DETAILED ACTION
The Applicant’s response, received 16 December 2025 has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 .
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.
Applicant's submission filed on 16 December 2025 has been entered.
Status of the Claims
Claims 1-10, 12-14, 17, 26, and 35 have been cancelled.
Claims 36-53 are pending.
Claims 36-53 are rejected.
Priority
The effective filing date of the claimed invention is 27 February 2018.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 16 December 2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement has been considered by the examiner.
Specification
The disclosure is objected to because it contains an embedded hyperlink and/or other form of browser-executable code. 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.
The Substitute Specification received 21 December 2023 contains at least one embedded hyperlink at least at paragraphs [00276], [00439], [00472], [00566], & [00601].
Claim Objections
The rejection of claim 36 in the Office action mailed 17 June 2025 is withdrawn in view of the amendment received 16 December 2025.
Claim Rejections - 35 USC § 112
The amendment received 16 December 2025 has been fully considered, however after further consideration, new grounds of rejection are raised in view of the amendment and arguments/remarks.
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 36-53 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.
Independent claim 36 and dependent claims 39, 40, 42, 43, 51, 52, and 53 are indefinite for reciting the limitation “pan-allele neural network model” because the amendment to claim 36 further recites “wherein the plurality of parameters of the pan-allele neural network model comprise parameters shared across a single network model of the set of MHC alleles” in lines 47-48, and further because the Applicant argues (Remarks, page 9) that the cited references, either individually or in combination, do not teach or render obvious the amended claim language, pointing to the specification and the drawings (paras. [0417] & [0397]; and FIG. 5) that describe a shared set of parameters across all MHC alleles using a single network model. However, in the response to arguments in the Office action mailed 17 June 2025 (para. 124), evidence was cited (O’Donnell et al.) that explicitly shows that the software NetMHCpan (i.e., the software utilized by Nielsen et al. in the rejection of record under 35 U.S.C. 103) uses a “pan-allele” approach, whereby a single model takes as input both the peptide and a representation of the MHC allele (O’Donnell et al., page 129, col. 2, para. 1) (this evidence and response to arguments is not addressed by the Applicant in the current response), and therefore it is not clear as to how the Applicant intends for the term “pan-allele neural network model” to be interpreted. It is further noted that the terms “pan-allele model”, “pan-specific model”, as well as “allele-integrated model” appear to overlap in the literature in terms of describing a machine learning framework designed to predict peptide binding to any Major Histocompatibility Complex (MHC) allele, and that integrate peptide-MHC sequence information as input for use in a single neural network architecture.
Claims 37-53 are indefinite for depending from claim 36 and for failing to remedy the indefiniteness of claim 36.
Claim Rejections - 35 USC § 101
The rejection of claims 1-10, 12-14, 17, 26, 35, and 37 under 35 U.S.C. 101 in the Office action mailed 17 June 2025 is withdrawn in view of these claims having been cancelled in the amendment received 16 December 2025.
The amendment received 16 December 2025 has been fully considered, however after further consideration, new grounds of rejection are raised under 35 U.S.C. 101 in view of the amendment and further in view of further consideration of the claims.
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 36-53 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgement, opinion).
Claim Interpretation
Claim 36 is interpreted to recite an embodiment wherein the only positively recited step is administering a composition comprising a personalized set of neoantigens selected (past tense) for the subject, wherein the personalized set of neoantigens is interpreted as a product-by-process limitation, with the product being the neoantigens, and further interpreted to not require the active steps of performing the process of selecting the neoantigens, e.g., obtaining genomic data from the tumor and normal cells of the subject, and performing the data analysis steps recited in instant claims 36-53. Therefore, this embodiment is not rejected under 35 U.S.C. 101.
Claim 36 is further interpreted to recite an alternative embodiment wherein the claim requires, prior to the step of administering a composition comprising a personalized set of neoantigens selected for the subject, performing active steps of obtaining genomic data from the tumor and normal cells of the subject, and performing the data analysis steps recited in instant claims 36-53. Therefore, this embodiment is rejected under 35 U.S.C. 101.
Claim 36 recites the limitation “extracting a prioritized plurality of the neoantigens from the selected subset as the personalized set of neoantigens by applying one or more neoantigen filters.” The term “extracting” is interpreted to mean “selecting” data (e.g., Specification, ¶ [0197]).
Claim 36 recites the limitation “obtaining at least one of exome, transcriptome, or whole genome nucleotide sequencing data…” This limitation is interpreted to mean obtaining one or more genomic sequencing data files, and not requiring an active step of using a genomic sequencer to perform sequencing of nucleic acid molecules.
Claim 36 recites the limitation “…a training data set comprising: for each sample in a plurality of samples, a label obtained by mass spectrometry…” The term ‘label’ is interpreted to mean an identifying element in the form of data that explains what other data is. This limitation is interpreted to mean using data from a data set, and not requiring an active step of using a mass spectrometer.
Claim 36 is interpreted to recite active steps of training the pan-allele neural network model (Specification, ¶¶ [00431] – [00433]).
Claim 50 recites the limitation “expression levels of the one or more MHC alleles in the subject, as measured by RNA-seq or mass spectrometry.” This limitation is interpreted as reciting a product-by-process limitation, with the product being the data of the expression levels of the one or more MHC alleles, and further interpreted as not requiring the process of producing the product (i.e., performing the active steps of using RNA-seq or mass spectrometry).
Subject matter eligibility evaluation in accordance with MPEP 2106.
Eligibility Step 1: Step 1 of the eligibility analysis asks: Is the claim to a process, machine, manufacture or composition of matter?
Claims 36-53 recite a method (i.e., a process). Therefore, these claims are encompassed by the categories of statutory subject matter, and thus, satisfy the subject matter eligibility requirements under Step 1.
