to obtain an enhanced signature corresponding to the gene signature; and testing the genetic sequence based on the enhanced signature). It is implicit that these applications involve obtaining sequencing data, a CNN, and reference data (obtaining a genetic sequence; obtaining reference data and a plurality of initial gene fragments included in the genetic sequence. Additionally, Poplin et al discloses a SNP and small insertion-and-deletion variant caller using deep neural networks. Termed “DeepVariant”, Poplin et al.’s variant caller discloses obtaining next generation sequencing reads and aligning them to a reference genome, scanning the reads for sites different from the reference genome and, after encoding the reads as an image, applies a trained CNN to calculate the genotype likelihoods for each site (pg. 983, para. 1, pg. 984, Figure 1, Abstract; obtaining a genetic sequence; testing the genetic sequence). Therefore, Poplin et al. discloses obtaining sample collection, sequence information, motif reads, gene signatures. Additionally, Lal et al. discloses AtacWorks, a deep CNN toolkit for the study of epigenomics; in the study, data from the Assay for Transposase Accessible Chromatin (ATAC) is used (hence, ATACWorks). In the results section, Lal et al. discloses how AtacWorks is utilized for denoising low-coverage chromatin-specific sequencing data, and states that the trained model is applied to enhance the resolution of single cell studies at single-base pair resolution by modeling with three inputs: a noisy signal track, a clean signal track, and the location of peaks in the clean dataset (Abstract, pg. 1 Results pg. 1, Methods, pg. 9; performing signature extraction; obtaining a convolutional neural network model; performing; enhancing the gene signature). Furthermore, Hong et al. discloses a generative adversarial network for enhancing high-throughput chromosome conformation capture sequencing data (pg. 1 Abstract, results, pg. 3; enhancing the gene signature). Finally, Koo, et al. discloses a CNN applied to genomic sequencing data to identify transcription factor binding motifs, a feature of sequencing data (Abstract, Introduction; Fig. 1; Table 1, pg. 1-6; testing; performing signature extraction on the genetic sequence). As such, the combination of additional elements recited in the claims is well-understood, routine and conventional.
The 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 claims do not amount to significantly more than the judicial exception itself (Step 2B: No). As such, claims 1-20 is/are not patent eligible.
Claim Rejections - 35 USC § 102
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)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-5, 7-9, 11, 13-16, 18 and 20 is/are rejected under 35 U.S.C. 102(b) as being anticipated by Zhiqiang Hu (U.S. PG Pub 2021/0082539 A1; hereby referred to as Hu).
The instant claims are directed to a method and apparatus to obtain a genetic sequence, perform signature extraction on the genetic sequence, obtain a gene signature, enhance the gene signature, obtain an enhanced signature, and test the genetic sequence based on the enhanced signature.
Hu is directed to a gene mutation identification method, apparatus, and storage medium, including: obtaining at least one gene sequencing read segment corresponding to a gene mutation candidate site; determining a sequence feature and a non – sequence feature of the gene mutation candidate site according to attribute information of the at least one gene sequencing read segment, where the sequence feature is a feature related to the position of the site; and identifying gene mutation of the gene mutation candidate site based on the sequence feature and the non - sequence feature.
