DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Status
Claim(s) 1-17 is/are currently pending and under exam herein.
Claim(s) 1-17 is/are rejected.
Priority
The instant application is a continuation of U.S. Nonprovisional Patent Application No. 16/160,986 filed October 15, 2018, which in turn claims priority to the following U.S. Provisional Patent Applications:
No. 62/573,144 filed October 16, 2017
No. 62/573,149 filed October 16, 2017
No. 62/573,153 filed October 16, 2017
No. 62/582,898 filed November 7, 2017
The claims to domestic benefit are acknowledged. Thus, the effective filing date of claims 1-17 is October 16, 2017.
Information Disclosure Statement
The information disclosure statements (IDS) were filed on 06/03/2022, 03/09/2023, 05/25/2023, 08/24/2023, 04/11/2024, 04/11/2024, 05/30/2024, 07/25/2024, 04/04/2025, and 10/15/2025. The IDS filed on 03/09/2023 and 07/25/2024 contained references that were cited incorrectly. Authorship, dates, and patent number have been corrected in the respective IDS, as marked by the strike through and textboxes on the attached IDS documents.
All information disclosure statements have been considered by the examiner.
Nucleotide and/or Amino Acid Sequence Disclosures
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 – 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. Amino acid sequences are specifically present in Fig. 16, Fig. 19, and Fig. 20.
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.
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.
Drawings
The drawings are objected to because . 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. The codes can be found in:
Paragraph [00248] on page 30 (http://raptorx.uchicago.edu/download/)
Paragraph [00324] on page 47 (https://sites.google.com/site/popgen/dbNSFP)
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 Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
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 8-12, 14, and 16 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.
Claims 8-12, 14 and 16 recites the limitation "wherein". There is insufficient antecedent basis for this limitation in the claim. In addition, claims 8-12, 14, and 16 depend from Claim 7 which cites “at least one conservation profile”, yet the language in claims 8-12, 14, and 16 seem to indicate only one conservation profile. Examiner will continue examination interpreting that there is more than one conservation profile present. However, applicant can choose to clarify and indicate that there is only one conservation profile in claims 8-12, 14 and 16. As a caveat, if applicant makes clear that there is only one conservation profile in claims 10-12, then the claims would become duplicate claims of claims 4-6 correspondingly.
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 1-17 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1) 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:
Claim 1-12 recites a computer-implemented method that takes as input, amino acid sequences and conservation profiles, before processing them through a neural network to determine if a nucleotide substitution results in a pathogenic or benign variant. The claims are merely collecting information (observation), comparing it to known references (evaluation), before outputting a result of pathogenicity (judgment). In addition, the sequences being classified are only twenty amino acids long which is short enough that the human mind is able to evaluate and make comparisons for, making it a mental process. Furthermore, claims to comparing sequences and determining the existence of alterations falls under a mental process that can be practically performed in the human mind according to University of Utah Research Foundation v. Ambry Genetics, 774 F.3d 755, 763, 113 USPQ2d 1241, 1246 (Fed. Cir. 2014).
Claims 13-16 adds onto the computer-implemented method of claim 7 to include more inputs and processing to generate secondary structure predictions and solvent accessibility predictions. Again, this is merely collecting known information about secondary structures and solvent accessibility (Protein DataBank), comparing it to the given sequence, before making a judgment on whether it is alpha helix, beta sheet, or beta coils and buried, intermediate, or exposed.
Claim 17 recites a broader computer-implemented method that takes inputs (two sequences and at lease one conservations profile) to determine if a nucleotide substitution is pathogenic or benign. The claim is merely data gathering (observation), comparing to known data (evaluating), before outputting a binary result (judgment), which again falls under a mental process. The sequences are only twenty amino acids long, and can be practically performed in the human mind based on University of Utah Research Foundation v. Ambry Genetics, 774 F.3d 755, 763, 113 USPQ2d 1241, 1246 (Fed. Cir. 2014).
While claims 1-17 recite performing some aspects of the analysis with a “neural network” or a “computer”, there are no additional limitations that indicate that the neural network or computer require 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, claims 1-17 recites an abstract idea. Furthermore, it should be noted that claims 1-17 attempts to correlate the presence of a naturally occurring variation with the pathogenicity of the variation, which constitutes a natural phenomenon. According to MPEP 2106.04(b).I, naturally occurring principles/relations are part of the storehouse of knowledge, free to all men and reserved exclusively to none, and hence are not patentable.
