CTNF 17/711,658 CTNF 101339 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Election/Restrictions 08-25-02 Applicant’s election of Group I (Claims 1-6, 15-20 ), drawn to a method and system for training a machine learning model to generate peptide mutations , in the reply filed on January 14 th , 2026 is acknowledged. Because applicant did not distinctly and specifically point out the supposed errors in the restriction requirement, the election has been treated as an election without traverse (MPEP § 818.01(a)). Claims 7-14 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected method of developing treatments for pathogens associated with MHC proteins, there being no allowable generic or linking claim. 08-23-02 AIA Applicant is reminded that upon the cancelation of claims to a non-elected invention, the inventorship must be corrected in compliance with 37 CFR 1.48(a) if one or more of the currently named inventors is no longer an inventor of at least one claim remaining in the application. A request to correct inventorship under 37 CFR 1.48(a) must be accompanied by an application data sheet in accordance with 37 CFR 1.76 that identifies each inventor by his or her legal name and by the processing fee required under 37 CFR 1.17(i). Claim Status Claims 1-6 and 15-20 are currently pending and under exam herein. Claims 7-14 are withdrawn. Claims 1-6 and 15-20 are rejected. Priority Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. The instant application claims priority to U.S. Provisional Patent Application No. 63/170,727, filed on April 5, 2021. At this point in examination, claims 1-6 and 15-20 have been interpreted as being accorded this effective filing date of April 5 th , 2021 . Information Disclosure Statement The information disclosure statement (IDS) filed on 04/01/2022 is in compliance with the provisions of 37 CFR 1.97 and has been considered in full. A signed copy of the list of references cited from the IDS is included with this Office Action. Drawings The Drawings filed on 04/01/2022 are accepted. Specification The Specification filed on 04/01/2022 is accepted. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 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 1-6 and 15-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. In accordance with MPEP § 2106, claims found to recite statutory subject matter ( Step 1 : YES ) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon ( Step 2A, Prong 1 ). In the instant application, the claims recite the following limitations that equate to an abstract idea: Claims 1 and 15 recites a computer-implemented method and system of training a machine learning model that comprises of predicting an action, including a modification to an amino acid (abstract idea; mental process), and using the state and the reward to generate modification that increases the presentation score (abstract idea; mental process and mathematical concepts). The claims are merely modifying an amino acid within a peptide sequence, evaluating how well the new peptide sequence will bind with a major histocompatibility complex (MHC) protein, using math to score the peptide for ranking, before picking the sequences that are above a threshold score. Although, the claims recite performing the steps in a generic computer environment, the limitations can be practically performed in the human mind as well. Therefore, the claim limitations constitute both mental processes and mathematical concepts, falling broadly under the category of abstract ideas. Please see MPEP § 2106.04(a)(2) for more details. Claims 1 and 15 recite embedding a state (peptide sequence and protein) as a vector, without limitations on the peptide sequence or protein. Base of the broadest reasonable interpretation, the claim is merely encoding a peptide sequence and/or protein into numerical representations, which can be practically performed in the human mind as well. Furthermore, the claim limitations also may be a verbal equivalent of a mathematical conversion, which would fall under mathematical concepts. Therefore, this claim limitation would constitute both as a mental process and mathematical concept, under the bigger umbrella of abstract ideas. Claims 2 and 16 recites a scoring model to generate a presentation score (abstract idea; mental process and mathematical concepts) that will be utilize in the method and system of claim 1 and 15 respectively. The process of evaluating two proteins (modified peptide and MHC), comparing it to known protein bindings, before making a judgment on how likely they will bind, is a mental process that can be practically done in the mind or with pen and paper. Claims 3 and 17 recites that the presentation score is merely a combination of binding affinity and antigen processing score (abstract idea; mathematical concept). The scores for binding affinity and antigen process can be mere numbers, and the process of obtaining the