DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
The instant application claims benefit of priority to U.S. Provisional Application No. 63/072,083 filed on 8/28/2020. The claim to the benefit of priority is acknowledged. As such, the effective filing date of claims 1-8, 12-13, 15-21, 23, 26, and 51 is 8/28/2020.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 3/1/2023 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Status
Claims 1-8, 12-13, 15-21, 23, 26, and 51 are pending.
Claims 1-8, 12-13, 15-21, 23, 26, and 51 are rejected.
Claim Objections
Claim 13 is objected to because of the following informalities: “any one of” in line 1 should be removed. Appropriate correction is required.
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 1-8, 12-13, 15-21, 23, 26 and 51 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more. The claims recite a method for preparing a vaccine. The judicial exception is not integrated into a practical application because while claims 1-8, 12-13, 15-21, 23, 26 and 51 attempt to integrated the exception into a practical application, said application is either generically recited computer elements that do not add a meaningful limitation to the abstract idea or it is insignificant extra solution activity and merely implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the computer elements only store and retrieve information in memory as well as perform basic calculations that are known to be well-understood, routine and conventional computer functions as recognized by the decisions listed in MPEP § 2106.05(d).
Framework with which to Analyze Subject Matter Eligibility:
Step 1: Are the claims directed to a category of stator subject matter (a process, machine, manufacture, or composition of matter)? [see MPEP § 2106.03]
Claims are directed to statutory subject matter, specifically a method (Claims 1-8, 12-13, 15-21), a CRM (Claim 51), and a system (Claim 26).
Step 2A Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? [see MPEP § 2106.04(a)]
The claims herein recite abstract ideas, specifically mental processes and mathematical concepts.
With respect to the Step 2A Prong One evaluation, the instant claims are found herein to recite abstract ideas that fall into the grouping of mental processes and mathematical concepts.
Claims 1, 26, and 51: Determining data corresponding to one or more candidate peptides, and calculating a probability of cleavage are processes of comparing/contrasting, identifying, selecting, and calculating information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes. Calculating a probability of cleavage is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 2: Choosing a peptide antigen based on the signal corresponding to the calculated probability is a process of comparing/contrasting, identifying, and selecting information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 3: Basing the choosing of the peptide antigen on a determination of whether the calculated probability is within a predetermined range is a process of comparing/contrasting, identifying, and selecting information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 4: Calculating a probability of cleavage for at least one N-terminal peptides, and calculating a probability of cleavage for at least one C-terminal peptide are processes of calculating information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes. Calculating a probability of cleavage for at least one N-terminal peptides, and calculating a probability of cleavage for at least one C-terminal peptide are verbal articulations of mathematical processes and are therefore abstract ideas, specifically mathematical concepts.
Claim 5: Calculating a probability of cleavage for at least one N-terminal peptides, and independently calculating a probability of cleavage for at least one C-terminal peptide are processes of calculating information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes. Calculating a probability of cleavage for at least one N-terminal peptides, and independently calculating a probability of cleavage for at least one C-terminal peptide are verbal articulations of mathematical processes and are therefore abstract ideas, specifically mathematical concepts.
Claim 6: Determining data corresponding to one or more neighboring variants, and calculating a probability of cleavage for the one or more variants are processes of comparing/contrasting, identifying, selecting, and calculating information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes. Calculating a probability of cleavage for the variants is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 7: The immune epitope database including the specified data types is merely further limiting the data itself, which is an abstract idea, specifically a mental process.
Claim 8: The immune epitope database comprising the specified information is merely further limiting the data itself, which is an abstract idea, specifically a mental process.
Claim 12: The immune epitope database comprising the specified information is merely further limiting the data itself, which is an abstract idea, specifically a mental process.
Claim 13: The flank size for the candidate peptides being the specified length is merely further limiting the data itself, which is an abstract idea, specifically a mental process.
Claim 15: The measurement of an accuracy of calculating being the ROC is merely further limiting the data itself, which is an abstract idea, specifically a mental process. The measurement of an accuracy of calculating being the ROC and an ROC closest to 1.0 is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 18: One or more candidate peptides being modeled without an explicit encoding is a process of comparing/contrasting, identifying, selecting, and calculating information that can be performed via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 19: The neural network including a parametric rectified linear unit activation function is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 20: Generating a first table, generating a second table, generating a third table and generating a fourth table a process of identifying, and selecting information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 23: The at least one protein being one of those specified is merely further limiting the data itself, which is an abstract idea, specifically a mental process.