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 in some other meaningful way. Rather, the instant claims recite additional elements that amount to mere instructions to implement the abstract idea in a generic computing environment. Specifically, the claims recite the following additional elements:
Claims 1-12 recites utilizing a pathogenicity prediction neural network to process all the inputs and output a prediction without additional detailing pertaining to the neural network.
Claims 13-14 recites a secondary structure neural network to process the conservation profile to generate secondary structure predictions.
Claims 15-16 recites a solvent accessibility neural network to process the conservation profile to generate solvent accessibility predictions.
Claim 17 recites a computer-implemented method to process all the inputs and output a prediction without additional steps.
There are no additional details pertaining to the neural networks or computer-implemented method that indicate 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. See also 573 U.S. at 224, 110 USPQ2d at 1984. In general, linking the use of an abstract idea to a particular technological environment, such as a computer, does not integrate the abstract idea into a practical application based on MPEP 2106.05(h). Therefore, claims 1-17 are directed to an abstract idea (mental process) and/or natural phenomenon as the additional elements do not integrate the judicial exceptions into a practical application.
Claims found to recite a judicial exception under Step 2A, Prong 2 are then further analyzed to determine if the claims as a whole amount to significantly more than the identified judicial exception (Step 2B). In claims 1-17, there is no further instructions or limitations to the additional element of neural networks and/or computer-implemented method that would indicate anything other than applying the abstract idea on a generic computer. According to MPEP 2106.05(d), courts have held computer‐implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amount to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e., by hand or by merely thinking). Therefore, the additional elements in claims 1-17 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.
In conclusion, claims 1-17 are directed to the abstract idea of predicting pathogenicity of single nucleotide variants by collecting information, analyzing it, and outputting the results of the collection and analysis. The claims do not provide an inventive concept, because the claims do not recite additional elements or a combination of elements that amount to significantly more than the judicial exception of the claims. Therefore, whether taken individually or as an order, the claims do not amount to significantly more than the judicial exception itself (Step 2B). As such, claims 1-17 are not patent eligible.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(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 17 is rejected under 35 U.S.C. 102(a)(1) as being anticipated by Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863).
With respect to claim 17, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, at least one conservation profile generated using cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 17. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position. It can be seen that Wei et al. teaches all the limitations of claim 17, and hence claim 17 is rejected as being anticipated by Wei et al.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3 and 5-6 are rejected under 35 U.S.C. 103 as being unpatentable over Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863) in view of Frey et al. (US 2016/0364522), and Thomas et al. (Trends in Genetic, 2002 Feb, Volume 18, Issue 2, pgs 104-8). The italicized text corresponds to the instant claim limitations.
With respect to claim 1, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, a primate conservation profile generated using primate cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 1. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position.
Regarding claim 2, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, a primate conservation profile generated using primate cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 2. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position.
Concerning claim 3, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, a primate conservation profile generated using primate cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 3. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position.
Pertaining to claim 5, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution).
With regards to claim 6, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution).
Wei et al. is silent to a using a neural network in claims 1-3 and 5-6; and a mammal conservation profile in claims 1, 2, and 5; along with a vertebrate conservation profile in claims 1, 3, and 6. However, these limitations were known in the art at the time of the effective filing date of the invention as taught by Frey et al. and Thomas et al.
With respect to claim 1-3 and 5-6, Frey et al. discloses the use of deep neural networks (convolutional, recurrent, and long-term short-term memory recurrent neural networks) and biological patterns to classify variants as benign or pathogenic (Claims 1, 4, and 7, a pathogenicity prediction neural network). The neural network in Frey et al. takes as input two different sequences that they refer to as the variant sequence and the reference sequence (Claim 1, a reference protein sequence and an alternative protein sequence). In addition, Frey et al. define variant as a difference from the reference sequence in one or more nucleotides, for example, by substitution (Paragraph [0041], differ by a variant amino acid caused by a nucleotide substitution).