presentation score would therefore be simple addition. Hence, the limitations of the claims constitute as a mathematical concept. Claims 4 and 18 recites minimizing a loss function that includes a clipping term, a reward term, and an exploration term (abstract idea; mathematical concept). Again, the limitations in the claim are reciting mathematical concepts. Specifically, the limitations are organizing information and manipulating information through mathematical correlation, that constitute the limitations as mathematical relationships under Digitech Image Techs., LLC v. Electronics for Imaging, Inc., 758 F.3d 1344, 1350, 111 USPQ2d 1717, 1721 (Fed. Cir. 2014). The limitations regarding predicting a modification to an amino acid sequencing using the presentation score as a reward are verbal equivalents that describe a mental process that can be performed in the mind or with pen and paper. While, the limitations regarding the presentation score and loss functions are mathematical relations that also fall under abstract ideas. These recitations are similar to the concepts of collecting information, analyzing it and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) and comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas. While claims 1-6, and 15-20 recite performing some aspects of the analysis with an “machine learning model”, there are no additional limitations that indicate that this analysis engine requires anything other than carrying out the recited mental process or mathematical concept in a generic computer environment. Merely reciting that a mental process is being performed in a generic computer environment does not preclude the steps from being performed practically in the human mind or with pen and paper as claimed. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then if falls within the “Mental processes” grouping of abstract ideas. As such, claims 1-6 and 15-20 recites an abstract idea ( Step 2A, Prong 1 : YES ). Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not ( Step 2A, Prong 2 ). This judicial exception is not integrated into a practical application because the claims do not recite an additional element that reflects an improvement to technology or applies or uses the recited judicial exception to affect a particular treatment for a condition. Rather, the instant claims recite additional elements that amount to mere instructions to implement the abstract idea in a generic computing environment. Specifically, the claims recite the following additional elements: Claim 1 recite a computer-implemented method of training a machine learning model Claims 5 and 19 recite that the embedding a state is done through a bi-directional long-short term memory (LSTM) neural network Claim 6 and 20 recite that the protein is a major histocompatibility complex (MHC) protein Claim 15, 16, 18, and 19 recite a system for training a model including a hardware processor and a memory that stores a computer program While the additional elements further limit the claims by specifying the protein type and embedding process, they do not indicate that the claimed analysis engine or the formats of the provided data require anything other than generic computing systems. As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. In general, linking the use of an abstract idea to a particular technological environment, such as a computer, does not integrate the abstract idea into a practical application based on MPEP 2106.06(h). As such, claims 1-6 and 15-20 are directed to an abstract idea as the additional elements do not integrate the judicial exceptions into a practical application ( Step 2A, Prong 2 : NO ). Claims found to be directed to a judicial exception under Step 2A, Prong 2 are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself. In the instant application, claims 1-6 and 15-20 do not recite further limitations or specification to the additional element that would indicate anything other than applying the abstract idea on a generic computer. According to MEPE 2106.05(d), courts have held computer-implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amount to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e. by hand or by merely thinking). Therefore, the additional elements in claim 1-6 and 15-20 do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception (Step 2B: NO). In conclusion, claims 1-6 and 15-20 are directed towards a process of modifying amino acids in peptide sequences, and scoring the sequences to generate peptides that bind well to MHC proteins. The claims do not provide an inventive concept because the claims do not recite additional elements or a combination of elements that amount to significantly more than the judicial exception of the claims. Therefore, the claims do not amount to significantly more than the judicial exception itself, and as such, claims 1-6 and 15-20 are not patent eligible. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-20-02-aia AIA This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention. Claims 1-4, 6, 15-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable in view of Yelensky et al. (CA3008641 A1, June 22 2017) over Olivecrona et al. (Journal of Cheminformatics, Sep 4 2017, Vol 9, article no. 48). The limitations of the instant claim are italicized below. With respect to claim 1, Yelensky et al. teaches an optimized approach for identifying and selecting neoantigens for personalized cancer vaccines ([0009]). The methods, depending on the embodiment, train statistic regression or nonlinear deep learning models (neural networks) that jointly model peptide-allele mapping ([0009], a computer-implemented method of training a machine learning model ). The method starts by inputting the peptide sequence of each neoantigen into one or more presentation models (Claim 1). The specification specifies that there is an encoding module (314) that encodes information such as the peptide sequences and one or more MHC alleles into numerical representations (pg. 54 [00311], pg. 55 [00314], pg. 60 [00343], embedding state, including a peptide sequence and a protein, as a vector ). Then, the method inputs the peptide sequence of each neoantigen into one or more presentation models to generate a set of numerical likelihoods that each of the neoantigens is presented by one or more MHC alleles (pg. 9 [0082]). Based on these numerical likelihood scores, the model can then rank the peptides to generate a set of selected peptides with a desired property following a selection criterion (pg. 11 [0087], using a presentation score of the peptide sequence by the protein as a reward, using the state and reward, to generation modifications that increase the presentation score ). Concerning claim 2, Yelensky et al. discloses one or more presentation models to generate a set of numerical likelihoods that each of the neoantigens is presented by one or more MHC alleles (pg. 9 [0082], training a scoring model that generates the presentation score ). Regarding claim 3, Yelensky et al. generates a set of numerical likelihoods that each of the neoantigens are presented by one or more MHC alleles on a tumor cell surface (Claim 1). These numerical likelihoods are informed by MHC-allele interacting features such as the predicted affinity with which the MHC allele and the neoantigen bind and the probability of presentation of the neoantigen (Claim 49, wherein the presentation score represents a combination of a peptide-protein binding affinity and an antigen processing score ). With respect to claim 6, Yelensky et al. teaches an encoding module (314) that one-hot encodes peptide sequences over a pre-determined 20-letter amino acid alphabet along with one or more MHC alleles (pg. 54 [00311], pg. 55 [00314], wherein the protein is a major histocompatibility complex (MHC) protein ). With respect to claim 15, Yelensky et al. teaches an optimized system and method for identifying and selecting neoantigens for personalized cancer vaccines ([0009]). The system contains a computer (1400) that is adapted to execute the specified functionality, program modules for the computer are stored on the storage device (1408), loaded into the memory (1406), and executed by the processor (1402) (pg. 88 [00459], a hardware processor; and a memory that stores a computer program, which when executed by the hardware processor, causes the hardware processor to ). Depending on the embodiment, the processor may train statistic regression or nonlinear deep learning models (neural networks) that jointly model peptide-allele mapping ([0009], a system for training a machine learning model ). The processor starts by inputting the peptide sequence of each neoantigen into one or more presentation models (Claim 1). The specification specifies that there is an encoding module (314) that encodes information such as the peptide sequences and one or more MHC alleles into numerical representations (pg. 54 [00311], pg. 55 [00314], pg. 60 [00343], embedding state, including a peptide sequence and a protein, as a vector ). Then, the method inputs the peptide sequence of each neoantigen into one or more presentation models to generate a set of numerical likelihoods that each of the neoantigens is presented by one or more MHC alleles (pg. 9 [0082]). Based on these numerical likelihood scores, the model can then rank the peptides to generate a set of selected peptides with a desired property following a selection criterion (pg. 11 [0087], using a presentation score of the peptide sequence by the protein as a reward, using the state and reward, to generation modifications that increase the presentation score ). Concerning claim 16, Yelensky et al. discloses one or more presentation models to generate a set of numerical likelihoods that each of the neoantigens is presented by one or more MHC alleles (pg. 9 [0082], the computer