[Step 1: YES]
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A: Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claim 36 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
the nucleotide sequencing data is used to obtain data representing peptide sequences of each of a set of neoantigens identified by comparing the nucleotide sequencing data from the tumor cells and the nucleotide sequencing data from the normal cells, wherein the peptide sequence of each neoantigen comprises at least one alteration that makes it distinct from the corresponding wild-type peptide sequence identified from the normal cells of the subject (i.e., mental processes);
encoding the peptide sequences of each of the neoantigens into a corresponding numerical vector, each numerical vector including information regarding a plurality of amino acids that make up the peptide sequence and a set of positions of the amino acids in the peptide sequence (i.e., mental processes and mathematical concepts);
the nucleotide sequencing data is used to obtain data representing a peptide sequence of each of the one or more MHC alleles of the subject (i.e., mental processes);
encoding the peptide sequences of each of the one or more MHC alleles of the subject into a corresponding numerical vector, each numerical vector including information regarding a plurality of amino acids that make up the peptide sequence and a set of positions of the amino acids in the peptide sequence (i.e., mental processes and mathematical concepts);
generate a set of presentation likelihoods for the set of neoantigens, each presentation likelihood in the set representing the likelihood that a corresponding neoantigen is presented by the one or more MHC alleles on the surface of the tumor cells of the subject (i.e., mental processes and mathematical concepts);
a plurality of parameters identified at least based on a training data set (i.e., mental processes) comprising:
for each sample in a plurality of samples, a label obtained by mass spectrometry measuring presence of peptides bound to at least one MHC allele in a set of MHC alleles identified as present in the sample (i.e., mental processes);
for each of the samples, training peptide sequences encoded as numerical vectors including information regarding a plurality of amino acids that make up the peptides and a set of positions of the amino acids in the peptides (i.e., mental processes and mathematical concepts); and
for each of the samples, training peptide sequences encoded as numerical vectors including information regarding a plurality of amino acids that make up the at least one MHC allele bound to the peptides of the sample and a set of positions of the amino acids in the at least one MHC allele (i.e., mental processes and mathematical concepts);
wherein at least one of the one or more MHC alleles of the subject is not included in the set of MHC alleles used for identifying the plurality of parameters (i.e., mental processes),
wherein the plurality of parameters of the pan-allele neural network model comprise parameters shared across a single network model of the set of MHC alleles (i.e., mental processes);
converting the set of neoantigens into a set of selected neoantigens corresponding to highest presentation likelihoods (i.e., mental processes and mathematical concepts); and
extracting a prioritized plurality of the neoantigens from the selected subset as the personalized set of neoantigens by applying one or more neoantigen filters (i.e., mental processes and mathematical concepts).
Dependent claims 37-47, and 49-51 further recite the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas, as noted below.
Dependent claim 37 further recites:
applying the one or more neoantigen filters comprises identifying one or more truncal peptides presented by a majority of tumor subclones, determining number and identity of tumor subclones likely to present a neoantigen, determining a risk of autoimmunity, determining a probability of sequencing artifact, determining a probability of immunogenicity, determining a level of gene expression, determining a coverage of HLA genes, and/or determining a coverage of HLA classes (i.e., mental processes and mathematical concepts).
Dependent claim 38 further recites:
applying the one or more neoantigen filters comprises identifying one or more truncal peptides presented by a majority of tumor subclones, determining number and identity of tumor subclones likely to present a neoantigen, determining a risk of autoimmunity, determining a probability of sequencing artifact, determining a probability of immunogenicity, determining a level of gene expression, determining a coverage of HLA genes, and/or determining a coverage of HLA classes (i.e., mental processes and mathematical concepts).
Dependent claim 39 further recites:
generate a dependency score for each of the one or more MHC alleles indicating whether the MHC allele will present the neoantigen based on the particular amino acids at the particular positions of the peptide sequences (i.e., mental processes and mathematical concepts).
Dependent claim 40 further recites:
transforming the dependency scores to generate a corresponding per-allele likelihood for each MHC allele indicating a likelihood that the corresponding MHC allele will present the corresponding neoantigen (i.e., mental processes and mathematical concepts); and
combining the per-allele likelihoods to generate the presentation likelihood of the neoantigen (i.e., mental processes and mathematical concepts).
Dependent claim 41 further recites:
transforming the dependency scores models the presentation of the neoantigen as mutually exclusive across the one or more MHC alleles (i.e., mental processes and mathematical concepts).
Dependent claim 42 further recites:
transforming a combination of the dependency scores to generate the presentation likelihood, wherein transforming the combination of the dependency scores models the presentation of the neoantigen as interfering between the one or more MHC alleles (i.e., mental processes and mathematical concepts).
Dependent claim 43 further recites:
the set of presentation likelihoods are further identified by at least one or more allele noninteracting features (i.e., mental processes), and further comprising:
generate a dependency score for the allele noninteracting features indicating whether the peptide sequence of the corresponding neoantigen will be presented based on the allele noninteracting features (i.e., mental processes and mathematical concepts).
Dependent claim 44 further recites:
combining the dependency score for each MHC allele of the one or more MHC alleles with the dependency score for the allele noninteracting features (i.e., mental processes and mathematical concepts);
transforming the combined dependency scores for each MHC allele to generate a per-allele likelihood for each MHC allele indicating a likelihood that the corresponding MHC allele will present the corresponding neoantigen (i.e., mental processes and mathematical concepts); and
combining the per-allele likelihoods to generate the presentation likelihood (i.e., mental processes and mathematical concepts).
Dependent claim 45 further recites:
combining the dependency scores for each of the MHC alleles and the dependency score for the allele noninteracting features (i.e., mental processes and mathematical concepts); and
transforming the combined dependency scores to generate the presentation likelihood (i.e., mental processes and mathematical concepts).
Dependent claim 46 further recites:
the one or more MHC alleles include two or more different MHC alleles (i.e., mental processes).
Dependent claim 47 further recites:
the peptide sequences comprise peptide sequences having lengths other than 9 amino acids (i.e., mental processes).
Dependent claim 49 further recites:
the training data set further comprises at least one of:
(a) data associated with peptide-MHC binding affinity measurements for at least one of the peptides (i.e., mental processes); and
(b) data associated with peptide-MHC binding stability measurements for at least one of the peptides (i.e., mental processes).
Dependent claim 50 further recites:
the set of presentation likelihoods are further identified by at least one of:
expression levels of the one or more MHC alleles in the subject, as measured by RNA-seq or mass spectrometry (i.e., mental processes);
predicted affinity between a neoantigen in the set of neoantigens and the one or more MHC alleles (i.e., mental processes);
predicted stability of the neoantigen encoded peptide-MHC complex;
C-terminal sequences flanking the neoantigen encoded peptide sequence within its source protein sequence (i.e., mental processes); and
N-terminal sequences flanking the neoantigen encoded peptide sequence within its source protein sequence (i.e., mental processes).
