DETAILED ACTION
Applicant's response, filed 1/30/2025, 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.
Continued Examination Under 37 CFR 1.114
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 1/30/2026 has been entered.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Acknowledgment is made of applicant’s claim for priority. Application claims benefit of U.S. Provisional Application 62/777,670 filed on 12/10/2018. As such, the effective filing date of claims 1-13 is 12/10/2018.
Claims Status
Claims 1-2 and 5-13 are pending.
Claims 1-2 and 5-13 are rejected.
Claims 3-4 are cancelled.
Claim Rejections - 35 USC § 103
Response to Amendment
In view of applicant’s amendments to the claims, a new review of the claims under 35 U.S.C. 103 was performed and is provided below.
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.
Claims 1-2 and 6-13 are rejected under 35 U.S.C. 103 as being unpatentable over Aswad et al. (US 20150205911 A1; previously cited) in view of Holley et al. (Proceedings of the Nation Academy of Sciences (1989) 152-156; previously cited).
Claim 1 is directed to a method of predicting the affinity of a candidate molecule for a second molecule wherein a three-dimensional structure of the candidate molecule bound to the second molecule, in addition to a plurality of candidate measurements regarding said structure is used by a computer to predict said affinity.
Aswad et al. teaches in paragraph [0025] a “method for measuring how well two or more proteins bind to one another, including methods that measure affinity, complementarity, energetic favorability, etc.” and in paragraph [0026] “As used herein, the term "sequence information", in the context of inputting sequence information, is intended to include inputting an identifier for a sequence, inputting a sequence, and inputting structure information for a sequence”, which reads on a method for predicting affinity of a candidate molecule for a second molecule and establishes a connection between structural information and affinity. In regards claim 1, docking the candidate molecule with the second molecule to obtain a three dimensional representation, Aswad et al. teaches in paragraph [0029] “as used herein, the term "model" refers to any way of representing data of the three dimensional structure” and in paragraph [0050] “In some embodiments, execution of the program by a user causes the computer to identify data files containing a model for the selected peptide, a model for the selected MHCII protein and a model for the selected TCR protein. The selected models are then docked to provide a peptide-MHCII model… Once a complex with optimal complementarity is identified, the degree of complementarity between the peptide and the binding groove in the pMHCII model can be calculated to quantify the most energetically favorable arrangement of the MHCII protein and the peptide”. In regards claim 1, generating a plurality of candidate measurements, wherein each candidate measurement is associated with at least one feature of the candidate structural representation, Aswad et al. teaches in paragraph [0050] “Once a complex with optimal complementarity is identified, the degree of complementarity between the peptide and the binding groove in the pMHCII model can be calculated to quantify the most energetically favorable arrangement of the MHCII protein and the peptide… In certain embodiments the free energy (G) of a protein or peptide is calculated using various approaches that take into account steric interactions, hydrophopic interactions, Van der Waals forces, etc.”. In regards claim 1, using the artificial neural network to predict the affinity of the candidate molecule for the second molecule based upon the plurality of candidate measurements, Aswad et al. teaches in paragraph [0051] “a score indicating the degree of complementarity between the peptide and the MHCII protein can be calculated, and this figure can be used in conjunction with other measures, to calculate the immunogenicity score described below”, which paragraph [0049] clarifies “predicts the immunogenicity of the peptide from the system” and paragraph [0052] states that “the score can indicate the strength of the association between the TCR protein and the peptide in the pMHCII complex”.
Aswad et al. does not teach claim 1, training an artificial neural network to generate a plurality of reference measurements from a training dataset comprising a plurality of reference measurements.
Holley et al. teaches in the abstract “A training phase was used to teach the network to recognize the relation between secondary structure and amino acid sequences on a sample set of 48 proteins of known structure”, which reads on the use of a training dataset to train a neural network model.
It would have been obvious at the time of first filing to modify the teachings of Aswad et al. for the method of predicting immunogenicity through binding affinities with the teachings of Holley et al. for a trained neural network that predicts protein structure in order to incorporate the neural network to predict affinity, as within the discussion section on page 155, column 2 Holley et al. says “…the neural network method is generally more accurate than prior methods when compared on identical proteins… An important observation from this method is that prediction strength is correlated with prediction accuracy”. While predicting binding affinities and secondary structural motifs are not exactly the same thing, the latter feeds into the former and as such would warrant investigation. A person of ordinary skill within the art would have a reasonable expectation of success given the similarity between the research, both in terms of fields and application, as well as the previous citations from Holley et al. outlining the advantages of using neural networks in such tasks. Therefore, it would have been obvious to a person of ordinary skill in the art to incorporate the neural network from Holley et al. into the method of Aswad et al. and to be successful.