program further causes the hardware processor to score train a scoring model that generates the presentation score ). Regarding claim 17, Yelensky et al. generates a set of numerical likelihoods that each of the neoantigens are presented by one or more MHC alleles on a tumor cell surface (Claim 1). These numerical likelihoods are informed by MHC-allele interacting features such as the predicted affinity with which the MHC allele and the neoantigen bind and the probability of presentation of the neoantigen (Claim 49, wherein the presentation score represents a combination of a peptide-protein binding affinity and an antigen processing score ). With respect to claim 20, Yelensky et al. teaches an encoding module (314) that one-hot encodes peptide sequences over a pre-determined 20-letter amino acid alphabet along with one or more MHC alleles (pg. 54 [00311], pg. 55 [00314], wherein the protein is a major histocompatibility complex (MHC) protein ). However, Yelensky et al. does not teach the limitation of predicting an action, including a modification to an amino acid in the peptide sequence and training a mutation policy model . However, these limitations were known in the art at the time of the effective filing date of the invention as taught by Olivecrona et al. Concerning claim 1 and 15, Olivecrona et al. discloses a method and system to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can generate structures with certain specified desirable properties (Abstract, training a mutation policy model ). Oliviecrona et al. specifies that a policy-based reinforcement learning is utilized to finetune prior models according to some specified scoring function (pg. 4 left col para 4). The model, when given a certain state and set of actions taken from the state, will determine the next action based on the rewards which acts as a measurement of how good it was to take an action (pg. 4 left col para 2, predicting an action, including a modification to an amino acid in the peptide sequence ). Olivecrona et al. further specifies that the states and actions used to train the policy can be generated by the model itself or by some other means (pg. 4 left col para 3). The model then takes a sequence of actions, generates the product of action probabilities which represents the likelihood of the sequence formed, and updates the policy from the prior policy in such a way to increase the expected score for the generated sequences (pg. 4 right col. Para 3, using the state and reward, to generation modifications that increase the presentation score ). Olivecrona et al. also stated how reinforcement learning has successfully demonstrated its ability to fine-tune pre-trained models, and significantly improve them based on a reward function (pg. 2 left col para 3). Concerning claim 4, Olivecrona et al. discloses that the goal of the reinforcement agent is to learn a policy which maximizes the expected return by minimizing the cost function (pg. 5 left col para 2, wherein training the mutation policy includes minimizing a loss function ). Olivecrona et al. goes on to teach that the cost function can vary depending on the desired properties and gives examples including a clip term (pg. 5 left col para 2, a clipping term ), reward term (pg. 5 left col para 2, a reward term ) and regularizing policy entropy term (pg. 7 left col para 3, an exploration term, specify in the specification as the entropy regularization loss ). Concerning claim 18, Olivecrona et al. discloses that the goal of the reinforcement agent is to learn a policy which maximizes the expected return by minimizing the cost function (pg. 5 left col para 2, where the computer program causes the hardware processor to train the mutation policy by minimizing a loss function ). Olivecrona et al. goes on to teach that the cost function can vary depending on the desired properties and gives examples including a clip term (pg. 5 left col para 2, a clipping term ), reward term (pg. 5 left col para 2, a reward term ) and regularizing policy entropy term (pg. 7 left col para 3, an exploration term, specify in the specification as the entropy regularization loss ). Therefore, it would have been prima facie obvious to one of ordinary skill in the art at the effective filing date of the invention to implement the reinforcement learning policy model from Olivecrona et al. with the neoantigen identifying model of Yelensky et al. to fine-tune the predictions of neoantigens obtained with high presentation scores and increase the number of possible neoantigens identified. The paradigm of reinforcement learning agents were well known before the effective filing date of the instant application, and one of ordinary skill in the art would have been motivated to implement this trial-and-error reward system to the field of neoantigen discovery to create new artificial peptide targets that have never been sequenced or discovered yet for