Dependent claim 51 further recites:
selecting the set of selected neoantigens comprises at least one of:
selecting neoantigens that have an increased likelihood of being presented on the tumor cell surface relative to unselected neoantigens based on the pan-allele neural network model (i.e., mental processes);
selecting neoantigens that have an increased likelihood of being capable of inducing a tumor-specific immune response in the subject relative to unselected neoantigens based on the pan-allele neural network model (i.e., mental processes);
selecting neoantigens that have an increased likelihood of being capable of being presented to naive T-cells by professional antigen presenting cells (APCs) relative to unselected neoantigens based on the pan-allele neural network model, optionally wherein the APC is a dendritic cell (DC) (i.e., mental processes);
selecting neoantigens that have a decreased likelihood of being subject to inhibition via central or peripheral tolerance relative to unselected neoantigens based on the pan-allele neural network model (i.e., mental processes); and
selecting neoantigens that have a decreased likelihood of being capable of inducing an autoimmune response to normal tissue in the subject relative to unselected neoantigens based on the pan-allele neural network model (i.e., mental processes).
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pen and paper (e.g., converting the set of neoantigens into a set of selected neoantigens corresponding to highest presentation likelihoods), and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas (e.g., generate a set of presentation likelihoods for the set of neoantigens) are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Therefore, claims 36-53 recite an abstract idea.
[Step 2A Prong One: YES]
Eligibility Step 2A Prong Two: In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP 2106.04(d) subsection I; MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
Dependent claims 37, 38, 41, 44-47, and 49-51 do not recite any elements in addition to the judicial exception, and thus are part of the judicial exception.
The additional elements in independent claim 36 include:
obtaining at least one of exome, transcriptome, or whole genome nucleotide sequencing data from the tumor cells and normal cells of the subject;
obtaining at least one of exome, transcriptome or whole genome nucleotide sequencing data from the tumor cells of the subject;
a computer processor;
inputting the numerical vectors encoding the peptide sequences of each of the neoantigens and the numerical vectors encoding the peptide sequences of each of the one or more MHC alleles;
a pan-allele neural network model; and
administering a composition comprising a personalized set of neoantigens.
The additional elements in dependent claims 39, 40, 42, 43, 48, 52, and 53 include:
inputting the numerical vectors encoding the peptide sequences of each of the neoantigens and the numerical vectors encoding the peptide sequences of each of the one or more MHC alleles into the pan-allele neural network model (claims 39, 40, and 42);
applying the pan-allele neural network model to the peptide sequence of the neoantigen and to the peptide sequence of the one or more MHC alleles (claim 39);
applying the pan-allele neural network model to the allele noninteracting features (claim 43);
a plurality of parameters identified at least based on a training data set generated from a plurality of samples wherein the plurality of samples comprise at least one of:
(a) one or more cell lines engineered to express a single MHC allele (claim 48);
(b) one or more cell lines engineered to express a plurality of MHC alleles (claim 48);
(c) one or more human cell lines obtained or derived from a plurality of patients (claim 48);
(d) fresh or frozen tumor samples obtained from a plurality of patients (claim 48); and
(e) fresh or frozen tissue samples obtained from a plurality of patients (claim 48);
the pan-allele neural network model comprises a series of nodes arranged in one or more layers, the pan-allele neural network model configured to receive numerical vectors encoding the peptide sequences of multiple different MHC alleles (claim 52); and
the plurality of parameters are identified by performing, by the pan-allele neural network model, a deconvolution step (claim 53).
The additional element of a computer processor (claim 36) invokes a computer and/or computer-related components merely as tools for use in the claimed process, e.g., to perform the functions of receiving and inputting data and to perform an abstract idea, such that it amounts to no more than mere instructions to apply the exceptions using a generic computer (MPEP 2106.05(f)), and therefore is not an improvement to computer functionality itself, or an improvement to any other technology or technical field (see MPEP 2106.04(d)(1)).
The additional elements of obtaining data (claim 36) and inputting data from a plurality of samples (claims 36, 39, 40, and 42) are merely pre-solution activities (e.g., gathering data) for use in the claimed process – nominal additions to the claims that do not meaningfully limit the claims, and therefore do not add more than insignificant extra-solution activity to the judicial exceptions (MPEP 2106.05(g)).
The additional element of a pan-allele neural network model (claims 39, 40, 42, 43, 52, and 53) provides nothing more than mere instructions to implement an abstract idea on a generic computer (MPEP 2106.05(f)), and merely confines the use of the abstract idea to the particular technological environment of neural networks (MPEP 2106.05(h)).
Thus, the additionally recited elements merely invoke a computer as a tool, and/or amount to insignificant extra-solution activities, and/or merely confine the use of the abstract idea to the particular technological environment of neural networks, and as such, when all limitations in claims 36-53 have been considered as a whole, the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 36-53 are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
Dependent claims 37, 38, 41, 44-47, and 49-51 do not recite any elements in addition to the judicial exception(s). The additional elements recited in independent claim 36 and dependent claims 39, 40, 42, 43, 48, 52, and 53 are identified above, and carried over from Step 2A: Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at Step 2A: Prong Two was re-evaluated at Step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements were evaluated to determine whether any additional elements or combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional elements of a computer processor (claim 36); obtaining data (claim 36); inputting data (claims 36, 39, 40, and 42); training data for the model (claim 48); and using a neural network (claims 39, 40, 42, 43, 52, and 53); are conventional (see MPEP at 2106.05(b) and 2106.05(d)(II) regarding conventionality of computer components and computer processes).
Therefore, when taken alone, all additional elements in claims 36-53 do not amount to significantly more than the above-identified judicial exception(s). Even when evaluated as a combination, the additional elements fail to transform the exception(s) into a patent-eligible application of that exception. Thus, claims 36-53 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
Response to Arguments
The Applicant’s arguments/remarks received 16 December 2025 have been fully considered, but are not persuasive.
