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 .
Claim Status
Claims 1-20 are pending and examined herein.
Claims 1-20 are rejected.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55. Claims 1-20 are granted the claim to the benefit of priority to foreign application CN202210314863.0 filed 28 March 2022. Thus, the effective filling date of claims 1-20 is 28 March 2022.
Information Disclosure Statement
The information disclosure statements (IDS) were received on 11 July 2024 and 16 October 2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements have been considered by the examiner.
Drawings
The drawings received 27 March 2023 are objected to for the reason provided below.
The drawings are objected to because “Fig. 1, Fig. 2, Fig. 3…” should read “FIG. 1, FIG. 2, FIG. 3…”. The MPEP states “View numbers must be preceded by the abbreviation "FIG."” (see MPEP 608.02(V) and 37 C.F.R. 1.84(u)(1)). Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Interpretation
Claim 2 recites “setting, in response to determining that a number of the plurality of edges is greater than a number of the plurality of chemical bonds, an edge vector representation of each virtual edge to a preset value…” and claim 12 recites “setting, in response to determining that a number of the plurality of edges comprised in the first fully connected graph is greater than a number of the plurality of first chemical bonds, an edge vector representation of each first virtual edge to a first preset value…” which are contingent limitations. The MPEP states the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met (see MPEP 2111.04(II)). The BRI of claims 2 and 12 do not require the limitation of setting an edge vector representation of each virtual edge to a preset value because there exists an embodiment of the claim where the condition of a number of the plurality of edges is greater than a number of the plurality of chemical bonds is not met.
Claim 16 recites “setting, in response to determining that a number of the plurality of edges is greater than a number of the plurality of chemical bonds, an edge vector representation of each virtual edge to a preset value…” and claim 19 recites “setting, in response to determining that a number of the plurality of edges is greater than a number of the plurality of chemical bonds, an edge vector representation of each virtual edge to a preset value…” which are contingent limitations. The MPEP states the broadest reasonable interpretation of a system (or apparatus or product) claim having structure that performs a function, which only needs to occur if a condition precedent is met, requires structure for performing the function should the condition occur (see MPEP 2111.04(II)). The BRI of claims 16 and 19 require that the system and non-transitory computer readable medium have structure for performing setting an edge vector representation of each virtual edge to a preset value should the condition of that a number of the plurality of edges is greater than a number of the plurality of chemical bonds occur.
Claim 11 recites “wherein the trained molecular representation model is trained based on operations comprising: obtaining input features and at least one attribute label of a sample molecule… inputting the input features into a molecular representation model to obtain a first molecular vector representation… inputting the first molecular representation into a predictor…, and adjusting, based on the at least one predicted attribute and the at least one attribute label…” which is a product by process limitation and the claimed method does not require active steps of training the molecular representation model (see MPEP 2113(I)). Claims 13 and 14 further limit the product by process limitations of claim 11 by further limiting the step of inputting the input features into the molecular representation model to obtain the first molecular vector representation, output by the molecular representation model, of the sample molecule (claim 13) and furthering limiting the attribute labels (claim 14).
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.
Claim 12 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 12 recites “the method according to claim 11, wherein the sample molecule further comprises a plurality of first chemical bonds… and the method further comprises: obtaining a first atom feature information of each of the plurality of first atoms and a first chemical bond feature information of each of the plurality of first chemical bonds…” which renders the metes and bounds of the claim indefinite. The indefiniteness arises because it is unclear if the recited steps after “the method further comprises:” is meant to further provide steps of the process of how the trained molecular representation model is trained (i.e., further limiting the process of the product by process limitations set out in claim 11) or if the recited steps after “the method further comprises:” is meant to further add method steps of the claims from which claim 12 depends from. For the sake of furthering examination, the limitations in claim 12 will be interpreted as further limiting the process of the product by process limitations set out in claim 11.
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 a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
(Step 1)
Claims 1-14 fall under the statutory category of a process and claims 15-20 fall under the statutory category of a machine.
(Step 2A Prong 1)
Under the BRI, the instant claims recite judicial exceptions that are an abstract idea of the type that is in the grouping of a “mental process”, such as procedures for evaluating, analyzing or organizing information, and forming judgement or an opinion. The instant claims further recite judicial exceptions that are an abstract idea of the type that is in the grouping of a “mathematical concept”, such as mathematical relationships and mathematical equations.