In regards to claims 1, 13 and 20, which refer to (individually and with one or more memories storing thereon computer-readable instructions that, when executed by one or more processors, one or more memories storing thereon computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:) obtaining, manipulating, and testing a genetic sequence, Hu teaches a non-transitory computer-readable storage medium, having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the operations of its invention (clm. 21) Additionally, Hu teaches a gene mutation identification method utilizing sequencing data. Hu teaches the limitations of claim 1 as it 1) obtains genetic sequences (clm. 1, ln. 2), 2) obtains genetic sequences corresponding to a position relative to a preset threshold (clm. 2, ln. 7-18), 3) performs signature extraction on genetic sequences to obtain gene signatures (Spec, para. 0092, ln. 16-28, “…a sequence feature and a non-sequence feature of the gene mutation candidate site are extracted…”), 4) modifies the gene signature by utilizing a convolutional neural network (CNN) to integrate gene features (Fig. 6, Spec, para. 0099), and 5) tests the genetic sequence based on a modified gene signature via the integration (Spec. para. 0077, “…the sequence feature and the non-sequence feature of the gene may be combined, thereby more comprehensively analyzing the feature of a gene mutation site…”). Hu specifically teaches utilizing a CNN for the purposes of “…avoiding interference caused by noise and errors, and better identifying gene mutation,” (Spec, para. 0086). “Enhancing” as disclosed in the specification of the instant application, means obtaining a gene signature in which the “quantity of information included in the enhanced signature is greater than the quantity of information included in the gene signature,” (Spec, para. 0154). Using the broadest reasonable interpretation (BRI) of the claims, the enhancement is interpreted as an improvement of the gene signature. Hu’s CNN not only “better identifies” or improves the gene signature via gene feature integration but also accounts for errors, increasing the quantity of information included in the gene signature, using computational methods. Therefore, Hu anticipates claim 1 of the invention.
In regards to dependent claim 2 and 14, which refer to obtaining a testing result, Hu teaches all limitations of claim 2. Hu teaches a non-transitory computer-readable storage medium, having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the operations of its invention (clm. 21). Additionally, Hu teaches a mutation identification method using a CNN, which performs a “screening out” and “analyzing” step, and returns an extracted gene features (non-sequence features, Spec, para. 0092). These steps of identification, screening, and analyzing are testing and are executed by computational methods; therefore, Hu anticipates claims 2 and 14 of the invention.
In regards to dependent claim 3, which refer to performing signature extraction on a genetic sequence and obtaining a gene signature, Hu teaches all limitations of claim 3. Hu teaches determining a to-be-analyzed gene fragment based on mutation presence (Spec, para 0005, “…corresponding to a gene mutation candidate site”), obtaining “sequence features” derived from a genomic sequences and gene features associated with genomic sequences obtained from gene sequencing and a CNN applied to gene sequencing data (clm. 1 ln 4-onward; clm. 8, ln. 1-6; Spec, para. 0092, “…a sequence feature and a non-sequence feature of the gene mutation candidate site are extracted by utilizing a neural network model…). As Hu teaches obtaining a sequence and extracting gene signatures from those sequences, Hu anticipates claim 3 of the invention.
In regards to dependent claim 4 and 15, which refer to obtaining reference data and a plurality of initial gene fragments included in the genetic sequence; and performing matching between the reference data and the genetic sequence to determine the to-be-analyzed gene fragment among the plurality of initial gene fragments, Hu teaches all limitations of claims 4 and 15. Hu teaches a non-transitory computer-readable storage medium, having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the operations of its invention (clm. 21). Additionally, Hu teaches obtaining sequence attribute information from a gene sequencing read segment in a preset site interval including: “determining a gene type…according to the comparison result between the gene sequence of each gene sequencing read segment and … the reference genome” (Spec, para. 0019). As Hu teaches comparing an obtained sequence to a reference genome using a computer, Hu anticipates claims 4 and 15 of the invention.
In regards to dependent claim 5 and 16, which refer to the status of the to-be-analyzed gene fragment having a base not matching the reference data at a threshold greater than a preset base threshold, Hu teaches all limitations of claim 5 and 16. Hu teaches “identifying the gene mutation of the gene mutation candidate site based on the integrated feature of the gene mutation candidate” by “obtaining a mutation value” such that if “the mutation value is greater than or equal to a preset threshold” one can determine “the existence of gene mutation of the gene mutation candidate site” (Spec, para. 0140). Hu also teaches obtaining a sequence, identifying a gene mutation candidate site, and assessing a mutation value against a preset threshold on dependent claim 9. As Hu teaches analyzing a gene fragment already compared to a reference genome (Spec, para. 0019, in regards to clm. 4 of the instant application) and then assessing the gene fragment for mutation presence using a preset threshold using a computer, Hu anticipates claims 5 and 16.