The Applicant states on page 8 of the Remarks that the Applicant notes in the most recent Office action mailed 17 June 2025, claim 36 was not rejected under 35 U.S.C. 101, and as stated on page 5 of the Office action, “the rejection of claim 36 under 35 U.S.C. 101 in the Office action mailed 09 October 2024 is withdrawn in view of further consideration that the only positively recited step is administering neoantigens selected (past tense) by…” and that without acquiescing to the rejection and to advance prosecution of this application, the Applicant hereby cancels claims 1-35 and presents claims 36-38 as well as new dependent claims 39-53 with this response. The Applicant further states on page 9 that as claim 36 was not rejected under 101, following entry of this response and amendments, claim 36 remains patent eligible, and that dependent claims 37-53 depend from the independent claim 36 and should be found patent eligible for at least the same reasons as above.
These arguments are not persuasive, because new grounds of rejection are raised under 35 U.S.C. 101 for the reasons given and discussed in the above rejection.
Claim Rejections - 35 USC § 103
The rejection of claims 1, 2, 9, 13, 14, 17, 26, 36, 37, and 38 under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. in the Office action mailed 17June 2025 is withdrawn in view of claims 1-10, 12-14, 17, 26, and 35 having been cancelled in the amendment received 16 December 2025.
The rejection of claims 3-8 under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 1, 2, 9, 13, 14, 17, 26, 36, 37, and 38 above, and further in view of Verma et al. in view of Cho et al. in view of Li et al. in view of Saloot et al. in the Office action mailed 17June 2025 is withdrawn in view of claims 1-10, 12-14, 17, 26, and 35 having been cancelled in the amendment received 16 December 2025.
The rejection of claim 10 under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 1, 2, 9, 13, 14, 17, 36, 37, and 38 above, and further in view of Trolle et al. in the Office action mailed 17June 2025 is withdrawn in view of claims 1-10, 12-14, 17, 26, and 35 having been cancelled in the amendment received 16 December 2025.
The rejection of claim 12 under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 1, 2, 9, 13, 14, 17, 36, 37, and 38 above, and further in view of Wei et al. in the Office action mailed 17June 2025 is withdrawn in view of claims 1-10, 12-14, 17, 26, and 35 having been cancelled in the amendment received 16 December 2025.
The rejection of claim 35 under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 1, 2, 9, 13, 14, 17, 36, 37, and 38 above, and further in view of Bassani-Sternberg et al. in the Office action mailed 17June 2025 is withdrawn in view of claims 1-10, 12-14, 17, 26, and 35 having been cancelled in the amendment received 16 December 2025.
The amendment received 16 December 2025 has been fully considered, however after further consideration, new grounds of rejection are raised under 35 U.S.C. 103 in view of the amendment.
Claim Interpretations
Independent claim 36 is interpreted to recite an embodiment (hereinafter “Embodiment A”) wherein the only positively recited step is administering a composition comprising a personalized set of neoantigens selected (past tense) for the subject, wherein the personalized set of neoantigens is interpreted as a product-by-process limitation, with the product being the neoantigens, and further interpreted to not require the active steps of performing the process of selecting the neoantigens, e.g., obtaining genomic data from the tumor and normal cells of the subject, and/or performing the data analysis steps recited in instant claims 36-53. Therefore, this embodiment only requires the claim 36 limitation reciting “administering a composition comprising a personalized set of neoantigens selected for the subject.”
Independent claim 36 is further interpreted to recite an alternative embodiment (hereinafter “Embodiment B”) wherein the claim requires, prior to the step of administering a composition comprising a personalized set of neoantigens selected for the subject, performing active steps of obtaining genomic data from the tumor and normal cells of the subject, and/or performing the data analysis steps recited in instant claims 36-53. Therefore, this embodiment requires performing the method steps of claims 36-53 as recited.
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 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.
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.
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.
Rejection of “Embodiment A”
Claims 36-53 are rejected under 35 U.S.C. 103 as being unpatentable over Ott et al. (“An immunogenic personal neoantigen vaccine for patients with melanoma.” Nature, 2017, Vol. 547, pp. 217-221; Supplemental Material: Methods, pp. 1-3; Supplemental Material: Extended Data, pp. 1-13, as cited in the Information Disclosure Statement (IDS) mailed 20 January 2021, newly cited).
Regarding independent claim 36 and those claims dependent therefrom, Ott et al. demonstrates the feasibility, safety, and immunogenicity of a vaccine that targets up to 20 predicted personal tumor neoantigens (Abstract); and shows the generation of a personal, multi-peptide neoantigen vaccine for patients with high-risk melanoma, and further shows a vaccine administration schedule (page 218, Figure 1).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method shown by Ott et al. to have incorporated a personalized set of neoantigens in a personal cancer vaccine, and then administering the personal vaccine to the subject. One of ordinary skill in the art would have been motivated to modify the methods of Ott et al. with regard to a personalized set of neoantigens, because Ott et al. shows that effective anti-tumor immunity in humans has been associated with the presence of T cells directed at cancer neoantigens, a class of HLA-bound peptides that arise from tumor-specific mutations (Abstract). This modification would have had a reasonable expectation of success because Ott et al. shows a process for the generation of a personal, multi-peptide neoantigen vaccine (Figure 1) that induces strong multi-functional T-cell responses in patients with high-risk melanoma (Figure 2).
Rejection of “Embodiment B”
Claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. (Royal Society Open Science, 2017, Vol. 4: 170050, pp. 1-12, as cited in the Office action mailed 22 June 2023) in view of Nielsen et al. (PLoS ONE, 2007, Vol. 2(8): e796, pp. 1-10, as cited in the Office action mailed 09 October 2024) in view of Kalaora et al. (Oncotarget, 2016, Vol. 7, No. 5, pp. 5110-5117; and Supplemental pp. 1-3, as cited in the Office action mailed 22 June 2023) in view of Jurtz et al. (The Journal of Immunology, 2017, Vol. 199(9): pp. 3360-3368, as cited in the Information Disclosure Statement (IDS) received 20 January 2021) in view of Estevez et al. (IEEE Transactions on Neural Networks, 2009, Vol. 20, No. 2, pp. 189-201, as cited in the Office action mailed 22 June 2023) in view of Hu et al. (bioRxiv, 2017, https://doi.org/10.1101/239236, pp. 1-20, as cited in the Office action mailed 22 June 2023) in view of Hundal et al. (Genome Medicine, 2016, Vol. 8, No. 11, pp. 1-11, as cited in the Office action mailed 22 June 2023).