Claim 2 is directed to the method of claim 1 but further specifies that each reference measurement is associated with at least one feature of the structural representations and the reference structural representation is a three-dimensional representation of a reference molecule bound to the second molecule.
Aswad et al. and Holley et al. teach the method of claim 1 as outlined above.
Aswad et al. further teaches in paragraph [0080] “The FireDock function includes a weighted combination of softened van der Waals, desolvation, electrostatics, hydrogen bonding, disulfide bonding, .pi.-stacking, aliphatic interactions, and rotamer preferences”, which reads on each reference measurement is associated with at least one feature of one or more reference structural representations. In regards claim 2, the reference structural representation is a three-dimensional representation of a reference molecule bound to the second molecule, Aswad et al. teaches in paragraph [0029] “as used herein, the term "model" refers to any way of representing data of the three-dimensional structure”.
Claim 6 is directed to the method of claim 2 and thus the method of claim 1 but further specifies that the processor be configured to the predict the affinity of the candidate molecule for the second molecule using a machine-learned model trained to predict affinity.
Aswad et al. and Holley et al. teach the method of claims 1 and 2 as outlined above.
Aswad et al. teaches the method of claims 1 and 2 as outlined above, and additionally in paragraph [0080] teaches “Statistical potentials specifically for peptide-MHC-TCR interactions can be derived. MHC class I complexes can be used for training the potentials”, these potentials being used later to predict the affinity for a peptide.
Claim 7 is directed to the method of claim 2 and thus the method of claim 1 but further specifies that the artificial neural network is configured to predict the affinity of the candidate molecule for the second molecule based upon the known affinity for each reference molecule for the second molecule.
Aswad et al. teaches in paragraph [0056] a “score that estimates the strength of the binding interactions in a pMHCII-TCR complex”, which reads on claim 7, wherein the artificial neural network is further configured to predict the affinity of the candidate molecule for the second molecule based upon the known affinity for each reference molecule for the second molecule.
Claim 8 is directed to the method of claim 1 but further specifies that the second molecule is an antigen presenting molecule.
Aswad et al. and Holley et al. teach the method of claim 1 as outlined above.
Aswad et al. teaches in paragraph [0019] “The terms "MHCI" and "MHC class I" include any human class I MHC molecules including all naturally occurring sequence variants of HLA-A, HLA-B and HLA-C, as well as equivalent molecules from other species”, which reads on claim 8, wherein the second molecule is an antigen presenting molecule.
Claim 9 is directed to the method of claim 8 and thus the method of claim 1 but further specifies that the antigen presenting molecule is a class I or class II MHC molecule.
Aswad et al. and Holley et al. teach the method of claims 1 and 8 as outlined above.
Aswad et al. teaches in paragraph [0019] “The terms "MHCI" and "MHC class I" include any human class I MHC molecules including all naturally occurring sequence variants of HLA-A, HLA-B and HLA-C, as well as equivalent molecules from other species”, which reads on claim 9, wherein the antigen presenting molecule is a class I MHC molecule or a class II MHC molecule.
Claim 10 is directed to the method claim 9 and therefore claims 8 and 1 but further specifies that the antigen presenting molecule is HLA-A2.
Aswad et al. and Holley et al. teach the method of claim 1, 8 and 9 as outlined above.
Aswad et al. teaches in paragraph [0019] “The terms "MHCI" and "MHC class I" include any human class I MHC molecules including all naturally occurring sequence variants of HLA-A, HLA-B and HLA-C, as well as equivalent molecules from other species”, which reads on claim 10, herein the antigen presenting molecule is HLA-A2, where HLA-A2 is merely a variant of HLA-A described in Aswad et al.
Claim 11 is directed to the method of claim 1 but further specifies the candidate or reference measurements are selected from the group consisting of solvent accessible surface areas, solvation energies, hydrophobicity, electrostatic interactions, and van der Waals interactions.
Aswad et al. and Holley et al. teach the method of claim 1 as outlined above.
Aswad et al. teaches in paragraph [0080] a function which “includes a weighted combination of softened van der Waals, desolvation, electrostatics, hydrogen bonding, disulfide bonding, .pi.-stacking, aliphatic interactions, and rotamer preferences” which reads on claim 11, wherein the plurality of candidate measurements and/or the plurality of reference measurements are selected from the group consisting of solvent accessible surface areas, solvation energies, hydrophobicity, electrostatic interactions, and van der Waals interactions.
Claim 12 is directed to the method of claim 1 but further specifies the candidate molecule to be a peptide.
Aswad et al. and Holley et al. teach the method of claim 1 as outlined above.