An invention would have been prima facie obvious to one of ordinary skill in the art at the effect filing date of the invention to modify the machine learning method of Wei et al. with the neural networks of Frey et al. to successfully produce a more efficient machine learning method that would be adept at solving sequence-based problems through motif discovery. One of ordinary skill in the art would have been motivated to replace the support vector machines of Wei et al. with neural networks because their filters pose as a series of motif scanners, efficiently fitted for recognizing patterns in large amounts of sequencing data, which is stated in the specification of the instant application ([00197-00199]). In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at performing the process of Wei et al. with the neural networks of Frey et al., as neural networks were well established in the field of genomics and motif detection during this time. Wei et al. also recites multiple examples of neural networks used by others in the field to predict characteristics of protein sequences, although they themselves choose another model.
However, both Wei et al. and Frey et al. are silent to the use of a mammal conservation profile for claims 1, 2, and 5 and a vertebrate conservation profile for claims 1, 3, and 6. However, these limitations were known in the art at the time of the effective filing date of the invention as taught by Thomas et al.
With respect to claim 1, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. emphasizes how using sequences from multiple species in a single comparison adds significant power to the identification of functionally conserved sequences and that sequencing vertebrates from interspersed evolutionary time points is necessary to fully understand the evolution and relevance of conserved orthologous sequences (pg 1, second col, para 1, a vertebrate conservation profile generated using vertebrate cross-species sequence alignment). In addition, Thomas et al. goes on to emphasize the similarities between humans and other mammals (mouse, chimpanzee, baboon, cow, pig, cat) and how comparative sequencing projects are increasing effort to sequence other mammals and vertebrates for comparison to the human genome (pg 4, first col, para 1, a mammal conservation profile generated using a mammal cross-species sequence alignment).
Regarding to claim 2, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. goes on to emphasize the similarities between humans and other mammals (mouse, chimpanzee, baboon, cow, pig, cat) and how comparative sequencing projects are increasing effort to sequence other mammals and vertebrates for comparison to the human genome (pg 4, first col, para 1, a mammal conservation profile generated using a mammal cross-species sequence alignment).
With respect to claim 3, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. emphasizes how using sequences from multiple species in a single comparison adds significant power to the identification of functionally conserved sequences and that sequencing vertebrates from interspersed evolutionary time points is necessary to fully understand the evolution and relevance of conserved orthologous sequences (pg 1, second col, para 1, a vertebrate conservation profile generated using vertebrate cross-species sequence alignment).
Regarding to claim 5, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. goes on to emphasize the similarities between humans and other mammals (mouse, chimpanzee, baboon, cow, pig, cat) and how comparative sequencing projects are increasing effort to sequence other mammals and vertebrates for comparison to the human genome (pg 4, first col, para 1, a mammal conservation profile generated using a mammal cross-species sequence alignment).
With respect to claim 6, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. emphasizes how using sequences from multiple species in a single comparison adds significant power to the identification of functionally conserved sequences and that sequencing vertebrates from interspersed evolutionary time points is necessary to fully understand the evolution and relevance of conserved orthologous sequences (pg 1, second col, para 1, a vertebrate conservation profile generated using vertebrate cross-species sequence alignment).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art at the effect filing date of the invention to include the mammalian and other vertebrate sequence data from Thomas et al. in the analysis of pathogenicity to increase comparison inputs and boost the accuracy of predictions made. Especially, making sure that the variants are free from human ascertainment bias when using an annotated database based on just humans and primates, as stated in the specification of the instant application ([00210]). The specification also states how the network is robust and accurate when alignment information extends throughout primates and mammals, confirming how the incorporate of mammalian and other vertebrate sequences help to increase the validity of the model ([00340]). In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating the protein sequences from mammals and vertebrates into the data analysis, as databases of these sequences and their comparison to human sequences were well established during this time. Furthermore, Wei et al. also cites databases with other mammalian and vertebrate protein sequences that could be utilized for analysis.
Claim(s) 4, 7-10 are rejected under 35 U.S.C. 103 as being unpatentable over Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863) in view of Frey et al. (US 2016/0364522). The italicized text corresponds to the instant claim limitations.
With respect to claim 4, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, a primate conservation profile generated using primate cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 4. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position.