Regarding claim 36, Zhou et al. shows an integrated software tool for cancer somatic mutation and tumor-specific neoantigen detection (Title, and Abstract); obtaining whole-genome / exome sequencing data of tumor-normal pairs (page 3, Section 2.2, para. 1); variant calling software (page 3, Section 2.1.5.) and mutation annotation software (page 3, Section 2.1.6) for comparing sequences to detect cancer somatic mutations in protein-coding regions (page 5, Section 3.2, para(s). 1-2); human leucocyte antigen typing software for obtaining HLA type sequences (page 3, Section 2.1.7); protein topology indicating software to detect peptide sequences (page 3, Section 2.1.8); obtaining amino acid sequences of membrane proteins (page 3, Section 2.3); positional information of amino acids within peptide sequences (page 4, Figure 1; and page 8, Table 3).
Zhou et al. does not show mass spectrometry data (claim 36); organizing data in vectors (claim 36); training a model (claim 36); a pan-allele neural network model (claim 36); dependency scores (claim 36); subset feature selection for the model (claim 36); at least one of the one or more MHC alleles of the subject is not included in the set of MHC alleles used for identifying the plurality of parameters (claim 36); the plurality of parameters of the pan-allele neural network model comprise parameters shared across a single network model of the set of MHC alleles (claim 36); or predicting presentation likelihoods (claim 36).
Nielsen et al. shows a high-throughput computational method that encompasses all HLA molecules that is used for epitope searches that are not only genome- and pathogen-wide, but also HLA-wide (Abstract). Nielsen et al. further shows using the NetMHCpan (i.e., a “pan-allele” approach, whereby a single model takes as input both the peptide and a representation of the MHC allele) method to identify peptide binders for MHC molecules that are specificity-wise unknown for two HLA alleles, and further shows performing a simulated “blind” leave-one-out validation by training networks using all data for the relevant loci, HLA-A or -B, except the data for the molecule in question. This was done for all HLA molecules represented in the data set, and thus, no peptide-HLA binding data from the validation set was included in the training of the pan-specific predictor (page 2, column 2, para. 2). Nielsen et al. further shows a pan-specific neural network method that demonstrates the ability to encompass all HLA-A and HLA-B molecules (page 3, column 2, para. 3), and further shows that the prediction approach was capable of extracting HLA sequence information and correctly relating this information to peptide binding even in the absence of any data for the specific query HLA molecule (page 2, column 2, para. 1).
Kalaora et al. shows a method that combines whole-exome sequencing analysis with HLA peptidome mass spectrometry to identify neoantigens (Title; and Abstract).
Jurtz et al. shows a method that demonstrates an increase in predictive performance identifying cancer neoantigens using NetMHCpan-4.0 (Abstract) that integrates MS (mass spectrometry) peptidome data into a prediction method of MHC peptide presentation (page 3366, column 2, para. 4); machine learning using a neural network (page 3361, column 2, para(s). 4-5); input data encoded using BLOSUM encoding software (page 3361, column 2, para. 7) but not vectors explicitly; training a neural network ensemble using multiple peptide and MHC molecule features, i.e., parameters (page 3361, column 2, para(s). 5-7); data from 169 MHC molecules (page 3362, column 2, para. 1); outputting likelihood predictions from a trained model (page 3363, column 2, para. 2: bottom; and Supplemental Figure 1); and using a deep learning method trained on integrated eluted ligand and peptide binding affinity data for improved peptide-MHC class I interaction predictions for predicting cancer neoantigens (Title; and Abstract).
Estevez et al. shows a filter method of feature selection based on mutual information (MI) called normalized mutual information feature selection (Title; and Abstract); an algorithm for finding subsets of the best features (page 193, column 1, para. 2); and an MLP neural network trained on selected subsets of features (page 189, column 1, para. 1).
Hu et al. shows that amino acid sequences need to be encoded as input vectors or matrices for training deep neural networks (page 13, para. 2).
Hundal et al. shows a genome-guided in silico approach for identification of personalized variant antigens by cancer screening that integrates tumor mutation and expression data (Title; and Abstract) to shortlist candidate neoantigen peptides that could potentially be used in a personalized vaccine after immunological screening (page 2, column 1, para. 4), and used to identify the neoantigen peptides for use in dendritic cell-based personalized vaccines in melanoma patients (Ibid.).
Regarding claim 39, Estevez et al. further shows several different criteria used for evaluating the goodness of a feature such as a dependency measure (page 189, column 2, para. 1); and distinguishing features of the MI as a dependency measure (page 190, column 2, para. 6).
Regarding claim 46, Zhou et al. further shows choosing 16 HLA (human leucocyte antigen) alleles (page 3, Section 2.2).
Regarding claim 49, Jurtz et al. further shows that most methods are trained on binding affinity (BA) data and, as a consequence, only model the single event of peptide-MHC binding, however, other factors, including Ag (antigen) processing and the stability of the peptide-MHC complex could influence the likelihood of a given peptide to be presented as an MHC ligand (page 3360, column 2, para. 3).
Regarding claim 50, Jurtz et al. further shows a method using two data types for predicting peptide-MHC interactions: 1) binding affinity and 2) mass spectrometry (Abstract); prediction scores assigned to HLA molecules based on expression data (Figures 9 & 10); and data sets with typed HLA expression data (page 3365, column 2, para. 1).
Regarding claim 51, Jurtz et al. further shows using NetMHCpan-4.0 to generate likelihood scores (page 3366, column 2, para. 2) after having been trained using leave-one-out (LOO) methods that removed a given MHC molecule from the data set prior to retraining the model (page, 3366, col. 1, para. 4).
Regarding claim 52, Jurtz et al. further shows using a neural network training approach with a network architecture wherein weights between the input and hidden layer are shared between the two input types, and wherein weights connecting the hidden and output layer are specific for each input type (page 3361, column 2, para. 5) and wherein networks with 60 and 70 hidden neurons (i.e., nodes) were trained, leading to an ensemble of 40 networks in total (page 3361, column 2, para. 6); and further shows using data on at least 127 class I MHC molecules (page 3361, column 1, paras. 5-6).