Independent claims 1, 15, and 18 recite mental processes of “obtaining a feature information of a molecule, wherein the molecule comprises a plurality of atoms”, “generating a fully connected graph of the plurality of atoms, wherein the fully connected graph comprises…”, “generating, based on the feature information, a plurality of atom vector representations and a plurality of edge vector representations, wherein the plurality of atom vector representations correspond to…”, and “generating, based on the plurality of updated atom vector representations, a molecular vector representation of the molecule”.
Independent claim 1 recites mathematical concepts of “generating, based on the feature information, a plurality of atom vector representations and a plurality of edge vector representations, wherein the plurality of atom vector representations correspond to…”, “performing, based on the fully connected graph, at least one aggregation on the plurality of atom vector representations and the plurality of edge vector representations to obtain…”, and “generating, based on the plurality of updated atom vector representations, a molecular vector representation of the molecule”.
Claim 8 recites a mental process and mathematical concept of “predicting, based on the molecular vector representation, at least one attribute of the molecule”.
The claims recite mental processes of as an observation (obtaining a feature information of a molecule), organizing data (generating a fully connected graph), and analyzing/evaluating data (generating, based on the feature information, a plurality of atom vector representations and a plurality of edge vector representations and generating, based on the plurality of updated atom vector representations, a molecular vector and predicting at least one attribute based on the molecular vector representation). The claims recite mathematical concepts of mathematical relationships as generating vector representations of atoms and edges using feature information and generating a molecular vector representation using updated atom vector representations (manipulating data and organizing data into mathematical representations) and a mathematical concept of mathematical calculations as performing aggregation (which encompasses aggregation utilizing a series of mathematical calculations and operations on the numerical vector representations as shown in [0114]-[0128] of the instant disclosure) and predicting properties using the vector molecular vector representation (which encompasses using a function on the vector representations to produce a numerical output of an attribute). Dependent claims 2-7, 9, 10-14, 16, 17, 19, and 20 further limit the mental process/mathematical concept recited in the independent claim but do not change their nature as a mental process/mathematical concept. Thus, claims 1-20 recite abstract ideas.
(Step 2A Prong 2)
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). Integration into a practical application is evaluated by identifying whether there are any additional elements recited in the claim and evaluating those additional elements to determine whether they integrate the exception into a practical application.
The additional element in claims 1, 15, 18 of using a generic computer to perform judicial exceptions, an electronic device comprising a processor and memory for performing judicial exceptions, and a non-transitory computer readable medium storing instruction to cause processors to perform judicial exceptions do not integrate the judicial exceptions into a practical application because this is applying the judicial exceptions to a generic computer without an improvement in computer technology. The additional elements of the generic computer/computer environment only interacts with the judicial exceptions in a manner of being utilized as a tool to perform the judicial exceptions.
Thus, the additional elements do not integrate the judicial exceptions into a practical application and claims 1-20 are directed to the abstract idea.
(Step 2B)
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because:
The additional element in claims 1, 15, 18 of using a generic computer to perform judicial exceptions, an electronic device comprising a processor and memory for performing judicial exceptions, and a non-transitory computer readable medium storing instruction to cause processors to perform judicial exceptions is conventional as shown by MPEP 2106.05(b) and MPEP 2106.05(d)(II).
Thus, the additional elements are not sufficient to amount to significantly more than the judicial exception because they are conventional.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless – (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 8, 9, 10-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lu et al. "Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective." arXiv preprint arXiv:1906.11081 (2019).
Independent claim 1 is directed to a computer implemented method, comprising obtaining a feature information of a molecule, wherein the molecule comprises a plurality of atoms
Lu et al. shows obtaining feature information of a molecule such as atoms in the molecule, spatial information, and information of the type of edges for the fully connected graph (or complete undirected graph) (Lu et al. page 3 left col.).
generating a fully connected graph of the plurality of atoms, wherein the fully connected graph comprises a plurality of edges
Lu et al. shows generating a complete undirected graph (which is a type of fully connected graph) following the assumption that every atom has the interactions with others so that the set of edges satisfies E = N(N-1)/2 (where is E is the set of edges and N is the number of atoms in the molecule) (Lu et al. page 3 left col.).