Step 2A Prong Two: If the claims recite a judicial exception under prong one, then is the judicial exception integrated into a practical application? [see MPEP § 2106.04(d) and MPEP § 2106.05(a)-(c) & (e)-(h)]
Because the claims do recite judicial exceptions, direction under Step 2A Prong Two provides that the claims must be examined further to determine whether they integrate the abstract ideas into a practical application.
The following claims recite the following additional elements in the form of non-abstract elements:
Claims, 1, 26, and 51: A device, processor, memory, program, system, non-transitory computer-readable storage medium, and instructions are generic and nonspecific elements of computers that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Providing an immune epitope database, providing a neural network, receiving data, and outputting a signal are all insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989), PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis), Cutting hair after first determining the hair style, In re Brown, 645 Fed. App'x 1014, 1016-1017 (Fed. Cir. 2016) (non-precedential), and Printing or downloading generated menus, Ameranth, 842 F.3d at 1241-42, 120 USPQ2d at 1854-55) [See MPEP § 2106.05(g)].
Claim 16: One or more convolutional layers, one or more fully connected layers, and a single convolutional layer are generic and nonspecific elements of computers that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)].
Claim 17: One or more convolutional layers, one or more fully connected layers, one or more layers in parallel, and each of the different layers having a different kernal size are generic and nonspecific elements of computers that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)].
Claim 21: The vaccine being for an infectious disease or a cancer is merely a field of use (See Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 78, 101 USPQ2d 1961, 1968 (2012), Flook, 437 U.S. at 595, 198 USPQ at 199, and Genetic Techs. Ltd. v. Merial LLC, 818 F.3d 1369, 1379, 118 USPQ2d 1541, 1549 (Fed. Cir. 2016)) [See MPEP § 2106.05(h)].
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? [see MPEP § 2106.05]
Because the additional claim elements do not integrate the abstract idea into a practical application, the claims are further examined under Step 2B, which evaluates whether the additional elements, individually and in combination, amount to significantly more than the judicial exception itself by providing an inventive concept.
The claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are generic, conventional or nonspecific. These additional elements include:
The additional elements of a device, processor, memory, program, system, non-transitory computer-readable storage medium, instructions, one or more convolutional layers, one or more fully connected layers, a single convolutional layer, one or more layers in parallel, and each of the different layers having a different kernal size are all generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein (Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values), and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)) [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of providing an immune epitope database, providing a neural network, receiving data, and outputting a signal are insignificant extra solution activities, specifically mere data gathering and necessary data outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989), PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis), Cutting hair after first determining the hair style, In re Brown, 645 Fed. App'x 1014, 1016-1017 (Fed. Cir. 2016) (non-precedential), and Printing or downloading generated menus, Ameranth, 842 F.3d at 1241-42, 120 USPQ2d at 1854-55) [See MPEP § 2106.05(g)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of the vaccine being for an infectious disease or a cancer (Conventional: Review - Han et al. Abstract: …development of vaccines against many infectious diseases as well as other diseases including malignant tumors) is merely a field use (See Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 78, 101 USPQ2d 1961, 1968 (2012), Genetic Techs. Ltd. v. Merial LLC, 818 F.3d 1369, 1379, 118 USPQ2d 1541, 1549 (Fed. Cir. 2016), and Flook, 437 U.S. at 595, 198 USPQ at 199) [See MPEP § 2106.05(h)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 1-8, 12-13, 15-21, 23, 26 and 51, when the limitations are considered individually and as a whole, are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
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.
Claims 1-8, 12-13, 15-19, 21, 23, 26, and 51 are rejected under 35 U.S.C. 102(a)(II) as being anticipated by Rooney et al. (WO 2020132586 A1).
Claim 1 is directed to a method of preparing a vaccine using a neural network to calculate a probability of cleavage.
Claim 26 is directed to a system for preparing a vaccine using a neural network to calculate a probability of cleavage.
Claim 51 is directed to a CRM for preparing a vaccine using a neural network to calculate a probability of cleavage.
