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
Claims 1-15 are pending and under consideration in this action.
Priority
The instant application is a 371 of PCT/US2021/062292, filed 12/08/2021, which claims priority to Chinese Application Number 202011623825.0, filed 12/31/2020, as reflected in the filing receipt mailed on 10/06/2023. Acknowledgment is made of Applicant's claim for foreign priority under 35 U.S.C. 119 (a)-(d). Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. The claims to the benefit of priority are acknowledged and the effective filing date of claims 1-15 is 12/31/2020.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 07/05/2023, 05/21/2025, and 10/07/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS’s have been considered by the examiner.
It is noted that certain references lack appropriate article numbers, provide the wrong journal name, and/or reference the wrong publication date (NPL #2, #5, and #7 from the IDS dated 07/05/2023). The Examiner has annotated those references herein. Applicant is kindly reminded to provide proper citations in compliance with 37 CFR 1.97 in all future submissions to the office.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description: The “spatial coordinate representation system 300” referenced in Specification Para. [0040] is not shown in Fig. 3.
The drawings are also objected to as failing to comply with 37 CFR 1.84(p)(4) because reference characters "810" and “820" in Fig. 8 have both been used to designate an example error map.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed. The following title is suggested: “Protein Structure Prediction using Structural Property Constraints”.
Claim Objections
Claim 9 is objected to because of the following informalities:
Claim 9 recites the limitation “determining respective differences between the plurality of constraints for the plurality of structural properties in the constrain set and the plurality of determined reference property values,” in lines 9-11 of the claim, which should be corrected to “determining respective differences between the plurality of constraints for the plurality of structural properties in the constraint set and the plurality of determined reference property values” for clarity and consistency with the rest of the claim.
Appropriate correction is required.
Claim Rejections - 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 1-15 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.
Claims 1 and 12 recite the limitations “extracting feature information from the plurality of constraints respectively” and “determining a plurality of weights corresponding to the plurality of constraints respectively…” in lines 4-5 and 7-9 of the claims, respectively. The metes and bounds of the claim are rendered indefinite due to the lack of clarity. It is unclear what “respectively” corresponds to, as there is not a list of items in either limitation. Examiner notes that “respectively” is typically used to describe multiple items in a list, keeping to a specific order. This rejection can be overcome by amendment of claim 1 to clarify what items “respectfully” corresponds to, or remove the term for clarity. Claims 2-11 and 13-15 are also rejected due to their dependency on claims 1 and 12.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite both (1) mathematical concepts (mathematical relationships, formulas or equations, or mathematical calculations) and (2) mental processes, i.e., concepts performed in the human mind (including observations, evaluations, judgements or opinions) (see MPEP § 2106.04(a)).
Step 1:
In the instant application, claims 1-11 are directed towards a method, and claims 12-14 are directed towards a machine, which falls into one of the categories of statutory subject matter (Step 1: YES).
Claim 15 is directed towards a computer program product. Regarding claim 15, the recitation of “a computer program product being tangibly stored in a computer storage medium” does not provide any structural components and therefore equates to “software per se”. Claims that equate to “software per se” are not a statutory category of invention (see MPEP § 2106.03(I)). However, claim 15 could be amended to be statutory subject matter by adding in structural components such as by replacing a computer program product being tangibly stored in a computer storage medium” with the phrase “a computer program product being tangibly stored in a non-transitory computer-readable medium”. Nonetheless, this amendment would still result in a rejection of the claim under 35 U.S.C. 101 for recitation of a judicial exception without significantly more. In the interest of compact prosecution, claim 15 has also been analyzed below under 35 U.S.C. 101 using the Alice/Mayo two-part test below.
Step 2A, Prong One:
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong One). The following instant claims recite limitations that equate to one or more categories of judicial exceptions:
Claims 1 and 12 recite a mental process (i.e., an evaluation of constraints to extract feature information) in “extracting feature information from the plurality of constraints respectively”; a mental process (i.e., an evaluation of the constraints to determine weights) in “determining a plurality of weights corresponding to the plurality of constraints respectively based on the feature information of the plurality of constraints, each weight indicating a degree of influence of the corresponding constraint in prediction of a structure of the target protein”; and a mental process (i.e., an evaluation of constraints and weights to predict structure) in “predicting the structure of the target protein based on the plurality of constraints in the constraint set and the plurality of weights”.
Claim 2 recites a mental process (i.e., an evaluation of the structural properties) in “wherein the plurality of structural properties comprise inter-residue distances and inter-residue orientations of a plurality of residues that for the target protein”; and a mental process (i.e., an observation of a probability distribution) in “wherein the plurality of constraints indicate probability distribution information of the property values for the plurality of structural properties”.