generating, based on the feature information, a plurality of atom vector representations and a plurality of edge vector representations, wherein the plurality of atom vector representations correspond to the plurality of atoms respectively, and the plurality of edge vector representations correspond to the plurality of edges respectively
Lu et al. shows using an embedding layer to directly embed vertices and edges of a graph into vectors where each atom in the molecule is represented as a vector and the vertices in the entire molecule are denoted as a matrix which holds each atom embedding vector in the molecule (Lu et al. page 3 left col.). Lu et al. further shows using an embedding layer to generate a plurality of edge vectors (Lu et al. page 3 left col. “Embedding Layer” section).
performing, based on the fully connected graph, at least one aggregation on the plurality of atom vector representations and the plurality of edge vector representations to obtain a plurality of updated atom vector representations
Lu et al. shows performing aggregation of the atom vector representations and the edge vector representations, which are based the fully connected graph, through interaction layers to obtain update atom vector representations (Lu et al. page 3 right col. – page 4 left col. “Interaction Layer” section and page 4 Fig. 2).
and generating, based on the plurality of updated atom vector representations, a molecular vector representation of the molecule.
Lu et al. shows after the interaction layers which provide atom representations at different levels, various atom representations to obtain a final feature map through concatenation (Lu et al. page 4 left col. – right col. “Readout Layer” section and page 4 Fig. 2). The concatenation of the various atom representations represents a molecular vector representation of the molecule that holds information as a concatenation of atom representations at different levels produced by the interaction layers (Lu et al. pages 3-4 “Interaction Layer” and “Readout Layer” sections and page 4 Fig. 2).
Independent claim 15 is directed to an electronic device, comprising: one or more processors and a memory storing one or more programs configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the operations of method claim 1. Independent claim 18 is directed to a non-transitory computer-readable storage medium storing one or more programs comprising instructions that, when executed by one or more processors of a computing device, cause the computing device to perform the operations of method claim 1.
Lu et al. shows that the model which operates in the manner described above for the method is implemented on a single core of a Xeon E5-2660 (which is a computer system comprising memory and a processor) (Lu et al. page 8 left col.).
Claims 2, 16, and 19 are directed to wherein the molecule further comprises a plurality of chemical bonds among the plurality of atoms, wherein the feature information comprises an atom feature information of each of the plurality of atoms and a chemical bond feature information of each of the plurality of chemical bonds, wherein the plurality of edges comprise at least the plurality of chemical bonds, and wherein the generating, based on the feature information, the plurality of atom vector representations and the plurality of edge vector representations comprises:
Lu et al. shows the feature information comprises atom feature information (such as atom type) and edge feature information (such as chemical bonds) (Lu et al. page 3 left col. and page 4 Fig. 2).
generating, for each atom of the plurality of atoms, an atom vector representation of the atom at least based on a corresponding atom feature information of the atom, generating, for each chemical bond of the plurality of chemical bonds, an edge vector representation of the chemical bond at least based on a corresponding chemical bond feature information of the chemical bond
Lu et al. shows generating embedding atom vector representations based on atom feature information of an atom and generating embedding edge vector representation of the chemical bond based on chemical bond feature information (Lu et al. page 3 left col. “Embedding Layer” section and page 4 Fig. 2).
and setting, in response to determining that a number of the plurality of edges is greater than a number of the plurality of chemical bonds, an edge vector representation of each virtual edge to a preset value, wherein the virtual edge is any edge of the plurality of edges except the plurality of chemical bonds.
Lu et al. shows that the representations generated by the embedding layer are only related to the inherent property of isolated atoms and bonds which shows that the edge vector representations which are not chemical bonds are not represented in the initial embedding and is interpreted as setting these edges in the complete graph to a preset value of zero (Lu et al. page 3 left col.- right col.). Lu et al. shows that the interaction terms are modeled in later subnetwork (Lu et al. page 3 right col.).
Claim 8 is directed to predicting based on the molecular vector representation, at least one attribute of the molecule. Claim 9 is directed wherein the at least one attribute comprises at least one of a water solubility, a toxicity, a degree of matching with preset proteins, a compound reactivity, a stability, a degradability, and an energy.