In regards to dependent claim 7 and 18, which refer to “enhancing” the gene signature using a CNN and obtaining the enhanced signature, Hu teaches all limitations of claims 7 and 18. Hu teaches a non-transitory computer-readable storage medium, having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the operations of its invention (clm. 21). Additionally, Hu teaches obtaining “sequence features” derived from a genomic sequences and gene features associated with genomic sequences obtained from gene sequencing and a CNN applied to gene sequencing data (clm. 1 ln 4-onward; clm. 8, ln. 1-6; Spec, para. 0092, “…a sequence feature and a non-sequence feature of the gene mutation candidate site are extracted by utilizing a neural network model…). As Hu teaches applying a CNN to sequencing data using a computer, Hu anticipates claims 7 and 18.
In regards to dependent claim 8, which refers to an enhanced gene signature which has a quantity of information greater than the original gene signature, Hu teaches all limitations of claim 8. Hu teaches applying sequence attribute information to a CNN (Fig. 6, Spec; para. 0085, para 0142, “The first branch [of the neural network] may be used for extracting the sequence feature… The neural network model… includes the convolutional layer…”). As Hu teaches applying sequence attribute information to a CNN, Hu anticipates claim 8.
In regards to dependent claim 9, which refers to a facet of the enhanced gene signature
having the same data magnitude as the preliminary gene signature, Hu teaches all
limitations of claim 9. Hu teaches using feature integration to combine a sequence feature and non-sequence feature matrix applied to branches of a CNN and obtaining a combined a gene sequence feature matrix (Spec, para. 0139, “…are combined into a feature matrix, so as to obtain an integrated feature matrix formed by feature integration…”; Fig. 6, Spec; para. 0085, para 0142, “The first branch [of the neural network] may be used for extracting the sequence feature… The neural network model… includes the convolutional layer…” Hu teaches that the sequence attribute information and the non-sequence attribute information corresponding to the gene mutation candidate site are integrated (Spec, para. 0139). Therefore, as Hu teaches returning a CNN-manipulated a genomic sequence, gene feature, or genomic sequence information of equal (or greater) importance or quality to its predecessor, Hu anticipates claim 9.
In regards to dependent claim 11, which refers to testing a genetic sequence based on the enhanced signature by obtaining a mutation testing result based on the mutation reference information, Hu teaches all limitations of claim 11. Hu teaches a method of “obtaining the…gene sequencing read segment corresponding to the gene mutation candidate site comprising obtaining a gene sequencing read segment obtained by performing gene sequencing on a somatic gene; comparing the gene sequence of the gene sequencing read segment with the gene sequence of the reference genome and obtaining a comparison result,” (clm. 10). As Hu teaches testing a genetic sequence based on the enhanced signature by obtaining a mutation testing result based on the mutation reference information, Hu anticipates claim 11.
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.
Claims 6, 12 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhiqiang Hu (U.S. Patent 20210082539A1; hereby referred to as Hu) as applied to claims 1-5, 7-9, 11, 13-16, 18 and 20 above, in view of Ole Benjamin Schulz-Trieglaff, et al. (US20190220704A1; hereby referred to as OLE).
The instant claims are drawn to a method and apparatus for (individually and with one or more processors; and one or more memories storing thereon computer-readable instructions) performing acts comprising performing signature extraction on the to-be-analyzed gene fragment, obtaining a base quality included in the to-be-analyzed gene fragment, and determining a confidence level based on base quality that affects signature extraction.
Hu et al. teaches claims 1-5, 7-9, 11, 13-16, 18 and 20 above.
Hu et al. does not teach a method to determine a confidence level corresponding specifically to an analyzed gene fragment based on the fragment’s base quality
OLE is directed to a deep learning-based variant classifier using a convolutional neural network (CNN) and capable of producing a confidence score if a mutation is present in a sequence.
In regards to dependent claim 6 and 17, Hu teaches a non-transitory computer-readable storage medium, having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the processor is caused to perform the operations of its invention (clm. 21). Additionally, Hu teaches performing signature extraction on a gene fragment obtained from gene sequencing (Spec, para. 0092, “…a sequence feature and a non-sequence feature of the gene mutation candidate site are extracted by utilizing a neural network model…”; Spec, para. 0106, “The preprocessing mode includes…sequencing quality screening, comparison quality screening…”). Hu does not teach a method to determine a confidence level corresponding to an analyzed gene fragment based on the fragment’s base quality.