Regarding claims 37 and 38, Nielsen et al. further shows that there is an unmet need to increase the coverage of HLA-I specificities as most existing HLA-I molecules have no or poorly characterized supertype relationships (page 1, column 2, para. 1); the identification of HLA supertypes (i.e., a type of classification) (page 3, column 2, 6) and further shows that the present analysis includes all known polymorphic HLA-A and -B molecules and suggests the existence of novel HLA supertypes, such as B51/B55, B35 (both split from B7), and A33, with specificities different from those described by previously defined HLA supertypes (page 4, column 1, para. 1).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating mass spectrometry information as disclosed by Kalaora et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Kalaora et al. because Kalaora et al. shows using whole-exome sequencing analysis with HLA peptidome mass spectrometry to identify neoantigens. This modification would have had a reasonable expectation of success given that both Zhou et al. and Kalaora et al. disclose using whole exome sequencing to identify human immunogenic neoantigens.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating a neural network model for recognizing non-linear patterns that contribute to peptide-HLA-I interactions as disclosed by Nielsen et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Nielsen et al. because Nielsen et al. shows using such a model, and further shows training the model using all of the data for the relevant loci, HLA-A or -B, except for the data for the molecule in question, in order to test the predictive performance of the method. This modification would have had a reasonable expectation of success given that both Zhou et al. and Nielsen et al. disclose methods for predicting tumor-specific neoantigens using the NetMHCpan software.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating methods for training and using a neural network as disclosed by Jurtz et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Jurtz et al. because Jurtz et al. shows using a deep learning method trained on integrated eluted ligand and peptide binding affinity data for improved peptide-MHC class I interaction predictions for predicting cancer neoantigens (Title; and Abstract). This modification would have had a reasonable expectation of success given that both Zhou et al. and Jurtz et al. disclose predictive modeling for identifying cancer neoantigens using the NetMHCpan software.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating a method for subset feature selection as disclosed by Estevez et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Estevez et al. because Estevez et al. shows using a normalized mutual information process for feature selection. This modification would have had a reasonable expectation of success given that both Zhou et al. and Estevez et al. show methods for selecting features of genomic sequences.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating a method for using data vectors such as disclosed by Hu et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Hu et al. because Hu et al. shows that amino acid sequences need to be encoded as input vectors for training deep neural networks. This modification would have had a reasonable expectation of success given that both Zhou et al. and Hu et al. disclose using neural networks and the NetMHCpan software.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. by incorporating an in silico approach for identifying tumor neoantigens as targets for vaccines as disclosed by Hundal et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. with Hundal et al. because Hundal et al. shows using the software tool pVAC-Seq to identify tumor antigens as targets for vaccines. This modification would have had a reasonable expectation of success given that both Zhou et al. and Hundal et al. show an approach for identifying neoantigen peptides from tumor tissue.
Claims 40-45 are rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and further in view of Verma et al. (U.S. Patent No.: US 6,931,351, as cited in the Office action mailed 22 June 2023) in view of Cho et al. (Proceedings of the IEEE, 2002, Vol. 90, No. 11, pp. 1744-1753, as cited in the Office action mailed 22 June 2023) in view of Li et al. (International Journal of Machine Learning and Computing, 2012, Vol. 2, No. 6, pp. 786-790, as cited in the Office action mailed 22 June 2023) in view of Saloot et al. (Proceedings of the Association for Computational Linguistics, 2015, pp.19-27, as cited in the Office action mailed 22 June 2023).
Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, does not show inputting the numerical vectors encoding the peptide sequences of each of the neoantigens and the numerical vectors encoding the peptide sequences of each of the one or more MHC alleles into the pan-allele neural network model further comprises: transforming the dependency scores to generate a corresponding per-allele likelihood for each MHC allele indicating a likelihood that the corresponding MHC allele will present the corresponding neoantigen (claim 40); and combining the per-allele likelihoods to generate the presentation likelihood of the neoantigen (claim 40); transforming the dependency scores models the presentation of the neoantigen as mutually exclusive across the one or more MHC alleles (claim 41); inputting the numerical vectors encoding the peptide sequences of each of the neoantigens and the numerical vectors encoding the peptide sequences of each of the one or more MHC alleles into the pan-allele neural network model further comprises: transforming a combination of the dependency scores to generate the presentation likelihood, wherein transforming the combination of the dependency scores models the presentation of the neoantigen as interfering between the one or more MHC alleles (claim 42); the set of presentation likelihoods are further identified by at least one or more allele noninteracting features, and further comprising: applying the pan-allele neural network model to the allele noninteracting features to generate a dependency score for the allele noninteracting features indicating whether the peptide sequence of the corresponding neoantigen will be presented based on the allele noninteracting features (claim 43); combining the dependency score for each MHC allele of the one or more MHC alleles with the dependency score for the allele noninteracting features; transforming the combined dependency scores for each MHC allele to generate a per-allele likelihood for each MHC allele indicating a likelihood that the corresponding MHC allele will present the corresponding neoantigen; and combining the per-allele likelihoods to generate the presentation likelihood (claim 44); combining the dependency scores for each of the MHC alleles and the dependency score for the allele noninteracting features, and transforming the combined dependency scores to generate the presentation likelihood (claim 45).
Regarding claims 40-45, Estevez et al. further shows using a normalized (transformed) dependency measure (Title; and Abstract).
Estevez et al. does not show combining the per-allele likelihoods to generate the presentation likelihood of the neoantigen (claim 40); wherein transforming the dependency scores models the presentation of the neoantigen as mutually exclusive across the one or more MHC alleles (claim 41); transforming a combination of the dependency scores to generate the presentation likelihood, wherein transforming the combination of the dependency scores models the presentation of the neoantigen as interfering between the one or more MHC alleles (claim 42); applying the pan-allele neural network model to the allele noninteracting features to generate a dependency score for the allele noninteracting features indicating whether the peptide sequence of the corresponding neoantigen will be presented based on the allele noninteracting features (claim 43); combining the dependency score for each MHC allele of the one or more MHC alleles with the dependency score for the allele noninteracting features (claim 44); transforming the combined dependency scores for each MHC allele to generate a per-allele likelihood for each MHC allele indicating a likelihood that the corresponding MHC allele will present the corresponding neoantigen (claim 44); and combining the per-allele likelihoods to generate the presentation likelihood (claim 44); combining the dependency scores for each of the MHC alleles and the dependency score for the allele noninteracting features (claim 45); and transforming the combined dependency scores to generate the presentation likelihood (claim 45).
