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 .
This action is in response to communications filed on 05/30/2023. Claims 1-20 are pending and have been examined.
Information Disclosure Statement
The information disclosure statement (IDS) submitted was filed on 08/04/2023. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
The information disclosure statement (IDS) submitted was filed on 12/03/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
The information disclosure statement (IDS) submitted was filed on 09/15/2025. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 112
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 15 and 20 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.
As per claim 15, it is unclear whether “the predicted charge of the plurality of segments” is referring to “predicting…charge…of each segment of the plurality of segments” (seen in claims 1 and also claim 15), or is different.
As per claim 20, it is unclear how a “non-transitory computer program product…comprising: a computer-readable medium” can be “executed by a server”. This raises question as to whether applicant intends for the “product” to refer to software per se (as software can be “executed” by a server), rather than a non-transitory computer-readable medium (which would not be interpreted as “executed” by a server in contrast to code [i.e. software] stored on the non-transitory computer-readable medium). For the purposes of examination, “non-transitory computer program product…comprising: a computer-readable medium” is interpreted as meaning a “computer-readable medium” that is not transitory media such as signals per se (i.e. a non-transitory computer-readable medium).
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a method, system, and product comprising constructing and determining by generating and predicting.
The limitation “constucting…” and “determining…by…generating…and predicting” as recited in claim 1 are each a process, under the broadest reasonable interpretation, covering performance of the limitations in the mind or by pen and paper (See Berkheimer v. HP, Inc., 881 F.3d 1360, 1366, 125 USPQ2d 1649 (Fed. Cir. 2018)) but for the recitation of generic computer components. The limitation “constructing one or more three-dimensional (3D) structure models indicating positions of atoms of the molecule” in the context of the claim encompasses the user making evaluations (e.g. imagining an arrangement of spheres). Other than reciting “using a machine learning model”, the limitation “determining the properties of the molecule in the environment by, for each 3D structure model of the constructed one or more 3D structure models: generating a surface model representing the environment, wherein the surface model includes a plurality of segments and the generated surface model defines a relationship between the indicated positions of the atoms of the 3D structure model and the plurality of segments; and predicting… charge and chemical potential of each segment of the plurality of segments based on the 3D structure model and the generated surface model” in the context of the claim encompasses the user making evaluations (e.g. imagining an arrangement of spheres connected with edges and associated properties) and calculations. If a claimed limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “mental processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim recites additional elements. The claim recites “computer-implemented”. The elements are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using a generic computer component (e.g. See MPEP 2106.05(f)). The limitation “using a machine learning model” amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)). Accordingly, the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements are no more than a generic computer component and/or field of use. Therefore, the claims are not patent eligible.
Claims 19 and 20 also recite similar claim language as claim 1, and thus have the same issues. It is noted, with respect to claim 19, that the claim recites “a processor and a memory with computer code instructions stored thereon, the processor and the memory, with the computer code instructions” to perform the method. The elements are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using a generic computer component(s) (e.g. See MPEP 2106.05(f)). It is noted, with respect to claim 20, that the claim further recites “non-transitory computer program product for determining properties of a molecule in an environment, the computer program product executed by a server in communication across a network with one or more clients and comprising: a computer-readable medium, the computer readable medium comprising program instructions, which, when executed by one or more processors, cause the one or more processors” to perform the method. The elements are recited at a high-level of generality, such that it amounts to no more than mere instructions to apply the exception using a generic computer component(s) (e.g. See MPEP 2106.05(f)). Accordingly, the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea and are not sufficient to amount to significantly more than the judicial exception.
Regarding claim 2, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further recites that the predicting is performing using a first machine learning model and a second machine learning model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 3, the claim does not include any additional elements that are sufficient to amount to significantly more than the judicial exception. For example, other than reciting a supplemental machine learning model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)), the claim further recites predicting energy which is a mental process (encompassing a user performing calculations).
Regarding claim 4, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes what each 3D model corresponds to, which is part of the mental steps and does not include any additional elements.