OLE teaches a method for determining the confidence of genetic variation as “A classification layer (e.g., a softmax layer) following the full-connected layers can produce classification scores for likelihood that each candidate variant at the target base position is a true variant or a false variant. In other implementations, the classification layer can produce classification scores for likelihood that each candidate variant at the target base position is a homozygous variant, a heterozygous variant, a non-variant, or a complex-variant.” (Spec, para. 0172). OLE continues, describing the likelihood score, noting “The output module includes translating analysis by the convolutional neural network into classification scores for likelihood that each candidate variant at the target base position is a true variant or a false variant. A final softmax classification layer of the convolutional neural network can produce normalized probabilities for the two classes that add up to unity (1). In the illustrated example, the softmax probability of the true positive (or true variant) is 0.85 and the softmax probability of the false positive (or false variant) is 0.15.” (Spec, para. 0192). Additionally, as OLE can identify copy number variations, as stated on paragraph 0087 of the specification, and OLE discusses use of a variant annotation tool on paragraph 0118 of the specification, OLE can analyze segments of DNA in a genetic sequence against a reference sequence and assign a potential gene annotation (effectively illustrating capability for confidence scoring in the context of a gene signature analysis). Therefore, the likelihood score functions as a numerical calculation to ascertain the validity of the presence of a variant in a genetic sequence given the quality of the input to the convolutional neural network. This method effectively functions similarly to a confidence interval.
In KSR Int'l v. Teleflex, the Supreme Court, in rejecting the rigid application of the teaching, suggestion, and motivation test by the Federal Circuit, indicated that “The principles underlying [earlier] cases are instructive when the question is whether a patent claiming the combination of elements of prior art is obvious. When a work is available in one field of endeavor, design incentives and other market forces can prompt variations of it, either in the same field or a different one. If a person of ordinary skill can implement a predictable variation, § 103 likely bars its patentability.” KSR Int'l v. Teleflex lnc., 127 S. Ct. 1727, 1740 (2007).
Applying the KSR standard to Hu and REID., the examiner concludes that the combination of Hu and REID represents the use of known techniques to improve similar methods. Both HU and OLE disclose methods to analyze genomic sequences, and both employ neural network models to manipulate genomic sequences, but OLE adds a confidence interval used to validate facets of genetic sequences (the presence of mutations).
One of ordinary skill in the art of sequence analysis would have been motivated to combine Hu’s signature extraction method with OLE’s confidence level determination method because all of the claimed elements were known in the prior art surrounding genetic sequence analysis, Hu’s art hinges on comparing a given genetic sequence with a reference genome, and OLE’s method is adapted to utilize user-input genetic data with reference genomes to generate genetic variant-phenotype association data (including, for example, copy number variants as detailed on paragraph 0087 of the Spec) from user-inputted genomic sequences. Furthermore, as the likelihood score determined in OLE’s invention is added to the CNN and is numerically calculated based on the sequence and reference sample, one skilled in the art could have combined the likelihood from OLE as claimed with no change in their respective functions, and the combination of this feature from OLE and Hu’s CNN would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention.
One of ordinary skill in the art of sequence analysis before the effective filing date of the claimed invention would have had a reasonable expectation of success because the teachings of Hu and REID analyze similar data (genomic sequences). Combine Hu’s signature extraction method with OLE’s confidence level determination method would have been expected to have provided a more-detailed metadata associated with genomic sequences, including expanded information on genetic variants within a sequence when compared against a reference genome and bolstered with statistical rigor, improving the significance of genomic sequence testing results. Therefore, the invention would have been prima facie obvious to one of skill in the art at the time of filing of the application, absent evidence to the contrary.