Lu et al. shows predicting an energy using the molecular vector representation of the molecule (Lu et al. page 4 right col. “Readout Layer” section).
Claims 10, 17, and 20 are directed to wherein the performing, based on the fully connected graph, at least one aggregation on the plurality of atom vector representations and the plurality of edge vector representations to obtain a plurality of updated atom vector representations comprises: inputting the fully connected graph, the plurality of atom vector representations and the plurality of edge vector representations into an aggregation updating module of a trained molecular representation model to obtain the plurality of updated atom vector representations output by the aggregation updating module,
Lu et al. shows inputting the complete undirected molecular graph, edge type, and atom type through an embedding layer to produce atom vector embeddings and edge vector embeddings (which holds information of the fully connected graph) which are utilized in the interaction layers to obtain a plurality of updated atom vector representations produced by each respective interaction layer (Lu et al. pages 3-4 right col. – left col. “Interaction Layer” section and page 4 Fig. 2).
and wherein the generating, based on the plurality of updated atom vector representations, the molecular vector representation of the molecule comprises: inputting the plurality of updated atom vector representations into a representation module of the trained molecular representation model to obtain the molecular vector representation, output by the representation module, of the molecule.
Lu et al. shows inputting the plurality of updated atom vector representations into a readout layer which aggregates the various atom representations (i.e., the plurality of updated atom vector representations) through concatenating the representations produced by each interaction layer and the concatenation represents the molecule as a vector representation of atom at various levels (Lu et al. page 4 left col. – right col. “Readout Layer” section and page 4 Fig. 2).
Claim 11 is directed to wherein the trained molecular representation model is trained based on operations comprising: obtaining input features and at least one attribute label of a sample molecule, wherein the sample molecule comprises a plurality of first atoms, wherein the input features comprise a first fully connected graph of the plurality of first atoms, a plurality of first atom vector representations, and a plurality of edge vector representations of the sample molecule, wherein the plurality of first atom vector representations correspond to the plurality of first atoms, respectively, and wherein the plurality of edge vector representations of the sample molecule correspond to a plurality of edges comprised in the first fully connected graph, respectively; inputting the input features into a molecular representation model to obtain a first molecular vector representation, output by the molecular representation model, of the sample molecule; inputting the first molecular vector representation into a predictor to obtain at least one predicted attribute, output by the predictor, of the sample molecule; and adjusting, based on the at least one predicted attribute and the at least one attribute label, parameters of the molecular representation model to obtain the trained molecular representation model.
This limitation is interpreted as a product by process limitation which describes the product (the trained molecular representation model) through the process of training the model (see MPEP 2113(I)). The claimed method does not require active steps of training this model. Lu et al. shows a product, the model, which performs the recited operations of updating atom representation vectors and generating a molecular vector representation and thus is interpreted as being the same product.
Claim 12 is directed to wherein the sample molecule further comprises a plurality of first chemical bonds among the plurality of first atoms; the plurality of edges comprised in the first fully connected graph comprise at least the plurality of first chemical bonds, and the method further comprises: obtaining a first atom feature information of each of the plurality of first atoms and a first chemical bond feature information of each of the plurality of first chemical bonds; generating, for each first atom of the plurality of first atoms, a first atom vector representation of the first atom at least based on a corresponding first atom feature information of the first atom; generating, for each first chemical bond of the plurality of first chemical bonds, an edge vector representation of the first chemical bond at least based on a corresponding first chemical bond feature information of the first chemical bond; and setting, in response to determining that a number of the plurality of edges comprised in the first fully connected graph is greater than a number of the plurality of first chemical bonds, an edge vector representation of each first virtual edge to a first preset value, wherein the first virtual edge is any edge of the plurality of edges comprised in the first fully connected graph except the plurality of first chemical bonds.
These limitations are interpreted as further limiting the process of the product by process limitations which describes the product (the trained molecular representation model) through the process of training the model (see MPEP 2113(I)). The claimed method does not require active steps of training this model. Lu et al. shows a product, the model, which performs the recited operations of updating atom representation vectors and generating a molecular vector representation and thus is interpreted as being the same product.
Claim 13 is directed to wherein the inputting the input features into the molecular representation model to obtain the first molecular vector representation, output by the molecular representation model, of the sample molecule comprises: inputting the input features into the aggregation updating module to obtain a plurality of updated first atom vector representations output by the aggregation updating module, wherein the plurality of updated first atom vector representations are obtained by performing, based on the first fully connected graph, at least one aggregation on the plurality of first atom vector representations and the plurality of edge vector representations of the sample molecule; and inputting the plurality of updated first atom vector representations into the representation module to obtain the first molecular vector representation output by the representation module.
These limitations are interpreted as further limiting the product by process limitations which describes the product (the trained molecular representation model) through the process of training the model (see MPEP 2113(I)). The claimed method does not require active steps of training this model. Lu et al. shows a product, the model, which performs the recited operations of updating atom representation vectors and generating a molecular vector representation and thus is interpreted as being the same product.
Claim 14 is directed to wherein the at least one attribute labels and the at least one predicted attribute respectively comprise at least one of: a water solubility, a toxicity, a degree of matching with preset proteins, a compound reactivity, a stability, a degradability, and an energy.
These limitations are interpreted as further limiting the product by process limitations which describes the product (the trained molecular representation model) through the process of training the model (see MPEP 2113(I)). The claimed method does not require active steps of training this model. Lu et al. shows a product, the model, which performs the recited operations of updating atom representation vectors and generating a molecular vector representation and thus is interpreted as being the same product.
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 3-7 are rejected under 35 U.S.C. 103 as being unpatentable over Lu et al. as applied to claim 1 as applied to 35 U.S.C. 102 above, and further in view of Wang et al. (Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science, vol 12891. Springer, Cham).
Claim 3 is directed to wherein each aggregation of the at least one aggregation comprises: performing, for any atom of the plurality of atoms, an aggregation on a plurality of current atom vector representations and a plurality of current edge vector representations to obtain an updated atom vector representation of the atom based on an attention mechanism; and for any edge of the plurality of edges: updating, based on the updated atom vector representation of each of two atoms connected by the edge, a current edge vector representation of the edge to obtain a first edge vector representation of the edge, and performing, based on the attention mechanism, aggregation on a plurality of first edge vector representations of the plurality of edges to obtain an updated edge vector representation of the edge.
Lu et al. does not show wherein the aggregation to obtain updated vector representation of the atom is based on an attention mechanism or for and for any edge of the plurality of edges: updating, based on the updated atom vector representation of each of two atoms connected by the edge, a current edge vector representation of the edge to obtain a first edge vector representation of the edge, and performing, based on the attention mechanism, aggregation on a plurality of first edge vector representations of the plurality of edges to obtain an updated edge vector representation of the edge.
Like Lu et al., Wang et al. shows utilizing a deep learning architecture for processing graphs data structures with node embedding vectors and edge embedding vectors. Wang et al. shows a deep learning architecture with attention mechanisms for updating node features in the node embedding and for updating edge features of the edge embedding (Wang et al. page 255-256 “3.1 Preliminary” section). Wang et al. shows updating node features using node and edge features to produce higher level updated node features using an attention mechanism (Wang et al. page 256-257 “3.3 Node Module” section). Wang et al. shows updating edge features to produce higher level updated edge features using the updated node features of connecting edges utilizing an attention mechanism (Wang et al. page 257-258 “3.4 Edge Module” and Fig. 2).
Claim 4 is directed to wherein the updating, based on the updated atom vector representation of each of two atoms connected by the edge, the current edge vector representation of the edge to obtain the first edge vector representation of the edge comprises: determining, based on the updated atom vector representation of each of the two atoms connected by the edge, a vector representation variation of the edge, and adding the current edge vector representation and the vector representation variation of the edge to obtain the first edge vector representation of the edge.
Lu et al. does not show determining, based on the updated atom vector representation of each of the two atoms connected by the edge, a vector representation variation of the edge, and adding the current edge vector representation and the vector representation variation of the edge to obtain the first edge vector representation of the edge.
Wang et al. shows during updating of on an edge feature the current edge is combined with information of updated atom vector representations and aggregated edge features on each updated node (Wang et al. page 258 within “3.4 Edge Module” section and page 258 Fig. 2).
Claim 5 is directed to wherein the performing, based on the attention mechanism, aggregation on the plurality of first edge vector representations of the plurality of edges to obtain the updated edge vector representation of the edge comprises: determining at least one adjacent edge pair of the edge, wherein each adjacent edge pair of the at least one adjacent edge pair comprises two adjacent edges of the edge, and the two adjacent edges are connected with the edge to form a triangle, and performing, based on the attention mechanism, aggregation on the first edge vector representation of each of the edge and each adjacent edge in the at least one adjacent edge pair to obtain the updated edge vector representation of the edge.
Claim 6 is directed to wherein the two adjacent edges of each adjacent edge pair of the at least one adjacent edge pair comprise a first adjacent edge connected to a first end point of the edge and a second adjacent edge connected to a second end point of the edge, and wherein the performing, based on the attention mechanism, aggregation on the first edge vector representation of each of the edge and each adjacent edge in the at least one adjacent edge pair to obtain the updated edge vector representation of the edge comprises: performing, based on the attention mechanism, aggregation on the edge and a first edge vector representation of each first adjacent edge in the at least one adjacent edge pair to obtain a second edge vector representation of the edge, and performing, based on the attention mechanism, aggregation on the edge and a second edge vector representation of each second adjacent edge in the at least one adjacent edge pair to obtain the updated edge vector representation of the edge.
Claim 7 is directed to wherein an attention weight of the edge and each adjacent edge in the at least one adjacent edge pair is determined at least based on a shortest chemical bond distance between two atoms corresponding to the edge.
Lu et al. shows processing molecule graphs in a hierarchical order where the interaction layers analyze different levels of information with certain levels including information from four nodes of a connected graph which includes interactions from a particular edge and adjacent edge pairs (i.e., each edge connecting a particular node and in the case of four nodes in a complete graph there are three edges connected to each node) (Lu et al. pages 3-4 “Interaction Layer” and “Readout Layer” sections and page 4 Fig. 2)). Further, this information as three edges connecting at each node is interpreted as the edge and adjacent edge pair forming a triangle (Lu et al. pages 3-4 “Interaction Layer” and “Readout Layer” sections and page 4 Fig. 2). Lu et al. shows the edge embeddings include information on edge type (such as bond type between two atoms) and distance between atoms and implicitly captures shortest bond distance as an edge feature of the embedding (Lu et al. pages 3-4 “Interaction Layer” and “Readout Layer” sections and page 4 Fig. 2).
Lu et al. does not show performing aggregation, based on attention mechanism to obtain updated edge vectors utilizing.
Wang et al. shows performing aggregation utilizing an attention mechanism to produce aggregated edge features of a particular node which includes all edges connected to a single node which is then used to generate the updated edge vector representation (or high-level edge features for a particular edge connecting nodes) (Wang et al. page 258 within “3.4 Edge Module” section and page 258 Fig. 2). Wang et al. shows the attention mechanism is utilizes edge features for updating and aggregation (Wang et al. page 258 within “3.4 Edge Module” section and page 258 Fig. 2).
An invention would have been obvious to one or ordinary skill in the art if some motivation in the prior art would have led that person to modify reference teachings to arrive at the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to have modified the interaction layers of Lu et al. to incorporate the graph attention mechanism of which updates node features and edge features based on updated node features of Wang et al. because this would allow for a deep learning architecture which produces a molecular feature vector from a molecular graph (where edges embeddings represent features of particular bonds between atoms and distances between atoms and node embeddings represent features associated with atom types) utilizing graph attention mechanism which is capable of updating edge and node features by extracting high level features from the nodes and edges and performs well in node-sensitive and edge sensitive domains (Wang et al. abstract, page 256 “3.3 Node Module” section and pages 257-258 within “3.4 Edge Module” section). One would have a reasonable expectation of success because Lu et al. shows generating a molecular graph into node and edge embeddings while Wang et al. shows a process of updating edge and node embedding to extract higher level features utilizing an attention mechanism.
Conclusion
No claims are allowed.
This Office action is a Non-Final action. A shortened statutory period for reply to this action is set to expire THREE MONTHS from the mailing date of this action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN EDWARD HAYES whose telephone number is (571)272-6165. The examiner can normally be reached M-F 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, Olivia Wise can be reached at 571-272-2249. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/J.E.H./Examiner, Art Unit 1685
/KAITLYN L MINCHELLA/Primary Examiner, Art Unit 1685
Prosecution Insights