Rooney et al. teaches in paragraph [0391] “In one aspect, the present disclosure provides method for predicting peptides that can accurately pair with, or bind to, a specific HLA class II alpha and beta chain heterodimer, such that the high fidelity binding of the peptide to HLA class II protein (comprising the alpha and beta chain heterodimer) ensures presentation of the specific peptide to the T lymphocytes, thereby eliciting a specific immune response and avoid any cross reactivity or immune promiscuity…Cancer vaccines and other immunotherapies would ideally take advantage of directing CD4+ T cell responses, but current efforts have forgone HLA class II antigen prediction entirely because the accuracy of current prediction tools is inadequate”, paragraph [0402] “The term “peptide” is used interchangeably with “mutant peptide” and “neoantigenic peptide” in the present specification. Similarly, the term “polypeptide” is used interchangeably with “mutant polypeptide” and “neoantigenic polypeptide” in the present specification. By “neoantigen” or “neoepitope” is meant a class of tumor antigens or tumor epitopes which arises from tumor-specific mutations in expressed protein”, paragraph [0633] “Data from IEDB was generally unsuitable for this purpose since the allele restriction of responses is almost always either undefined or imputed. Therefore, a large dataset of tetramer-guided epitope mapping (TGEM) data was assembled”, paragraph [0750] “Data from these assays are compiled in the Immune Epitope Database (IEDB) and used to train HLA class II prediction algorithms such as NetMHCIIpan”, paragraph [0760] “To address this constraint, convolutional neural networks (CNNs) were employed, which have been successful in the field of computer vision because of their proficiency in translationally invariant pattern recognition. For each allele, an ensemble of CNNs were trained”, paragraph [850] “Four PBMC samples and published datasets were used to benchmark the ability of cleavage-related variables/predictors to enhance the identification of presented HLA class II epitopes…To build integrated predictors that predict peptide presentation using both binding potential and cleavage potential, constructed datasets were first using the same approach described for FIG. 31B”, claim 2 “identifying, based at least on the plurality of binding predictions, a peptide sequence of the plurality of peptide sequences that has a probability greater than a threshold binding prediction probability value of binding to at least one of the one or more proteins encoded by a class II HLA allele of a cell of the subject”, claim 47 “obtaining, by a computer processor, a candidate peptide comprising an epitope, and a plurality of peptide sequences, each comprising the epitope; (b) processing, by a computer processor, amino acid information…”, and paragraph [0071] “In some embodiments, the machine -learning HLA-peptide presentation prediction model comprises a plurality of predictor variables identified at least based on the training data, wherein the training data comprises training peptide sequence information comprising amino acid position information, wherein the training peptide sequence information is associated with the HLA protein expressed in cells; and a function representing a relation between the amino acid position information and the presentation likelihood generated as output based on the amino acid position information and the plurality of predictor variables”, reading on a method of preparing a vaccine comprising a peptide antigen or an immunotherapy treatment for cancer comprising a peptide antigen, wherein a device includes at least one processor and a memory storing at least one program for execution by the at least one processor, the at least one program including instructions which, when executed by the at least one processor, cause the at least one processor to perform the method, the method comprising: providing an immune epitope database; providing a neural network; receiving data corresponding to at least one protein into the neural network; receiving data corresponding to one or more candidate peptides corresponding to potential cleavage products of the at least one protein, or determining, using the neural network, data corresponding to one or more candidate peptides corresponding to potential cleavage products of the at least one protein; calculating, using the neural network, a probability of cleavage of the protein to result in each of the one or more candidate peptides; and outputting a signal corresponding to the calculated probability.
Claim 2 is directed to the method of claim 1 but further specifies choosing a peptide antigen based on the signal corresponding to the calculated probability.
Rooney et al. teaches in claim 2 “identifying, based at least on the plurality of binding predictions, a peptide sequence of the plurality of peptide sequences that has a probability greater than a threshold binding prediction probability value of binding to at least one of the one or more proteins encoded by a class II HLA allele of a cell of the subject”, reading on further comprising choosing a peptide antigen based on the signal corresponding to the calculated probability and preparing the vaccine with the chosen peptide antigen.
Claim 3 is directed to the method of claim 2 and thus claim 1, but further specifies that the choosing is based on whether the probability is within a predetermined range.
Rooney et al. teaches in paragraph [0490] “In some embodiments, the probability is configured to measure the likelihood that an event may occur. In some embodiments, the probability ranges from about 0 and 1, 0.1 to 0.9, 0.2 to 0.8, 0.3 to 0.7, or 0.4 to 0.6”, reading on wherein the choosing the peptide antigen based on the signal corresponding to the calculated probability is based on a determination of whether the calculated probability is within a predetermined range of values.
Claim 4 is directed to the method of claim 1 but further specifies that the method is used to calculate the probability of cleavage of N-terminals or C-terminals in a peptide.
Rooney et al. teaches in paragraph [0853] “To learn a cleavage signal from the MS-observed cut sites, all unique 6mer amino acid sequences from U3 to N3, and C3 to D3 (using the nomenclature introduced in the section, “Characterizing observed cleavage sites of HLA class II peptides, related to FIG. 40A”) in the tumor tissue-derived HLA class II ligandomes from were used as positive examples for training two distinct neural networks, modeling N-terminal cuts and C- terminal cuts, respectively”, reading on wherein the calculating, using the neural network, the probability of cleavage for each of the one or more candidate peptides includes: calculating, using the neural network, a probability of cleavage for at least one N-terminal of each of the one or more candidate peptides; or calculating, using the neural network, a probability of cleavage for at least one C-terminal of each of the one or more candidate peptides.
Claim 5 is directed to the method of claim 1 but further specifies that the method is used to calculate the probability of cleavage of N-terminals and C-terminals in a peptide.
Rooney et al. teaches in paragraph [0853] “To learn a cleavage signal from the MS-observed cut sites, all unique 6mer amino acid sequences from U3 to N3, and C3 to D3 (using the nomenclature introduced in the section, “Characterizing observed cleavage sites of HLA class II peptides, related to FIG. 40A”) in the tumor tissue-derived HLA class II ligandomes from were used as positive examples for training two distinct neural networks, modeling N-terminal cuts and C- terminal cuts, respectively”, reading on wherein the calculating, using the neural network, the probability of cleavage for each of the one or more candidate peptides includes: calculating, using the neural network, a probability of cleavage for at least one N-terminal of each of the one or more candidate peptides; and independent of the N-terminal calculation, calculating, using the neural network, a probability of cleavage for at least one C-terminal of each of the one or more candidate peptides.
Claim 6 is directed to the method of claim 1 but further specifies determining data corresponding one or more neighboring variants.
Rooney et al. teaches in paragraph [0821] “While amino acids may be represented by a“one-hot” encoding, others have opted to encode amino acids using the PMBEC matrix and the BLOSUM matrix (Henikoff and Henikoff, 1992), in which similar amino acids have similar feature profiles. For the purposes of our peptide featurization, a novel matrix based on amino acid proximities was generated in solved protein structures. The concept of this approach is that the typical neighbors of an amino acid should reflect its chemical properties. For each amino acid in each of -100,000 DSSP protein structures, the residue that was closest in 3D space but at least 10 amino acids away in primary sequence was determined. Using this data, the number of times the nearest neighbor of alanine was alanine was determined, the number of times the nearest neighbor of alanine was a cysteine, etc., to create a 20x20 matrix of proximity counts”, reading on further comprising: determining, using the neural network, data corresponding to one or more neighboring variants of the one or more candidate peptides; and calculating a probability of cleavage for the one or more neighboring variants.
Claim 7 is directed to the method of claim 1 but further specifies the data the database comprises.
Rooney et al. teaches in paragraph [0625] “In all cases, 2-3 replicates were sufficient to observe at least 1500 unique peptides”, in paragraph [0626] “Since the ends of MHC II binding peptides do not need to fit within the MHC binding groove, multiple distinct peptide species can bind equally well if they share the same core binding sequence. When the peptides were pooled with overlapping sequence into “nested sets”, 500-700 unique nested sets per HLA class II allele were observed”, and paragraph [0019] “In some embodiments, the machine learning HLA peptide presentation prediction model has a positive predictive value (PPV) of at least 0.07 when amino acid information of a plurality of test peptide sequences are processed to generate a plurality of test presentation predictions, each test presentation prediction indicative of a likelihood that the one or more proteins encoded by a class II HLA allele of a cell of the subject can present a given test peptide sequence of the plurality of test peptide sequences, wherein the plurality of test peptide sequences comprises at least 500 test peptide sequences comprising (i) at least one hit peptide sequence identified by mass spectrometry to be presented by an HLA protein expressed in cells and (ii) at least 499 decoy peptide sequences contained within a protein encoded by a genome of an organism”, reading on wherein the immune epitope database includes data representing one or more unique antigen proteins, one or more unique peptides, one or more unique peptide/protein pairs, and one or more decoys.