Regarding claim 7, Wei et al. discloses a method of predicting phenotypes of missense mutations, both deleterious and neutral, through machine learning (pg 1, left col, para 1, a computer-implemented method…generating as output a pathogenicity prediction for nucleotide substitution). Wei et al. utilizes mutation sequences without insertion or deletion within 10 amino acids on either side of the mutation of amino acid differences, that only include single-site nucleotide substitutions (pg 2, right col, para 3, a reference protein sequences with at least twenty amino acids, an alternative protein sequence aligned with the reference protein sequence wherein the alternative sequence is at least twenty amino acids, and differs by a variant amino acid from the reference sequences, caused by a nucleotide substitution). Wei et al. also teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, at least one conservation profile generated using cross-species multiple sequence alignment). The phrase conservation profile is not explicitly defined in claim 7. Hence, for the broadest reasonable interpretation they are taken to mean a pattern/motif detecting input. PSSMs are a motif detection input that scores how likely a particular amino acid or nucleotide will appear at a specific position.
Concerning claim 8 which further limits claim 7, Wei et al. teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5). Although, position-specific frequency matrix (PSFM) is not explicitly mentioned in Wei et al., the conversion between PSFMs and PSSMs is general mathematics, as PSSMs are the log-likelihood ratios of the distributions in PSFMs. Therefore, it is obvious that to produce PSSMs, one might utilize PSFMs. In addition, based on the broadest reasonable interpretation and the specifications, applicant believes PSFMs and PSSMs can be used interchangeably as they serve similar functions (Specification [0094]).
Pertaining to claim 9 which further limits claim 7, Wei et al. teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, wherein the conservation profile is a position-specific scoring matrix).
With regards to claim 10 which further limits claim 7, Wei et al. teaches the use of position-specific scoring matrices (PSSMs) for both human and primate protein sequences to help with prediction of phenotypes (pg 2, right col, para 5, wherein the conservation profile is a primate conservation profile generated using cross-species multiple sequence alignment).
Wei et al. is silent to a using a neural network in claims 4, and 7-10. However, these limitations were known in the art at the time of the effective filing date of the invention as taught by Frey et al.
With respect to claim 4, and 7-10, Frey et al. discloses the use of deep neural networks (convolutional, recurrent, and long-term short-term memory recurrent neural networks) and biological patterns to classify variants as benign or pathogenic (Claims 1, 4, and 7, a pathogenicity prediction neural network). The neural network in Frey et al. takes as input two different sequences that they refer to as the variant sequence and the reference sequence (Claim 1, a reference protein sequence and an alternative protein sequence). In addition, Frey et al. define variant as a difference from the reference sequence in one or more nucleotides, for example, by substitution (Paragraph [0041], differ by a variant amino acid caused by a nucleotide substitution).
An invention would have been prima facie obvious to one of ordinary skill in the art at the effect filing date of the invention to modify the machine learning method of Wei et al. with the neural networks of Frey et al. to successfully produce a more efficient machine learning method that would be adept at solving sequence-based problems through motif discovery. One of ordinary skill in the art would have been motivated to replace the support vector machines of Wei et al. with neural networks because their filters pose as a series of motif scanners, efficiently fitted for recognizing patterns in large amounts of sequencing data, which is stated in the specification of the instant application ([00197-00199]). In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at performing the process of Wei et al. with the neural networks of Frey et al., as neural networks were well established in the field of genomics and motif detection during this time. Wei et al. also recites multiple examples of neural networks used by others in the field to predict characteristics of protein sequences, although they themselves choose another model.
Claims 11-12 are rejected under 35 U.S.C. 103 as being unpatentable over Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863) in view of Frey et al. (US2016/0364522), as applied to Claim 7 above, and Thomas et al. (Trends in Genetic, 2002 Feb, Volume 18 Issue 2, pgs 104-8). The italicized text corresponds to limitations of the instant application.
The limitations of claim 7 have been taught by Wei et al. and Frey et al. above.
Regarding to claim 11, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. goes on to emphasize the similarities between humans and other mammals (mouse, chimpanzee, baboon, cow, pig, cat) and how comparative sequencing projects are increasing effort to sequence other mammals and vertebrates for comparison to the human genome (pg 4, first col, para 1, wherein the conservation profile is a mammal conservation profile generated using a mammal cross-species sequence alignment).