Aswad et al. teaches in paragraph [0063] “the method can be employed to identify an immunologically inert fragment of a target protein” which reads on claim 12, wherein the candidate molecule is a peptide, where the inert fragment of a target protein from Aswad et al. is a peptide.
Claim 13 is directed to the method of claim 12 and thus claim 1 but further specifies that the candidate molecule be a neoantigen, non-mutated self-peptide, or a post-translationally modified peptide.
Aswad et al. and Holley et al. teach the method of claims 1 and 12 as outlined above.
Aswad et al. teaches in paragraph [0064] “the method can also be used to identify an auto-antigen in a subject having an autoimmune disease” which reads on claim 13, wherein the candidate molecule is a neoantigen, a viral peptide, a non-mutated self-peptide, or a post-translationally modified peptide.
Claims 3 and 4 are rejected under 35 U.S.C. 103 as being unpatentable over Aswad et al. (US 20150205911 A1) and Holley et al. (Proceedings of the Nation Academy of Sciences (1989) 152-156) as applied to claims 1,2, and 6-13 above, and further in view of Bremel et al. (US 20130330335 A1).
Claim 3 is directed to the method of claim 2 and thus the method of claim 1 but further specifies that the processor is configured to predict the equilibrium dissociation constant of the candidate peptide.
Aswad et al. and Holley et al. teach the method of claims 1 and 2 as outlined above.
Aswad et al. and Holley et al. do not teach the use of the equilibrium dissociation constant of the candidate molecule.
Bremel et al. teaches in paragraph [0121] “the term "affinity" refers to a measure of the strength of binding between two members of a binding pair, for example, an antibody and an epitope and an epitope and a MHC-I or II haplotype. K.sub.d is the dissociation constant and has units of molarity. The affinity constant is the inverse of the dissociation constant. An affinity constant is sometimes used as a generic term to describe this chemical entity. It is a direct measure of the energy of binding.”
It would have been obvious at the time of first filing to modify the teachings of Aswad et al. for the method of claims 1 and 2, with the methods of Bremel et al. to use the method of calculating and predicting affinity using the equilibrium dissociation constant. A person of ordinary skill in the art would have had a reasonable expectation of success as both Aswad et al. and Bremel et al. were both successful in using various structural and chemical aspects of molecules to predict binding affinities for molecules. Therefore, it would have been obvious to a person of ordinary skill in the art to modify the teachings of each and to be successful.
Claim 4 is directed to the method of claim 2 and thus the method of claim 1 but further specifies that the processor is configured to predict the half maximal inhibitory concentration of the candidate molecule.
Aswad et al. and Holley et al. teach the method of claims 1 and 2 as outlined above.
Aswad et al. and Holley et al. does not teach the use of the half maximal inhibitory concentration of the candidate molecule.
Bremel et al. teaches in paragraph [0121] “Affinity may also be expressed as the ic50 or inhibitory concentration 50, that concentration at which 50% of the peptide is displaced. Likewise, ln(ic50) refers to the natural log of the ic50”.
It would have been obvious at the time of first filing to modify the teachings of Aswad et al. for the method of claims 1 and 2, with the methods of Bremel et al. to use the method of calculating and predicting affinity using the half maximal inhibitory concentration. A person of ordinary skill in the art would have had a reasonable expectation of success as both Aswad et al. and Bremel et al. were both successful in using various structural and chemical aspects of molecules to predict binding affinities for molecules. Therefore, it would have been obvious to a person of ordinary skill in the art to modify the teachings of each and to be successful.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Aswad et al. (US 20150205911 A1) and Holley et al. (Proceedings of the Nation Academy of Sciences (1989) 152-156) as applied to claims 1,2, and 6-13 above, and further in view of Layton et al. (Biochemistry (2010) 10831-41).
Claim 5 is directed to the method of claim 21 but further specifies that the processor is configured to predict the melting temperature of candidate molecule when bound to the second molecule.
Aswad et al. and Holley et al. teach the method of claims 1 and 2 as outlined above.
Aswad et al. and Holley et al. does not teach the use of the melting temperature of the candidate molecule.
Layton et al. teaches in the abstract “We determine affinity constants by analysis of ligand-mediated shifts in melting-temperature midpoint values. Ligand affinity is determined in a ligand titration series from shifts in free energies of stability at a common reference temperature”, reading on wherein the artificial neural network is configured to predict the melting temperature (Tm) of the candidate molecule when bound to the second molecule, and wherein each reference molecule has a known Tm when bound to the second molecule.
