DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Applicant's response filed 3/16/2026 has been fully considered. The following rejections
and/or objections are either reiterated or newly applied.
Status of Claims
Claims 1, 3-9, 11-15, and 17-20 pending and examined on the merits.
Claims 2, 10, and 16 canceled.
Priority
The instant application filed on 1/7/2022 claims the benefit of foreign priority to Patent Application No. CN202110367301.8 filed on 4/6/2021. Thus, the effective filing date of the claims is 4/6/2021.
The applicant is reminded that amendments to the claims and specification must comply with 35 U.S.C. § 120 and 37 C.F.R. § 1.121 to maintain priority to an earlier-filed application. Claim amendments may impact the effective filing date if new subject matter is introduced that lacks support in the originally filed disclosure. If an amendment adds limitations that were not adequately described in the parent application, the claim may no longer be entitled to the priority date of the earlier filing.
Withdrawn Rejections
35 USC § 112(b)
The rejection of claim 4 under 35 USC 112(b) withdrawn in view of Applicant's claim amendments filed on 3/16/2026.
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, 3-9, 11-15, and 17-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of a mental process, a mathematical concept, organizing human activity, or a law of nature or natural phenomenon without significantly more. 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 1). In the instant application, the claims recite the following limitations that equate to an abstract idea:
Claims 1, 9, and 15: “determining a correlation between a candidate drug and a target” and “determining a parameter value of the correlation between the candidate drug and the target in accordance with the second atom feature of the atomic node set” provides a mathematical relationship (determining a correlation involves calculating a mathematical relationship) that is considered a mathematical concept, which is an abstract idea.
“establishing a spatial molecular graph of the candidate drug and the target” provides a mathematical calculation (establishing a spatial molecular graph involves determining spatial differences which involves mathematical calculations of distance, specifically in reference to para.0031-32 "A distance between any two atoms in the atomic node set in the three-dimensional space is calculated in advance to obtain a distance matrix D") that is considered a mathematical concept, which is an abstract idea.
“establishing the spatial molecular graph in accordance with a distance between atomic nodes in the atomic node set” provides a mathematical calculation (similar to claim 1, establishing a spatial molecular graph involves determining spatial differences which involves mathematical calculations of distance) that is considered a mathematical concept, which is an abstract idea.
“a distance between two atomic nodes in the atomic node set for any edge in the edge set is smaller than or equal to a predetermined distance threshold” provides an evaluation (determining whether a distance is smaller than or equal to a threshold involves a comparison) that may be performed in the human mind and is therefore considered a mental process, which is an abstract idea.
Claims 3, 7, 11, and 17: “encoding a distance between atomic nodes in the atomic node set to obtain a first distance vector between the atomic nodes in the atomic node set” provides a mathematical calculation (encoding a distance between nodes involves calculations) that is considered a mathematical concept, which is an abstract idea.
Claims 5, 13, and 19: “determining a neighboring edge set for an edge between an ith atomic node and a jth atomic node in the edge set” provides a mathematical calculation (determining an edge set requires solving for the set) that is considered a mathematical concept, which is an abstract idea.
“determining an initial feature representation of the edge in the neighboring edge set in accordance with a target distance vector between atomic nodes for the edge in the neighboring edge set, a first atom feature of the atomic nodes for the edge in the neighboring edge set, as well as a first activation function, a first transfer matrix, and an offset vector in the first GAT” provides a mathematical calculation (determining a feature representation requires calculations between vertices) that is considered a mathematical concept, which is an abstract idea.
“determining a first standardized weight in accordance with the initial feature representation of the edge in the neighboring edge set, as well as a first weight matrix, a second activation function, and a first attention weight in the first GAT” provides a mathematical calculation and relationship (determining weights requires calculation, and an activation function is a mathematical relationship) that are considered mathematical concepts, which are abstract ideas.
“determining a target feature representation of the edge between the ith atomic node and the jth atomic node in accordance with the initial feature representation of the edge in the neighboring edge set, the first standardized weight, and the first weight matrix in the first GAT” provides a mathematical calculation (determining a feature representation requires calculations between vertices) that is considered a mathematical concept, which is an abstract idea.