Claims 3 and 13 recite a mathematical concept (i.e., determining scores using a trained model) in “determining, based on the extracted feature information, a plurality of quality scores for the plurality of constraints respectively using a constraint quality analysis model, the constraint quality analysis model being trained with ground-truth property values of a plurality of structural properties in a known structure of a protein”; and a mental process (i.e., an evaluation of scores to assign scores) in “assigning the plurality of weights to the plurality of constraints based on the plurality of quality scores for the plurality of constraints”.
Claims 4 and 14 recite a mental process (i.e., an evaluation of constraints for removal) in “discarding at least one constraint from the constraint set, to obtain a reduced constraint set”; a mental process (i.e., an evaluation of constraints and weights to predict structure) in “generating at least one predicted structure of the target protein based on the reduced constraint set and the weights assigned to a plurality of constraints in the reduced constraint set”; and a mental process (i.e., an evaluation of the structures produced in the iterations to determine a structure) in “determining the structure of the target protein based on a plurality of predicted structures generated in the plurality of iterations”.
Claim 5 recites a mathematical concept (i.e., generating potential functions) in “generating a plurality of protein-specific potential functions corresponding to the plurality of structural properties respectively, each protein-specific potential function being based on weighting of a group of constraints for the corresponding structural property in the constraint set, and the weighting being based on respective weights for the group of constraints”; a mathematical concept (i.e., determining a first objective function) in “determining, based on the plurality of protein-specific potential functions, a first objective function for a structure prediction model used for predicting a structure of a protein”; and a mental process (i.e., evaluating if the objective function reaches a convergence target and if the structure satisfies the constraints) in “determining the structure of the target protein using the structure prediction model by at least causing the first objective function to reach a convergence target, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions”.
Claim 6 recites a mathematical concept (i.e., generating a geometric potential function) in “generating at least one geometric potential function, the at least one geometric potential function being based on at least one constraint for at least one basic geometry structural property of a protein, and the at least one constraint being based on a property value of the at least one basic geometry structural property determined from a native peptide of a known protein”; a mental process (i.e., an evaluation of the geometric potential function to determine a second objective function) in “determining a second objective function for the structure prediction model based on the at least one geometric potential function”; and a mental process (i.e., an evaluation of whether the objective functions reach convergence and if the structure satisfies constraints) in “determining the structure of the target protein using the structure prediction model by causing the first and second objective functions to reach their convergence targets respectively, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions, and a geometry of the structure satisfying the constraint used in the at least one geometric potential function”.
Claim 7 recites a mental process (i.e., an evaluation of the intermediate predicted structure; whether the objective function reaches convergence; and whether the intermediate structure satisfies constraints) in “in a first stage, determining at least one intermediate predicted structure of the target protein by causing the first objective function to reach the convergence target, the plurality of structural properties of the at least one intermediate predicted structure satisfying the constraints used in the plurality of protein-specific potential functions”; and a mental process (i.e., updating a structure in response to objective functions reaching their convergence targets) in “in a second stage, updating the at least one intermediate predicted structure by causing the first and second objective functions to reach their convergence targets, to determine the structure of the target protein”.
Claim 8 recites a mental process (i.e., an evaluation of the basic geometry structural property) in “wherein the at least one basic geometry structural property comprises at least one of the following: a pairwise distance of two neighboring Cα atoms, a sequential interval between Cα atoms, a length of a peptide bond, a distance between an O atom within a residue and a N atom within a next residue, a distance between an O atom within a residue and a Cα atom within a next residue of the residue, and a difference of a distance between any pair of atoms and a sum of radiuses of the pair of atoms”.
Claim 9 recites a mental process (i.e., an evaluation of predicted structures) in “selecting at least one of a plurality of predicted structures generated in a previous iteration of the given iteration”; a mental process (i.e., an evaluation of reference property values) in “determining, from at least one selected predicted structure, a plurality of reference property values for the plurality of structural properties”; a mathematical concept (i.e., calculating differences) in “determining respective differences between the plurality of constraints for the plurality of structural properties in the constraint set and the plurality of determined reference property values”; a mental process (i.e., an evaluation of values exceeding a threshold to discard constraints) in “in accordance with a determination that the difference between a property value indicated by at least one of the plurality of constraints and the corresponding reference property value exceeds a threshold difference, discarding the at least one constraint from the constraint set, to obtain a reduced constraint set”; and a mental process (i.e., an evaluation of the reduced constraint set and weights to determine structure) in “determining a plurality of predicted structures of the target protein in the given iteration based on the reduced constraint set and the weights assigned to the constraints in the reduced constraint set”.