Regarding claim 5, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely generally describes the machine learning model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 6, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely generally describes a neural network, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 7, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes the activation function, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 8, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely generally describes training the model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 9, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely generally describes training the model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 10, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes using one or more algorithms which is a mental process (encompassing a user performing calculations), and updating the neural network, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 11, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely generally describes the training dataset, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 12, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes deriving feature data and predicting also based on the feature data, which are mental steps (encompassing a user making evaluations and calculations) using the machine learning model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 13, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes the derived feature data, which is part of the mental steps (encompassing a user making evaluations) and does not include any additional elements.
Regarding claim 14, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes receiving user requirements and selecting based on determined properties and the user requirements, which are mental steps (encompassing a user making evaluations) and does not include any additional elements.
Regarding claim 15, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes correcting and determining, which are mental steps (encompassing a user making evaluations) using the machine learning model, which amounts to generally linking the use of the judicial exception to a particular technological environment or field of use (e.g. see MPEP 2106.05(h)).
Regarding claim 16, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes the constructing of 3D models, which is part of the mental steps (encompassing a user making evaluations) and does not include any additional elements.
Regarding claim 17, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes the constructing of 3D models, which is part of the mental steps (encompassing a user making evaluations) and does not include any additional elements.
Regarding claim 18, the claim does not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception. For example, the claim merely further describes the generating of the surface model, which is part of the mental steps (encompassing a user making evaluations) and does not include any additional elements.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-13, 16-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. (US 20190108320 A1) in view of Kaser et al. (“Neural Network Potentials for Chemistry: Concepts, Applications and Prospects”, arXiv:2209.11581v3 [physics.chem-ph] 22 Dec 2022, 96 pages) and Schutt et al. ("SchNet - a deep learning architecture for molecules and materials," arXiv: 1712.06113v3 [physics.chem-ph] 22 March 2018, 11 pages as cited in the IDS dated 08/04/2023).
As per independent claim 1, Fan teaches a computer-implemented method for determining properties of a molecule in an environment, the method comprising:
constructing one or more three-dimensional (3D) structure models indicating positions of atoms of the molecule (e.g. in paragraphs 26, 52, and 54, “a three-dimensional (3D) conformation generator 112 configured to generate potential 3D conformations of a chemical compound based on two-dimensional (2D) structure, e.g., chemical formula and/or molecular descriptors, of the compound… distances between the atoms, and the angle between the force and the bonds of the atoms”); and
determining the properties of the molecule in the environment by, for each 3D structure model of the constructed one or more 3D structure models (e.g. in paragraphs 26 and 40, “extract features of the 3D conformations generated by 3D conformation generator 112. Processing component 110 may further include a property predictor 116 configured to employ the neural network to predict properties…of the compound based on features extracted by feature extractor… Extract information regarding bond environment of each atom in the amino acids of a protein”):
generating a surface model representing the environment, wherein the surface model includes a plurality of segments and the generated surface model defines a relationship between the indicated positions of the atoms of the 3D structure model and the plurality of segments (e.g. in paragraphs 26 and 40, “generate potential 3D conformations… Extract information regarding bond environment of each atom in the amino acids of a protein… a local structure… bond lengths” and figures 3-4 showing surface model(s)); and
predicting, using a machine learning model, the properties based on the 3D structure model and the generated surface model (e.g. in paragraphs 26 and 31, “extract features of the 3D conformations generated by 3D conformation generator 112. Processing component 110 may further include a property predictor 116 configured to employ the neural network to predict properties…of the compound based on features extracted by feature extractor”),
but does not specifically teach wherein properties include charge and chemical potential of each segment of the plurality of segments.
However, Kaser teaches predicting properties including charge of each segment of a plurality of segments (e.g. in pages 5-6, 21, 23, and 45, “ML models and their application in computational chemistry… [using] chemical bond… Bag of Bonds… bond distance… [for] predicted atomic charges”). 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 teachings of Fan to include the teachings of Kaser because one of ordinary skill in the art would have recognized the benefit of allowing relevant properties to be determined (also amounts a simple substitution that yields predictable results [e.g. see KSR Int'l Co v. Teleflex Inc., 550 US 398,82 USPQ2d 1385,1396 (U.S. 2007) and MPEP 2143(B)]).
but does not specifically teach wherein properties include chemical potential.