Claims 6, 14, and 20: “determining a target neighboring edge set for the ith atomic node” provides a mathematical calculation (determining an edge set requires solving for the set) that is considered a mathematical concept, which is an abstract idea.
“determining the second atom feature of the ith atomic node in accordance with a target feature representation of the edge in the target neighboring edge set, the first atom feature of the i atomic node, a target distance vector between atomic nodes for the edge in the target neighboring edge set, as well as a second attention weight, a second transfer matrix, and a second weight matrix in the first GAT” provides a mathematical calculation (determining a feature representation requires calculations between vertices) that is considered a mathematical concept, which is an abstract idea.
These recitations are similar to the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), 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)) and 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)) that the courts have identified as concepts that can be practically performed in the human mind or are mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas. Additionally, while claims 9-20 recite performing some aspects of the analysis on “An electronic device comprising: at least one processor; and a memory in communication connection with the at least one processor, wherein the memory stores therein instructions” and “A non-transitory computer-readable storage medium storing therein computer instructions, wherein the computer instructions are configured to be executed by a computer”, there are no additional limitations that indicate that this requires anything other than carrying out the recited mental processes or mathematical concepts in a generic computer environment. Merely reciting that a mental process is being performed in a generic computer environment does not preclude the steps from being performed practically in the human mind or with pen and paper as claimed. If a claim 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. As such, claims 1, 3-9, 11-15, and 17-20 recite an abstract idea (Step 2A, Prong 1: YES).
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). The judicial exceptions listed above are not integrated into a practical application because the claims do not recite an additional element or elements that reflects an improvement to technology. Specifically, the claims recite the following additional elements:
Claims 1, 9, and 15: “inputting a first atom feature of the atomic node set and the spatial molecular graph into a first Graph Attention Network (GAT)” provides insignificant extra-solution activities (inputting data into a model is a pre-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
“prediction to obtain a second atom feature of the atomic node set” provides insignificant extra-solution activities (outputting data from a model is a post-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claims 3, 7, 11, and 17: “converting the first distance vector between the atomic nodes in the atomic node set into a target distance vector between the atomic nodes in the atomic node set” provides insignificant extra-solution activities (transforming data is a pre-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
“inputting the first atom feature of the atomic node set, the spatial molecular graph, and the target distance vector between the atomic nodes in the atomic node set into the first GAT” provides insignificant extra-solution activities (inputting data into a model is a pre-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Claims 4, 8, 12, and 18: “inputting the target distance vector” provides insignificant extra-solution activities (inputting data into a model is a pre-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
“using the first atom feature of the atomic node set, the target distance vector between the atomic nodes in the atomic node set, and the target feature representation of the edge in the edge set in accordance with the first GAT to predict the second atom feature of the atomic node set” (as interpreted above) provides insignificant extra-solution activities (outputting data from a model is a post-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
The steps for transforming input data prior to inputting and outputting data to and from computational models are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application because they are pre- and post-solution activities involving data gathering, data manipulation, and sample manipulation steps (see MPEP 2106.04(d)(2)). Furthermore, the limitations regarding implementing program instructions do not indicate that they require anything other than mere instructions to implement the abstract idea in a generic way or in a generic computing environment. As such, this limitation equates to mere instructions to implement the abstract idea on a generic computer that the courts have stated does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984. Therefore, claims 1, 3-9, 11-15, and 17-20 are directed to an abstract idea (Step 2A, Prong 2: NO).
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 because the claims recite additional elements that are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application, or equate to mere instructions to apply the recited exception in a generic way or in a generic computing environment.
As discussed above, there are no additional elements to indicate that the claimed “An electronic device comprising: at least one processor; and a memory in communication connection with the at least one processor, wherein the memory stores therein instructions” and “A non-transitory computer-readable storage medium storing therein computer instructions, wherein the computer instructions are configured to be executed by a computer” requires anything other than generic computer components in order to carry out the recited abstract idea in the claims. Claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible. MPEP 2106.05(f) discloses that mere instructions to apply the judicial exception cannot provide an inventive concept to the claims. Additionally, the limitations for transforming input data prior to inputting and outputting data to and from computational models are insignificant extra-solution activities that do not serve to integrate the recited judicial exceptions into a practical application. Furthermore, no inventive concept is claimed by these limitations as they are well-understood, routine, and conventional.