In regards to dependent claims 12 and 17, which refer to testing the genetic sequence based on the enhanced signature by inputting the enhanced signature into a three-dimensional network model, wherein the three-dimensional network model is trained to test the genetic sequence based on the gene signature, Hu in view of Ole teaches all limitations of claim 12. Hu teaches performing signature extraction on a gene fragment obtained from gene sequencing (Spec, para. 0092, “…a sequence feature and a non-sequence feature of the gene mutation candidate site are extracted by utilizing a neural network model…”; Spec, para. 0106, “The preprocessing mode includes…sequencing quality screening, comparison quality screening…”). Hu does not teach a method of inputting the enhanced signature into a three-dimensional network model, wherein the three-dimensional network model is trained to test the genetic sequence based on the gene signature.
OLE teaches a deep learning-based variant classifier using a convolutional neural network (CNN). OLE teaches that the CNN “Uses a backpropagation-based gradient update technique that progressively matches the output of the convolutional neural network with the corresponding ground truth label to produce raw read fragments across variant candidate sites labeled as true variants,” and that “The array of input features encodes the data for a group of reads aligned to the reference sequence…each input feature in the array corresponds to a base in the raw read fragment and has a plurality of dimensions…” (clm. 14).
Applying the KSR standard to Hu and OLE, the examiner concludes that the combination of Hu and OLE represents some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. Both Hu and OLE disclose methods to analyze genomic sequences, but OLE discloses the teaching of applying a CNN to genomic data.
One of ordinary skill in the art would have been motivated to combine Hu’s signature extraction method with the CNN within OLE’s variant caller because OLE’s variant caller is equipped to process a plurality of aligned reads that span a target base position (Abstract; clm. 14; Spec., para. 0063), which Hu can provide. One skilled in the art would have been motivated to combine Hu’s signature extraction method with the CNN within OLE’s variant caller to apply a three-dimensional network model, as taught within OLE’s art, and modify it such that it is trained to test a genetic sequence based on a gene signature derived from Hu’s signature extraction method to achieve the claimed invention. One would have reasonable expectation of success in combining Hu’s signature extraction method with the CNN within OLE’s variant caller as the two arts both analyze genetic sequences using a CNN that one skilled in the art would be capable of modifying. Therefore, the invention would have been prima facie obvious to one of skill in the art at the time of filing of the application, absent evidence to the contrary.
Claims 10 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhiqiang Hu (U.S. PG Pub 2021/0082539 A1; hereby referred to as Hu) as applied to claims 1-5, 7-9, 11, 13-16, 18 and 20 above, in view Mo Xiaodong, et al. (WO 2018214010A1; hereby referred to as XIAODONG) and in further view of Guo Ruidong et al. (WO 2019047181A1; hereby referred to as RUIDONG)
Claim 10 is a method of testing directed to obtaining, based on the enhanced signature, mutation reference information corresponding to the enhanced signature, wherein the mutation reference information comprises at least one of the following: prediction information of 21 genotypes; zygote prediction information; first allele mutation length information; and second allele mutation length information.
Claim 19 is a device executing the method of testing of claim 10.
Hu is directed to a method of testing a genetic sequence by “obtaining the…gene sequencing read segment corresponding to the gene mutation candidate site comprising obtaining a gene sequencing read segment obtained by performing gene sequencing on a somatic gene; comparing the gene sequence of the gene sequencing read segment with the gene sequence of the reference genome and obtaining a comparison result,” (clm. 10).
Hu does not explicitly teach obtaining mutation reference information comprising at least prediction information of 21 genotypes; zygote prediction information; first allele mutation length information; and second allele mutation length information.
Xiodong is directed to a method, a device, and a storage medium for detecting mutation on the basis of sequencing data in which sequencing reads identify “The Minor allele frequency (MAF) and/or the Hardy-Weinberg equilibrium (HWE), the cumulative result of the population variation information is obtained, and the so-called "group variation information accumulation result" includes each variation site.” (clm. 3, Spec; detailed description).
Xiodong does not teach genotyping.
Ruidong is directed to a method for genotyping based on low depth genome sequencing.