However, Schutt teaches predicting properties including chemical potential (e.g. in pages 4-6 sections A and C, “SchNet models… predict various properties… visualize the learned representation with a "local chemical potential"… “local chemical potentials" inferred by the networks”). 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 teachings of the combination to include the teachings of Schutt because one of ordinary skill in the art would have recognized the benefit of allowing relevant properties to be determined (also amounts a simple substitution that yields predictable results [e.g. see KSR Int'l Co v. Teleflex Inc., 550 US 398,82 USPQ2d 1385,1396 (U.S. 2007) and MPEP 2143(B)]).
As per claim 2, the rejection of claim 1 is incorporated and the combination further teaches wherein the machine learning model comprises a first machine learning model (e.g. Kaser in pages 5-6, 21, 23, and 45, “ML models and their application in computational chemistry [for] predicted atomic charges”) and a second machine learning model (e.g. Schutt in pages 4-6 sections A and C, “SchNet models”), and wherein predicting the charge and the chemical potential of each segment of the plurality of segments based on the 3D structure model and the generated surface model comprises: predicting, using the first machine learning model, electric charge of each segment of the plurality of segments based on the 3D structure model and the generated surface model (e.g. Kaser in pages 5-6, 21, 23, and 45, “ML models and their application in computational chemistry… [using] chemical bond… Bag of Bonds… bond distance… [for] predicted atomic charges”); and predicting, using the second machine learning model, the chemical potential of each segment of the plurality of segments based on the 3D structure model and the generated surface model (e.g. Schutt, in pages 4-6 sections A and C, “SchNet models… predict various properties… visualize the learned representation with a "local chemical potential"… “local chemical potentials" inferred by the networks”).
As per claim 3, the rejection of claim 1 is incorporated and the combination further teaches wherein determining the properties of the molecule in the environment by, for each 3D structure model of the constructed one or more 3D structure models, further comprises: predicting, using a supplemental machine learning model, energy corresponding to the 3D structure model based on the 3D structure model and the generated surface model (e.g. Kaser, in pages 15 and 24, “NNs that decompose the potential energy into atomic contributions… NNs…are trained to predict the short-range atomic energy contributions”; Schutt, in pages 1 and 5-6, “SchNet that allows to model complex atomic interactions in order to predict potential energy surfaces… predict formation energies… prediction of potential energy surfaces and force fields”).
As per claim 4, the rejection of claim 1 is incorporated and the combination further teaches wherein each 3D structure model of the constructed one or more 3D structure models corresponds to a respective conformer of the molecule (e.g. Fan, in paragraph 26, “a three-dimensional (3D) conformation generator 112 configured to generate potential 3D conformations of a chemical compound based on two-dimensional (2D) structure, e.g., chemical formula and/or molecular descriptors, of the compound”).
As per claim 5, the rejection of claim 1 is incorporated and the combination further teaches wherein the machine learning model comprises a neural network (e.g. Fan, in paragraph 26, “employ the neural network to predict properties”).
As per claim 6, the rejection of claim 5 is incorporated and the combination further teaches wherein the neural network comprises one or more hidden layers and the neural network is configured to employ an activation function at one or more nodes of the one or more hidden layers (e.g. Fan, in paragraphs 35 and 69, “neural network may include layers for quantifying the input information regarding the compound… FIG. 7 is a schematic diagram illustrating the structures, e.g., layer structure, of an exemplary neural network” and figure 7 showing “Hidden Layers” and “Softmax” activation function; Kaser, in page 12, “NNs comprise a larger number of hidden layers” which comprises figure B showing “Activation function” and figure C showing “ReLU” and “SoftMax” as “Examples of common activation functions”).
As per claim 7, the rejection of claim 6 is incorporated and the combination further teaches wherein the activation function is one of a rectified linear activation function and a softmax function (e.g. Fan, in figure 7 showing “Softmax” activation function; Kaser, in page 12 which comprises figure C showing “ReLU” and “SoftMax” as “Examples of common activation functions”).
As per claim 8, the rejection of claim 1 is incorporated and the combination further teaches training the machine learning model based on a training data set (e.g. Fan, in paragraphs 58 and 68, “training data may be obtained from real-world protein structure data, such as Protein Database (PDB) files from the Research Collaboratory for Structural Bioinformatics (RCSB). For example, correct feature vectors may be constructed for the conformations shown in the PDB file… the neural network may be trained using input data of known compounds. For example, the training data may include chemical formula, physical description, boiling point, water solubility, and pKa value of a known compounds”; Kaser, in pages 14, 17, and 23, “Training comprises the parameter fitting process of the weights and biases to match the prediction y(x) to the reference results t for a set of Ndata data points… trained using the energies of the molecules… trains a separate NN with reference charges”).