immunotherapy. In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating a reinforcement learning policy into the prior model of neoantigens as incorporation of reinforcement learning agents into neural networks were well established during this time and was shown to be success through Olivecrona et al. Claims 5 and 19 are rejected under 35 U.S.C. 103 as being unpatentable in view of Yelensky et al. over Olivecrona et al., as applied to Claim 1 above, further in view of Venkatesh et al. (Bioinformatics, July 1 2020 36(Suppl1): i399-i406). The limitations of the instant claim are italicized below. The limitations of claims 1 and 15 have been taught by Yelensky et al. and Olivecrona et al. above. With respective to claim 5, although Yelensky et al. does describe the use of network models such as long short-term memory networks (LSTM) to capture the interaction between amino acids at different positions in a peptide sequence and how this interaction affects peptide presentation (pg. 62 [00353] – pg. 63 [00354]), Yelensky et al. does not explicitly teach the use of LSTM to embed the state. However, Venkatesh et al. teaches the use of bidirectional long short-term memory (Bi-LSTM) encoder to embed the amino acid sequences (pg. i400 right col para 6, wherein embedding the state is performed using a bi-directional long-short term memory (LSTM) neural network ). The Bi-LSTM was chosen specifically as it is capable of processing sequences with variable lengths and contains information from both the past and future context for analysis (pg. i401 left col para 5). Venkatesh et al. further states that the improvement in results of the model is mainly due to the use of Bi-LSTMs to encode the amino acid information (pg. i405 left col para 3). With respective to claim 19, although Yelensky et al. does describe the use of network models such as long short-term memory networks (LSTM) to capture the interaction between amino acids at different positions in a peptide sequence and how this interaction affects peptide presentation (pg. 62 [00353] – pg. 63 [00354]), Yelensky et al. does not explicitly teach the use of LSTM to embed the state. However, Venkatesh et al. teaches the use of bidirectional long short-term memory (Bi-LSTM) encoder to embed the amino acid sequences (pg. i400 right col para 6, wherein the computer program causes the hardware processor to embed the state is performed using a bi-directional long-short term memory (LSTM) neural network ). The Bi-LSTM was chosen specifically as it is capable of processing sequences with variable lengths and contains information from both the past and future context for analysis (pg. i401 left col para 5). Venkatesh et al. further states that the improvement in results of the model is mainly due to the use of Bi-LSTMs to encode the amino acid information (pg. i405 left col para 3). It would have been prima facie obvious to one of ordinary skill in the art at the effective filing date of the invention to implement the Bi-LSTM embedding method of Venkatesh et al. with the models of Olivecrona et al. and Yelensky et al. allow for variable lengths in peptide sequences and higher variety of neoantigen peptides. As stated in Venkatesh et al. , one of ordinary skill in the art would have been motivated to incorporate the Bi-LSTM embedding method to handle a large variety of peptide with different lengths, along with bi-directional information to analyze the relationship within amino acid sequences. In addition, one of skill in the art before the effective filing date of the claimed invention would have a reasonable expectation of success at incorporating the Bi-LSTM embedding peptide sequences as Bi-LSTM encoding of amino acid sequences in neural networks were well established during this time and was shown to be success through Venkatesh et al. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to WENYU YANG whose telephone number is (571)272-0035. The examiner can normally be reached 7:30am - 5:00 pm. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Olivia Wise can be reached at (571) 272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /W.Y./Examiner, Art Unit 1685 /OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685 Application/Control Number: 17/711,658 Page 2 Art Unit: 1685 Application/Control Number: 17/711,658 Page 3 Art Unit: 1685 Application/Control Number: 17/711,658 Page 4 Art Unit: 1685 Application/Control Number: 17/711,658 Page 5 Art Unit: 1685 Application/Control Number: 17/711,658 Page 6 Art Unit: 1685 Application/Control Number: 17/711,658 Page 7 Art Unit: 1685 Application/Control Number: 17/711,658 Page 8 Art Unit: 1685 Application/Control Number: 17/711,658 Page 9 Art Unit: 1685 Application/Control Number: 17/711,658 Page 10 Art Unit: 1685 Application/Control Number: 17/711,658 Page 11 Art Unit: 1685 Application/Control Number: 17/711,658 Page 13 Art Unit: 1685 Application/Control Number: 17/711,658 Page 14 Art Unit: 1685