Claim 8 is directed to the method of claim 1 but further specifies the data the database is restricted to.
Rooney et al. teaches in paragraph [0164] “Provided herein is a method for assaying immunogenicity of a MHC class II binding peptide…”, reading on wherein the immune epitope database is restricted to major histocompatibility complex (MHC) pathways, MHC Class I (MHC-I) pathways, human-only immune epitopes, or sequences that positively bind to MHC.
Claim 12 is directed to the method of claim 1 but further specifies that the database include tandem mass spec data.
Rooney et al. teaches in paragraphs [0802]-[0803] “HLA-Peptide sequencing by tandem mass spectrometry”, reading on wherein the immune epitope database includes tandem mass spectrometry data where a single MHC-allele is not identified.
Claim 13 is directed to the method of claim 1 but further specifies a flank size of at least 6 and no more than 20.
Rooney et al. teaches in paragraph [0443] “Peptides bound to HLA class II molecules are believed to have a 9-amino acid binding core with flanking residues on either N- or C-terminal side that overhang from the groove (Jardetzky et ah, 1996; Stem et ah, 1994). These peptides are usually 12-16 amino acids in length and often contain 3-4 anchor residues at positions PI, P4, P6/7 and P9 of the binding register (Rossjohn et ah, 2015)”, reading on wherein a flank size for each of the one or more candidate peptides is greater than or equal to 6 and less than or equal to 20.
Claim 15 is directed to the method of claim 1 but further specifies the use of a ROC where the closer to 1.0 is the ideal.
Rooney et al. teaches in paragraph [0685] “Performance was also evaluated by receiver-operator curves”, and it is inherent to ROC curves that the closer to 1.0, the less error, and therefore reads on wherein a measurement of an accuracy of the calculating, using the neural network, the probability of cleavage for each of the one or more candidate peptides includes a receiver operating characteristic (ROC), and wherein an ROC closest to 1.0 is ideal.
Claim 16 is directed to the method of claim 1 but further specifies the network architecture.
Rooney et al. teaches in paragraph [0301] “FIG. 9 depicts an exemplary neural network architecture. Input peptides are represented as 20mers, with shorter peptides being filled in with “missing” characters. Each peptide has a 31-dimensional embedding, so the input into the neural network is a 20x31 matrix. Before being processed by the neural network, feature normalization on the 20x31 matrix is performed based on feature value means and standard deviations in the training set. The first convolutional layer has a kernel of 9 amino acids and 50 filters (also called channels) with a Rectified Linear Unit (ReLU) activation function. This is followed by batch normalization then spatial dropout with a dropout rate of 20%. This is followed by another convolutional layer with a kernel of 3 amino acids and 20 filters with a ReLU activation function and then again followed by batch normalization and spatial dropout with a dropout rate of 20%. Global max pooling is then applied, taking the maximally-activated neuron in each of the 20 filters; then these 20 values are passed into a fully connected (dense) layer with a single neuron using a Sigmoid activation function. The output of this layer is treated as the binding/non-binding prediction. L2 regularization is applied to the weights of the first convolutional layer, second convolutional layer, and dense layer with weights of 0.05, 0.1, and 0.01, respectively. Additional models used have varied the number of convolutional layers and the kernel size of each layer”, reading on wherein the neural network includes: one or more convolutional layers; and one or more fully connected layers, and wherein the one or more convolutional layers consists of a single convolutional layer.
Claim 17 is directed to the method of claim 1 but further specifies the network architecture.