As per claim 9, the rejection of claim 8 is incorporated and the combination further teaches wherein the machine learning model comprises a neural network (e.g. Fan, in paragraph 26, “employ the neural network to predict properties”) and wherein training the machine learning model based on the training data set comprises: training the neural network by iteratively updating one or more network weights of the neural network based on the training data set (e.g. Kaser, in pages 14, 17, and 23, “Training comprises the parameter fitting process of the weights and biases to match the prediction y(x) to the reference results t for a set of Ndata data points… Different loss functions for fitting NNs can be used as well.76 In general, the loss function is highly nonlinear and is minimized iteratively by a gradient descent algorithm”).
As per claim 10, the rejection of claim 9 is incorporated and the combination further teaches wherein iteratively updating the one or more network weights of the neural network based on the training data set comprises employing one or more of an adaptive moment estimation solver algorithm and an early stopping algorithm (e.g. Kaser, in pages 14, 17, and 23, “Training comprises the parameter fitting process of the weights and biases to match the prediction y(x) to the reference results t for a set of Ndata data points… Different loss functions for fitting NNs can be used as well.76 In general, the loss function is highly nonlinear and is minimized iteratively by a gradient descent algorithm”; Schutt, in page 4 section F, “all models are trained with mini-batch stochastic gradient descent using the ADAM optimizer… use a validation set for early stopping”; note: ADAM refers to Adaptive Moment Estimation).
As per claim 11, the rejection of claim 8 is incorporated and the combination further teaches wherein the training data set comprises data for one or more of: example molecules, example conformers, example segments, example segment charges, example segment chemical potentials, and example continuum model energies (e.g. Fan, in paragraph 58, “training data may be obtained from real-world protein structure data, such as Protein Database (PDB) files from the Research Collaboratory for Structural Bioinformatics (RCSB). For example, correct feature vectors may be constructed for the conformations shown in the PDB file”; Kaser, in page 24, “NNs provided with ACSFs and the atomic charge information are trained”).
As per claim 12, the rejection of claim 1 is incorporated and the combination further teaches deriving input feature data based on the 3D structure model and predicting, using the machine learning model, the charge and the chemical potential of each segment of the plurality of segments based on the 3D structure model, the generated surface model, and the derived input feature data (e.g. Fan, in paragraphs 26 and 40, “extract features of the 3D conformations generated by 3D conformation generator 112. Processing component 110 may further include a property predictor 116 configured to employ the neural network to predict properties…of the compound based on features extracted by feature extractor… bond environment of each atom in the amino acids of a protein”; Kaser, in pages 5-6, 21, 23, and 45, “ML models and their application in computational chemistry… [using] chemical bond… Bag of Bonds… bond distance… [for] predicted atomic charges”; Schutt, in pages 4-6 sections A and C, “SchNet models… predict various properties… visualize the learned representation with a "local chemical potential"… “local chemical potentials" inferred by the networks”).
As per claim 13, the rejection of claim 12 is incorporated and the combination further teaches wherein the derived input feature data comprises an indication of one or more of: atom type, atom-atom distance, atom-segment distance, bond type, bond angle, torsion angle, formal charge, 3D atom position, and atom-type specific features (e.g. Fan, in paragraphs 35 and 52, “data about the atoms comprising the molecule… the type of atom… distances between the atoms, and the angle between the force and the bonds of the atoms”).
As per claim 16, the rejection of claim 1 is incorporated and the combination further teaches wherein constructing the one or more 3D structure models indicating the positions of the atoms of the molecule is based on indications of one or more of: atom type, coordinates, and chemical connectivity (e.g. Fan, in paragraphs 33, 35, and 52, “extracting and learning some important chemical features… data about the atoms comprising the molecule… the type of atom… distances between the atoms, and the angle between the force and the bonds of the atoms”; Kaser, in pages 9, 15-16, and 27, “position of the nuclei... atomic positions… atomic coordinates… Cartesian atom positions… quantum chemical ab initio calculation is carried out for each geometry”).
As per claim 17, the rejection of claim 1 is incorporated and the combination further teaches wherein constructing the one or more 3D structure models indicating the positions of the atoms of the molecule comprises employing one or more of: rule-based geometrical models, force fields, and quantum-chemically derived geometrical models (e.g. Kaser, in pages 9, 15-16, 27, and 63, “position of the nuclei... atomic positions… atomic coordinates… Cartesian atom positions… quantum chemical ab initio calculation is carried out for each geometry”).
Claim 19 is the system claim corresponding to method claim 1, and is rejected under the same reasons set forth and the combination further teaches a processor and a memory with computer code instructions stored thereon, the processor and the memory, with the computer code instructions, being configured to cause the system to perform the method (e.g. Fan, in paragraph 24, “non-transitory computer readable media that include program instructions or program code that, when executed by one or more processors, perform one or more computer-implemented operations”).
Claim 20 is the system claim corresponding to method claim 1, and is rejected under the same reasons set forth and the combination further teaches a non-transitory computer program product, the computer program product executed by a server in communication across a network with one or more clients and comprising a computer-readable medium, the computer readable medium comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform the method (e.g. Fan, in paragraphs 24-26 and 30, “non-transitory computer readable media that include program instructions or program code that, when executed by one or more processors, perform one or more computer-implemented operations… system 100 may be…a server, a server cluster consisting of a plurality of servers, a cloud computing service center, etc… send the prediction results to a user”).
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. (US 20190108320 A1) in view of Kaser et al. (“Neural Network Potentials for Chemistry: Concepts, Applications and Prospects”, arXiv:2209.11581v3 [physics.chem-ph] 22 Dec 2022, 96 pages) and Schutt et al. ("SchNet - a deep learning architecture for molecules and materials," arXiv: 1712.06113v3 [physics.chem-ph] 22 March 2018, 11 pages as cited in the IDS dated 08/04/2023) as applied above, and further in view of Yang et al. (US 20220130487 A1).
As per claim 14, the rejection of claim 1 is incorporated and the combination further teaches for each molecule of a plurality of molecules, performing the constructing and the determining the properties (e.g. Fan, in paragraphs 26 and 40, “a three-dimensional (3D) conformation generator 112 configured to generate potential 3D conformations of a chemical compound based on two-dimensional (2D) structure, e.g., chemical formula and/or molecular descriptors, of the compound… extract features of the 3D conformations generated by 3D conformation generator 112. Processing component 110 may further include a property predictor 116 configured to employ the neural network to predict properties…of the compound based on features extracted by feature extractor… bond environment of each atom in the amino acids of a protein”),
but does not specifically teach receiving one or more user requirements, wherein each molecule of a plurality of molecules include each candidate molecule of a plurality of candidate molecules; and selecting a given molecule from among the plurality of candidate molecules based on the determined properties of the given molecule and the received one or more user requirements.
However, Yang teaches receiving one or more user requirements, wherein each molecule of a plurality of molecules include each candidate molecule of a plurality of candidate molecules (e.g. in paragraphs 6 and 16, “compound library usually has several hundreds of thousands of molecules… user can define the key characteristics of the drug… set the physical and chemical properties that the candidate compound should have [of] compounds”) and selecting a given molecule from among the plurality of candidate molecules based on the determined properties of the given molecule and the received one or more user requirements (e.g. in paragraphs 16 and 38, “set the physical and chemical properties that the candidate compound should have… updates the parameters according to user-defined requirements, and generates a batch of compounds that meet the conditions… select the top 5%-15% compounds”). 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 teachings of the combination to include the teachings of Yang because one of ordinary skill in the art would have recognized the benefit of facilitating drug screening.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. (US 20190108320 A1) in view of Kaser et al. (“Neural Network Potentials for Chemistry: Concepts, Applications and Prospects”, arXiv:2209.11581v3 [physics.chem-ph] 22 Dec 2022, 96 pages) and Schutt et al. ("SchNet - a deep learning architecture for molecules and materials," arXiv: 1712.06113v3 [physics.chem-ph] 22 March 2018, 11 pages as cited in the IDS dated 08/04/2023) as applied above, and further in view of Kasina et al. (US 6024937 A).
As per claim 15, the rejection of claim 1 is incorporated, but the combination does not specifically teach, as a whole, wherein predicting, using the machine learning model, the charge and the chemical potential of each segment of the plurality of segments based on the 3D structure model and the generated surface model comprises: correcting one or more residual charges of the plurality of segments; and determining an overall formal charge of the plurality of segments based on the corrected one or more residual charges of the plurality of segments, wherein the determined overall formal charge is the predicted charge of the plurality of segments.
However, the combination further teaches wherein predicting, using the machine learning model, the charge and the chemical potential of each segment of the plurality of segments based on the 3D structure model and the generated surface model and a determined charge including the predicted charge of the plurality of segments (e.g. Fan, in paragraphs 26 and 40, “extract features of the 3D conformations generated by 3D conformation generator 112. Processing component 110 may further include a property predictor 116 configured to employ the neural network to predict properties…of the compound based on features extracted by feature extractor… bond environment of each atom in the amino acids of a protein”; Kaser, in pages 5-6, 21, 23, and 45, “ML models and their application in computational chemistry… [using] chemical bond… Bag of Bonds… bond distance… [for] predicted atomic charges”; Schutt, in pages 4-6 sections A and C, “SchNet models… predict various properties… visualize the learned representation with a "local chemical potential"… “local chemical potentials" inferred by the networks”) and Kasina teaches correcting one or more residual charges and determining an overall formal charge based on the corrected one or more residual charges, wherein the determined overall formal charge is a determined charge (e.g. in column 16 lines 15-33, “residual positive charge of these cationic metal chelates results from chelation of the positively charged metal or metal oxide or nitride (e.g., Tc=0, +3) with a chelating compound which complexes the metal or metal oxide or nitride through only two formal negative charges… The overall charge of such a metal chelate is +1 by virtue of the chelating sulfur atoms each bearing single formal negative charge, thus reducing the +3 charge due to the metal species by -2 [i.e. correcting] through complexation with each of the sulfur atoms”). 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 teachings of the combination to include the teachings of Kasina because one of ordinary skill in the art would have recognized the benefit of accounting for residual charges.
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Fan et al. (US 20190108320 A1) in view of Kaser et al. (“Neural Network Potentials for Chemistry: Concepts, Applications and Prospects”, arXiv:2209.11581v3 [physics.chem-ph] 22 Dec 2022, 96 pages) and Schutt et al. ("SchNet - a deep learning architecture for molecules and materials," arXiv: 1712.06113v3 [physics.chem-ph] 22 March 2018, 11 pages as cited in the IDS dated 08/04/2023) as applied above, and further in view of Klamt et al. ("The COSMO and COSMO-RS solvation models," WIREs Comput Mol Sci 2017, e1338. doi: 10.1002/wcms.1338, 2017, 11 pages as cited in the IDS dated 08/04/2023).
As per claim 18, the rejection of claim 1 is incorporated, but the combination does not specifically teach wherein generating the surface model representing the environment comprises employing a cavity construction model. However, Klamt teaches generating a surface model representing an environment comprising employing a cavity construction model (e.g. in pages 2, 4, and 8, “Surface Charge Models… for a given solute geometry, first, a cavity r separating the solute volume from the embedding dielectric continuum is constructed and is described as a set of m surface segments, with positions…and area … geometry optimization of the solute in the presence of the dielectric solvent. In such cases, each geometry update requires a new cavity generation”). 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 teachings of the combination to include the teachings of Klamt because one of ordinary skill in the art would have recognized the benefit of geometry optimization of a solute.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
For example,
Rong et al. (US 20210158904 A1) teaches “generate a chemical structure graph corresponding to the chemical structure information according to the chemical structure information, where the chemical structure graph may include a node corresponding to the atom and an edge corresponding to the chemical bond…and predict properties of the target compound according to the target feature of the edge, and output a property prediction result of the target compound” (e.g. in paragraph 34).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM WONG whose telephone number is (571)270-1399. The examiner can normally be reached Monday-Friday 9am-5pm.
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, TAMARA KYLE can be reached at (571)272-4241. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/W.W/Examiner, Art Unit 2144 04/18/2026
/TAMARA T KYLE/Supervisory Patent Examiner, Art Unit 2144
Prosecution Insights