In regards to dependent claim 10 and 19, which refers to obtaining, based on the enhanced signature, mutation reference information corresponding to the enhanced signature, comprising: prediction information of 21 genotypes; zygote prediction information; first allele mutation length information; and second allele mutation length information, Hu in view of XIAODONG addresses all limitations of claim 10. Hu teaches testing a genetic sequence via a method “obtaining the…gene sequencing read segment corresponding to the gene mutation candidate site comprising obtaining a gene sequencing read segment obtained by performing gene sequencing on a somatic gene; comparing the gene sequence of the gene sequencing read segment with the gene sequence of the reference genome and obtaining a comparison result,” (clm. 10). Hu does not teach prediction information for genotypes, zygote prediction information, or first allele or second allele mutation length information.
XIAODONG teaches a method, a device, and a storage medium for detecting mutation on the basis of sequencing data in which sequencing reads identify “The Minor allele frequency (MAF) and/or the Hardy-Weinberg equilibrium (HWE), the cumulative result of the population variation information is obtained, and the so-called "group variation information accumulation result" includes each variation site.” (clm. 3, Spec; detailed description). HWE implies a primary and secondary allele frequency, and XIAODONG teaches that "secondary allele frequency" refers to the frequency of unusual alleles in a given population” (clm. 3, Spec; detailed description). XIAODONG also teaches allele mutation length information via a comparison and variation and detecting device capable of identifying mutations, noting “The comparison and variation detecting device [201] is configured to compare the sequencing data of the plurality of individuals from the same group to the reference genome and perform mutation detection to obtain the read length matching position and the variation information”, and “ The method of the embodiments of the present invention is particularly suitable for single nucleotide polymorphism (SNP) variation, insertion/deletion (Ins/Del) mutation detection…” (Spec, detailed description) XIAODONG does not explicitly teach genotyping.
RUIDONG teaches a method for genotyping based on low depth genome sequencing, including “… genotyping at least one known mutation site of the organism to be tested…determining the pedigree of the organism based on the result of the genotyping,” (clm. 11-12). As RUIDONG teaches genotyping, their method includes potential combinations of the four primary nucleotides (“A”, “C”, “T”, “G”).
Applying the KSR standard to Hu, XIAODONG, and RUIDONG, the examiner concludes that the combination of Hu, XIAODONG, and RUIDONG represents some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. Hu, XIAODONG, and RUIDONG disclose methods to analyze genomic sequences, but the combination of the three arts includes mutation identification and genotyping in addition to sequence analysis and improvement.
One of ordinary skill in the art would have been motivated to combine Hu’s signature extraction method with XIAODONG’s mutation identification method and RUIDONG’s genotyping method, as all three arts examine genomic sequences with additive and complimentary techniques; XIAODONG’s mutation identification is complementary to RUIDONG’s genotyping and both arts are complementary to Hu’s CNN. Furthermore, all arts are computational in nature and their models are similar in nature to a degree in which one of ordinary skill in the art would be capable of modifying them.
One skilled in the art would have had a reasonable expectation of success to combine the elements as claimed with no change in their respective functions, as all of the claimed elements were known in the prior art, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention. Therefore, the invention would have been prima facie obvious to one of skill in the art at the time of filing of the application, absent evidence to the contrary.
Pertinent Art
The examiner suggests, Lal et al. (bioRxiv preprint, November 4, 2019, pages 1-18) as pertinent to the application as filed. As previously stated, Lal et al. discloses AtacWorks, a deep CNN toolkit for the study of epigenomics. In the results section, Lal et al. discloses how AtacWorks is utilized for denoising low-coverage chromatin-specific sequencing data, and states that the trained model is applied to enhance the resolution of single cell studies at single-base pair resolution by modeling with three inputs: a noisy signal track, a clean signal track, and the location of peaks in the clean dataset (Abstract, pg. 1 Results pg. 1, Methods, pg. 9; performing signature extraction; obtaining a convolutional neural network model; performing; enhancing the gene signature). As the application as filed references enhancing sequences, AtacWorks may provide a relevant template for the applicant detailing a neural network fit to denoise sequencing data’s prior use in the field of epigenetics.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN T STUBBS whose telephone number is (571)272-0340. The examiner can normally be reached M-F 8-5 EST.
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, Larry Riggs can be reached at 571-270-3062. 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.
/J.T.S./Examiner, Art Unit 1686
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686