With respect to claim 12, Thomas et al. teaches how interspecies comparison, especially between mammal, vertebrates, and humans, is a powerful tool in genomic sequencing that can help determine functional annotations or coding regions that could control gene expression (pg 1, first col, para 2). Thomas et al. emphasizes how using sequences from multiple species in a single comparison adds significant power to the identification of functionally conserved sequences and that sequencing vertebrates from interspersed evolutionary time points is necessary to fully understand the evolution and relevance of conserved orthologous sequences (pg 1, second col, para 1, wherein the conservation profile is a vertebrate conservation profile generated using vertebrate cross-species sequence alignment).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art at the effect filing date of the invention to include the mammalian and other vertebrate sequence data from Thomas et al. in the analysis of pathogenicity to increase comparison inputs and boost the accuracy of predictions made. Especially, making sure that the variants are free from human ascertainment bias when using an annotated database based on just humans and primates, as stated in the specification of the instant application ([00210]). The specification also states how the network is robust and accurate when alignment information extends throughout primates and mammals, confirming how the incorporate of mammalian and other vertebrate sequences help to increase the validity of the model ([00340]). In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating the protein sequences from mammals and vertebrates into the data analysis, as databases of these sequences and their comparison to human sequences were well established during this time. Furthermore, Wei et al. also cites databases with other mammalian and vertebrate protein sequences that could be utilized for analysis.
Claims 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863) in view of Frey et al. (US 2016/0364522), as applied to claim 7 above, and further in view of Rost et al. (Proceedings of the National Academy of Sciences, 1993 Aug 15, Volume 90, pgs 7558-7562). The italicized text corresponds to the instant claim limitations.
The limitations of claim 7 have been taught by Wei et al. and Frey et al. above.
With respect to claim 13, Rost et al. discloses how neural networks can be utilized to generate three-state secondary structure predictions for amino acid sequences (pg 1, left col, para 2, a three-state secondary structure prediction…in the first chain of amino acids).
With respect to claim 14, Rost et al. teaches a method of predicting three-state secondary-structure with neural networks that helps to increase both the accuracy and quality of predictions (pg 1, left col, para 1, a secondary structure neural network…generates the three-state secondary structure predictions). Rost et al. also utilized multiple sequence alignment rather than single sequences as input to the neural network, using homologues of protein sequences to increase accuracy by 6% (pg 1, right col, para 2, neural network processes the conservation profiles). In addition, Rost et al. states that compared to classical methods of protein secondary structure prediction, the neural network model achieved a three-state prediction accuracy of 69.7%, making it suitable model to estimate the structural type of newly sequenced proteins (pg 1, left col, para 1).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate Rost et al.’s secondary structure prediction neural network into the pathogenicity prediction model of Wei et al. and Frey et al. in order to increase the accuracy and understanding of pathogenic predictions. Understanding the secondary structure would give researchers insight into the physical properties and stability of the mutated variant, how it binds with other proteins/molecules/cells or even how it might move throughout the cell. These insights would help to increase the understanding and validity of the mutated variant, contributing to more accurate predictions. In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating Rost et al.’s secondary structures into the data analysis, as the technique of adding various neural network layers into established neural networks was well understood. Furthermore, protein secondary structure prediction itself was a well-established field in of itself with various databases to help analysis of numerous sequences and their possible structures.
Claims 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Wei et al. (PLoS One, 2013 Jul 9, Volume 8, Issue 7, e67863) in view of Frey et al. (US 2016/0364522), as applied to claim 7 above, and further in view of Ahmad et al. (Bioinformatics, 2002 June 1, Volume 18, No. 6, pgs 819-824). The italicized text corresponds to the instant claim limitations.
The limitations of claim 7 have been taught by Wei et al. and Frey et al. above.
With respect to claim 15, Ahmad et al. teaches how neural networks can be utilized to generate three-state solvent accessibility predictions for amino acid sequences (pg 1, right col, para 1, a three-state solvent accessibility prediction…in the first chain of amino acids).
Regarding claim 16, Ahmad et al. discloses a method of predicting solvent-accessibility with neural networks that learns faster to provide results that are better than other methods (pg 1, right col, para 1, a solvent accessibility neural network…generates the three-state solvent accessibility prediction). Ahmad et al. utilized a set of 215 protein, with up to 25% homology for the model (pg 2, right col, para 1, neural network process the conservation profile). In addition, Ahmad et al. confirm the applicability of the neural network model for larger data set and wider range of state thresholds, making it a suitable model to estimate the accessibility of numerous sequenced proteins (pg 6, left col, para 1).