Rooney et al. teaches in paragraph [0301] “FIG. 9 depicts an exemplary neural network architecture. Input peptides are represented as 20mers, with shorter peptides being filled in with “missing” characters. Each peptide has a 31-dimensional embedding, so the input into the neural network is a 20x31 matrix. Before being processed by the neural network, feature normalization on the 20x31 matrix is performed based on feature value means and standard deviations in the training set. The first convolutional layer has a kernel of 9 amino acids and 50 filters (also called channels) with a Rectified Linear Unit (ReLU) activation function. This is followed by batch normalization then spatial dropout with a dropout rate of 20%. This is followed by another convolutional layer with a kernel of 3 amino acids and 20 filters with a ReLU activation function and then again followed by batch normalization and spatial dropout with a dropout rate of 20%. Global max pooling is then applied, taking the maximally-activated neuron in each of the 20 filters; then these 20 values are passed into a fully connected (dense) layer with a single neuron using a Sigmoid activation function. The output of this layer is treated as the binding/non-binding prediction. L2 regularization is applied to the weights of the first convolutional layer, second convolutional layer, and dense layer with weights of 0.05, 0.1, and 0.01, respectively. Additional models used have varied the number of convolutional layers and the kernel size of each layer”, reading on wherein the neural network includes: one or more convolutional layers; and one or more fully connected layers, wherein the one or more convolutional layers comprises the one or more convolutional layers in parallel, and wherein each of the one or more convolutional layers has a different size kernel.
Claim 18 is directed to the method of claim 1 but further specifies that peptides are modeled without an explicit encoding of a cleavage marker.
Rooney et al. teaches in paragraph [0265] “In some embodiments, the polynucleic acid construct comprises an expression vector, further comprising one or more of: a promoter, a linker, one or more protease cleavage sites, a secretion signal, dimerization factors, ribosomal skipping sequence, one or more tags for purification and or detection”, reading on wherein one or more candidate peptides are modeled without an explicit encoding of a cleavage marker.
Claim 19 is directed to the method of claim 1 but further specifies that the neural network includes a parametric rectified linear unit activation function.
Rooney et al. teaches in paragraph [0301] “he first convolutional layer has a kernel of 9 amino acids and 50 filters (also called channels) with a Rectified Linear Unit (ReLU) activation function”, reading on wherein the neural network includes a parametric rectified linear unit activation function.
Claim 21 is directed to the method of claim 1 but further specifies that the vaccine is for an infectious disease or cancer.
Rooney et al. teaches in claim 25 “The method of any one of the preceding claims, wherein each peptide sequence of the plurality of peptide sequences is associated with a cancer”, and in the abstract “The present disclosure provides method for preparing a personalized cancer vaccine”, reading on wherein the vaccine is for an infectious disease or a cancer.
Claim 23 is directed to the method of claim 21 and thus claim 1, but further specifies that the protein is one of those specified.
Rooney et al. teaches in paragraph [0004] “Understanding the peptide-binding preferences of every HLA class II heterodimer is the key to successfully predicting which cancer or tumor-specific antigens are likely to elicit the cancer or tumor-specific T cell responses. There is a need for methods of identifying and isolating specific HLA class Il-associated peptides (e.g., neoantigen peptides)”, reading on wherein the at least one protein is a tumor-associated antigen, a neoantigen, or an antigen from a virus, bacterium, fungus, protozoa, prion, or helminth.
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.
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Rooney et al. (WO 2020132586 A1) as applied to claims 1-8, 12-13, 15-19, 21, 23, 26, and 51 above.
Claim 20 is directed to the method of claim 1 but further specifies the number and structure of the output tables.
Rooney et al. teaches the method of claim 1 as previously described.
Rooney et al. does not teach the specific table design and number of tables used as output in the instant application.
While Rooney et al. does not explicitly teach the specified output table number and structure, Rooney et al. does teach the use of the software NetMHCIIPan, whose output, as seen in the NetMHCIIPan Output documentation is a table containing some of the information contained within the tables specified by the claim limitation. It would therefore have been obvious to a person skilled in the art to optimize the output structure and information of Rooney et al., including changing the layout, number of tables, etc. as these are merely a matter of routine optimization and design choice to present the data in a more user-friendly or readable format. One of ordinary skill in the art would expect the result of an optimized structure of data output, and would be a predictable and obvious result.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
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 at 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.
/K.N.A./Examiner, Art Unit 1687
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights