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 .
Status of the claims
The supplemental claim set received 17 April 2026 has been entered into the application.
Claims 1-39 are cancelled.
Claims 40-65 are new.
Claims 46 and 64 are objected to.
Claims 40-65 are pending.
Priority
The Application is a Continuation of PCT/IB22/54705 filed 19 May 2022 which closes foreign priority to EP 21382464.2 filed 21 May 2021.
Information Disclosure Statement
The information disclosure statements (IDSs) submitted on 20 November 2023, 01 March 2024, 17 July 2024, 31 October 2024, and 27 November 2024 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
The drawing received 20 November 2023 are accepted and have been entered into the application.
The replacement drawings were received 20 January 2026. These drawing are accepted.
Specification
The specification received 20 November 2023 has been entered into the application.
The amended and substitute specifications received 20 January 2026 have been entered into the application.
Claim Objections
Claim 46 is objected to because of the following informalities: Claim 64 recites “wherein the function is a continuous time dynamic graph function or a a discrete-time dynamic graph function.” The claim should be amended to recite “wherein the function is a continuous time dynamic graph function or a [ discrete-time dynamic graph function.” Appropriate correction is required to address grammatical correctness of the claim.
Claim 60 is objected to because of the following informalities: Claim 60 recites “The system of claim 58, further configured to impute the generated polypeptide structure into a database.” The claim should be amended to recite “The method of claim 58, further configured to impute the generated polypeptide structure into a database.” Appropriate correction is required to address the correctness of the claim.
Claim Rejections - 35 USC § 112
35 USC § 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 47-49 and 58-65 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 40 is drawn to a computing system for performing in silico polypeptide structure generation. Moreover, claims 47-49 recite the system of claim is configured to. However, it is not clear which part of the computer system is being further limited because the claims do not recite which part of the system is configured to perform the steps of claim 47-49. It is recommended to amend the claim to provide which part of the system of claim 40 claims 47-49 are “configured to”.
Claim 58 (c) recites” …biologically relevant…”. The claimed step renders the claim indefinite because the term “biologically relevant” is a relative term. It is not clear what information is considered “biologically relevant” for determining druggability with respect to secondary and tertiary structure information. The mete and bounds of what would be considered “relevant” is unclear.
Claims 41-49 and 59-65 are rejected because they fail to provide limitations to overcome the deficiencies of the base claim(s).
Claim 65 recites the protein therapeutic of claim 64, for use in therapy. The claim is rejected because the claim only recites a use with no steps. See MPEP 2173.05(q).
It is noted that claims 40-65 contain multiple and significant issues that render the scope of the claim’s indefinite. It is recommended to amend the claim set to address the issues raised to obviate the rejection and provide a clear claim set.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 40-65 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim Analysis
Claims 50-57 are drawn to a system. However, the claim 50 do not recite using any processors and/or other hardware such that a system can be claimed. Thus, under Broadest Reasonable Interpretation (BRI), claims 50-57 are interpreted as instructions/method stored on a storage device.
Step I - Process, Machine, Manufacture or Composition
Claim 40-49 are drawn to a system of in silico polypeptide generation, so a machine.
Claims 50-57 are drawn to a method of in silico polypeptide generation, so a process.
Claim 58-63 are drawn to a method of determining druggability of a polypeptide in silico, so a process. However, claims 64 and 65 are drawn to a protein therapeutic obtained from the method of claim 58, so a composition.
Step 2A Prong I - Identification of an Abstract Idea
Claim 40 recites:
(1) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide
This step encompasses performing mathematical computation of Molecular Dynamics simulations using tertiary structure conformation information of the polypeptide (i.e., numerical values) to generate output data (i.e., quantitative data/numerical value/variables) which encompasses using mathematical formulas such as Newton’s Second Law, forces from potential energy, force fields, and time-integration which reads on abstract ideas.
(2) encoding the output data into a function to generate a vector map, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide
This step can be performed can be performed in the human mind by organizing data (i.e., output data) to generate a vector map of residue-specific properties from MD simulations and a pairwise property and is therefore an abstract idea. This step encompasses taking information (i.e., output information), manipulating data via mathematical correlation (i.e., encoding), and organizing the information into a different form (i.e., vector map). See MPEP 2106.04(a)(2)(I)(A)(iv).
(3) applying a machine learning algorithm to the vector map to generate a predicted polypeptide structure based on the at least one residue-specific property and the at least one pairwise property
This step can be performed in the human mind by observing and evaluating residue- specific properties and pairwise properties to generate a polypeptide structure. Here, even though the claimed steps apply a “machine learning algorithm”, the machine learning model is broadly and generically recited and reads on mere instructions to implement an abstract idea on a generic computer and reads on mathematical/statistical computations (i.e., linear region, bootstrap aggregation [Spec page 10 para 39]). See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.04(a)(2)(III)(C)(1-3) and 2106.05(f). Furthermore, it is noted that the claimed step recites “to generate an in-silico polypeptide structure”. Here, the “generated in-silico polypeptide structure” is interpreted as information (i.e., organized amino acid sequence data) and not physical steps for generating a physical polypeptide.
Claim 50 recites:
(a) a first model for performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide
This step encompasses using a first model. Here, even though the claimed step uses “a first model” the first model is broadly and generically recited and reads on mathematical computations. This step encompasses performing mathematical computation of Molecular Dynamics simulations using tertiary structure conformation information of the polypeptide (i.e., numerical values) to generate output data (i.e., quantitative data/numerical value/variables) which encompasses using mathematical formulas such as Newton’s Second Law, forces from potential energy, force fields, and time-integration which reads on abstract ideas.
(b) a computer-readable memory comprising instructions for performing the method of in silico polypeptide structure generation comprising generating a vector map based on processing the output data, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide; and(ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide
This step can be performed can be performed in the human mind by organizing data (i.e., output data) to generate a vector map of residue-specific properties from MD simulations and a pairwise property and is therefore an abstract idea. This step encompasses taking information (i.e., output information), manipulating data via mathematical correlation (i.e., encoding), and organizing the information into a different form (i.e., vector map). See MPEP 2106.04(a)(2)(I)(A)(iv).
(c) a second model trained to predict a polypeptide structure based on the at least one residue- specific property and the at least one pairwise property to generate the in-silico polypeptide structure.
This step can be performed in the human mind by observing and evaluating residue- specific properties and pairwise properties to generate am in-silico polypeptide structure. Here, even though the claimed steps use “second model trained” to predict a polypeptide structure for generating an in-silico polypeptide structure, the second model is broadly and generically recited and reads on mere instructions to implement an abstract idea on a generic computer and reads on mathematical/statistical computations (i.e., linear region, bootstrap aggregation [Spec page 10 para 39]). See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.04(a)(2)(III)(C) (1-3) and 2106.05(f). Furthermore, it is noted that the claim recites “to generate an in-silico polypeptide structure”. Here, the “generated in-silico polypeptide structure” is interpreted as information (i.e., organized amino acid sequence data) and not physical steps for generating a physical polypeptide.
Claim 58 recites:
(a) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises secondary and tertiary structure conformation information of the polypeptide
This step encompasses performing mathematical computation of Molecular Dynamics simulations using tertiary structure conformation information of the polypeptide (i.e., numerical values) to generate output data (i.e., quantitative data/numerical value/variables) which encompasses using mathematical formulas such as Newton’s Second Law, forces from potential energy, force fields, and time-integration which reads on abstract ideas.
(b) encoding the output data into a function to generate a vector map, wherein the vector map comprises: (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide
This step can be performed can be performed in the human mind by organizing data (i.e., output data) to generate a vector map of residue-specific properties from MD simulations and a pairwise property and is therefore an abstract idea. This step encompasses taking information (i.e., output information), manipulating data via mathematical correlation (i.e., encoding), and organizing the information into a different form (i.e., vector map). See MPEP 2106.04(a)(2)(I)(A)(iv).
(c) applying a machine learning algorithm to the vector map to model the secondary and tertiary structure conformation information to biologically relevant properties to determine the druggability of the polypeptide structure.
Here, even though the claimed steps apply a “machine learning algorithm (MLA)”, the MLA is broadly and generically recited and reads on mere instructions to implement an abstract idea on a generic computer and reads on mathematical/statistical computations (i.e., linear region, bootstrap aggregation [Spec page 10 para 39]). See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.04(a)(2)(III)(C)(1-3) and 2106.05(f). This step encompasses taking information (i.e., vector map), manipulating data via mathematical correlation (i.e., MLA), and organizing the information into a different form (i.e., druggability of the polypeptide structure). See MPEP 2106.04(a)(2)(I)(A)(iv).
Claims 41-49, 51-57, and 59-63 are further drawn to limitations that describe the abstract ideas of claim 1 and are therefore also abstract ideas.
Step 2A Prong II - Consideration of Practical Application
Claims 40, 50, and 58 do not recite any additional element which integrates the recited judicial exception into a practical application.
Here, in the instant case, the claims merely set forth a method of data analysis yielding an in-silico generated polypeptide using a machine learning algorithm (claim 40 system) and second model (claim 50 system) while claim 58 yields the druggability of the polypeptide structure. As such, practicing the claims merely results in the generation of a polypeptide and druggability value. Moreover, it is noted in Step 2A Prong I above, the “generated in-silico polypeptide structure” of claims 40 and 50 is interpreted as information (i.e., organized amino acid sequence data) and not physical steps for generating a physical polypeptide. Thus, the results of claims 40, 50, and 58 only produce information (i.e., organized nucleic acid data) which does not provide for a practical application in the physical-realm of physical things and acts, i.e., the claims do not utilize the data generated by the judicial exception to affect any type of change.
Furthermore, and for sake of compact prosecution, even if the machine learning algorithm (MLA) (claim 40) and the second model (SM) (claim 50) are also considered additional elements, the MLA and SM are used to generally apply the abstract idea without limiting how the trained (MLA) and SM function. The MLA and SM is described at a high level such that it amounts to using a computer with a generic MLA or SM to apply the abstract idea. These limitations only recite the outcomes for “applying a machine learning algorithm to the vector map to generate the polypeptide structure” without any details about how the polypeptide is generated (claim 40 (3)). Additionally, these limitations of claim 50 step (c) only recite the outcomes for “generating an in-silico polypeptide structure using the second model trained on residue-specific and pairwise properties” without any details about how the polypeptide is generated (claim 50). Therefore, the judicial exception is not integrated into a practical application, and the claims do not provide significantly more because this type of recitation is equivalent to the words "apply it". See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.05(f).
For further sake of compact prosecution, even if the machine learning algorithm (MLA) (claim 58) is also considered additional elements, the MLA is used to generally apply the abstract idea without limiting how the trained MLA. The MLA is described at a high level such that it amounts to using a computer with a generic MLA to apply the abstract idea. These limitations only recite the outcomes for “(c) applying a machine learning algorithm to the vector map to model the secondary and tertiary structure conformation information to biologically relevant properties to determine the druggability of the polypeptide structure.” without any details about how to determine the druggability of the polypeptide structure based on biological relevant information. Additionally, these limitations of claim 58 step (c) only recite the outcomes for “determining druggability of the polypeptide structure” without any details about how druggability is determined using the MLA which does not integrate the judicial exception into a practical application and does not provide significantly more because this type of recitation is equivalent to the words "apply it". See 2024 Subject Matter Eligibility Update (AI) [Example 47 Claim 2] and MPEP 2106.05(f).
Claim 64 does not recite any additional element which integrates the recited judicial exception into a practical application. For example, and with respect to claim 64 “synthesizing a protein therapeutic”, the recitation of the claimed synthesizing step attempts to cover any method/solution with no restriction on how the result is accomplished (i.e., synthesizing a protein therapeutic) and no description of the methods/techniques used for accomplishing the result which does not integrate a judicial exception into a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it.