The 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 claims do not amount to significantly more than the judicial exception itself (Step 2B: No). As such, claims 1, 3-9, 11-15, and 17-20 are not patent eligible.
Response to Arguments under 35 USC § 101
Applicant’s arguments filed 3/16/2026 are fully considered but they are not persuasive.
Applicant asserts that independent claims 1, 9, and 15 is not directed to the judicial exception of an abstract idea because they "explicitly require 'establishing a spatial molecular graph of the candidate drug and the target', in which the atomic node set simultaneously includes atoms of the candidate drug and atoms of the target, and the edge set includes at least one atom connection edge". Applicant further argues that "this feature is not abstract data collection or organization" which is "not a mere pre-solution data manipulation as characterized in the Office Action" (Remarks 3/16/2026 pages 4-5). Examiner agrees that this limitation is "not a mere pre-solution data manipulation", and notes that the Office Action characterized the cited limitation as a judicial exception because it provides a mathematical calculation (establishing a spatial molecular graph involves determining spatial differences which involves mathematical calculations of distance, specifically in reference to para.0031-32 "A distance between any two atoms in the atomic node set in the three-dimensional space is calculated in advance to obtain a distance matrix D") that is considered a mathematical concept, which is an abstract idea.
Applicant argues that in claim 3, "encoding a distance between atomic nodes into a first distance vector and coverting the first distance vector into a target distance vector [] constitute improvements to the structure and input representation of a specific machine learning model rather than optional data manipulation (Remarks 3/16/2026 page 5). Examiner asserts that while the data manipulation may provide structure to the input representation, optionality was never in question and is not part of the Step 2A, Prong 2 analysis. Therefore, the cited additional elements of claim 3 remain as insignificant extra-solution activities (transforming data and inputting data into a model are pre-solution activities involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Applicant also asserts that the invention, taken as a whole, provides an improvement to "the ability of a computer system to model three-dimensional molecular structural relationships" because the claimed architecture does "not merely apply generic mathematical operations using a conventional model; rather, they define an improved graph attention network computation framework" (Remarks 3/16/2026 pages 5-6). Examiner notes that the mathematical operations being generic or the model being conventional is not in question, rather it is the mathematical steps performed to generate the model which are considered a mathematical concept, which is an abstract idea. For the judicial exceptions themselves, their conventionality is not material to the determination. Furthermore, Applicant asserts that "the claimed output is therefore not an abstract display of results but a technical output used in a concrete application". Examiner notes that the prediction outputs have been identified above as an additional element (not a judicial exception constituting an abstract idea) which provides insignificant extra-solution activities (outputting data from a model is a post-solution activity involving data manipulation steps) that do not serve to integrate the judicial exceptions into a practical application.
Therefore, the rejection of claims 1, 9, and 15 under 35 USC 101 is maintained. All other claims depend from these independent claims; therefore, their rejection is likewise maintained.
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.
Claims 1, 9, and 15 rejected under 35 U.S.C. 103 as being unpatentable over Xu et al. (CN-111816252) in view of Liu et al. (CN-111199779).
Regarding claims 1, 9, and 15, Xu teaches a method for determining a correlation between a candidate drug and a target (Page 1 claim 1 "A method of drug screening, comprising [] acquiring protein molecules and target molecules contained in a drug database [] determining structural features [] determining a node information transfer sub-network of a graph neural network in a drug screening model [] combining the protein molecules and the target molecules through the drug screening model [] and screening the drugs based on the activity of the protein molecules and the target molecule binding products").
Xu also teaches establishing a spatial molecular graph of the candidate drug and the target, the spatial molecular graph comprising an atomic node set and an edge set, the atomic node set comprising atoms in the candidate drug and atoms in the target, the edge set comprising at least one atom connection edge (Page 2 claim 3 "determining a node information transfer subnetwork of a graph neural network in a drug screening model using target amino acid chain nodes and edges based on structural features of the protein molecule" and claim 7 "determining a first node feature vector and a first edge feature vector in the structural features of the protein molecule [] determining a second node feature vector and a second edge feature vector in the structural feature of the target molecule").
Xu does not explicitly teach: inputting a first atom feature of the atomic node set and the spatial molecular graph into a first Graph Attention Network (GAT) for prediction to obtain a second atom feature of the atomic node set; nor determining a parameter value of the correlation between the candidate drug and the target in accordance with the second atom feature of the atomic node set.
However, Liu teaches inputting molecule characteristics to an attention network for screening activity of the molecule and determining a parameter value of the correlation (activity) between the candidate drug and the target in accordance with the second atom feature of the atomic node set (Page 1 Claim 1 "giving weight to the vector representing the characteristics of the drug molecules through an attention network to obtain a vector model of the drug molecules; and screening the activity of the drug molecules according to the vector model" as the activity of the drug molecule with a protein is a type of correlation parameter value).
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to apply the attention network of Liu to the graph neural network (GNN) of Xu in order to pass attention weighting between layers automatically without human participation (Xu page 11 paragraph 1 "the working process of an information transfer network (MPNN Message Passing Neural Networks) is firstly introduced, specifically, the forward propagation of MPNN comprises two stages, the first stage is called a Message Passing stage, and the second stage is called a readout stage" and Liu page 5 first paragraph after S15 description "According to the technical scheme, the structural information is expanded into n-dimensional vectors, and features are automatically extracted by using an LSTM network and an attention mechanism, so that the screening of the drug molecule activity is realized. The technical scheme of the invention has the advantages that: 1. activity the model is highly automatic, and the characteristic engineering construction without human participation is carried out in the whole process"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling drug-target interactions.
Furthermore, regarding claims 9 and 15, in In re Venner, 262 F.2d 91, 95, 120 USPQ 193, 194 (CCPA 1958), the court held that broadly providing an automatic or mechanical means to replace a manual activity which accomplish the same result is not sufficient to distinguish over the prior art (see also Manual of Patent Examining Procedure, U.S. Trademark and Patent Office, section 2144.04, III).
In the instant case, the claimed invention merely makes the process of Xu et al. and Liu et al. as computer-implemented or automatic and indeed accomplishes the same result. It is thus not sufficient to distinguish over Xu et al. and Liu et al. Therefore, the claimed invention, i.e. “An electronic device comprising: at least one processor; and a memory in communication connection with the at least one processor, wherein the memory stores therein instructions” (claim 9) and “A non-transitory computer-readable storage medium storing therein computer instructions, wherein the computer instructions are configured to be executed by a computer” (claim 15) would have been obvious to a person of ordinary skill in the art at the time the invention was made over the process disclosed by Xu et al. and Liu et al. There would have been a reasonable expectation of success because the court held regarding software that “writing code for such software is within the skill of the art, not requiring undue experimentation, once its functions have been disclosed.” Fonar Corp., 107 F.3d at 1549, 41 USPQ2d at 1805.
Regarding amendments to claims 1, 9, and 15 (which now encompass canceled claims 2, 10, and 16), Xu also teaches establishing the spatial molecular graph in accordance with a distance between atomic nodes in the atomic node set (Page 2 paragraph 4 "determining atoms and chemical bonds corresponding to the target molecules, and determining the structural characteristics of the target molecules based on the atoms and chemical bonds corresponding to the target molecules").
Xu also teaches a distance between two atomic nodes in the atomic node set for any edge in the edge set is smaller than or equal to a predetermined distance threshold (Page 2 paragraph 2 "determining an amino acid matrix map corresponding to the protein molecules based on the amino acid distance threshold" and page 10 paragraph 7 "the distance matrix is obtained, a fixed threshold d can be used").
Claims 3-4, 11-12, and 17-18 rejected under 35 U.S.C. 103 as being unpatentable over Xu et al. (CN-111816252) in view of Liu et al. (CN-111199779) as applied to claims 1, 9, and 15 above, and further in view of Verma et al. (Verma et al. "3D-QSAR in drug design-a review." Current topics in medicinal chemistry 10.1 (2010): 95-115).
Xu et al. in view of Liu et al. are applied to claims 1, 9, and 15.
Regarding claims 3-4, 11-12, and 17-18, Xu in view of Liu teach the method of Claims 1, 9, and 15 on which this claim depends/these claims depend, respectively.
Xu nor Liu explicitly teach: encoding a distance between atomic nodes in the atomic node set to obtain a first distance vector between the atomic nodes in the atomic node set; converting the first distance vector between the atomic nodes in the atomic node set into a target distance vector between the atomic nodes in the atomic node set; inputting the first atom feature of the atomic node set and the spatial molecular graph into the first GAT for prediction to obtain the second atom feature of the atomic node set comprises: inputting the first atom feature of the atomic node set, the spatial molecular graph, and the target distance vector between the atomic nodes in the atomic node set into the first GAT for prediction to obtain the second atom feature of the atomic node set; inputting the target distance vector between the atomic nodes in the atomic node set, the spatial molecular graph, and the first atom feature of the atom node set into the first GAT for prediction, to obtain a target feature representation of an edge in the edge set; nor using the first atom feature of the atomic node set, the target distance vector between the atomic nodes in the atomic node set, and the target feature representation of the edge in the edge set in accordance with the first GAT to predict the second atom feature of the atomic node set (as interpreted above)
However, Verma teaches generating the distance between molecular structures (structuring the data as a vector is also suggested) as input into a QSAR (quantitative structure-activity relationships) model for predicting ligand affinity for their binding sites (Page 5 col 2 paragraph 1 "Computationally the 3D-structures can be generated by three methods: (a) [], (b) numerically by using mathematical techniques like distance geometry, quantum or molecular mechanics []", coupled with the graph neural network and attention network of Xu and Liu, it would have been obvious to one of ordinary skill in the art to combine these model approaches with the data structures of Verma).
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Xu and Liu as taught by Verma in order to correlate drug molecules with potential targets (Page 1 Abstract "In the classical QSAR studies, affinities of ligands to their binding sites, inhibition constants, rate constants, and other biological end points, with atomic, group or molecular properties such as lipophilicity, polarizability, electronic and steric properties (Hansch analysis) or with certain structural features (Free-Wilson analysis) have been correlated"). One skilled in the art would have a reasonable expectation of success because both methods are modeling molecular interactions.
Claims 5-8, 13-14, and 19-20 rejected under 35 U.S.C. 103 as being unpatentable over Xu et al. (CN-111816252) in view of Liu et al. (CN-111199779) and Verma et al. (Verma et al. "3D-QSAR in drug design-a review." Current topics in medicinal chemistry 10.1 (2010): 95-115) as applied to claims 1, 3-4, 9, 11-12, 15, and 17-18 above, and further in view of Pitman et al. (US-20140052755).
Xu et al. in view of Liu et al. and Verma et al. are applied to claims 1, 3-4, 9, 11-12, 15, and 17-18.
Regarding claims 5-6, 13-14, and 19-20, Xu in view of Liu and Verma teach the method of Claims 4, 12, and 18 on which this claim depends/these claims depend, respectively.
Xu and Liu also teach determining a neighboring edge set for an edge between an ith atomic node and a jth atomic node in the edge set, where i and j are integers, 1<=i<=N, 1<=j<=M, N represents a total quantity of atomic nodes in the atomic node set, and M represents a quantity of atomic nodes in the atomic node set that have an edge with the ith atomic node (Xu, Page 7 Detailed Description paragraph 8 "the representation of the node is influenced by the neighbor nodes around the node, and the connection of the graph is unchanged; the representation of graph structure enables graph-based reasoning" and Liu, Page 5 Embedding Layer "The Embedding layer is used for converting structural information represented by long integer numbers into floating point data information with n dimensions. The dimension n is used as a network hyper-parameter and can be obtained by parameter adjustment. As shown in FIG. 3, the drug molecule and pathogenic protein complex is expressed by SMILES and then converted into n-scale structural information through the Embedding layer").
Liu also teaches determining an initial feature representation of the edge in the neighboring edge set in accordance with a target distance vector between atomic nodes for the edge in the neighboring edge set, a first atom feature of the atomic nodes for the edge in the neighboring edge set, as well as a first activation function, a first transfer matrix, and an offset vector in the first GAT [claims 5, 13, and 19] and determining the second atom feature of the ith atomic node in accordance with a target feature representation of the edge in the target neighboring edge set, the first atom feature of the i atomic node, a target distance vector between atomic nodes for the edge in the target neighboring edge set, as well as a second attention weight, a second transfer matrix, and a second weight matrix in the first GAT [claims 6, 14, and 20] (Page 4 paragraph 3 "the virtual drug screening method based on molecular docking further comprises the step that the attention network comprises a first attention network and a second attention network, the first attention network adopts a relu activation function to screen effective vectors, and the second attention network adopts a sigmoid activation function to enable the weight to be within the range of 0-1" and describes input matrices (of all parameters, including molecular features and distance vectors) for the models used [claims 5, 13, and 19], and the two activation functions are used in series as described at the bottom of page 4 [claims 6, 14, and 20]).
Liu also teaches determining a target feature representation of the edge between the ith atomic node and the jth atomic node in accordance with the initial feature representation of the edge in the neighboring edge set, the first standardized weight, and the first weight matrix in the first GAT (Page 3 Disclosure of Invention paragraph 2 "According to an embodiment of the invention, a virtual drug screening method based on molecular docking comprises the following steps: inputting drug molecule information; converting the drug molecule information into n-dimensional floating point data information; outputting information of each atom of the drug molecules according to n-dimensional floating point type data information by adopting an LSTM network, and summarizing the information of each atom to obtain a vector representing the characteristics of the drug molecules; giving weight to the vector representing the characteristics of the drug molecules through an attention network to obtain a vector model of the drug molecules; the activity of the drug molecules was screened according to the vector model").
Xu, Liu, nor Verma teach determining a first standardized weight in accordance with the initial feature representation of the edge in the neighboring edge set, as well as a first weight matrix, a second activation function, and a first attention weight in the first GAT
However, Pitman teaches a tuning procedure based on weights of various feature components of the query molecule (Para.0074 "Features taken from a query molecule are used to foam alignments with fragment pairs in the database. An assembly algorithm may then be used to merge the fragment pairs into full structures, aligned to the query. Important to the system 100 is the use of a context adaptive descriptor scaling procedure as the basis for similarity. This helps to allow the user to tune the weights of the various feature components based on examples relevant to the particular context under investigation").
Therefore, it would have been obvious to one of ordinary skill in the art as of the effective filing date of the claimed invention to modify the methods of Xu, Liu, and Verma as taught by Pitman in order to determine if the base molecule can be merged with or bind a target molecule (para.0158 "The first phase of an assembly step may be termed the base expansion phase. In this phase, the list of potential merges of fragment pairs with bases may be determined. It results from consideration of the fronts of the growing bases. The front of a base is defined as the set of rotatable bond edges between a matched and an unmatched fragment node on the fragment graph. Any fragment pair from the set of hypotheses that includes both a frontal rotatable bond edge and matches the fragment conformer present in the base can potentially merge with the base"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling interaction and/or binding of molecules.
Regarding claims 7-8, Xu in view of Liu and Pitman teach the method of Claim 1 on which this claim depends/these claims depend.
Verma also teaches generating the distance between molecular structures (structuring the data as a vector is also suggested) as input into a QSAR (quantitative structure-activity relationships) model for predicting ligand affinity for their binding sites (Page 5 col 2 paragraph 1 "Computationally the 3D-structures can be generated by three methods: (a) [], (b) numerically by using mathematical techniques like distance geometry, quantum or molecular mechanics []", coupled with the graph neural network and attention network of Xu and Liu, it would have been obvious to one of ordinary skill in the art to combine these model approaches with the data structures of Verma).
Response to Arguments under 35 USC § 103
Applicant’s arguments filed 3/16/2026 are fully considered but they are not persuasive.
Applicant asserts that "the proposed combination of Xu and Liu fails to arrive at the invention of claim 1, as amended to incorporate claim 2" (Remarks 3/16/2026 page 7). Applicant argues that the proposed combination lacks a first and second "establishing step" (Remarks 3/16/2026 pages 8-10). Specifically, Applicant argues that "Xu's claims 3 and 7 do not disclose establishing a spatial molecular graph that jointly represents a candidate drug and a target as required by [instant] claim 1" (Remarks 3/16/2026 page 8). Examiner notes that Xu in fact does represent a protein graph and small molecule (target) graph jointly (page 1 abstract "combining the protein molecule and the target molecule through a drug screening model; the screening of the drugs is realized based on the activity of the protein molecule and target molecule combination product, so that the structural characteristics of a protein graph and a small molecule graph can be effectively expressed through a drug screening model, the protein molecule and the target molecule can be accurately combined"). Further, Applicant argues that Xu does not teach or suggest instant claim 2, Liu is not cited as teaching this element, therefore amended claim 1 is not taught (Remarks 3/16/2026 page 9). Examiner notes that Xu has been indicated above as teaching claim 2 (Page 2 paragraph 4 "determining atoms and chemical bonds corresponding to the target molecules, and determining the structural characteristics of the target molecules based on the atoms and chemical bonds corresponding to the target molecules"), therefore amended claim 1 is also taught or suggest by the combination of Xu and Liu.
Applicant also asserts that the nodes involved in Xu's graph correspond to amino acid chains rather than atoms (Remarks 3/16/2026 page 10). Examiner agrees that while Xu does not explicitly teach distances and thresholding between individual atoms, Liu does explicitly suggest including these and other parameters based on molecular docking ("According to an embodiment of the present invention, a virtual drug screening device based on molecular docking includes: the drug molecule information includes: atom type, chemical bond energy size, atomic spacing, and type of bound amino acid" and page 1 claim 2). Therefore, it would have been obvious for the reasons mentioned above (section "Claim Rejections - 35 USC 103") to combine Xu and Liu in order to arrive at the claimed atomic node set which has been incorporated into claim 1.
Applicant also asserts that Liu fails to teach or suggest "inputting a first atom feature of the atomic node set and the spatial molecular graph into a first Graph Attention Network (GAT) for prediction to obtain a second atom feature of the atomic node set (Remarks 3/16/2026 pages 11-13). Specifically, Applicant argues that "the attention network disclosed in Liu is not a Graph Attention Network (GAT)" because Liu does not disclose a "graph attention message passing mechanism - operating on a spatial molecular graph and producing updated atom-level features" (Remarks 3/16/2026 page 12). Examiner notes that while Liu does not explicitly suggest a GAT, its combination with Xu would render the limitation obvious for the reasons mentioned above (section "Claim Rejections - 35 USC 103") to combine Xu and Liu in order to arrive at the claimed inputting and prediction mechanism of claim 1. Applicant also argues that Liu does not disclose predicting second atom features or determining a drug-target correlation parameter (Remarks 3/16/2026 pages 12-13). Examiner has indicated above that Liu does in fact teach predicting second atom features in the form of a vector model, and that drug activity prediction is also performed which is encompasses under the broadest reasonable interpretation of "a drug-target correlation parameter" (Page 1 Claim 1 "giving weight to the vector representing the characteristics of the drug molecules through an attention network to obtain a vector model of the drug molecules; and screening the activity of the drug molecules according to the vector model").
Therefore, the rejection of claims 1, 9, and 15 under 35 USC 103 is maintained. All other claims depend from these independent claims; therefore, their rejection is likewise maintained.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Application No. 18/126,887 in view of Xu et al. (CN-111816252). Although the claims at issue are not identical, they are not patentably distinct from each other because both involve graph-based drug-target correlation prediction using molecular features. Both also utilize models involving an attention mechanism.
While application 18/126,887 does not explicitly teach using a graph attention network for prediction, it would have been obvious to one of ordinary skill in the art to apply the attention mechanism of 18/126,887 to the graph neural network (GNN) of Xu in order to pass attention weighting between layers automatically without human participation (Xu page 11 paragraph 1 "the working process of an information transfer network (MPNN Message Passing Neural Networks) is firstly introduced, specifically, the forward propagation of MPNN comprises two stages, the first stage is called a Message Passing stage, and the second stage is called a readout stage" and Liu page 5 first paragraph after S15 description "According to the technical scheme, the structural information is expanded into n-dimensional vectors, and features are automatically extracted by using an LSTM network and an attention mechanism, so that the screening of the drug molecule activity is realized. The technical scheme of the invention has the advantages that: 1. activity the model is highly automatic, and the characteristic engineering construction without human participation is carried out in the whole process"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling drug-target interactions.
Claims 1-20 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Application No. 18/895,554 in view of Liu et al. (CN-111199779). Although the claims at issue are not identical, they are not patentably distinct from each other because both involve graph-based drug-target correlation prediction using molecular features. Both also utilize models involving a type of deep learning network.
While application 18/126,887 does not explicitly teach using a graph attention network for prediction, it would have been obvious to one of ordinary skill in the art to apply the deep learning network model of 18/126,887 to the attention network of Liu in order to pass attention weighting between layers automatically without human participation (Liu page 5 first paragraph after S15 description "According to the technical scheme, the structural information is expanded into n-dimensional vectors, and features are automatically extracted by using an LSTM network and an attention mechanism, so that the screening of the drug molecule activity is realized. The technical scheme of the invention has the advantages that: 1. activity the model is highly automatic, and the characteristic engineering construction without human participation is carried out in the whole process"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling drug-target interactions.
Claims 1-20 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Application No. 17/820,688 in view of Liu et al. (CN-111199779). Although the claims at issue are not identical, they are not patentably distinct from each other because both involve graph-based drug-target correlation prediction using molecular features. Both also utilize models involving a graph neural network or GNN.
While application 17/820,688 does not explicitly teach using a graph attention network for prediction, it would have been obvious to one of ordinary skill in the art to apply the GNN model of 17/820,688 to the attention network of Liu in order to pass attention weighting between layers automatically without human participation (Liu page 5 first paragraph after S15 description "According to the technical scheme, the structural information is expanded into n-dimensional vectors, and features are automatically extracted by using an LSTM network and an attention mechanism, so that the screening of the drug molecule activity is realized. The technical scheme of the invention has the advantages that: 1. activity the model is highly automatic, and the characteristic engineering construction without human participation is carried out in the whole process"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling drug-target interactions.
Claims 1-20 rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Application No. 17/570,416 in view of Liu et al. (CN-111199779). Although the claims at issue are not identical, they are not patentably distinct from each other because both involve graph-based drug-target correlation prediction using molecular features. Both also utilize models involving a type of deep learning network (training a loss function).
While application 17/570,416 does not explicitly teach using a graph attention network for prediction, it would have been obvious to one of ordinary skill in the art to apply the deep learning network model of 17/570,416 to the attention network of Liu in order to pass attention weighting between layers automatically without human participation (Liu page 5 first paragraph after S15 description "According to the technical scheme, the structural information is expanded into n-dimensional vectors, and features are automatically extracted by using an LSTM network and an attention mechanism, so that the screening of the drug molecule activity is realized. The technical scheme of the invention has the advantages that: 1. activity the model is highly automatic, and the characteristic engineering construction without human participation is carried out in the whole process"). One skilled in the art would have a reasonable expectation of success because both methods are concerned with modeling drug-target interactions.
Response to Arguments under Double Patenting
Applicant’s arguments filed 3/16/2026 are fully considered but they are not persuasive.
Applicant asserts that they are "concurrently filing a terminal disclaimer over" U.S. Applicant Nos. 18/126,887, 18/895,554, 17/820,688, and 17/570,416 (Remarks 3/16/2026 pages 14-15). Examiner notes that no such terminal disclaimer has been filed for the instant application or any of the applications mentioned above as evidenced by no terminal disclaimer fees being paid according to the latest fee worksheets.
Conclusion
No claims are allowed.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the TH REE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this finaI action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Robert A. Player whose telephone number is (571)272-6350. The examiner can normally be reached Mon-Fri, 8am-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, Larry D. Riggs can be reached on 571-270-3062. 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.
/R.A.P./Examiner, Art Unit 1686
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights