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 .
Applicant’s amendments and arguments filed 5/26/2026 are acknowledged and entered.
Withdrawn Rejections/Objections
The objection to the specification in the Office Action mailed 2/6/2026 is withdrawn in view of the amendments filed 5/26/2026.
The objection to the drawings in the Office Action mailed 2/6/2026 is withdrawn in view of the amendments filed 5/26/2026.
The rejection of claims 4, 8-9, 23, 27-28, and 41 under 35 U.S.C. §112, Second Paragraph, in the Office action mailed 2/6/2026 is withdrawn in view of the amendments filed 5/26/2026.
Rejections and/or objections not reiterated from previous office actions are hereby withdrawn. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Claim Status
Claims 1-2, 4-21, 23-41 are pending.
Claims 3, and 22 are cancelled.
Claims 1-2, 4-21, 23-41 are rejected.
Specification
Response to Amendment
In view of applicant’s amendments to the specifications, previous objections to the specification regarding use of tradenames and hyperlinks have been withdrawn.
Drawings
Response to Amendment
In view of applicant’s amendments to the specification, previous objections to the drawings regarding minor informalities have been withdrawn.
Claim Rejections - 35 USC § 112
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 112 for use of tradenames in the claims and indefiniteness have been withdrawn.
Claim Rejections - 35 USC § 101
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 101 for directing the invention to abstract ideas without significantly more have been reviewed, updated, and provided below.
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 1-2, 4-21, and 23-41 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, system and CRM for determining protein-protein interaction affinity. The judicial exception is not integrated into a practical application because while the pending claims attempt to integrate 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 simply 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 statutory subject matter (a process, machine, manufacture, or composition of matter)? [see MPEP § 2106.03]
Claims are directed to statutory subject matter, specifically methods (claims 1-19, and 40-41), a system (claims 19-38), a CRM (claim 39).
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, 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, 20, 39, and 40: Determining a low energy score state, generating an energy score, and determining a score difference between the energy scores are process of comparing/contrasting and calculating that can be done via pen and paper or within the human mind are therefore abstract ideas, specifically mental processes. Generating an energy score, and determining a score difference between the energy scores are verbal articulation of a mathematical process and are therefore abstract ideas, specifically mathematical concepts.
Claims 2, 21: The top number of hypotheses comprising at least 5 is merely a process of selecting the top number of outputs which can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claims 6, 25: Using a relax algorithm to determine the low energy score state is a process of calculating that can be done via pen and paper or within the human mind is therefore an abstract idea, specifically a mental process. Using a relax algorithm to determine the low energy score state is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claims 7, 26: Applying the relax algorithm to side chain and backbone 3D structures is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claims 8, 27: The relax algorithm being one of those specified is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claims 9, 28: Generating the energy scores via the score function is a process of calculating that can be done via pen and paper or within the human mind is therefore an abstract idea, specifically a mental process. Generating the energy scores via the function is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claims 16, 35: Selecting at least one interaction of residue pairs, and substituting at least one amino acid of the protein sequence are process of choosing and modifying data that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claims 17, 36: The selection of the at least one interaction of residue pairs being based on one of the specified criteria is merely a process of selecting which can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claims 18, 37: Substituting an amino acid having a relatively low binding energy is a process of calculating, altering, and comparing/contrasting that can be done via pen and paper or within the human mind is therefore an abstract idea, specifically a mental process.
Claims 19, 38: Substituting an amino acid having a higher binding energy is a process of calculating, altering, and comparing/contrasting that can be done via pen and paper or within the human mind is therefore 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, 20, 39, and 40: Obtaining amino acid sequence data, feeding the sequence data into a deep learning model, obtaining 3D structure data, feeding sequence data into a trained second deep learning model, the deep learning model comprising the specified structure, and obtaining a 3D structure model of the protein-protein complex are insignificant extra solution activities, specifically necessary data gathering/inputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)]. A system, memory, computer-readable instructions, a processor, computer program product, and a computer are generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)].
Claims 2, 21: Sampling a protein conformational space to find the lowest energy scores is an insignificant extra solution activity, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 4, 23: The first and second deep learning model comprising at least one of the models specified is an insignificant extra solution activity, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 5, 24: The second deep learning model being the first deep learning model is an insignificant extra solution activity, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 10, 29: The first and second protein parts comprising CDR loops is an insignificant extra solution activity, specifically necessary data outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 11, 30: The first protein part comprising an antigen is an insignificant extra solution activity, specifically necessary data outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 12, 31: The second protein part comprising an antibody is an insignificant extra solution activity, specifically necessary data outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 13, 32: Feeding a third input and the protein -protein complex comprising a known binding site complex are insignificant extra solution activities, specifically necessary data gathering and outputting, respectively (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 14, 33: The known binding site complex comprising a mutation of the sequence is an insignificant extra solution activity, specifically necessary data outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
Claims 15, 34: The amino acid sequence comprising FASTA format sequence data is an insignificant extra solution activity, specifically necessary data outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)].
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, nonspecific, or insignificant extra solution activity. These additional elements include:
The additional elements of a system, memory, computer-readable instructions, a processor, computer program product, and a computer are generic and nonspecific elements of a computer that are well-understood, routine and conventional within the art and therefore do not improve the functioning of any computer or technology described therein (See 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 2106.05(d)(II)]. Therefore, taken both individually and as whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of obtaining amino acid sequence data (Conventional: Edmunds et al. 2021 – Page 23 Abstract), feeding the sequence data into a deep learning model (Conventional: Edmunds et al. 2021), obtaining 3D structure data (Conventional: Edmunds et al. 2021), feeding sequence data into a trained second deep learning model (Conventional: Edmunds et al. 2021), the deep learning model comprising the specified structure (Conventional: Lorenza et al. pages 89-91, Subheading Network Architecture), feeding a third input (Conventional: Edmunds et al. 2021), sampling a protein conformational space to find the lowest energy scores (Conventional: Edmunds et al. 2021), the first and second deep learning model comprising at least one of the models specified (Conventional: Edmunds et al. 2021), the second deep learning model being the first deep learning model (Conventional: Edmunds et al. 2021), applying the relax algorithm to side chain and backbone 3D structures (Conventional: Edmunds et al. 2021), the relax algorithm being one of those specified (Conventional:), obtaining a 3D structure model of the protein-protein complex (Conventional: Edmunds et al. 2021), the first and second protein parts comprising CDR loops (Conventional: Edmunds et al. 2021 – Page 30), the first protein part comprising an antigen (Conventional: Edmunds et al. 2021 – Page 58), the second protein part comprising an antibody (Conventional: Edmunds et al. 2021 – Page 58), the protein - protein complex comprising a known binding site complex (Conventional: Edmunds et al. 2021 – Page 58), the known binding site complex comprising a mutation of the sequence (Conventional: Edmunds et al. 2021), and the amino acid sequence comprising FASTA format sequence data (Conventional: Edmunds et al. 2021 - Page 29) are insignificant extra solution activities, specifically necessary data gathering/inputting/outputting (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968, OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also 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)) [See MPEP § 2106.05(g)]. Therefore, taken both individually and as whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 1-2, 4-21, and 23-41, when the limitations are considered individually and as a whole, are rejected
under 35 USC § 101 as being directed to non-statutory subject matter.
Response to Arguments
Applicant's arguments filed 5/26/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 21 of the Remarks filed 5/26/2026 that the claims do not recite a mental process or mathematical step as the steps involved cannot be practically performed within the human mind or with pen and paper, and recites the model structure, inclusion of an evoformer, as well as the data size as evidence of this.
This argument is not persuasive. The courts do not distinguish between scales of information sizes, rather an abstract idea is based upon the information types, i.e. the amount of information, or the scale of operations is not what qualifies or disqualifies a limitation from being an abstract idea, rather it is the process itself and the information itself which do, such as in Example 39 from the Subject Matter Eligibility Examples. Furthermore, MPEP 2106.04(a)(2)(III) states - Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind” [See Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘‘[W]ith the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’)].
Applicant asserts on page 22 of the Remarks filed 5/26/2026 that the claims integrate any exception into a practical application. Additionally, applicant asserts the production of a concrete and useful result of an affinity score. This argument is not persuasive. An affinity score is not a concrete thing, but rather the judicial exception itself, as this is merely data representation of how well two molecules bind. MPEP 2106.05(c) which discusses the particular transformation specifically states in paragraph 5 - An "article" includes a physical object or substance. The physical object or substance must be particular, meaning it can be specifically identified. "Transformation" of an article means that the "article" has changed to a different state or thing. Changing to a different state or thing usually means more than simply using an article or changing the location of an article. A new or different function or use can be evidence that an article has been transformed. Purely mental processes in which thoughts or human based actions are "changed" are not considered an eligible transformation. Furthermore, the practical application cannot also be an improvement to technology as according to MPEP 2106.05(a) - It is important to note, the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements. Finally, the system itself is not integral to the claim as MPEP 2106.05(b) states - It is important to note that a general purpose computer that applies a judicial exception, such as an abstract idea, by use of conventional computer functions does not qualify as a particular machine, and the accompanying additional elements have been shown to be nothing more than mere generic computer elements or elements that are well-understood, routine and conventional within the art.
Applicant asserts on page 23 of the Remarks filed 5/26/2026 that the claims recite an ordered combination that is not well-understood, routine or conventional within the field and amount to significantly more. However, examiner has provided cited art, Lorenza et al., that is a review of the structural methods used in protein folding prediction including the amended limitations, showing them to be well-understood, routine, and conventional within the field.
Claim Rejections - 35 USC § 103
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 103 for obviousness have been reviewed, updated, and 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, 3-9, 15-16, 18-19, 20-21, 23-28, 34-35, and 37-41 are rejected under 35 U.S.C. 103 as being unpatentable over Evans et al. (biorxiv (2021) 1-25; previously cited), in view of Edmunds et al. (Structural Proteomics: High-Throughput Methods (2021) 23-52; previously cited) and Lorenza et al. (Fusion of Multidisciplinary Research, An International Journal 1.2 (2020): 85-96; newly cited).
Claim 1 is directed to a method for determining protein-protein interaction affinity using two neural networks one to predict protein structure and the other to predict the structure of the protein-protein complex, and determining from that an energy score for both the complex and the individual proteins.
Claim 20 is directed to a system for determining protein-protein interaction affinity using two neural networks one to predict protein structure and the other to predict the structure of the protein-protein complex, and determining from that an energy score for both the complex and the individual proteins.
Claim 39 is directed to a computer program product for determining protein-protein interaction affinity using two neural networks one to predict protein structure and the other to predict the structure of the protein-protein complex, and determining from that an energy score for both the complex and the individual proteins.
Claim 40 is directed to a method for determining protein-protein interaction affinity using two neural networks one to predict protein structure and the other to predict the structure of the protein-protein complex, and determining from that an energy score for both the complex and the individual proteins.
Evans et al. teaches in the abstract “In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy” and in the abstract “…we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer…”, it is inherent to the Alphafold-Multimer platform that it is based on the Alphafold 2 platform (Evidentiary Reference: AlphaFold Multimer Cosmic2) which uses two neural networks that are integrated into a single network to predict a protein structure (Evidentiary Reference: AlphaFold2 Description), or in the case of Alphafold-Multimer a protein complex, and Evans et al. teaches on page 1, paragraph 3 “it combines information from the amino acid sequence, multiple sequence alignments and homologous structures in order to predict the structure of individual protein chains”, reading on a computerized method for determining protein-protein interaction affinity, comprising: obtaining, from an amino acid sequence database, amino acid sequence data corresponding to a first protein part and a second protein part; feeding the amino acid sequence data corresponding to the first protein part and the second protein part, respectively, into a trained first deep learning model, wherein the trained first deep learning model is trained to predict a 3D structure model based on a first input of amino acid sequence data corresponding to a protein part; obtaining 3D structure models of the first protein part and the second protein part predicted by the trained first deep learning model; feeding the amino acid sequence data corresponding to the first protein part and the second protein part into a trained second deep learning model, wherein the trained second deep learning model is trained to predict a 3D structure model of a protein-protein complex based on a second input of amino acid sequence data corresponding to protein-protein complex parts; obtaining a 3D structure model of the protein-protein complex comprising the first protein part and the second protein part predicted by the trained second deep learning model.
Edmunds et al. teaches on page 31, paragraph 4 “Early versions of quality checks focused on stereochemical calculations measuring, amongst others, bond angles, steric clashes, and Ramachandran outliers. Others were based on calculating an energy score based on the model’s perceived distance from a hypothetical free energy minimum. The so-called energy function checks fell broadly into two groups: those calculating a statistical score by analyzing the model against known protein structures and those calculating an empirically derived energy score from force field and molecular dynamic data… Current MQAPs (a selection listed in Table 5) attempt to overcome these shortcomings by combining a number of approaches. Firstly, as well as giving a global score for the overall model many programs will also give a local, or per residue score which assesses each amino acid residue and the favorability of the surroundings in which it finds itself in the proposed chain… in addition to basic stereochemical checks and energy considerations…”, on page 32 paragraph 3 “Refinement is the process of taking a raw model and attempting to improve its quality score by making small changes to the 3D structure in the hope and expectation that the newly produced model will be closer to the native protein than the original. Refinement programs essentially perform two separate functions; the first is one of sampling, that is, to create improved 3D models from those already built by the modeling software (often by MD employing the AMBER or CHARMM force fields) and the second is one of scoring these models, mostly via energy functions (such as DFIRE, RWPlus, and Rosetta), so that improvements can easily be identified”, and on page 41 “Rosetta algorithms then perform 3-D modeling on a domain by domain basis and also check potential interface areas by Alanine scanning (each amino acid is in-turn replaced by Alanine and the effect on the calculated binding energy computed) for binding and interaction prediction”, reading on determining a low energy score state for the 3D structure models of each of the first protein part, the second protein part, and the protein-protein complex; generating, based on the low energy score states, an energy score for the 3D structure models of each of the first protein part, the second protein part, and the protein-protein complex; and determining a score difference between the energy score for the 3D structure model of the protein-protein complex and a sum of the energy scores for the 3D structure models of the first protein part and the second protein part, wherein the score difference defines a binding affinity score.
Lorenza et al. teaches on page 87, paragraph 2 “Novel Neural Network Architectures: AlphaFold incorporates several novel neural network architectures and training procedures, such as: The "Evoformer" block, which jointly embeds multiple sequence alignments (MSAs) and pairwise features. An end-to-end structure prediction output representation and associated loss function. A new equivariant attention architecture. Iterative refinement of predictions using intermediate losses. Masked MSA loss to jointly train with the structure. Learning from unlabeled protein sequences using self-distillation. Evolutionary, Physical, and Geometric Constraints: AlphaFold’s neural networks are trained on evolutionary, physical, and geometric constraints of protein structures, enabling it to capture the intricate relationships between amino acid sequences and their corresponding three-dimensional conformations”, and on page 89, paragraph 3 “Preprocessing: This component prepares the input data, including the protein sequence, multiple sequence alignment (MSA), and structural templates. Evoformer: The Evoformer is a novel transformer-based architecture that processes the input data. It uses a two-tower design, with one tower attending to the MSA and the other to the pair representation. Key innovations in the Evoformer include: Triangle multiplicative updates and triangle self-attention. Explicit modeling of the evolutionary and structural information. Structure Module: This module introduces an explicit 3D structure representation and refines it iteratively. It models the protein as a "residue gas" and predicts affine transformations to position the residues in 3D space. The Invariant Point Attention (IPA) module is a key innovation in this component”, reading on wherein the trained first deep learning model comprises a system of sub-networks coupled together into a single end-to-end model trained as a single integrated structure, the system of sub- networks comprising an evoformer module and a structure prediction module, the evoformer module configured to progressively refine vectors of information for relationships between amino acid residues using an attention mechanism learned from Multiple Sequence Alignment data, and the structure prediction module configured to generate a 3D structure prediction based on output of the evoformer module.
It would have been obvious at the time of invention to modify the teachings of Evans et al. for the method of Alphafold-Multimer, with the teachings of Edmunds et al. for determining low energy score states and differences as Edmunds et al. teaches on page 31, the use of such score states is what early models were based on, and in fact such is Rosetta, which is later referred to in both Edmunds et al. and the claims of the instant application. Furthermore, it would have been obvious to combine the teachings of Evans et al. and Edmunds et al. for the method, system, and CRM of claims 1, 20, 39, and 40, with the teachings of Lorenza et al. for the specified network architecture as the latter describes within the abstract “This abstract underscores the transformative impact of machine learning on protein function prediction, highlighting its potential to enhance our understanding of complex biological systems and drive advancements in biomedical research”. One would have had a reasonable expectation of success given that Edmunds et al. serves as an overview and review of the current methods within the field of protein structure prediction and Evans et al. is merely the newest (at the time) method within said field and is based on a method (Alphafold and Alphafold 2) that are cited within Edmunds et al. (page 37). Additionally, one would have had a reasonable expectation of success given that Edmunds et al. is using the same method whose network architecture is described in Lorenza et al. for AlphaFold. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 2 is directed to the method of claim 2 and thus claim 1, but further specifies that the number of hypotheses comprise at least 5.
Claim 21 is directed to the system of claim 21 and thus claim 20, but further specifies that the number of hypotheses comprise at least 5.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group… Rosetta algorithms then perform 3-D modeling on a domain by domain basis and also check potential interface areas by Alanine scanning (each amino acid is in-turn replaced by Alanine and the effect on the calculated binding energy computed) for binding and interaction prediction”, and page 45 Table 10, it is inherent to the Rosetta program that through the use of random seeds for Monte Carlo sampling of the conformational space and predicts binding affinities of at least the top 100 low energy structures (Evidentiary Reference: Rosetta Documentation 2), therefore reading on wherein the top predetermined number of hypotheses comprises at least five hypotheses.
Claim 4 is directed to the method of claim 1 but further specifies that the deep learning model comprise one of the models specified.
Claim 23 is directed to the system of claim 20 but further specifies that the deep learning model comprise one of the models specified.
Evans et al. teaches in the abstract “In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer…”, reading on wherein the first deep learning model and the second deep learning model comprise at least one of the following: a deep learning model trained to predict protein 3D structure from amino acid sequence data, a deep learning model trained to predict multimeric protein 3D structures from amino acid sequence data, a deep learning model trained to predict antibody 3D structure from amino acid sequence data, a deep learning model trained to predict complementarity-determining region loop 3D structure from amino acid sequence data.
Claim 5 is directed to the method of claim 4 and thus claim 1, but further specifies that the first deep learning model is the second deep learning model.
Claim 24 is directed to the system of claim 23 and thus claim 20, but further specifies that the first deep learning model is the second deep learning model.
Evans et al. teaches in the abstract “In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy”, and in the abstract “…we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer…”, it is inherent to the Alphafold-Multimer platform that it is based on the Alphafold 2 platform which uses two neural networks that are integrated into a single network to predict a protein structure, or in the case of Alphafold-Multimer a protein complex, reading on wherein the second deep learning model is the first deep learning model.
Claim 6 is directed to the method of claim 1 but further specifies the use of a relax function to determine the low energy score state for the 3D structure models.
Claim 25 is directed to the system of claim 20 but further specifies the use of a relax function to determine the low energy score state for the 3D structure models.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Robetta platform, “Robetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group”, it is inherent to the Rosetta program to use the Rosetta Relax function to find low-energy conformations of a protein structure (Evidentiary Reference: Rosetta Documentation), thereby reading on further comprising using a relax algorithm to determine the low energy score state for the 3D structure models of each of the first protein part, the second protein part, and the protein-protein complex.
Claim 7 is directed to the method of claim 6 and thus claim 1, but further specifies that the relax algorithm is applied to amino acid side chains and backbone structure of the protein parts and complex.
Claim 26 is directed to the system of claim 25 and thus claim 20, but further specifies that the relax algorithm is applied to amino acid side chains and backbone structure of the protein parts and complex.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group”, it is inherent to the Rosetta program to use the Rosetta Relax function to find low-energy conformations of a protein structure (Evidentiary Reference: Rosetta Documentation) and furthermore Edmunds et al. teaches on page 41, paragraph 5, “Users can paste (FASTA) or upload an amino acid sequence and also upload templates or alignments of their own if required”, which would include the entirety of the protein including backbone, side-chain, etc., thereby reading on wherein the relax algorithm is applied to amino acid side chain and backbone 3D structure models of each of the first protein part, the second protein part, and the protein-protein complex.
Claim 8 is directed to the method of claim 6 and thus claim 1, but further specifies that the relax algorithm comprise a physics-based and statistics-based relaxation algorithm that minimizes a score function comprising a weighted sum of physical and statistical energy terms.
Claim 27 is directed to the system of claim 25 and thus claim 20, but further specifies that the relax algorithm comprise a physics-based and statistics-based relaxation algorithm that minimizes a score function comprising a weighted sum of physical and statistical energy terms.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group”, it is inherent to the Rosetta program to use the Rosetta Relax function to find low-energy conformations of a protein structure (Evidentiary Reference: Rosetta Documentation), thereby reading on wherein the relax algorithm comprises at least one of the following: a physics-based and statistics-based relaxation algorithm that minimizes a score function comprising a weighted sum of physical and statistical energy terms.
Claim 9 is directed to the method of claim 8 and thus claim 1, but further specifies that the energy scores are generated using the score function of the physics-based and statistics-based relaxation algorithm.
Claim 28 is directed to the system of claim 27 and thus claim 20, but further specifies that the energy scores are generated using the score function of the physics-based and statistics-based relaxation algorithm.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group”, it is inherent to the Rosetta program to use the Rosetta Relax function to find low-energy conformations of a protein structure (Evidentiary Reference: Rosetta Documentation), thereby reading on wherein the energy scores for the 3D structure models of each of the first protein part, the second protein part, and the protein-protein complex are generated using the score function of the physics-based and statistics-based relaxation algorithm.
Claim 15 is directed to the method of claim 1 but further specifies that the amino acid sequence data comprise FASTA format sequence data.
Claim 34 is directed to the method of claim 20 but further specifies that the amino acid sequence data comprise FASTA format sequence data.
Evans et al. teaches in the abstract “In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer, significantly increases accuracy of predicted multimeric interfaces over input-adapted single-chain AlphaFold while maintaining high intra-chain accuracy” and in the abstract “…we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer…”, it is inherent to the Alphafold-Multimer platform that it is based on the Alphafold 2 platform which uses FASTA format for inputting protein sequences (Evidentiary Reference: AlphaFold Multimer Cosmic2), reading on wherein the amino acid sequence data corresponding to a first protein part and a second protein part comprises FASTA format sequence data.
Claim 16 is directed to the method of claim 1 but further specifies selecting residues in the protein interface and substituting them to control binding affinity.
Claim 35 is directed to the system of claim 20 but further specifies selecting residues in the protein interface and substituting them to control binding affinity.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group… Rosetta algorithms then perform 3-D modeling on a domain by domain basis and also check potential interface areas by Alanine scanning (each amino acid is in-turn replaced by Alanine and the effect on the calculated binding energy computed) for binding and interaction prediction”, and page 45 Table 10, and on page 45, paragraph 2 “A number of different docking approaches have been developed to predict protein–protein interactions… All approaches have had success over the rounds of CAPRI experiments… RosettaDock has also enjoyed success, predicting all 5 small targets with medium to high accuracy”, it is inherent to the Rosetta program to substitute amino acids in protein interfaces to examine binding affinities using Monte Carlo sampling of the conformational space, reading on selecting at least one interaction of residue pairs in interfaces between the first and second protein sequences based on the binding affinity score; and substituting at least one amino acid of the first or second protein sequences to control a binding affinity for the at least one interaction of residue pairs.
Claim 18 is directed to the method of claim 16 and thus claim 1, but further specifies the substitution as going from a low binding affinity to a high binding affinity.
Claim 37 is directed to the system of claim 35 and thus claim 20, but further specifies the substitution as going from a low binding affinity to a high binding affinity.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group… Rosetta algorithms then perform 3-D modeling on a domain by domain basis and also check potential interface areas by Alanine scanning (each amino acid is in-turn replaced by Alanine and the effect on the calculated binding energy computed) for binding and interaction prediction”, on page 45 Table 10, and on page 45, paragraph 2 “A number of different docking approaches have been developed to predict protein–protein interactions… All approaches have had success over the rounds of CAPRI experiments… RosettaDock has also enjoyed success, predicting all 5 small targets with medium to high accuracy”, it is inherent to the Rosetta program to substitute amino acids in protein interfaces to examine binding affinities using Monte Carlo sampling of the conformational space (Evidentiary Reference: Rosetta Documentation 2) and therefore would be prima facie obvious to substitute for those amino acids that either increase or decrease affinity depending on the goal of the project, and would therefore read on wherein substituting the at least one amino acid comprises substituting an amino acid having a relatively low binding energy with respect to a binding energy mean for a corresponding protein sequence to increase the binding affinity for the at least one interaction of residue pairs.
Claim 19 is directed to the method of claim 16 and thus claim 1, but further specifies the substitution as going from a high binding affinity to a low binding affinity.
Claim 38 is directed to the system of claim 35 and thus claim 20, but further specifies the substitution as going from a high binding affinity to a low binding affinity.
Edmunds et al. teaches on page 41, paragraph 4 the use of the Rosetta platform, “Rosetta is the public-facing webpage of the Rosetta server prediction program developed by the Baker lab at the University of Washington, USA, and now administered by the Rosetta Commons group… Rosetta algorithms then perform 3-D modeling on a domain by domain basis and also check potential interface areas by Alanine scanning (each amino acid is in-turn replaced by Alanine and the effect on the calculated binding energy computed) for binding and interaction prediction”, on page 45 Table 10, and on page 45, paragraph 2 “A number of different docking approaches have been developed to predict protein–protein interactions… All approaches have had success over the rounds of CAPRI experiments… RosettaDock has also enjoyed success, predicting all 5 small targets with medium to high accuracy”, it is inherent to the Rosetta program to substitute amino acids in protein interfaces to examine binding affinities using Monte Carlo sampling of the conformational space (Evidentiary Reference: Rosetta Documentation 2) and therefore would be prima facie obvious to substitute for those amino acids that either increase or decrease affinity depending on the goal of the project, and would therefore read on wherein substituting the at least one amino acid comprises substituting an amino acid having a relatively high binding energy with respect to a binding energy mean for a corresponding protein sequence to decrease the binding affinity for the at least one interaction of residue pairs.