Claim 64 also recites “expressing a protein therapeutic in a microorganism”. Here, the claim does not integrate the judicial exception because claim 58 is recited as just “apply it” to the protein therapeutic of claim 64. Here, druggability is not applied to any peptides in the subsequent steps, and/or there are no druggability thresholds utilized such that peptide can be selected as an intervention based on the determined druggability. Furthermore, the recitation of the claimed synthesizing attempts to cover any microorganism (i.e., bacteria, virus, amoeba) for synthesizing the protein therapeutic. It is further disjointed because claim 58 is drawn to an “in-silico” method while claim 60 recites “system of claim 58 is configured to”, claim 61 recites “method of claim 60 further configured to”, and claim 62 recites “the method of claim 60 (i.e., system of claim 60)”, but claim 58 does not contain any computer processes, components, equipment, and/or any software modules that can be configured to impute in-silico amino acids to generate a polypeptide structure and/or configured to link the generated polypeptide structure to a disease state in a database. Additionally, claim 60 recites a system but claim 58 is drawn to a method that does not contain computer elements (i.e., computer system) that can be configured to impute a generated polypeptide structure. Therefore, the synthesization limitation of claim 64 is not integrated with the judicial exception to construct a practical application or provide significantly more because this type of recitation is equivalent to the words "apply it. See MPEP 2106.05(f)(I).
This judicial exception is not integrated into a practical application because the claims do not meet any of the following criteria:
An additional element reflects an improvement in the functioning of a computer, or an improvement to other technology or technical field;
an additional element that applies or uses a judicial exception to effect a particular treatment or prophylaxis for a disease or medical condition;
an additional element implements a judicial exception with, or uses a judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim;
an additional element effects a transformation or reduction of a particular article to a different state or thing; and
an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception.
Step 2B
The claimed method also recites "additional elements" that are not limitations drawn to an abstract idea.
The recited additional element of using computer processes, components, and equipment of claims 40, 50, and 58 (i.e., in-silico) does not add significantly more because using computer to store, process, and evaluate abstract ideas is merely tangential to the claimed methods and is deemed well-known and conventional. See MPEP 2106.04(a)(2)(III)(C), 2106.05(b), 2106.05(d)(II), and 2106.05(g).
The recited additional element of synthesizing a protein and expressing a protein therapeutic in a microorganism of claim 64 does not add significantly more because synthesizing proteins and expression in a microorganism is deemed well-known and conventional extra-solution activity. To provide evidence of conventionality of synthesizing and expressing a protein therapeutic, Song et al. (Song) teaches a method for constructing expression vectors to produce the tIK, a anti-inflammatory peptide [page 5 section 2.2]. Song teaches method for expressing tIK-9mer, 14 mer, and 18mer [page 6 section 2.3]. Song teaches using e. coli for expressing tIK polypeptides [page 7-8 section 3.1]. (Molecules (Basel, Switzerland), 2020-09, Vol.25 (19), p.4358). To provide further evidence of conventionality, Naveed et al. (Naveed) teaches using E. coli for constructing vaccine for SARS-CoV-2 [abstract]. (Journal of infection and public health, 2021-07, Vol.14 (7), p.938-946).
In conclusion, and when viewed as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea recited in the instantly presented claims into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. Therefore, the claim(s) are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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.
Claim Rejections - 35 USC § 103
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 40, 42, and 44-49 are rejected under 35 U.S.C. 103 as being unpatentable over Greving et al. (Int. Patent Pub: WO 2020/242766, Int. Patent Pub Date: 12 March 2020) in view of Zhou et al. (US Patent Pub: US 2003/0014231, Patent Pub Date: 16 January 2003).
Claims 40-59:
Claim 40 recites (1) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide.
Claim 40 recites (2) encoding the output data into a function to generate a vector map, wherein the vector map comprises (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Claim 40 recites (3) applying a machine learning algorithm to the vector map to generate a predicted polypeptide structure based on the at least one residue-specific property and the at least one pairwise property.
Greving et al. (Greving) discloses that characteristic of one or more candidate peptides are determined by computer simulation [Greving, claim 68]. Greving discloses the simulation can be molecular dynamic simulations [Greving, claim 69]. Greving discloses that molecular dynamics can be limited by time such as a time frame of 30 nanoseconds. Greving discloses obtaining 80% of conformational information observed with any timeframe to achieve conformation [Greving, page 24 para 0077]. Greving discloses analyzing alpha and beta amino acid structures and analyzing tertiary proteins [Greving, fig 11-12]. Greving discloses methods for selecting a generated engineered polypeptides based on information spatially-associated topological characteristics from reference target and candidate peptides [Greving, claim 66]. Greving discloses using machine learning methods [Greving, page 3 para 0010-0012]. Greving discloses training machine learning models and utilizing the machine learning models for processing polypeptide blueprints [Greving, claims 1, 8-9, and 12-16], as in instant claim 40 (1) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide. It is noted that although Greving does not directly disclose in silico methods, it is obvious the molecular dynamic simulations and machine learning elements provide in silico generation of polypeptides.
Greving discloses the representation is a vector. The vector is an ordered list of number of intervening scaffold residues between target-residue positions. Greving discloses an example of the vector representation using first, second, third, and fourth elements constructing vector representation [Greving, page 20, para 69]. Greving discloses the representation may be a one-dimensional vector of numbers, a two-dimensional matrix of alphanumerical data, a three-dimensional tensor of normalized numbers [Greving, page 9-10 para 0043]. Greving discloses data preparation modules that are configured to encode a blueprint into a blueprint record and further convert the blueprint record into a representation of the blueprint record suitable for use in a machine learning model (i.e., encoding) [Greving, page 9 para 0042]. Greving discloses predetermined positions can represent physiochemical properties (i.e., polar/non-polar, size, hydrophobicity) [Greving, page 4 para 0032]. Greving discloses generating amino acid positions (i.e., at least one or more amino acids) for blueprint records (i.e., amino acid sequences) [Greving, claim 3], as in instant claim 40 (2) encoding the output data into a function to generate a vector map, wherein the vector map comprises (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide.
Greving discloses using machine learning models to process representations (i.e., vectors) generate engineered polypeptides [Greving, claims 1 and 12-17], as in instant claim 40 (3) applying a machine learning algorithm to the vector map to generate a predicted polypeptide structure based on the at least one residue-specific property and the at least one pairwise property.
Dependent claim(s): 44-46
Greving discloses computer simulation can be molecular dynamics or Monte Carlo or any combination thereof [Greving, claim 69], as in instant claim 44.
Greving discloses each converted residue positions of the target and scaffold proteins of the blueprint record may be assigned either a fixed amino acid identity (i.e., static embedding) or a variable identity (dynamic residue embedding) [Greving, page 6 para 0032]. Greving discloses the representation can be a three-dimensional tensor of normalized numbers [Greving, page 10 para 0043] [Instant Spec page 9 para 35], as in instant claim 45.
Greving discloses the reference target structure may include dynamic terms from molecular dynamics simulations or experimentally (i.e., crystallography) [Greving, page 5, para 0031]. Greving discloses sets of blueprint records (e.g., a blueprint file encoded in a table of alphanumeric data) can be generated from a predetermined portion of the reference target structure [Greving, page 9 para 0042]. Greving discloses using density function theory based on molecular dynamics energy simulator and/or the like for subsequent machine learning processing [Greving, page 14 para 0055], as in instant claim 46. Here, it is obvious that vector maps (i.e., representations) of crystal structures can be generated for candidate, target, reference, and/or engineered proteins/polypeptides.
Greving does not teach claim 40 (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide. Greving does not teach claims 42 and 47-49.
Zhou et al. (Zhou) disclose for a system which interacts through pairwise additive forces [Zhou, page 5 left col para 69]. Zhou discloses force potential can be expressed as the sum of forces stretching, bending, torsion, van der Waals, and electrostatic interaction [Zhou, page 7 left col para 0095]. Zhou discloses a molecular dynamics system that uses algorithm having an electrostatic interaction calculating function and a multiple time step function, and subdividing forces based on distances over which said forces act [Zhou, claim 1]. Zhou discloses forces are divided by distances [Zhou, claim 2], as in instant claim 40 (2) (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Obvious claim(s): 42 and 47-49
Greving discloses labeling blueprint records [Greving, claim 26]. Greving discloses labeling amino acid residues with Rosetta remodeler [Greving, fig 6]. Greving discloses constraints are derived from per-residue energy and per-residue atomic distance [Greving, claim 67] (i.e., residue-specific properties). Zhou discloses using molecular dynamics (MD) for analyzing molecular interactions [Zhou, claim 1]. Zhou et al. (Zhou) disclose for a system which interacts through pairwise additive forces [Zhou, page 5 left col para 69]. Zhou discloses force potential can be expressed as the sum of forces stretching, bending, torsion, van der Waals, and electrostatic interaction [Zhou, page 7 left col para 0095] (i.e., pairwise properties), as in instant claim 42.
Greving discloses scaffold-residue positions of the blueprint may be assigned amino acid at that position (i.e., an X representing any amino acid). Additionally, the scaffold-residue position may be assigned by selection from a subset of possible natural or unnatural amino acids (e.g., small polar amino acid residue, large hydrophobic amino-acid residue, etc.). Similarly, the blueprint may tolerate insertion or deletion of residue positions. For example, a target- or scaffold-residue position may be assigned to be present or absent or the position may be assigned to be 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more residues [Greving, page 6 para 0032]. Greving, discloses using Rosetta remodeler for predicting structure (i.e., imputing into a database) [Greving, fig 6]. Zhou discloses using a database for storing data of biomolecular system and performing an algorithm that includes an electrostatic interaction (e.g., short-range and/or long-range electrostatic force) calculating function and a multiple time step function (e.g., RESPA), and subdivide forces based on distances over which the forces act (i.e., database). Greving discloses a method for selecting candidate peptide such that engineered peptides can be generated [Greving, claim 66]. Greving discloses a user of a program may select a target protein as input for designing an engineered polypeptide. Greving discloses the target maybe antigen from a pathogenic organism, a protein involved in cellular function associated with a disease. Greving discloses the engineered polypeptide me be intended for antibody discovery, vaccination, diagnostic, or used in a method of treatment [Greving page 5 para 30]. [Zhou, page 2 left col para 0015], as in instant claim 47-49. Therefore, the combination of Greving and Zhou would construct a database that could assign variables (i.e., imputing) to generated polypeptides. Furthermore, because Greving discloses that engineered polypeptides can be associated with a disease and can be used as a vaccination, diagnostic, or used in treatment and Zhou discloses a database with algorithm processing abilities, it makes obvious engineered polypeptides can be linked to a disease(s), and engineered polypeptides can be selected by a user or program based on the combine analysis of Greving and Zhou.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention would modify engineered polypeptide system of Greving in view Zhou because Zhou expands on utilizing electrostatic interactions and multiple step time functions of molecule dynamics (MD) simulations with respect to evaluating biomolecular system using pairwise additive forces (i.e., electrostatic) and distance properties. One of ordinary skill in the art would recognize that while Zhou does not disclose using machine learning elements or generating polypeptide structures Zhou discloses more explicit implementation of MD analysis with respect to evaluating properties for propagating protein systems. Thus, one of ordinary skill in the art would have a reasonable expectation of success combining Greving in view of Zhou because Zhou discloses a more targeted MD analysis targeting the chemical interactions and properties of biomolecular system (i.e., polypeptide) and discloses the system improves force analysis accuracy [Zhou, page 8 left col para 0111], Therefore, combing the teachings of Greving in view of Zhou would yield a predictable in silico method/system using a combination of MD simulations and machine learning algorithms for analyzing peptide properties and molecular distances for generating polypeptide that can be subsequently utilized as therapies for treating diseases.
Claim(s) 43 is rejected under 35 U.S.C. 103 as being unpatentable over Greving in view of Zhou, as applied to claims 40, 42, and 44-49, and in further view of Nguyen et al. (IEEE transactions on emerging topics in computational intelligence, 2021-12, Vol.5 (6), p.931-946).
Greving in view of Zhou teach claims 40, 42, and 44-49.
Greving in view of Zhou disclose an in-silico method for generating polypeptide structure using MD and machine learning elements.
Greving in view of Zhou does not teach claim 43.
Nguyen et al. (Nguyen) teaches a continuous-time dynamic network [Nguyen, page 970 right col]. Nguyen discloses the function, as in instant claim 43.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Greving in view of Zhou and in further view of Nguyen because Nguyen teaches the mathematical and algorithmic theory for creating and processing sequences of discrete snapshot graphs from the continuous-time representation of a graph [Nguyen, page 970 right col]. Here, although one of ordinary skill in the art would recognize that while Nguyen does not teach implementing the continuous-time dynamic network for analyzing amino acid sequences (i.e., polypeptides), one of ordinary skill would recognize the framework of Nguyen can be utilized for processing crystal structure and/or other protein structure data with respect to time. Therefore, combining the MD simulations and machine learning methods for generating engineered polypeptide of Greving in view of the further MD simulation methods of Zhou with continuous-time dynamic network/function of Nguyen would construct a predictable method step using continuous-time dynamic network/function for processing polypeptide crystal structure for generating polypeptide that can be subsequently select as and for an intervention therapy associated with a disease.
Claims 50 and 52-57
Claim(s) 50 and 52-57 are rejected under 35 U.S.C. 103 as being unpatentable over Greving in view of Zhou.
Claim 50 recites (a) a first model for performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide.
Claim 50 recites (b) a computer-readable memory comprising instructions for performing the method of in silico polypeptide structure generation comprising generating a vector map based on processing the output data, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide; and(ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Claim 50 recites (c) a second model trained to predict a polypeptide structure based on the at least one residue- specific property and the at least one pairwise property to generate the in-silico polypeptide structure.
Greving discloses a molecular dynamic simulation module (i.e., model) [Greving, page 9 para 0041 and fig. 1]. Greving discloses that characteristic of one or more candidate peptides are determined by computer simulation [Greving, claim 68]. Greving discloses the simulation can be molecular dynamic simulations [Greving, claim 69]. Greving discloses that molecular dynamics can be limited by time such as a time frame of 30 nanoseconds. Greving discloses obtaining 80% of conformational information observed with any timeframe to achieve conformation [Greving, page 24 para 0077]. Greving discloses analyzing alpha and beta amino acid structures and analyzing proteins (i.e., tertiary) [Greving, fig 11-12]. Greving discloses methods for selecting a generated engineered polypeptides based on information spatially-associated topological characteristics from reference target and candidate peptides [Greving, claim 66], as in instant claim 50 (a) a first model for performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide.
Greving discloses a processor-readable medium for storing instructions [Greving, claim 22]. Greving discloses the representation is a vector. The vector is an orders list of number of intervening scaffold residues between target-residue positions. Greving discloses an example of the vector representation using first, second, third, and fourth elements constructing vector representation [Greving, page 20, para 69]. Greving discloses the representation may be a one-dimensional vector of numbers, a two-dimensional matrix of alphanumerical data, a three-dimensional tensor of normalized numbers [Greving, page 9-10 para 0043]. Greving discloses data preparation modules that are configured to encode a blueprint into a blueprint record and further convert the blueprint record into a representation of the blueprint record suitable for use in a machine learning model (i.e., encoding) [Greving, page 9 para 0042]. Greving discloses predetermined positions can represent physiochemical properties (i.e., polar/non-polar, size, hydrophobicity) [Greving, page 4 para 0032]. Greving discloses generating amino acid positions (i.e., at least one or more amino acids) for blueprint records (i.e., amino acid sequences) [Greving, claim 3]. Greving discloses constraints are derived from per-residue energy and per-residue atomic distance [Greving, claim 67] (i.e., residue-specific properties), as in instant claim 50 (b) performing the method of in silico polypeptide structure generation comprising generating a vector map based on processing the output data, wherein the vector map comprises (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide.
Greving discloses using machine learning models to process representations (i.e., vectors) generate engineered polypeptides [Greving, claims 1 and 12-17], as in instant claim 50 (c) applying a machine learning algorithm to the vector map to generate a predicted polypeptide structure based on the at least one residue-specific property and the at least one pairwise property.
Dependent claim(s): 53-54
Greving discloses computer simulation can be molecular dynamics or Monte Carlo or any combination thereof [Greving, claim 69], as in instant claim 53.
Greving discloses the reference target structure may include dynamic terms from molecular dynamics simulations or experimentally (i.e., crystallography) [Greving, page 5, para 0031]. Greving discloses sets of blueprint records (e.g., a blueprint file encoded in a table of alphanumeric data) can be generated from a predetermined portion of the reference target structure [Greving, page 9 para 0042]. Greving discloses using density function theory based on molecular dynamics energy simulator and/or the like for subsequent machine learning processing [Greving, page 14 para 0055], as in instant claim 54. Here, it is obvious that vector maps (i.e., representations) of crystal structures can be generated for candidate, target, reference, and/or engineered proteins/polypeptides.
Greving does not teach claim 50 (b) (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide. Greving does not teach claims 52 and 55-57
Zhou et al. (Zhou) disclose for a system which interacts through pairwise additive forces [Zhou, page 5 left col para 69]. Zhou discloses force potential can be expressed as the sum of forces stretching, bending, torsion, van der Waals, and electrostatic interaction [Zhou, page 7 left col para 0095]. Zhou discloses a molecular dynamics system that uses algorithm having an electrostatic interaction calculating function and a multiple time step function, and subdividing forces based on distances over which said forces act [Zhou, claim 1]. Zhou discloses forces are divided by distances [Zhou, claim 2], as in instant claim 50 (b) (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Obvious claim(s): 52 and 55-57
Greving discloses labeling blueprint records [Greving, claim 26]. Greving discloses labeling amino acid residues with Rosetta remodeler [Greving, fig 6]. Greving discloses constraints are derived from per-residue energy and per-residue atomic distance [Greving, claim 67] (i.e., residue-specific properties). Zhou discloses using molecular dynamics (MD) for analyzing molecular interactions [Zhou, claim 1]. Zhou et al. (Zhou) disclose for a system which interacts through pairwise additive forces [Zhou, page 5 left col para 69]. Zhou discloses force potential can be expressed as the sum of forces stretching, bending, torsion, van der Waals, and electrostatic interaction [Zhou, page 7 left col para 0095] (i.e., pairwise properties), as in instant claim 52.
Greving discloses scaffold-residue positions of the blueprint may be assigned amino acid at that position (i.e., an X representing any amino acid). Additionally, the scaffold-residue position may be assigned by selection from a subset of possible natural or unnatural amino acids (e.g., small polar amino acid residue, large hydrophobic amino-acid residue, etc.). Similarly, the blueprint may tolerate insertion or deletion of residue positions. For example, a target- or scaffold-residue position may be assigned to be present or absent or the position may be assigned to be 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more residues [Greving, page 6 para 0032]. Greving, discloses using Rosetta remodeler for predicting structure (i.e., imputing into a database) [Greving, fig 6]. Greving discloses a method for selecting candidate peptide such that engineered peptides can be generated [Greving, claim 66]. Zhou discloses using a database for storing data of biomolecular system and performing an algorithm that includes an electrostatic interaction (e.g., short-range and/or long-range electrostatic force) calculating function and a multiple time step function (e.g., RESPA), and subdivide forces based on distances over which the forces act (i.e., database) [Zhou, page 2 left col para 0015], as in instant claim 55-57. Therefore, the combination of Greving and Zhou would construct a database could assign variables (i.e., imputing) to generated polypeptides. Furthermore, because Greving discloses engineered polypeptides can be associated with a disease and can be used as a vaccination, diagnostic, or used in treatment and Zhou discloses a database with algorithm processing abilities, it makes obvious engineered polypeptides can be linked to a disease(s), and engineered polypeptides (i.e., intervention therapies) can be selected by a user or program based on the combine analysis of Greving and Zhou.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention would modify engineered polypeptide system of Greving in view Zhou because Zhou expands on utilizing electrostatic interaction and multiple step time functions of molecule dynamics simulations (MD) evaluating biomolecular system using pairwise additive forces (i.e., electrostatic) and distance properties. One of ordinary skill in the art would recognize that while Zhou does not disclose using machine learning elements or generating polypeptide structures Zhou discloses more explicit implementation of MD analysis with respect to evaluating properties for propagating protein systems. Thus, one of ordinary skill in the art would have a reasonable expectation of success combining Greving in view of Zhou because Zhou discloses a specific MD analysis targeting the chemical interactions and properties of biomolecular system (i.e., polypeptide) and discloses the system improves force analysis accuracy [Zhou, page 8 left col para 0111]. Therefore, combing the teachings of Greving in view of Zhou would yield a predictable modular in silico system using a combination MD simulations and machine learning algorithms/models/modules for analyzing peptide properties and molecular distances for generating polypeptide that can be subsequently utilized as therapies for treating diseases.
Claims 58
Claim(s) 58-62 and 64-65 are rejected under 35 U.S.C. 103 as being unpatentable over Greving in view of Zhou in view of Yuan (Journal of chemical information and modeling, 2020-03, Vol.60 (3), p.1685-1699)
Claim 58 recites (a) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises secondary and tertiary structure conformation information of the polypeptide.
Claim 58 recites (b) encoding the output data into a function to generate a vector map, wherein the vector map comprises: (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Claim 58 recites (c) applying a machine learning algorithm to the vector map to model the secondary and tertiary structure conformation information to biologically relevant properties to determine the druggability of the polypeptide structure.
Greving discloses a molecular dynamic simulation module (i.e., model) [Greving, page 9 para 0041 and fig. 1]. Greving discloses that characteristic of one or more candidate peptides are determined by computer simulation [Greving, claim 68]. Greving discloses the simulation can be molecular dynamic simulations [Greving, claim 69]. Greving discloses that molecular dynamics can be limited by time such as a time frame of 30 nanoseconds. Greving discloses obtaining 80% of conformational information observed with any timeframe to achieve conformation [Greving, page 24 para 0077]. Greving discloses analyzing alpha and beta amino acid structures (i.e., secondary) and analyzing proteins (i.e., tertiary) [Greving, fig 11-12]. Greving discloses methods for selecting a generated engineered polypeptides based on information spatially-associated topological characteristics from reference target and candidate peptides [Greving, claim 66]. Greving discloses molecular dynamic simulations can be performed to obtain 80% confirmational information [Greving, page 24 para 0077]. Greving discloses analyzing alpha and beta amino acid structures and analyzing tertiary proteins [Greving, fig 11-12], as in instant claim 58 (a) performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises secondary and tertiary structure conformation information of the polypeptide
Greving discloses a processor-readable medium for storing instructions [Greving, claim 22]. Greving discloses the representation is a vector. The vector is an orders list of number of intervening scaffold residues between target-residue positions. Greving discloses an example of the vector representation using first, second, third, and fourth elements constructing vector representation [Greving, page 20, para 69]. Greving discloses the representation may be a one-dimensional vector of numbers, a two-dimensional matrix of alphanumerical data, a three-dimensional tensor of normalized numbers [Greving, page 9-10 para 0043]. Greving discloses data preparation modules that are configured to encode a blueprint into a blueprint record and further convert the blueprint record into a representation of the blueprint record suitable for use in a machine learning model (i.e., encoding) [Greving, page 9 para 0042]. Greving discloses predetermined positions can represent physiochemical properties (i.e., polar/non-polar, size, hydrophobicity) [Greving, page 4 para 0032]. Greving discloses generating amino acid positions (i.e., at least one or more amino acids) for blueprint records (i.e., amino acid sequences) [Greving, claim 3]. Greving discloses constraints are derived from per-residue energy and per-residue atomic distance [Greving, claim 67] (i.e., residue-specific properties), as in instant claim 58 (b) performing the method of in silico polypeptide structure generation comprising generating a vector map based on processing the output data, wherein the vector map comprises (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide.
Dependent claim(s): 59
Greving discloses using supervised learning [Greving, claims 12-16], as in instant claim 59.
Greving does not teach claim 58 (b) (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide. Greving does not teach claim 58 (c) applying a machine learning algorithm to the vector map to model the secondary and tertiary structure conformation information to biologically relevant properties to determine the druggability of the polypeptide structure. Greving does not teach claims 60-65.
Zhou et al. (Zhou) disclose for a system which interacts through pairwise additive forces [Zhou, page 5 left col para 69]. Zhou discloses force potential can be expressed as the sum of forces stretching, bending, torsion, van der Waals, and electrostatic interaction [Zhou, page 7 left col para 0095]. Zhou discloses a molecular dynamics system that uses algorithm having an electrostatic interaction calculating function and a multiple time step function, and subdividing forces based on distances over which said forces act [Zhou, claim 1]. Zhou discloses forces are divided by distances [Zhou, claim 2], as in instant claim 58 (b) (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Obvious claim(s): 60-62 and 64-65.
Greving discloses scaffold-residue positions of the blueprint may be assigned amino acid at that position (i.e., an X representing any amino acid). Additionally, the scaffold-residue position may be assigned by selection from a subset of possible natural or unnatural amino acids (e.g., small polar amino acid residue, large hydrophobic amino-acid residue, etc.). Similarly, the blueprint may tolerate insertion or deletion of residue positions. For example, a target- or scaffold-residue position may be assigned to be present or absent or the position may be assigned to be 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, or more residues [Greving, page 6 para 0032]. Greving, discloses using Rosetta remodeler for predicting structure (i.e., imputing into a database) [Greving, fig 6]. Greving discloses a method for selecting candidate peptide such that engineered peptides can be generated [Greving, claim 66]. Zhou discloses using a database for storing data of biomolecular system and performing an algorithm that includes an electrostatic interaction (e.g., short-range and/or long-range electrostatic force) calculating function and a multiple time step function (e.g., RESPA), and subdivide forces based on distances over which the forces act (i.e., database) [Zhou, page 2 left col para 0015], as in instant claim 60-62. Therefore, the combination of Greving and Zhou would construct a database could assign variables (i.e., imputing) to generated polypeptides. Furthermore, because Greving discloses engineered polypeptide can be associated with a disease and can be used as a vaccination, diagnostic, or used in treatment and Zhou discloses a database with algorithm processing abilities, it makes obvious engineered polypeptides can be linked to a disease(s), and engineered polypeptides can be selected by a user or program based on the combine analysis of Greving and Zhou. Morevoer, with that in mind, it would be further obvious the engineered polypeptide obtained from the analysis of Greving and Zhou could can be considered a therapeutic and used as a therapeutic intervention for treating an associated disease, as in instant claims 64-65.
Yuan et al. teaches druggability assessment using a combination of machine learning and molecular dynamics analysis [abstract]. Yuan teaches the druggability of positive and negative protein samples [page 1691 fig 5]. Yuan teaches benchmarking their pipeline using different machine learning algorithms such as support vector machine and neural network, for example [page 1692 Table 2].
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention would modify engineered polypeptide system of Greving in view Zhou because Zhou expands on utilizing electrostatic interaction and multiple step time functions of molecule dynamics simulations (MD) evaluating biomolecular system using pairwise additive forces (i.e., electrostatic) and distance properties. One of ordinary skill in the art would recognize that while Zhou does not disclose using machine learning elements or generating polypeptide structures Zhou discloses more explicit implementation of MD analysis with respect to evaluating properties for propagating protein systems. Thus, one of ordinary skill in the art would have a reasonable expectation of success combining Greving in view of Zhou because Zhou discloses a specific MD analysis targeting the chemical interactions and properties of biomolecular system (i.e., polypeptide) and discloses the system improves force analysis accuracy [Zhou, page 8 left col para 0111]. Therefore, combing the teachings of Greving in view of Zhou would yield a predictable modular in silico system using a combination MD simulations and machine learning algorithms/models/modules for analyzing peptide properties and molecular distances for generating polypeptide that can be subsequently utilized as therapies for treating diseases.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention to modify Greving in view Zhou in view of Yuan because Yuan teaches using MD simulations and machine learning analyses for analyzing amino acid property data of proteins for determining the proteins druggability. One of ordinary skill in the art would recognize that Greving, Zhou, and Yuan are in similar fields of endeavor of protein simulation and teach similar methods for evaluating proteins but Yuan expands on the method of Greving and Zhou by using MD and machine learning determining druggability of proteins. Thus, one of ordinary skill in the art would be motivated to combine Greving in view of Zhou in view of Yuan because Yuan teaches parameters and methods for using MD and machine learning algorithm generated polypeptides which could be utilized to analyze the engineered polypeptides of Greving to determine if the engineered polypeptides contained druggable attributes. Therefore, one of ordinary skill in the art would have a reasonable expectation of success combining the engineered proteins of Greving in view of electrostatic interaction analysis of Zhou with Yuan because Yuan teach applying Lipinski’s rule-of-five (RO5) as a requirement for determining if proteins in a dataset are orally druggable [Yuan, page 1686 right col NRDLD Dataset]. Therefore, combining Greving, Zhou, and Yuan would yield a predicting method for determining the druggability of an in-silico generated polypeptide.
Claim(s) 63 are rejected under 35 U.S.C. 103 as being unpatentable over Greving in view of Zhou in view of Yuan, as applied to claims 58-62 and 64-65, and in further view of Sigiki et al. (Expert opinion on drug discovery, 2014-10, Vol.9 (10), p.1189-1204).
Greving in view of Zhou in view of Yuan teach claims 58-62 and 64-65.
Greving in view of Zhou in view of Yuan teach a method using MD and machine learning elements for determining the druggability of an in-silico generated polypeptide structure.
Greving in view of Zhou in view of Yuan does not teach claim 63.
Sigiki et al. (Sigiki) reviews methods for producing proteins in drug discovery processes [abstract]. Sigiki teaches a comparison of different methods for producing compounds such as using E. coli, yeast, mammalian, and cell-free methods.
It would be obvious to one of ordinary skill in the art by the effective filing date of the claimed invention would modify Greving in view Zhou in view of Yuan and in further view of Sigiki because Sigiki teaches different methods for producing proteins discovered in drug discovery processes. Here, even though Sigiki does not provide in-silico amino acid analysis similar to Greving, Zhou, and Yuan, Sigiki provides the tools (i.e., synthesizing method) which one of ordinary skill in the art would utilize to synthesize a polypeptide for subsequent therapeutic use (i.e., experimental/clinical implementation). Thus, one of ordinary skill in the art would expect a reasonable success choosing one or more of the production methods of Sigiki to produce the engineered polypeptide of Greving. Therefore, using the protein producing methods of Sigiki in conjunction with the data analyses of Greving, Zhou, and Yuan would yield a predictable method step for synthesizing generated peptides (i.e., therapeutic interventions).
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 40-49
Claims 40-49 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-5, 7-8, and 10-13 of copending Application No. 18/598,701 (‘701).
Claim 40 recites (1) performing a molecular dynamic (MD) simulation of the polypeptide structure to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide.
Claim 40 recites (2) encoding the output data into a function to generate a vector map, wherein the vector map comprises (i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Claim 40 recites (3) applying a machine learning algorithm to the vector map to generate a predicted polypeptide structure based on the at least one residue-specific property and the at least one pairwise property.
(‘701) discloses performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide [(‘701) claim 1 a)], as in instant claim 40 (1).
(‘701) discloses generating a vector map based on processing the output data using a function, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide; and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide [(‘701) claim 1 (b)], as in claim 40 (2)
(‘701) discloses generating a predicted polypeptide structure based on the at least one residue- specific property and the at least one pairwise property using at least one model trained to predict a polypeptide structure [(‘701) claim 1 (b)], as in claim 40 (c).
Claims 41-49:
(‘701) discloses wherein the vector map comprises a D-dimensional array, wherein D is the number of residue-specific properties of (i) and the pairwise properties of (ii) [(‘701) claim 2], as instant claim 41.
(‘701) discloses wherein the at least one residue-specific property comprises Coulombic energy, Van Der Waals energy, a residue label, a GRAVY score, or any combination thereof. (‘701) discloses wherein the at least one pairwise property comprises a Coulombic energy between the at least two amino acid, a Van Der Waals energy between the at least two amino acids, a distance between the at least two amino acids, or any combination thereof [(‘701) claims 3 and 4], as in instant claim 42
(‘701) discloses wherein the function is a continuous time dynamic graph function [(‘701) claim 5], as in instant claim 43.
(‘701) discloses wherein the MD simulation comprises Replica Exchange Molecular Dynamics. (‘701) discloses wherein the MD simulation comprises Monte Carlo Dynamics [(‘701) claims 7-8], as in instant claim 44.
(‘701) discloses generating of the vector map comprises processing data from a crystal structure into the function [(‘701) claim 10], as in instant claim 46.
(‘701) discloses comprising imputing the predicted polypeptide structure into a database [(‘701) claim 11], as in instant claim 47.
(‘701) discloses comprising linking the predicted polypeptide structure to a disease state in the database [(‘701) claim 12], as in instant claim 48.
(‘701) discloses comprising selecting an intervention therapy based on the predicted polypeptide structure and the disease state [(‘701) claim 13], as in instant claim 49.
Although the claims at issue are not identical, they are not patentably distinct from each other because the claims of (‘701) and the instant claim are drawn to the same invention with slightly different variations in claim language.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Claims 50-57
Claim 50-57 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1-4, 7-8, and 10-13 of copending Application No. 18/598,701 (‘701).
Claims 50
Claim 50 recites (a) a first model for performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide.
Claim 50 recites (b) a computer-readable memory comprising instructions for performing the method of in silico polypeptide structure generation comprising generating a vector map based on processing the output data, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide; and(ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide.
Claim 50 recites (c) a second model trained to predict a polypeptide structure based on the at least one residue- specific property and the at least one pairwise property to generate the in-silico polypeptide structure.
(‘701) discloses performing a molecular dynamic (MD) simulation of a polypeptide to generate output data as a function of time, wherein the output data comprises tertiary structure conformation information of the polypeptide [(‘701) claim 1 a)], as in instant claim 50 (a). Here, even though the instant claims recite a first model, the analysis limitations of (‘701) are similar to claim 58 step (a).
(‘701) discloses generating a vector map based on processing the output data using a function, wherein the vector map comprises:(i) at least one residue-specific property derived from the MD simulation for an amino acid in the polypeptide; and (ii) at least one pairwise property derived from the MD simulation for at least two amino acids in the polypeptide [(‘701) claim 1 (b)], as in claim 50 (b).
(‘701) discloses generating a predicted polypeptide structure based on the at least one residue- specific property and the at least one pairwise property using at least one model trained to predict a polypeptide structure [(‘701) claim 1 (c)], as in claim 50 (c). Here, even though the instant claims recite a second model, the analysis limitations of (‘701) step (c) are similar to claim 50 step (c).
Claims 51-57:
(‘701) discloses wherein the vector map comprises a D-dimensional array, wherein D is the number of residue-specific properties of (i) and the pairwise properties of (ii) [(‘701) claim 2], as instant claim 51.
(‘701) discloses wherein the at least one residue-specific property comprises Coulombic energy, Van Der Waals energy, a residue label, a GRAVY score, or any combination thereof. (‘701) discloses wherein the at least one pairwise property comprises a Coulombic energy between the at least two amino acid, a Van Der Waals energy between the at least two amino acids, a distance between the at least two amino acids, or any combination thereof [(‘701) claims 3 and 4], as in instant claim 52.
(‘701) discloses wherein the MD simulation comprises Replica Exchange Molecular Dynamics. (‘701) discloses wherein the MD simulation comprises Monte Carlo Dynamics [(‘701) claims 7-8], as in instant claim 53.
(‘701) discloses generating of the vector map comprises processing data from a crystal structure into the function [(‘701) claim 10], as in instant claim 54.
(‘701) discloses comprising imputing the predicted polypeptide structure into a database [(‘701) claim 11], as in instant claim 55.
(‘701) discloses comprising linking the predicted polypeptide structure to a disease state in the database [(‘701) claim 12], as in instant claim 56.
(‘701) comprising selecting an intervention therapy based on the predicted polypeptide structure and the disease state [(‘701) claim 13], as in instant claim 57.
Although the claims at issue are not identical, they are not patentably distinct from each other because the claims of (‘701) and the instant claim are drawn to the same invention with slightly different variations in claim language.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Conclusion
Claims 40-65 are rejected.
No claims are allowed.
Finality
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH C PULLIAM whose telephone number is (571)272-8696. The examiner can normally be reached 0730-1700 M-F.
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.
/J.C.P./Examiner, Art Unit 1687
/Anna Skibinsky/
Primary Examiner, AU 1635
Prosecution Insights