Regarding claims 40-45, Verma et al. shows using combined likelihood values to determine the confidence of a classifier decision making process for classifying samples to one of a number of predetermined classes (Title; Abstract; column 4, lines 30-41).
Verma et al. in view of Cho et al. shows classifying gene expression data of cancer using classifier ensemble trained with mutually exclusive features (Title; and Abstract).
Verma et al. in view of Cho et al. in view of Li et al. shows an ensemble approach to the learning of a neural network with reduced interference (Title; and Abstract); grouping of non-interfering datasets (page 788, column 2, para. 5); and an algorithm for determining the interference between attributes (page 787, column 2, para(s). 1-2).
Verma et al. in view of Cho et al. in view of Li et al. in view of Saloot et al. shows a method utilizing the aggregation of all the dependency scores (page 23, column 1, para. 2).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating a method of combining likelihood values as disclosed by Verma et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Verma et al., because Verma et al. shows combining likelihood values as a step in a process for determining the most likely class assignment by the machine learning classifier (column 4, lines 5-8). This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Verma et al. show a method for calculating a likelihood with regard to classifying sample data.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating methods utilizing mutually exclusive features as disclosed by Cho et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Verma et al. in view of Cho et al. because Cho et al. shows classifying data using an ensemble classifier with mutually exclusive features. This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Verma et al. in view of Cho et al. show a method for classifying data using mutually exclusive features to encourage the classifiers to learn different aspects of the training data.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating an algorithm for determining the interference between attributes as disclosed by Li et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Verma et al. in view of Cho et al. in view of Li et al. because Li et al. shows a method for training a neural network ensemble with a reduced interference effect among input attributes. This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and the method of Verma et al. in view of Cho et al. in view of Li et al. show a method to improve the accuracy of the model training process.
It would have been further obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating aggregated dependency scores as disclosed by Saloot et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Verma et al. in view of Cho et al. in view of Li et al. in view of Saloot et al., because Saloot et al. shows using a dependency-based frequency feature for normalizing data used in a model. This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Verma et al. in view of Cho et al. in view of Li et al. in view of Saloot et al. show methods for managing data for use in a machine learning model.
Claim 47 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and further in view of Trolle et al. (Journal of Immunology, 2016, Vol. 196(4), pp. 1480-1487, as cited in the Information Disclosure Statement (IDS) received 20 January 2021).
Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, does not show the peptide sequences comprise peptide sequences having lengths other than 9 amino acids.
Regarding claim 47, Trolle et al. shows that HLA class I binding predictions are widely used to identify candidate peptide targets, and that many approaches focus exclusively on a limited range of peptide lengths, typically 9 and sometimes 9-10 amino acids, despite multiple examples of dominant epitopes of other lengths (Abstract). Trolle et al. further shows that peptides of other lengths can bind HLA-I molecules and elicit immune responses as evidenced by multiple dominant epitopes of length 8, 10, and 11, and occasionally much longer peptides up to length 15 (page 2, para. 2).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating peptide sequences of lengths other than 9 amino acids as disclosed by Trolle et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Trolle et al., because Trolle et al. shows that sequences of 8-11 amino acids are capable of eliciting immune responses (page 2, para. 2). This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Trolle et al. show methods for determining binding predictions for HLA molecules.
Claim 48 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and further in view of Wei et al. (Nature Genetics, 2011, Vol. 43, No. 5, pp. 442-446; and Online Methods, pp. 1-2, as cited in the Office action mailed 22 June 2023).
Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, does not show the plurality of samples comprise at least one of: (a) one or more cell lines engineered to express a single MHC allele; (b) one or more cell lines engineered to express a plurality of MHC alleles; (c) one or more human cell lines obtained or derived from a plurality of patients; (d) fresh or frozen tumor samples obtained from a plurality of patients; and (e) fresh or frozen tissue samples obtained from a plurality of patients (claim 48).
Regarding claim 48, Wei et al. shows tumor tissues were from fresh frozen melanoma tumors (Online Methods; Supplemental page 1, column 1, para. 1).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating fresh frozen tumor samples as disclosed by Wei et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Wei et al., because Wei et al. shows isolating DNA and exome capture from fresh frozen tumor samples (Online Methods; Supplemental page 1, column 1, para(s). 1-2). This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Wei et al. show tissue sample collection and preservation methods used for obtaining cell lines used for DNA isolation and exome capture.
Claim 53 is rejected under 35 U.S.C. 103 as being unpatentable over Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and further in view of Bassani-Sternberg et al. (The Journal of Immunology, 2016, Vol. 197(6): pp. 2492-2499, as cited in the Information Disclosure Statement received 20 January 2021).
Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, does not show wherein the plurality of parameters are identified by performing, by the pan-allele neural network model, a deconvolution step (claim 53).
Regarding claim 53, Bassani-Sternberg et al. shows unsupervised HLA peptidome deconvolution improves ligand prediction accuracy and predicts cooperative effects in peptide-HLA interactions (Title; Abstract). Bassani-Sternberg et al. further shows that to exploit the wealth of data provided by high-throughput technology toward a better understanding of HLA-binding mechanisms, one should ideally deconvolute the contribution of each HLA allele (page 2494, column 1, Results, para. 1) and further shows a computational method for HLA peptidome deconvolution (page 2493, column 1, Materials and Methods, para. 3).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing data of the claimed invention to have modified the methods shown by Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, by incorporating computations for a deconvolution procedure for identifying parameters as disclosed by Bassani-Sternberg et al. and discussed above. One of ordinary skill in the art would have been motivated to combine the method of Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, with the method of Bassani-Sternberg et al., because Bassani-Sternberg et al. shows using an algorithm to deconvolute HLA class I peptidome data that consists of a superposition of different motifs that represent up to six class I alleles expressed in any given sample. This modification would have had a reasonable expectation of success given that both Zhou et al. in view of Nielsen et al. in view of Kalaora et al. in view of Jurtz et al. in view of Estevez et al. in view of Hu et al. in view of Hundal et al. as applied to claims 36, 37, 38, 39, 46, 49, 50, 51, and 52 above, and Bassani-Sternberg et al. show methods for identifying parameters used in machine learning models.
Response to Arguments
The Applicant’s arguments/remarks received 12 December 2025 have been fully considered, but are not persuasive.
The Applicant states on page 9 (bottom paragraph) of the Remarks that the cited references, either individually or in combination, do not teach or render obvious the amended language of “wherein the plurality of parameters of the pan-allele model comprise parameters shared across a single network model of the set of MHC alleles….” The Applicant points to the Specification at paragraph [0417] describing a single network model, as well as Figure 5 in the Drawings which illustrates an exemplary network model, and further points to the Specification (para. [0397]) which describes embodiments of network models (Remarks, page 10). The Applicant further states that the Nielsen reference does not teach the specific architecture of the claimed pan-allele model (Remarks, page 10), and further states (page 11, para. 2) that nowhere does Nielsen teach the claimed architecture where “the plurality of parameters of the pan-allele neural network model comprise parameters shared across a single network model of the set of MHC alleles…” as recited in claim 36. The Applicant further states (page 11) that the Jurtz reference teaches a fundamentally different neural network model than claimed, and (page 12) the additional cited references, either individually or in combination, do not teach or render obvious this language of claim 36, nor does the Office action allege that they do, and thus, claim 36 and dependent claims are patentably distinct in view of the cited references.
These arguments are not persuasive, because first, Nielsen et al. shows an alternative method, NetMHCpan, exploiting both peptide and primary HLA sequence as input information for ANN-driven predictions pooling all available data and at the same time incorporate all HLA specificities, and that the method is successfully demonstrated to predict the affinity of interaction of any peptide with any human HLA-A or HLA-B molecule, i.e., the method is pan-specific (page 2, col. 1, para. 2: bottom). Furthermore, Jurtz et al. shows that a framework is “pan-specific,” because it can leverage information across MHC molecules, data types, and peptide lengths into a single model (page 3361, col. 1, para. 3). Second, one of ordinary skill in the art would have known that Nielsen et al. further teaches a pan-allele model, as evidenced by O’Donnell et al. (Cell Systems, 2018, Vol. 7, pp. 129-132, as cited in the Information Disclosure Statement (IDS) received 20 January 2021). O’Donnell et al. shows a method for predicting the binding affinity of major histocompatibility complex I (MHC I) proteins and their peptide ligands (Abstract), and discusses other predictive tools in the art and shows that NetMHCpan (i.e., the software utilized by Nielsen et al. in the rejection above) uses a “pan-allele” approach, whereby a single model takes as input both the peptide and a representation of the MHC allele (page 129, column 2, para. 1).
Double Patenting
The rejection of claims 1, 2, 3, 4, 6, 7, 8, 9, 10, 12, 13, and 26 on the ground of nonstatutory double patenting as being unpatentable over claims 1, 2, 3, 4, 6, 7, 8, 10, 11, 13, 14, and 26, respectively, of U.S. Patent No. 11,264,117 in the Office action mailed 17 June 2025 is withdrawn in view of the amendment received 16 December 2025.
The Applicant’s amendment received 16 December 2025 has been fully considered, however, after further consideration, new grounds of rejection are raised on the ground of nonstatutory double patenting in view of the amendment.
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 USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The 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/process/file/efs/guidance/eTD-info-I.jsp.
Claims 36, 39, 40, 41, 43, 44, 45, 46, 47, 48, 49, and 52 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1, 2, 3, 4, 6, 7, 8, 10, 11, 13, 14, and 26, respectively, of U.S. Patent No. 11,264,117 in view of Ott et al. (as cited above). Although the claims at issue are not identical, they are not patentably distinct from each.
The instant application is directed to identification of neoantigens that bind MHC alleles and U.S. Patent No. 11,264,117 is directed to neoantigen identification using species of MHC presentation hotspots. The instant application and U.S. Patent No. 11,264,117 are both directed to neoantigen identification.
Independent claim 1 of the ‘117 patent shows using the method of instant independent claim 36 for identifying one or more neoantigens from one or more tumor cells of a subject that are likely to be presented on a surface of the tumor cells, however claim 1 of the ‘117 patent does not show using the identified one or more neoantigens as part of a personalized cancer vaccine that is administered to the subject.
Ott et al. demonstrates the feasibility, safety, and immunogenicity of a vaccine that targets up to 20 predicted personal tumor neoantigens (Abstract); and shows the generation of a personal, multi-peptide neoantigen vaccine for patients with high-risk melanoma, and further shows a vaccine administration schedule (page 218, Figure 1).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the ‘117 patent to use the one or more neoantigens from one or more tumor cells of a subject that are likely to be presented on a surface of the tumor cells (i.e., a personalized set of neoantigens) in a cancer vaccine that is administered to the subject. One of ordinary skill in the art would have been motivated to modify the ‘117 patent by incorporating a treatment step using the personalized set of neoantigens, because Ott et al. shows that effective anti-tumor immunity in humans has been associated with the presence of T cells directed at cancer neoantigens, a class of HLA-bound peptides that arise from tumor-specific mutations (Abstract). This modification would have had a reasonable expectation of success because Ott et al. shows a process for the generation of a personal, multi-peptide neoantigen vaccine (Figure 1) that induces strong multi-functional T-cell responses in patients with high-risk melanoma (Figure 2).
Claims 36, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, and 52 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1 and 23-25, 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14-16, 17-19, and 26-28, respectively, of copending Application No. 19/341,661 (reference application). Although the claims at issue are not identical, they are not patentably distinct from each other because independent claim 1 of the ‘661 copending application would be anticipatory of instant claim 36.
Claim 1 of copending Application No. 19/341,661 (reference application) would be anticipatory of instant claim 36 because the copending claim recites “identifying one or more T-cells that are antigen-specific for at least one of the neoantigens in the subset,” which is a species of the instant claim limitation reciting “extracting a prioritized plurality of the neoantigens from the selected subset as the personalized set of neoantigens” (i.e., the personalized neoantigens are prioritized and selected for their desired antigen-specificity and ability to induce strong T-cell responses).
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Conclusion
No claims are allowed.
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this application.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEVEN W. BAILEY whose telephone number is (571)272-8170. The examiner can normally be reached Mon - Fri. 1000 - 1800.
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, KARLHEINZ SKOWRONEK can be reached on (571) 272-9047. 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.
/S.W.B./Examiner, Art Unit 1687
/Joseph Woitach/Primary Examiner, Art Unit 1687