Claim 41 is directed to the method of claim 40 but further specifies that the model be a deep learning model trained to predict multimeric protein 3D structures from amino acid sequence data.
Evans et al. teaches in the abstract “In this work, we demonstrate that an AlphaFold model trained specifically for multimeric inputs of known stoichiometry, which we call AlphaFold-Multimer…”, reading on wherein the trained deep learning model comprises a deep learning model trained to predict multimeric protein 3D structures from amino acid sequence data.
Claims 10-14, 17, 29-33, and 36 are rejected under 35 U.S.C. 103 as being unpatentable over Evans et al. (biorxiv (2021) 1-25; previously cited), Edmunds et al. (Structural Proteomics: High-Throughput Methods (2021) 23-52; previously cited), and Lorenza et al. (Fusion of Multidisciplinary Research, An International Journal 1.2 (2020): 85-96; newly cited) as applied to claims 1-9, 15, 20-28, 34, and 41 above, and further in view of Weitzner et al. (Nature protocols (2017) 401-416; previously cited).
Claim 10 is directed to the method of claim 1 but further specifies that the protein parts comprise flexible complementary-determining regions.
Claim 29 is directed to the system of claim 20 but further specifies that the protein parts comprise flexible complementary-determining regions.
Evans et al., Edmunds et al., and Lorenza et al. teach the method of claim 1 and the system of claim 20 as previously described.
Evans et al., Edmunds et al., and Lorenza et al. do not teach that the protein parts comprise flexible complementary-determining regions.
Weitzner et al. teaches in the abstract “We describe Rosetta-based computational protocols for predicting the 3D structure of an antibody from sequence… Antibody modeling leverages canonical loop conformations to graft large segments from experimentally determined structures, as well as offering (i) energetic calculations to minimize loops, (ii) docking methodology to refine the VL–VH relative orientation and (iii) de novo prediction of the elusive complementarity determining region (CDR) H3 loop”, reading on wherein the first protein part and the second protein part each comprise flexible complementary-determining region (CDR) loop structures.
It would have been obvious at the time of invention to modify the teachings of Evans et al., Edmunds et al., and Lorenza et al. for the method of claims 1 and 20 with the teachings of Weitzner et al. for modeling and docking of antibody structures using Rosetta as that is one of the models described in detail for structure and complex modeling in Edmunds et al., and is described as having success predicting CAPRI simulations. One would have had a reasonable expectation of success given that all three papers are within the same field and using either similar or identical methods and are merely extending them to additional situations. Therefore, it would have been obvious at the time of filing to have modified the teachings of each and to be successful.
Claim 11 is directed to the method of claim 10 and thus claim 1, but further specifies that the first protein part be an antigen.
Claim 20 is directed to the system of claim 29 and thus claim 20, but further specifies that the first protein part be an antigen.
Evans et al., Edmunds et al., and Lorenza et al. teach the method of claim 1 and the system of claim 20 as previously described.
Evans et al., Edmunds et al., and Lorenza et al. do not teach that the first protein part be an antigen.
Weitzner et al. teaches in the abstract “We describe Rosetta-based computational protocols for predicting the 3D structure of an antibody from sequence… Antibody modeling leverages canonical loop conformations to graft large segments from experimentally determined structures, as well as offering (i) energetic calculations to minimize loops, (ii) docking methodology to refine the VL–VH relative orientation and (iii) de novo prediction of the elusive complementarity determining region (CDR) H3 loop. To alleviate model uncertainty, antibody–antigen docking resamples CDR loop conformations and can use multiple models to represent an ensemble of conformations for the antibody, the antigen or both. These protocols can be run fully automated via the ROSIE web server”, reading on wherein the first protein part comprises an antigen (Ag).
Claim 12 is directed to the method of claim 11 and thus claim 1, but further specifies that the second protein part comprise an antibody.
Claim 31 is directed to the system of claim 30 and thus claim 20, but further specifies that the second protein part comprise an antibody.
Evans et al., Edmunds et al., and Lorenza et al. teach the method of claim 1 and the system of claim 20 as previously described.
Evans et al., Edmunds et al., and Lorenza et al. do not teach that the second protein part comprise an antibody.
Weitzner et al. teaches in the abstract “We describe Rosetta-based computational protocols for predicting the 3D structure of an antibody from sequence… Antibody modeling leverages canonical loop conformations to graft large segments from experimentally determined structures, as well as offering (i) energetic calculations to minimize loops, (ii) docking methodology to refine the VL–VH relative orientation and (iii) de novo prediction of the elusive complementarity determining region (CDR) H3 loop. To alleviate model uncertainty, antibody–antigen docking resamples CDR loop conformations and can use multiple models to represent an ensemble of conformations for the antibody, the antigen or both. These protocols can be run fully automated via the ROSIE web server”, reading on wherein the second protein part comprises an antibody (Ab).
Claim 13 is directed to the method of claim 1 but further specifies that the complex comprises a known binding site complex, and the amino acid sequence includes a third input of the binding site.
Claim 32 is directed to the system of claim 20 but further specifies that the complex comprises a known binding site complex, and the amino acid sequence includes a third input of the binding site.
Evans et al., Edmunds et al., and Lorenza et al. teach the method of claim 1 and the system of claim 20 as previously described.
Evans et al., Edmunds et al., and Lorenza et al. do not teach that the complex comprises a known binding site complex, and the amino acid sequence includes a third input of the binding site.
Weitzner et al. teaches in the abstract “We describe Rosetta-based computational protocols for predicting the 3D structure of an antibody from sequence… Antibody modeling leverages canonical loop conformations to graft large segments from experimentally determined structures, as well as offering (i) energetic calculations to minimize loops, (ii) docking methodology to refine the VL–VH relative orientation and (iii) de novo prediction of the elusive complementarity determining region (CDR) H3 loop. To alleviate model uncertainty, antibody–antigen docking resamples CDR loop conformations and can use multiple models to represent an ensemble of conformations for the antibody, the antigen or both. These protocols can be run fully automated via the ROSIE web server”, and it would be inherent to antibody-antigen docking to comprise the binding site, therefore reading on wherein the protein-protein complex comprises a known binding site complex, and wherein feeding the amino acid sequence data corresponding to the first protein part and the second protein part into the trained second deep learning model comprises feeding a third input comprising the known binding site complex into the trained second deep learning model.
Claim 14 is directed to the method of claim 13 and thus claim 1, but further specifies that the binding site comprises a mutation in the amino acid sequence.
Claim 33 is directed to the system of claim 32 and thus claim 20, but further specifies that the binding site comprises a mutation in the amino acid sequence.
Evans et al., Edmunds et al., and Lorenza et al. teach the method of claim 1 and the system of claim 20 as previously described.
Evans et al., Edmunds et al., and Lorenza et al. do not teach that the binding site comprises a mutation in the amino acid sequence.
Edmunds et al. teaches on page 47, paragraph 6 “Phyre Investigator give access to extra information on model quality analysis, alignment confidence, and Ramachandran analysis as well as catalytic site, mutation analysis…”, reading on wherein the known binding site complex comprises a mutation of the amino acid sequence data corresponding to a first protein part and a second protein part.
Claim 17 is directed to the method of claim 16 and thus claim 1, but further specifies the interaction be between those structures specified.
Claim 36 is directed to the system of claim 35 and thus claim 20, but further specifies the interaction be between those structures specified.
Weitzner et al. teaches in the abstract “We describe Rosetta-based computational protocols for predicting the 3D structure of an antibody from sequence… Antibody modeling leverages canonical loop conformations to graft large segments from experimentally determined structures, as well as offering (i) energetic calculations to minimize loops, (ii) docking methodology to refine the VL–VH relative orientation and (iii) de novo prediction of the elusive complementarity determining region (CDR) H3 loop”, reading on wherein the selection of the at least one interaction of residue pairs is based on at least one of: the at least one interaction comprising a conserved helix structure, a repulsive energy between the potential residue pairs, or a distance between the potential residue pairs.
Response to Arguments
Applicant’s arguments, see pages 23-26 of the Remarks, filed5/26/2026, with respect to the rejections of claims 1-2, 4-21, and 23-41 under 35 U.S.C. 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view ofLorenza et al. .
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 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