Claim 10 recites a mental process (i.e., an evaluation of the structures) in “determining at least one initial structure of the target protein based on the at least one selected predicted structure”; and a mental process (i.e., an evaluation of the structure for optimization) in “determining the plurality of predicted structures of the target protein in the give iteration by optimizing the at least one initial structure”.
Claim 11 recites a mental process (i.e., an evaluation of ranking to select a structure) in “selecting the at least one predicted structure from the plurality of predicted structures based on the ranking”.
These recitations are similar to the concepts of collecting information, and displaying certain results of the collection and analysis is Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)), and organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships.
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification, and are determined to be directed to mental processes that in the simplest embodiments are not too complex to practically perform in the human mind. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Specifically, claims 1 and 12 involves nothing more than extracting feature information from constraints, determining weights corresponding to the constraints, and predicting the structure based on the constraints and weights. Since there are no specifics in the methodology, the steps of extracting feature information from constraints, determining weights corresponding to the constraints, and predicting the structure based on the constraints and weights, are something that under BRI, one could perform mentally. Therefore, the claimed steps are not further defined beyond something that reads on merely looking at data and making a determination, using a computer as a tool. As such, said steps are directed to judicial exceptions. The instant claims must therefore be examined further to determine whether they integrate the abstract idea into a practical application (Step 2A, Prong One: YES).
Step 2A, Prong Two:
In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that when examined as a whole integrates the judicial exception(s) into a practical application (MPEP § 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP § 2106.04(d)(I)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP § 2106.04(d)(III)). The following independent claims recite limitations that equate to additional elements:
Claim 1 recites “computer-implemented”; and “obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein”.
Claim 12 recites “a processing unit”; “a memory coupled to the processing unit and having instructions stored thereon, the instructions, when executed by the processing unit, cause the device to perform steps”; and “obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein”.
Regarding the above cited limitations in claims 1 and 12 of (i) computer-implemented (claim 1); and (ii) a processing unit and a memory coupled to the processing unit and having instructions stored thereon, the instructions, when executed by the processing unit, cause the device to perform steps (claim 12). These limitations require only a generic computer component, which does not improve computer technology. Therefore, these limitations equate to mere instructions to implement an abstract idea on a generic computer, which the courts have established does not render an abstract idea eligible in Alice Corp. 573 U.S. at 223, 110 USPQ2d at 1983.
Regarding the above cited limitation in claims 1 and 12 of (iii) obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein. This limitation equates to insignificant, extra-solution activity of mere data gathering because this limitation gathers data before the recited judicial exceptions of extracting feature information from constraints, determining weights corresponding to the constraints, and predicting the structure based on the constraints and weights (see MPEP § 2106.04(d)).
Additionally, none of the recited dependent claims recite additional elements which would integrate the judicial exception into a practical application. Specifically, claim 11 recites a generic extra-solution “apply it” step to determine the ranking using a neural network model (see MPEP § 2106.05(f)); and claim 15 recites generic computer components analogous to claims 1 and 12 above. As such, claims 1-15 are directed to an abstract idea (Step 2A, Prong Two: NO).
Step 2B:
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The instant independent claims recite the same additional elements described in Step 2A, Prong Two above.
Regarding the above cited limitations in claims 1 and 12 of (i) computer-implemented (claim 1); and (ii) a processing unit and a memory coupled to the processing unit and having instructions stored thereon, the instructions, when executed by the processing unit, cause the device to perform steps (claim 12). These limitations equate to instructions to implement an abstract idea on a generic computing environment, which the courts have established does not provide an inventive concept (see MPEP § 2106.05(d) and MPEP § 2106.05(f)).
Regarding the above cited limitation in claims 1 and 12 of (iii) obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein. This limitation does not include any specific steps for obtaining the constraint set for the target protein. Under the BRI, this limitation is merely receiving data for the subsequent step of extracting feature information from the constraints. Therefore, this limitation equates to receiving/transmitting data over a network, which the courts have established as a WURC limitation of a generic computer in buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014).
These additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial exception into a patent-eligible application of the judicial exception. Therefore, the instant claims do not amount to significantly more than the judicial exception itself (Step 2B: NO). As such, claims 1-15 are not patent eligible.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-4 and 9-15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Senior et al. (WO 2020/058177 A1; published 03/26/2020; cited in the IDS dated 07/05/2023).
Regarding claim 1, Senior et al. teaches a method, system, and computer program encoded on a computer-storage medium, for performing protein structure prediction (i.e., a computer-implemented method) (Abstract). Senior et al. further teaches that one step of the method includes obtaining initial values of a plurality of structure parameters defining the predicted structure (Para. [0006]). In some implementations, a geometry score representing an estimate of a similarity measure between the predicted structure defined by the current values of the structure parameters and an actual structure of the given protein is generated. Determining the quality score may further comprise determining, based on the current values of the structure parameters, a physics or physical constraint score characterizing a likelihood of the current values of the structure parameters dependent upon how closely the current values of the structure parameters conform to biochemical or physical constraints on a structure of the given protein. For example, steric constraints on the structure may be modelled by a van der Waals term (i.e., obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein) (Para. [0020]-[0021]). Senior et al. further teaches that determining the input may include extracting components of (i) a representation of the sequence of amino acid residues, and (ii) alignment features derived from a multiple sequence alignment (MSA) which includes the sequence of amino acid residues. The alignment features may include covariation features (amongst the sequences in the MSA), which can help to identify residues in contact (Para. [0030]). Additional profile features may be extracted using PSI-BLAST. The number of amino acid sequences in the MSA may be an additional alignment feature. The alignment features and the representation of the amino acid sequence can be represented as a two-dimensional array of features, where each (i, j) feature is the concatenation of the one-dimensional features for both the i and j residues as well as the two-dimensional features for the residue pair (i, j). The alignment features described here can be used as inputs for each of the scoring neural networks (i.e., extracting feature information from the plurality of constraints respectively) (Para. [0234]). Senior et al. further teaches that the system generates a distance map which characterizes estimated distances between each pair of amino acids in the protein using the distance map crops. For example, the system may generate the distance map as a weighted average of the distance map crops, where the weight assigned to a distance map crop is based on the number of amino acid (sub)sequences in the MSA processed to generate the distance map crop. In a particular example, each of the distance map crops may include binary variables which indicate whether each pair of amino acids in the amino acid subsequence corresponding to the distance map crop are predicted to be in contact. For a given pair of amino acids in the protein, the system may determine a weighted average of the binary variables corresponding to the given pair of amino acids in each distance map crop and round the weighted average to 0 or 1 to generate a binary variable (i.e., determining a plurality of weights corresponding to the plurality of constraints respectively based on the feature information of the plurality of constraints, each weight indicating a degree of influence of the corresponding constraint in prediction of a structure of the target protein) (Para. [0362]). Senior et al. further teaches that the system can output the predicted structure defined by the current parameter values after the last update the current parameter values. The system can determine a final predicted structure of the protein by repeatedly performing the process to generate multiple predicted structures of the protein, and selecting the final predicted structure to be the generated predicted structure with the highest quality score (i.e., predicting the structure of the target protein based on the plurality of constraints in the constraint set and the plurality of weights) (Para. [0330], Fig. 9, and Fig. 11).
Regarding claim 2, Senior et al. teaches that in some implementations the one or more scoring neural networks comprise a distance prediction neural network configured to process the representation of the sequence of amino acids to generate a distance map for the given protein. In implementations the distance map defines, for each of a plurality of pairs of amino acids in the sequence, a respective probability distribution over possible distance ranges between the pair of amino acids. For example, the possible distance ranges may be quantized, or the probability distribution over possible distance ranges may be represented by a parameterized probability distribution. A range between the pair of amino acids may be defined by a distance between particular, corresponding atoms of the amino acids (residues) such as alpha and/or beta carbon atoms (i.e., wherein the plurality of structural properties comprise inter-residue distances of a plurality of residues that form the target protein; and wherein the plurality of constraints indicate probability distribution information of property values for the plurality of structural properties) (Para. [0012]). Senior et al. further teaches that the set of structural parameters includes a set of backbone atom torsional angles and backbone atom coordinates (i.e., wherein the plurality of structural properties comprise inter-residue orientations of a plurality of residues that form the target protein) (Para. [0057]-[0058]).
Regarding claim 3, Senior et al. teaches that the distance map may be used for determining a predicted structure of the given protein. For example, this may involve obtaining initial values for structure parameters defining the protein structure and updating these based on a quality score for the structure defined by the distance map. The updating may comprise, for one or more or each of the structure parameters: optimizing the quality score by adjusting a current value of the structure parameter, e.g., by determining a gradient of the quality score with respect to the current value of the structure parameter and then updating the current value of the structure parameter using the gradient of the quality score; or by another optimization process (i.e., determining, based on the extracted feature information, a plurality of quality scores for the plurality of constraints respectively using a constraint quality analysis model) (Para. [0032]). Senior et al. further teaches that the training domains define actual (ground truth) domains of respective training proteins (which are different from the target protein). The training domains can be manually determined by human experts (i.e., the constraint quality analysis model being trained with ground-truth property values of a plurality of structural properties in a known structure of a protein) (Para. [0342]). Senior et al. further teaches that the quality score may be dependent upon a combination, e.g. a weighted combination, of the geometry score and a value score estimating a quality of the predicted structure at a future iteration. The value score may be derived from a value neural network configured to process the representation of the sequence of amino acids of the given protein and the current values of the structure parameters (Para. [0041]). The values of the generative neural network weights may be repeatedly updated using machine learning training techniques (e.g., stochastic gradient descent) to cause the generative neural network to generate structure parameters which define realistic structure fragments by processing network inputs (i.e., assigning the plurality of weights to the plurality of constraints based on the plurality of quality scores for the plurality of constraints) (Para. [0198]).
Regarding claim 4, Senior et al. teaches that at one or more iterations, an alternative predicted structure of the given protein is determined based on the current predicted structure, wherein the alterative predicted structure is defined by alternative values of the structural parameters (i.e., predicting the structure of the target protein in a plurality of iterations) (Para. [0037]). Senior et al. further teaches that in some implementations, the method obtains a structure fragment defined by (corresponding to) values of a subset of the structural parameters and generates the alternative predicted structure using a portion of the current predicted structure and the structure fragment (i.e., discarding at least one constraint from the constraint set, to obtain a reduced constraint set) (Para. [0039]). Senior et al. further teaches that the method may further comprise, at one or more iterations, processing, using a geometry neural network and in accordance with current values of geometry neural network weights, a network input comprising: (i) a representation of a sequence of amino acid residues in the given protein, and (ii) the alternative values of the structure parameters, to generate an output characterizing an alternative geometry score that is an estimate of a similarity measure between the alternative predicted structure and the actual structure of the given protein (i.e., generating at least one predicted structure of the target protein based on the reduced constraint set and the weights assigned to a plurality of constraints in the reduced constraint set) (Para. [0037]). Senior et al. further teaches that determining the predicted structure of the given protein to be defined by the current values of the plurality of structure parameters after a final update iteration of the plurality of update iterations (i.e., determining the structure of the target protein based on a plurality of predicted structures generated in the plurality of iterations) (Para. [0008]).
Regarding claim 9, Senior et al. teaches that at one or more iterations, an alternative predicted structure of the given protein is determined based on the current predicted structure, wherein the alterative predicted structure is defined by alternative values of the structural parameters (i.e., predicting the structure of the target protein in a plurality of iterations) (Para. [0037]). Senior et al. further teaches that the method may further comprise, at one or more iterations, determining an alternative predicted structure of the given protein based on the current predicted structure, wherein the alternative predicted structure is defined by alternative values of the structure parameters (i.e., selecting at least one of a plurality of predicted structures generated in a previous iteration of the given iteration) (Para. [0037]). Senior et al. further teaches that an update engine determines whether to update its respective current predicted structure to any of the alternative predicted structures using the quality scores of the alternative predicted structures (i.e., the reference structures) and the quality score of the current predicted structure (Para. [0166]). Quality scores are determined with respect to the structural parameters (i.e., determining, from the at least one selected predicted structure, a plurality of reference property values for the plurality of structural properties) (Para. [0007]). Senior et al. further teaches that the update engine may determine whether to update the current predicted structure to an alternative predicted structure using a deterministic procedure based on the quality scores. For example, the update engine may determine to update the current predicted structure to a particular alternative predicted structure if the particular alternative predicted structure has a higher quality score than the current predicted structure and any of the other alternative predicted structures (Para. [0167]). The scores associated with the predicted structures may be, for example, backbone-atom quality scores or full-atom quality scores (Para. [0170]). The system also determines a respective gradient of the quality score with respect to each current structure parameter value. To determine the gradient of the quality score with respect to a current structure parameter value, the system can determine the gradient of each of the individual scores used to determine the quality score with respect to the current structure parameter value (i.e., determining respective differences between the plurality of constraints for the plurality of structural properties in the constrain set and the plurality of determined reference property values) (Para. [0326]). Senior et al. further teaches that as an example, the system may determine the termination criterion is satisfied if the change in the current structure parameter values caused by updating the current structure parameter values is less than a predetermined threshold (Para. [0329]). In some implementations, the method obtains a structure fragment defined by (corresponding to) values of a subset of the structural parameters and generates the alternative predicted structure using a portion of the current predicted structure and the structure fragment (i.e., in accordance with a determination that the difference between a property value indicated by at least one of the plurality of constraints and the corresponding reference property value exceeds a threshold difference, discarding the at least one constraint from the constraint set, to obtain a reduced constraint set) (Para. [0039]). Senior et al. further teaches that once the termination criterion is satisfied, the output predicted structure for the iteration is output (Fig. 11). As described with reference to Fig. 9, the system can determine a final predicted structure of the protein by repeatedly performing the process to generate multiple predicted structures of the protein, and selecting the final predicted structure to be the generated predicted structure with the highest quality score (Para. [0330]). The predicted structure of the target protein is based on the reduced constraint set and the weights assigned to a plurality of constraints in the reduced constraint set as described for claim 4 above (i.e., determining a plurality of predicted structures of the target protein in the given iteration based on the reduced constraint set and weights assigned to the constraints in the reduced constraint set).
Regarding claim 10, Senior et al. teaches that to generate a predicted structure, the optimization system first obtains initial values of the set of structure parameters which define the structure of the protein. Generally, the optimization system determines the initial values of the set of structure parameters using a process that involves some randomness, thereby enabling the optimization system to "explore" the space of possible predicted structures. In a particular example, if the optimization system has previously generated one or more predicted structures for the protein, to determine the initial values of the structure parameters, the optimization system may obtain the values of structure parameters defining a previously generated predicted structure for the protein. Subsequently, the optimization system may determine the initial values of the structure parameters by perturbing the values of the structure parameters defining the previously generated predicted structure using random noise values (i.e., determining at least one initial structure of the target protein based on the at least one selected predicted structure) (Para. [0285]). Senior et al. further teaches that having determined the initial values of the structure parameters, the optimization system iteratively updates (i.e., adjusts) the values of structure parameters over multiple update iterations. When the optimization system determines that a termination criterion is satisfied, the optimization system outputs a predicted structure that is defined by the current values of the structure parameters after the final update iteration (i.e., determining the plurality of predicted structures of the target protein in the given iteration by optimizing the at least one initial structure) (Para. [0286]).
Regarding claim 11, Senior et al. teaches that the quality score may be based on respective outputs of one or more scoring neural networks which are each configured to process: (i) the current values of the structure parameters, or (ii) a representation of the sequence of amino acids of the given protein, or (iii) both (Para. [0006]). The quality score may be dependent upon a combination, e.g. a weighted combination, of the geometry score and a value score estimating a quality of the predicted structure at a future iteration. The value score may be derived from a value neural network configured to process the representation of the sequence of amino acids of the given protein and the current values of the structure parameters (Para. [0041]). The neural network may be trained to characterize the ranking of predicted structures (i.e., determining ranking of a plurality of predicted structures generated in the previous iteration using a structure quality analysis model, the structure quality analysis model comprising one or more neural network models based on ranking learning) (Para. [0219]). Senior et al. further teaches that the system may determine the final predicted structure to be a predicted structure stored in the central memory that has a highest score (i.e., selecting the at least one predicted structure from the plurality of predicted structure based on the ranking) (Para. [0257]).
Regarding claim 12, Senior et al. teaches that computers suitable for the execution of a computer program can be based on general or special purpose microprocessors or both, or any other kind of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory or a random access memory or both (i.e., a processing unit; and a memory coupled to the processing unit and having instructions stored thereon, the instructions, when executed by the processing unit, causing the device to perform acts) (Para. [0389]). Senior et al. further teaches the limitations of obtaining a constraint set for a target protein, the constraint set comprising a plurality of constraints for a plurality of structural properties of the target protein; extracting feature information from the plurality of constraints respectively; determining a plurality of weights corresponding to the plurality of constraints respectively based on the feature information of the plurality of constraints, each weight indicating a degree of influence of the corresponding ng constraint in prediction of a structure of the target protein; and predicting the structure of the target protein based on the plurality of constraints in the constraint set and the plurality of weights as described for claim 1 above.
Regarding claim 13, Senior et al. teaches the limitations of determining, based on the extracted feature information, a plurality of quality scores for the plurality of constraints respectively using a constraint quality analysis model, the constraint quality analysis model being trained with ground-truth property values of a plurality of structural properties in a known structure of a protein; and assigning the plurality of weights to the plurality of constraints based on the plurality of quality scores for the plurality of constraints as described for claim 3 above.
Regarding claim 14, Senior et al. teaches the limitations of predicting the structure of the target protein in a plurality of iterations; discarding at least one constraint from the constraint set, to obtain a reduced constraint set; generating at least one predicted structure of the target protein based on the reduced constraint set and the weights assigned to a plurality of constraints in the reduced constraint set; and determining the structure of the target protein based on a plurality of predicted structures generated in the plurality of iterations as described for claim 4 above.
Regarding claim 15, Senior et al. teaches that embodiments of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly-embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, e.g., one or more modules of computer program instructions encoded on a tangible non-transitory storage medium for execution by, or to control the operation of, data processing apparatus (i.e., a computer program product being tangible storing in a computer storage medium and comprising machine-executable instructions, which when executed by a device, case the device to perform the method of claim 1) (Para. [0384]).
Therefore, Senior et al. teaches all the limitations in claims 1-4 and 9-15.
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.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 5-8 are rejected under 35 U.S.C. 103 as being unpatentable over Senior et al. as applied to claims 1-4 and 9-15 above, and further in view of Wang et al. (Artificial intelligence-based multi-objective optimization protocol for protein structure refinement. Bioinformatics. 36(2): 437-448 (2020); published 07/05/2019).
Regarding claim 5, Senior et al. teaches that some implementations of a protein structure prediction system may use one or more neural networks to predict a distance between pairs of residues in the structure and/or to directly estimate the accuracy of a candidate structure, and/or to directly generate protein structures. These approaches may be combined with one or more optimization techniques such as simulated annealing e.g. using multiple computing units or gradient descent, e.g. to optimize a score. Such a score may thus be considered as a potential to be minimized, such as a distance potential or a potential of mean force (i.e., generating a plurality of protein-specific potential functions corresponding to the plurality of structural properties respectively) (Para. [0101]). The scoring system generates one or more of: (i) a structure parameter likelihood score, (ii) a geometry score, (iii) a distance likelihood score, or (iv) one or more additional scores, and thereafter combines them (e.g., as a weighted linear combination) to generate the quality score (i.e., each protein-specific potential function being based on weighting of a group of constraints for the corresponding structural property in the constraint set, and the weighting being based on respective weights for the group of constraints) (Para. [0295]).
Regarding claim 8, Senior et al. teaches that the distance map characterizes estimated distances between each pair of amino acids in the protein. The distance between a first amino acid and a second amino acid in the protein refers to a physical distance (e.g., measured in angstroms) between a particular atom (e.g., a carbon-alpha atom or carbon-beta atom) in the first amino acid and a particular e.g. corresponding atom in the second amino acid in the structure of the protein (i.e., wherein the at least one basic geometry structural property comprises at least one of the following: a pairwise distance of two neighboring Cα atoms) (Para. [0341]).
Senior et al., as applied to claims 1-4 and 9-15 above, does not teach determining, based on the plurality of protein-specific potential functions, a first objective function for a structure prediction model used for predicting a structure of protein (claim 5); determining the structure of the target protein using the structure prediction model by at least causing the first objective function to reach a convergence target, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions (claim 5); generating at least one geometric potential function, the at least one geometric potential function being based on at least one constraint for at least one basic geometry structural property of a protein, and the at least one constraint being based on a property value of the at least one basic geometry structural property determined from a native peptide of a known protein (claim 6); determining a second objective function for the structure prediction model based on the at least one geometric potential function (claim 6); determining the structure of the target protein using the structure prediction model by causing the first and second objective functions to reach their convergence targets respectively, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions, and a geometry of the structure satisfying the constraint used in the at least one geometric potential function (claim 6); in a first stage, determining at least one intermediate predicted structure of the target protein by causing the first objective function to reach the convergence target, the plurality of structural properties of the at least one intermediate predicted structure satisfying the constraints used in the plurality of protein-specific potential functions (claim 7); and in a second stage, updating the at least one intermediate predicted structure by causing the first and second objective functions to reach their convergence targets, to determine the structure of the target protein (claim 7).
Regarding claim 5, Wang et al. teaches a method for protein structure refinement that uses multiple energy functions as multi-objectives in an effort to correct the potential inaccuracy from a single function, outputting a final refined structure after enough iterations (Abstract). Wang et al. further teaches the use of three different energy functions. They formulate the protein structure refinement in a multi-objective optimization problem, i.e. detecting the best conformation solution through the co-constraints of the multi-objective (Pg. 441, Col. 1, Para. 2). Wang et al. further teaches that the multi-objective protein structure refinement can be formulated as:
minimize
f
1
C
i
k
=
E
R
o
s
e
t
t
a
f
2
C
i
k
=
E
R
W
p
l
u
s
f
3
C
i
k
=
E
C
H
A
R
M
M
s
.
t
.
C
i
k
∈
Ω
, where
f
1
is the 1st objective,
f
2
is the 2nd objective,
f
3
is the 3rd objective,
C
i
k
is the conformation of particle
i
updated in the
k
th iteration, and
Ω
is the overall conformational search space (i.e., determining, based on the plurality of the protein-specific potential functions, a first objective function for a structure prediction model used for predicting the structure of a protein) (Pg. 441, Col. 1, Para. 2). Wang et al. further teaches that the objective functions converge with increasing iterations (Pg. 443, Col. 1, Para. 2). Wang et al. further teaches that they tested their method on refined protein targets from CASP 11 and CASP 12. The template modeling score (TM-score), global distance test high accuracy score (GDT_TS score) and RSMD are used as the assessment criteria of the refinement quality. They compared the best model and the model 1 from their output with the initial released model for each target protein. From the perspective of the best model generated by the current model, in all the 56 targets, 52 initial models are improved (93%) to some degree after being refined in terms of TM-score. Based on GDT_TS score and RSMD score, 48 (86%) and 51 (91%) targets show improvement. For the model 1, 89%, 80% and 91% targets are improved in terms of TM-score, GFT-TS and RSMD, respectively (i.e., determining the structure of the target protein using the structure prediction model by at least causing the first objective function to reach a convergence target, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions) (Pg. 443, Col. 1, Para. 3).
Regarding claim 6, Wang et al. teaches that they represent the conformation of the protein backbone by a list of main-chain torsion angles in the internal coordinates: φ (phi), ψ (psi) and ω (omega). The conformation of a sequence with
L
amino acids can be represented as a
3
×
L
-
3
dimensional vector (
C
):
C
=
[
φ
1
,
ψ
1
,
ω
1
…
φ
i
,
ψ
i
,
ω
i
…
φ
L
-
1
,
ψ
L
-
1
,
ω
L
-
1
]
, where
φ
i
,
ψ
i
,
ω
i
is the three torsion angles of the
i
th amino acid. During the iteration, conformation modification occurs in torsion space firstly, where the torsion angles ω are fixed at the value of 180 according to the properties of the amide plane, while the angles φ and ψ of every amino acid change according to the particle updating rules (i.e., generating at least one geometric potential function, the at least one geometric potential function being based on at least one constraint for at least one basic geometry structural property of a protein, and the at least one constraint being based on a property value of the at least one basic geometry structural property determined from a native peptide of a known protein) (Pg. 440, Col. 1, Para. 4-5). Wang et al. further teaches that the multi-objective function includes the overall conformational searching space,
Ω
, as described for claim 5 above (i.e., determining a second objective function for the structure prediction model based on the at least one geometric potential function) (Pg. 441, Col. 1, Para. 2). Wang et al. further teaches that the objective functions converge with increasing iterations (Pg. 443, Col. 1, Para. 2). In their specific problem of protein structure refinement, a particle represents a structure conformation, and the searching space comprises all conformations represented by all possible φ and ψ angles. At the beginning of the initialization, all particles are different initial structures, each of which is represented as
C
i
0
. Then, their positions in the space are updated to get the optimal conformation from the main cycle of the simulation. In the
k
th iteration, the new conformation
C
i
k
of particle
i
is updated according to the velocity updating equation and the position updating equation (i.e., determining the structure of the target protein using the structure prediction model by causing the first and second objective functions to reach their convergence targets respectively, the plurality of structural properties of the structure satisfying the constraints used in the plurality of protein-specific potential functions, and a geometry of the structure satisfying the constraint used in the at least one geometric potential function) (Pg. 441, Col. 2, Para. 2).
Regarding claim 7, Wang et al. teaches that in the multi-objective optimization, multiple iterations are used to optimize the energy landscape (Pg. 440, Fig. 1). Each iteration cycle includes two parts: (i) update the position of the particles through movement operation, i.e. update the conformation of the structures
C
i
k
, and (ii) evaluate the particles by the three fitness functions, and then select those equivalently efficient solutions as for the three fitness functions (also named non-dominated solutions) into the Pareto sets, which is a collection of the output for multi-objective optimization problem (Pg. 439, Col. 2, Para. 6 – Pg. 440, Col. 1, Para. 1). Wang et al. further teaches that the objective functions converge with increasing iterations (i.e., in a first stage, determining at least one intermediate predicted structure of the target protein by causing the first objective function to reach the convergence target, the plurality of structural properties of the at least one intermediate predicted structure satisfying the constraints used in the plurality of protein-specific potential functions and in a second stage, updating the at least one intermediate predicted structure by causing the first and second objective functions to reach their convergence targets, to determine the structure of the target protein) (Pg. 443, Col. 1, Para. 2).
Therefore, regarding claims 5-8, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method of iteratively predicting protein structures using a neural network of Senior et al. with the potential functions defining structural properties of Wang et al. because the multi-objective optimization of Wang et al. provides an expanded conformational search space and thereby a more effective search for final predicted structures (Wang et al., Pg. 445, Col. 2, Para. 4 – Pg. 446, Col. 1, Para. 1). One of ordinary skill in the art would be able to combine the teachings of Senior et al. with Wang et al. with reasonable expectation of success due to the same nature of the problem to be solved, since both are drawn towards a method for iteratively predicting protein structures. Therefore, regarding claims 5-8, the instant invention is prima facie obvious (MPEP § 2142).
Conclusion
No claims allowed.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DIANA P SANFORD whose telephone number is (571)272-6504. The examiner can normally be reached Mon-Fri 8am-5pm EST.
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.
/D.P.S./Examiner, Art Unit 1687
/Lori A. Clow/Primary Examiner, Art Unit 1687
Prosecution Insights