It would have been obvious at the time of first filing to modify the teachings of Aswad et al. and Holley et al. for the method of claims 1 and 2 with the teachings of Layton et al. for the use of melting-temperature in predicting affinity to therefore predict melting-temperature from affinity given that a computational relationship exists between the two measures. One would have had a reasonable expectation of success given that Layton et al. is merely performing the method of claim 5 but in reverse. Therefore, it would have been obvious to a person of ordinary skill in the art to modify the teachings of each and to be successful.
Response to Affidavit
The Declaration under 37 CFR 1.132 filed 1/30/2026 is insufficient to overcome the rejection of claims 1-2, 5-9, and 11-13 based upon 35 U.S.C 103 as set forth in the last Office action because:
Applicant asserts Aswad et al. does not teach the same approach of using features derived from 3D structures to train a neural network. Examiner agrees, which is why Holley et al. was used to cure said deficiencies. Applicant asserts that Holley et al. does not use 3D structure which is differentiated from secondary/tertiary structure in the literature. Examiner agrees, which is why Aswad et al. was used to cure said deficiencies.
Response to Arguments
Applicant's arguments filed 1/30/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 2 of the Remarks filed 1/30/2026 that the cited references of Aswad et al. and Holly et al. do not raise a prima facie case of obviousness as they do not teach every element of the claims. Specifically, applicant states that the use of Holly et al.to cure the deficiencies of Aswad et al. fails in so much as the “use of secondary structure is distinct from the use of three-dimensional structures, as tertiary structure is a much more complex arrangement of secondary structural elements”. However, Aswad et al. teaches in paragraph [0026] “As used herein, the term "sequence information", in the context of inputting sequence information, is intended to include inputting an identifier for a sequence, inputting a sequence, and inputting structure information for a sequence (e.g., the atomic coordinates of a sequence)”, the latter of which is tertiary structure. In addition, applicant asserts that the features extracted by Holly et al. are from amino acid sequences, however the above citation would inherently include three-dimensional features for any machine learning algorithm applied to such information. Finally, applicant arguments indicate that claims are limited to tertiary structure, but claims and arguments merely recite “each candidate measurement is associated with at least one feature of the candidate structural representation”. It is arguable that secondary structure is part of the three-dimensional representation since the types of secondary structures control where those atoms that end up in in tertiary structure are to a certain extent and thus it is still a feature of any three-dimensional representation. Therefore, the arguments are not commensurate in scope with the claims.
Applicant further asserts on page 2 and 3 of the Remarks filed 1/30/2026 that the cited reference Holly et al. possesses differences between the results of the claimed method, of which were acknowledged in the previous application. However, in the previous application, examiner provided an evidentiary reference which clearly shows a relation between structure of molecules and their corresponding binding affinities, let alone the cited reference of Aswad et al. which teaches in paragraph [0073] “A multi-parametric scoring function will be used to rank the top pMHCII complexes based on affinity”, as well as previously cited evidentiary references Gomes et al. (arXiv preprint (2017)) and Hu et al. (bioRxiv (2017)) which teach the ubiquitous use of neural networks within the field of chemical prediction for numerical values and on page 155, column 2 Holley et al. says “…the neural network method is generally more accurate than prior methods when compared on identical proteins… An important observation from this method is that prediction strength is correlated with prediction accuracy”.
Applicant further asserts on page 3 and 4 of the Remarks filed 1/30/2026 that it would not have been obvious to incorporate the neural network of Holly et al. into the method of Aswad et al. specifically citing portions of Holly et al. which at the time showed that the accuracy was well below applications such as tertiary structure. However, applicant conveniently leaves out that the time frame of Holly et al. was 1989, as well as the previously cited evidentiary references Gomes et al. (arXiv preprint (2017)) and Hu et al. (bioRxiv (2017)) which teach the ubiquitous use of neural networks within the field of chemical prediction for numerical values, including binding affinity, the former of which specifically uses three-dimensional spatial convolution of protein structure to predict binding affinity.
Finally on page 4 of the Remarks filed 1/30/2026, applicant asserts that binding affinity and secondary structure are distinct. However, examiner never stated that binding affinity and secondary structure are not distinct, rather that in view of the evidentiary references neural network models for predicting binding affinity using structure are both common within the field and obvious in view of the method of Aswad et al. and the neural network of Holly et al.
Conclusion
All claims are identical to or patentably indistinct from, or have unity of invention with claims in the application prior to the entry of the submission under 37 CFR 1.114 (that is, restriction (including a lack of unity of invention) would not be proper) and all claims could have been finally rejected on the grounds and art of record in the next Office action if they had been entered in the application prior to entry under 37 CFR 1.114. Accordingly, THIS ACTION IS MADE FINAL even though it is a first action after the filing of a request for continued examination and the submission under 37 CFR 1.114. See MPEP § 706.07(b). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
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 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.
/K.N.A./Examiner, Art Unit 1687
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685