It would have been obvious to one of ordinary skill in the art at the time the invention was made to incorporate Ahmad et al.’s solvent accessibility prediction neural network in the pathogenicity prediction model of Wei et al. and Frey et al. in order to increase the accuracy and understanding of pathogenic predictions. Similar to the addition of secondary structures, understanding the solvent accessibility or accessible surface area would give researchers insight into the physical properties and stability of the mutated variant. It would give further insights into how the mutated variant might binds with other proteins/molecules/cells or even how it might move throughout the cell. These insights would help to increase the understanding and validity of the mutated variant, contributing to more accurate predictions. In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating Ahmad et al.’s solvent accessibility predictions into the data analysis, as the technique of adding various neural network layers into established neural networks was well understood. Furthermore, protein solvent accessibility prediction itself was a well-established field in of itself with various databases to help analysis of numerous sequences and their possible structures.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-17 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-5 of U.S. Patent No. 11315016 titled Deep Convolutional Neural Networks for Variant Classification. Although the claims at issue are not identical, they are not patentably distinct from each other.
Claim 1-12, and 17 of the instant application recites using a pathogenicity prediction neural network to predict pathogenicity for single nucleotide substitutions by processing: a reference protein sequence, an alternative protein sequence that differs by a variant amino acid from the reference sequence due to a nucleotide substitution, and three different (primate, mammal, and vertebrate) conservation profiles as input. In searching the specification, the conservation profiles are interpreted to be matrices that represent motifs in biological sequences. Specifically, positional frequency matrices, position weight matrices, and position-specific scoring matrices were cited as examples in the specification and claims. In U.S. Patent No. 11315016 Claim 1, 4, and 5, it also recites using a neural network classifier (Claim 1) that is trained to classify a variant sequence as benign or pathogenic (Claim 4) based on processing as input: a reference translated unit sequence, a targeted translated unit sequence that is produced by a single base variant from the reference sequence, and positional frequency matrices (PFM) based on primates, mammals and vertebrates (Claim 5). Both sets of claims are an invention to predict the pathogenicity of variants in sequences through utilizing deep learning in the form of a neural networks. And both do this through processing motif-detecting inputs from primates, mammals, and vertebrates. Although, not worded identically, claims 1-12, 17 of the instant application is not patentably distinct from Claim 1, 4, and 5 of U.S. Patent No. 11315016.
Claims 13-14 of the instant application further adds to the pathogenicity prediction neural network by reciting a secondary structure neural network that predicts the three-state secondary structure for the amino acid sequences. In U.S. Patent No. 11315016 Claim 2, it also recites a secondary structure subnetwork, that is trained to predict the three-state secondary structure within a translated sequence. Both add onto their respective neural networks to generate structural predictions for their sequences, and therefore Claims 13-14 of the instant applications is not patentably distinct from Claim 2 of U.S. Patent No. 11315016.
Claim 15-16 of the instant application also further adds to the pathogenicity prediction neural network of previous claims by reciting a solvent-accessibility neural network to generate three-state solvent accessibility predictions for each amino acid sequence. In U.S. Patent No. 11315016 Claim 3, it also recites a solvent accessibility subnetwork that is trained to predict a three-state solvent accessibility in each translated sequence. Both add onto their respective neural networks to generate solvent accessibility predictions for their sequences, and therefore Claims 15-16 of the instant application is not patentably distinct from Claim 3 of U.S. Patent No. 11315016.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Stamatoyannopoulos, US20160004814A1, 01/07/2016
Wang, Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5506
Makalowska, Computational Biology and Chemistry, Vol 29, Issue 1, 2005, pages 1-12
Sundaram, Nature Genetics, Volume 50, 07/23/2018, pages 1161-1170
Kent, Genome Research, Volume 12, Issue 6, 06/12/2002, pages 996-1006
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WENYU YANG whose telephone number is (571)272-0035. The examiner can normally be reached 7:30am - 5:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Olivia Wise can be reached at (571) 272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/W.Y./Examiner, Art Unit 1685
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685