DETAILED ACTION
Applicant’s response filed 06/20/2025 has been fully considered. The following rejections and/or objections are either reiterated or newly applied.
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 2, 11-15, 20-22 and 27-30 are cancelled by Applicant
Claim 57 is newly added.
Claims 1, 3-10, 16-19, 23-26 and 31-57 are currently pending and are herein under examination.
Claims 1, 3-10, 16-19, 23-26 and 31-57 are rejected.
Claims 1, 16, 18-19 and 47 are objected.
Priority
The instant application claims benefit of priority to U.S. Provisional Application No. 62/910,068 filed 10/03/2019. The claim to the benefit of priority for claims 1, 3-10, 18-19, 23-26, 31-42, 44-45, 47-51, 54 and 57 is acknowledged. As such, the effective filing date of claims 1, 3-10, 18-19, 23-26, 31-42, 44-45, 47-51, 54 and 57 is 10/03/2019.
Claims 43 recites:
“The method of claim 1, wherein each respective set of chemical compound -protein disease target descriptors in the plurality of chemical compound -protein disease target descriptors is a voxel map in a plurality of voxel maps and the inputting B)ii comprises: i) unfolding each voxel map in the plurality of voxel maps into a corresponding vector, thereby creating a plurality of vectors, wherein each vector in the plurality of vectors is the same size; ii) inputting each respective vector in the plurality of vectors to the target model, wherein the target model is a convolutional neural network that includes (a) an input layer for sequentially receiving the plurality of vectors, (b) a plurality of convolutional layers, and (c) the scorer, wherein the plurality of convolutional layers includes an initial convolutional layer and a final convolutional layer, each layer in the plurality of convolutional layers is associated with a different set of weights, responsive to input of a respective vector in the plurality of vectors, the input layer feeds a first plurality of values into the initial convolutional layer as a first function of values in the respective vector, each respective convolutional layer, other than the final convolutional layer, feeds intermediate values, as a respective second function of (a) the different set of weights associated with the respective convolutional layer and (b) input values received by the respective convolutional layer, into another convolutional layer in the plurality of convolutional layers, and the final convolutional layer feeds final values, as a third function of (a) the different set of weights associated with the final convolutional layer and (b) input values received by the final convolutional layer, into the scorer.”
However, the provisional application does not disclose any claims referencing material from claim 43. Claims 46 and 52-53 depend on claim 43 and are therefore are also included in this limitation that is not supported by the provisional. Thus, claims 43, 46 and 52-53 are not granted the claim to benefit of priority to U.S. Provisional Application No. 62/910,068 filed 10/03/2019. Furthermore, claims 55 and 56 which disclose a system and a computer readable medium that contain a method for reduction of test objects in a test object dataset are not disclosed in the provisional. Additionally, claims 16 and 17 that discuss applying a polymer to a target model based upon three-dimensional coordinates for a crystal structure and deriving three-dimensional coordinates for a polymer from nuclear magnetic resonance neutron diffraction, or cryo-electron microscopy are not mentioned in the provisional application. As such, the effective filing date for claims 16-17, 43, 46, 52-53 and 55-56 is 09/30/2020.
Claim Objections
The objection to claim 13 is withdrawn in view of Applicant cancelling claim 13.
Claims 1, 16, 18-19 and 47 are objected to because of the following informalities:
Claim 1, line 15, recites the phrase “each respective compound” which should recite “each respective chemical compound”.
Claims 1 and 55-56 in step F) recites the phrase “F) determining” which should recite “F) determining”.
Claims 1 and 55-56 in step F)(v) recite the phrase “test objects” which should be changed to “chemical compounds”.
Claim 16, line 2, recites the phrase “to the the respective” which should be changed to “to the respective”.
Claim 18, line 3, recites the phrase “test objects” which should be changed to “chemical compounds”.
Claim 19, line, 3 recites “1000” which should be “1,000”.
Claim 47, line 2, recites “1000” which should be “1,000”.
Appropriate correction is required.
Withdrawn Rejections
35 USC 112(b)
The rejection of claims 21-22 under 35 USC 112(b) are withdrawn in view of Applicant cancelling these claims.
Claim Rejections - 35 USC § 112
35 USC 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1, 3-10, 16-19, 23-26 and 31-57 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
This rejection is newly recited and is necessitated by claim amendment.
Claim 1 step F)(v) recites the phrase “wherein the plurality of chemical compounds, before application, of an instance of the eliminating E), comprises at least 100 million” which renders the claim indefinite. In the previous claim set, this limitation appeared to be required. However, in the current claim set, due to the phrase being embedded within step F)v) rather than within step E), it is unclear whether the phrase is required by the whole claim or if it is only required if the predefine reduction criteria are not satisfied in step F). To overcome this rejection, it is suggested to clarify if the phrase is required whether or not the reduction criteria are satisfied.
Furthermore, claims 1, 3-10, 16-19, 23-26, 31-54 and 57 are also rejected because they depend on claim 1, which is rejected, and because they do not resolve the issue of indefiniteness.
Claims 55-56 are rejected for the same reasons discussed directly above regarding the phrase “wherein the plurality of chemical compounds, before application, of an instance of the eliminating E), comprises at least 100 million” in claim 1.
Claim 57, line 2, recites the phrase “G) upon completion of the determining F)” which renders the claim indefinite. It is unclear whether completing step F) means either satisfying or not satisfying the predefined reduction criteria. For examination purposes, the phrase is interpreted as the predefined reduction criteria being satisfied. To overcome this rejection, it is suggested to amend the phrase, for example, to something similar to “G) wherein when the one or more predefined reduction criteria are satisfied in determining F), experimentally …”
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, 3-10, 18-19, 23-26, 31-42, 45, 48-51 and 55-57 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Any newly recited portions herein are necessitated by claim amendment.
Step 2A, Prong 1:
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 phenomena (Step 2A, Prong 1). In the instant application, claims 1, 3-10, 18-19, 23-26, 31-42, 45, 48-51 and 57 recite a method, claim 55 recites a system, and claim 56 recites a product. The instant claims recite the following limitations that equate to one or more categories of judicial exception:
Claims 1 and 55-56 recite “vi) using the plurality of scores to compute the corresponding target model score; C) training … a predictive model in an initial trained state using at least i) the subset of chemical compounds as independent variables and ii) the corresponding subset of target model scores as dependent variables, thereby updating the predictive model to an updated trained state, wherein the predictive model is a neural network having a second computational complexity that is less than the first computational complexity; D) applying … the predictive model in the updated trained state to the plurality of chemical compounds thereby obtaining an instance of a plurality of predictive results, wherein the instance of the plurality of predictive results includes a respective predictive score for an interaction between each chemical compound in the plurality of chemical compounds and the protein disease target; E) eliminating a portion of the chemical compounds from the plurality of chemical compounds based at least in part on the instance of the plurality of predictive scores; F) determining … whether one or more predefined reduction criteria are satisfied, wherein, when the one or more predefined reduction criteria are not satisfied, the method further comprises: (i) applying the target model, for each respective chemical compound in an additional subset of chemical compounds from the plurality of chemical compounds, to the respective chemical compound and the three-dimensional spatial coordinates of the protein disease target to obtain a corresponding target model score for an interaction between the respective chemical compound and the protein disease target, thereby obtaining an additional subset of target model scores, wherein the additional subset of chemical compounds is selected from the instance of the plurality of predictive scores; (ii) updating the subset of chemical compounds by incorporating the additional subset of chemical compounds into the subset of chemical compounds; (iii) updating the subset of target model scores by incorporating the additional subset of target model scores into the subset of target model scores; (iv) modifying, after the updating ii and the updating iii, the predictive model by applying the predictive model to at least 1) the subset of chemical compounds as a plurality of independent variables of the predictive model and 2) the corresponding subset of target model scores as a corresponding plurality of dependent variables of the predictive model, thereby providing the predictive model in an updated trained state; and (v) repeating the applying D), eliminating E), and determining F), wherein the plurality of chemical compounds, before application of an instance of the eliminating E), comprises at least 100 million.
Claim 3 recites “wherein the chemical compound dataset includes a plurality of feature vectors, wherein each feature vector is for a respective chemical compound in the plurality of chemical compounds.”
Claim 4 recites “wherein the applying B) further comprises randomly selecting one or more chemical compounds from the plurality of chemical compounds to form the subset of chemical compounds.”
Claim 5 recites “wherein the applying B) further comprises selecting one or more chemical compounds from the plurality of chemical compounds for the subset of chemical compounds based on evaluation of one or more features selected from the plurality of feature vectors.”
Claim 6 recites “wherein each feature vector in the plurality of feature vectors is a one-dimensional vector.”
Claim 7 recites “herein the applying F)(i) further comprises forming the additional subset of chemical compounds by selecting one or more chemical compounds from the plurality of chemical compounds based on evaluation of one or more features selected from the plurality of feature vectors.”
Claim 8 recites “wherein satisfaction of the one or more predefined reduction criteria comprises comparing each predictive result in the plurality of predictive results to a corresponding target model score from the subset of target model scores.”
Claim 9 recites “wherein satisfaction of the one or more predefined reduction criteria comprises determining that the number of chemical compounds in the plurality of chemical compounds has dropped below a threshold number of chemical compounds.”
Claim 18 recites “wherein the plurality of chemical compounds, before application of an instance of the eliminating E), comprises at least 500 million test objects.”
Claim 19 recites “wherein the one or more predefined reduction criteria require the plurality of chemical compounds after application of the eliminating E) to have no more than 1000 chemical compounds.”
Claim 23 recites “wherein the subset of chemical compounds comprises at least 1,000 chemical compounds.”
Claim 24 recites “wherein the additional subset of chemical compounds comprises at least 1,000 chemical compounds.”
Claim 25 recites “wherein the additional subset of chemical compounds is distinct from the subset of chemical compounds.”
Claim 26 recites “wherein the modifying F)(iv) of the predictive model comprises retraining the predictive model.”
Claim 31 recites “wherein, when the one or more predefined reduction criteria are satisfied, the method further comprises: i) clustering the plurality of chemical compounds, thereby assigning each chemical compound in the plurality of chemical compounds to a cluster in a plurality of clusters; and ii) eliminating one or more chemical compounds from the plurality of chemical compounds based at least in part on redundancy of chemical compounds in individual clusters in the plurality of clusters.”
Claim 32 recites “the method further comprising selecting the subset of chemical compounds from the plurality of chemical compounds by:i) clustering the plurality of chemical compounds thereby assigning each chemical compound in the plurality of chemical compounds to a respective cluster in a plurality of clusters, andii) selecting the subset of chemical compounds from the plurality of chemical compounds based at least in part on a redundancy of chemical compounds in individual clusters in the plurality of clusters.”
Claim 33 recites “wherein, when the one or more predefined reduction criterion are satisfied, the method further comprises applying the predictive model to the plurality of chemical compounds and the protein disease target, thereby causing the predictive model to provide a respective interaction score for each chemical compound in the plurality of chemical compounds.”
Claim 34 recites “wherein each respective interaction score corresponds to an interaction between a respective chemical compounds and the protein disease target.”
Claim 35 recites “wherein each respective interaction score is used to characterize the protein disease target.”
Claim 36 recites “wherein the eliminating (E) comprises:i) clustering the plurality of chemical compounds, thereby assigning each chemical compound in the plurality of hemical compounds to a respective cluster in a plurality of clusters, andii) eliminating a subset of chemical compounds from the plurality of chemical compounds based at least in part on a redundancy of chemical compounds in individual clusters in the plurality of clusters.”
Claim 37 recites “wherein clustering the plurality of chemical compounds is performed using a density-based spatial clustering algorithm, a divisive clustering algorithm, an agglomerative clustering algorithm, a k-means clustering algorithm, a supervised clustering algorithm, or ensembles thereof.”
Claim 38 recites “wherein the eliminating E) comprises:ranking the plurality of chemical compounds based on the instance of the plurality of predictive results, andremoving from the plurality of chemical compounds those chemical compounds in the plurality of chemical compounds that fail to have a corresponding predictive result that satisfies a threshold cutoff.”
Claim 39 recites “wherein the threshold cutoff is a top threshold percentage.”
Claim 40 recites “wherein the top threshold percentage is the top 90 percent, the top 80 percent, the top 75 percent, the top 60 percent, or the top 50 percent of the plurality of predictive results.”
Claim 41 recites “wherein each instance of the eliminating E) eliminates between one tenth and nine tenths of the chemical compounds in the plurality of chemical compounds.”
Claim 42 recites “wherein each instance of the eliminating E) eliminates between one quarter and three quarters of the chemical compounds in the plurality of chemical compounds.”
Claim 45 recites “wherein the scorer comprises a decision tree, a multiple additive regression tree, a clustering algorithm, a principal component analysis, a nearest neighbor analysis, a linear discriminant analysis, a quadratic discriminant analysis, a support vector machine, an evolutionary method, a projection pursuit, or an ensemble thereof.”
Claim 47 recites “wherein the plurality of different poses comprises 2 or more poses, 10 or more poses, 100 or more poses, or 1000 or more poses.”
Claim 48 recites “wherein the plurality of different poses is obtained using a docking scoring function in one of markup chain Monte Carlo sampling, simulated annealing, Lamarckian Genetic Algorithms, or genetic algorithms.”
Claim 49 recites “wherein the plurality of different poses is obtained by incremental search using a greedy algorithm.”
Claim 50 recites “wherein the using the plurality of scores to compute the corresponding target model score comprises taking a measure of central tendency of the plurality of scores.”
Claim 51 recites “wherein the using the plurality of scores to compute the corresponding target model score comprises using the plurality of scores to characterize the respective chemical compound comprises taking a weighted average of the plurality of scores.”
Limitations reciting a mental process.
The following limitations, which are cited directly above, in claims 1, 4-5, 7-9, 26, 31-33, 36, 38 and 55-56 are recited at such a high level of generality that they equate to a mental process because they 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)), which the courts have identified as concepts that can be practically performed in the human mind.
Regarding the above cited limitations in claims 1 and 55-56 of C) training, D) applying, E) eliminating, and F) determining. The broadest reasonable interpretation (BRI) of a predictive model that is a neural network includes it being a single layer perceptron. A human could practically perform tasks of training a neural network with one perceptron as it requires performing the operations of the perceptron and manually updating parameters, and the task of applying the trained perceptron to obtain predictive results to then manually eliminate test objects from a plurality of test objects based on the predictive results. Therefore, these limitations equate to reciting a mental process.
Regarding steps F)i)-F)v) in claims 1 and 55-56, these limitations are not being analyzed on their merits because they are contingent limitations and are thus not required by the claim (MPEP 2111.04(II)). They are contingent because they are only required when the predefined reduction criteria in step F) is not satisfied.
Regarding the above cited limitations in claims 4-5, 7-9, 31-32, 36 and 38 of selecting, selecting based on an evaluation, comparing, determining, eliminating based on clustering, selecting a subset based on clustering and eliminating, and ranking and removing, these limitations are considered a mental process because they are recited at such a high level of generality that a human could practically perform them with pen and paper. Therefore, these limitations equate to reciting a mental process.
Regarding the above cited limitations in claim 33, these limitations equate to a mental process because a human could practically perform the operations of a predictive model, which under the BRI is a single layer perceptron, to derive an interaction score. Therefore, these limitations equate to reciting a mental process.
Regarding the above cited limitation in claim 26 of retraining the predictive model, this limitation equates to be a mental process because a human could practically with pen and paper retrain a predictive model, wherein the BRI of the predictive model is a single layer perceptron, by performing the operations of the neural network to then updated the parameters of the neural network. Therefore, these limitations equate to reciting a mental process.
Limitations reciting a mathematical concept.
The following limitations, which are cited directly above, in claims 1, 26, 33, 37, 45, 48-51 and 55-56 equate to a mathematical concept because these limitations are similar to the concepts of 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)), which the courts have identified as mathematical concepts.
Regarding the above cited limitation in claims 1, 26, and 55-56 of training/retraining a predictive model, wherein the predictive model is said to be a neural network. This limitation equates to a mathematical concept because the specification in para. [215] recites that forward or backward propagation can be used to train/retrain a neural network, which are both mathematical functions that perform calculations. Therefore, these limitations equate to a mathematical concept.
Regarding the above cited limitation in claim 33 of applying the predictive model to generate an interaction score, this limitation equates to a mathematical concept because the BRI of this limitation includes performing calculations with a neural network, which may be a single-layer perceptron, to derive a numerical value. Therefore, this limitation equates to a mathematical concept.
Regarding claims 45 and 48-51, a principal component analysis, a genetic algorithm, a greedy algorithm, taking a measure of central tendency, and taking a weighted average are mathematical concepts including equations that perform calculations. Therefore, these limitations equate to a mathematical concept.
Limitations included in the recited judicial exception.
Regarding the above cited limitations in claims 3, 6, 18-19, 23-25, 34-35, and 39-42, these limitations are included in the judicial exception of claims 1, 31, 33 and 38 because they limit chemical compound dataset, feature vectors, the plurality of chemical compounds, the one or more predefined reduction criteria, the additional subset of chemical compounds, each respective interaction score, the thresh old cutoff, and step E), but do not change the fact that these components are still part of the judicial exception.
As such, claims 1, 3-10, 18-19, 23-26, 31-42, 45, 48-51 and 55-57 recite an abstract idea (Step 2A, Prong 1: Yes).
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). The judicial exception is not integrated into a practical application because the claims do not recite additional elements that reflect an improvement to a computer, technology, or technical field (MPEP § 2106.04(d)(1) and 2106.5(a)), require a particular treatment or prophylaxis for a disease or medical condition (MPEP § 2106.04(d)(2)), implement the recited judicial exception with a particular machine that is integral to the claim (MPEP § 2106.05(b)), effect a transformation or reduction of a particular article to a different state or thing (MPEP § 2106.05(c)), nor provide some other meaningful limitation (MPEP § 2106.05(e)). Rather, the claims include limitations that equate to instructions to implement an abstract idea on a computer (MPEP § 2106.05(f)) and insignificant extra-solution activity (MPEP § 2106.05(g)). The instant claims recite the following additional elements:
Claims 1 and 55-56 recite “A) obtaining, in electronic format, the chemical compound dataset; B) applying, using a computer system, a target model, for each respective chemical compound in a subset of chemical compounds from the plurality of chemical compounds, to a description of the respective chemical compound posed against three-dimensional spatial coordinates of the protein disease target to obtain, as output from the target model, a corresponding target model score for an interaction between the respective chemical compound and the protein disease target, thereby obtaining a corresponding subset of target model scores, wherein the target model is a convolutional neural network or a graph neural network having a first computational complexity, and wherein the applying for each respective compound comprises: i) modeling the respective chemical compound with the protein disease target in each pose of a plurality of different poses, thereby creating a plurality of sets of chemical compound - protein disease target descriptors, wherein each respective set of chemical compound - protein disease target descriptors in the plurality of chemical compound - protein disease target descriptors comprises the respective chemical compound in a respective pose in the plurality of different poses; ii) inputting each respective set of chemical compound - protein disease target descriptors in the plurality of sets of chemical compound - protein disease target descriptors to the target model, wherein the target model comprises a scorer; and iii) obtaining a corresponding plurality of scores from the scorer, wherein each score in the corresponding plurality of scores corresponds to the input of a set of chemical compound - protein disease target descriptors into the target model; C) … using a computer system …; D) … using a computer system …; F) … using a computer system.”
Claim 10 recites “wherein the target model is a convolutional neural network”,
Claim 55 recites “A computer system for reducing a number of chemical compounds in a plurality of chemical compounds in a chemical compound dataset, in order to reduce screening cost and time of screening the plurality of chemical compounds for binding affinity to a protein disease target that is an enzyme with an active site, the computer system comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, the one or more programs including instructions for:”
Claim 56 recites “A non-transitory computer readable storage medium and one or more computer programs embedded therein, the one or more computer programs comprising instructions which, when executed by a computer system, cause the computer system to perform a method for reducing a number of chemical compounds in a plurality of chemical compounds in a chemical compound dataset, in order to reduce screening cost and time of screening the plurality of chemical compounds for binding affinity to a protein disease target that is an enzyme with an active site, the method comprising:”
Claim 57 recites “G) upon completion of the determining F), experimentally testing a selection of the plurality of compounds, using a wet lab binding affinity assay, to determine which of the selection of compounds have binding affinity to the protein disease target.”
Regarding the above cited limitations in claim 1 of using a computer system, in claim 55 of the computer system comprising processors, memory and instructions stored on a program, in claim 56 of a non-transitory computer readable storage medium and instructions stored on computer programs. There are no limitations that these limitations require anything other than a generic computing system. As such, these limitations equate to mere instructions to implement the abstract idea on a generic computer, which 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.
Regarding the above cited limitations in claims 1, 10 and 55-56 of A) obtaining, B) applying a convolutional neural network, B)i), modeling, B)ii) inputting, and B)iii) obtaining, these limitations equate insignificant, extra-solution activity of mere data gathering because they are necessary data gathering steps that acquire data for use of the judicial exception recited in claims 1 and 55-56 of steps C)-F).
Regarding the above cited limitation in claim 57, this limitation equates to mere instructions to “apply” the recited judicial exception in a generic way because it recites only the idea of an outcome but fails to recite details for how the outcome solves a problem (See MPEP 2106.05(f)(1)). Although claim 57 requires performing a wet lab binding affinity assay on a selection of the plurality of compounds, after an instance of E) eliminating, there is no description of what type of chemical compounds are to be assayed that would solve a problem. For example, the BRI of claim 57 includes assaying compounds with low or intermediate levels of predicted binding affinity because there is no requirement that compounds with high predicted binding affinities are assayed. Given this example, there would be no practical application of reducing screening time and cost because compounds with low or intermediate predicted binding affinities would be assayed.
As such, claims 1, 3-10, 18-19, 23-26, 31-42, 45, 48-51 and 55-57 are directed to an abstract idea (Step 2A, Prong 2: No).
Step 2B:
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). These claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because these claims recite additional elements that equate to instructions to apply the recited exception in a generic computing environment (MPEP § 2106.05(f)) and to well-understood, routine and conventional (WURC) limitations (MPEP § 2106.05(d)). The instant claims recite the following additional elements:
Claims 1 and 55-56 recite “A) obtaining, in electronic format, the chemical compound dataset; B) applying, using a computer system, a target model, for each respective chemical compound in a subset of chemical compounds from the plurality of chemical compounds, to a description of the respective chemical compound posed against three-dimensional spatial coordinates of the protein disease target to obtain, as output from the target model, a corresponding target model score for an interaction between the respective chemical compound and the protein disease target, thereby obtaining a corresponding subset of target model scores, wherein the target model is a convolutional neural network or a graph neural network having a first computational complexity, and wherein the applying for each respective compound comprises: i) modeling the respective chemical compound with the protein disease target in each pose of a plurality of different poses, thereby creating a plurality of sets of chemical compound - protein disease target descriptors, wherein each respective set of chemical compound - protein disease target descriptors in the plurality of chemical compound - protein disease target descriptors comprises the respective chemical compound in a respective pose in the plurality of different poses; ii) inputting each respective set of chemical compound - protein disease target descriptors in the plurality of sets of chemical compound - protein disease target descriptors to the target model, wherein the target model comprises a scorer; and iii) obtaining a corresponding plurality of scores from the scorer, wherein each score in the corresponding plurality of scores corresponds to the input of a set of chemical compound - protein disease target descriptors into the target model; C) … using a computer system …; D) … using a computer system …; F) … using a computer system ”
Claim 10 recites “wherein the target model is a convolutional neural network.”
Claim 55 recites “A computer system for reducing a number of chemical compounds in a plurality of chemical compounds in a chemical compound dataset, in order to reduce screening cost and time of screening the plurality of chemical compounds for binding affinity to a protein disease target that is an enzyme with an active site, the computer system comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, the one or more programs including instructions for:”
Claim 56 recites “A non-transitory computer readable storage medium and one or more computer programs embedded therein, the one or more computer programs comprising instructions which, when executed by a computer system, cause the computer system to perform a method for reducing a number of chemical compounds in a plurality of chemical compounds in a chemical compound dataset, in order to reduce screening cost and time of screening the plurality of chemical compounds for binding affinity to a protein disease target that is an enzyme with an active site, the method comprising:”
Claim 57 recites “G) upon completion of the determining F), experimentally testing a selection of the plurality of compounds, using a wet lab binding affinity assay, to determine which of the selection of compounds have binding affinity to the protein disease target.”
Regarding the above cited limitations in claims 1 and 55-56 of A) obtaining, B)ii) inputting, and B)iii) obtaining, the BRI of these limitations includes that they are performed by a generic computer. Therefore, these limitations equate to receiving/transmitting data over a network, which the courts have established as WURC limitation of a generic computer in buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014).
Regarding the above cited limitations in claim 1 of using a computer system, in claim 55 of the computer system comprising processors, memory and instructions stored on a program, in claim 56 of a non-transitory computer readable storage medium and instructions stored on computer programs. These limitations equate to instructions to implement an abstract idea on a generic computing environment, which the courts have established does not provide an inventive concept in Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). Additionally, storing code on a non-transitory computer readable medium and storing programs in memory as stated in claim 55 and 56 equate to storing information in memory, which the courts have established as a WURC function of a generic computer in Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
Regarding the above cited limitation in claim 57, as discussed in section Step 2A, Prong 2, this limitation equates to mere instructions to apply the judicial exception, which does not provide significantly more than the judicial exception itself (MPEP 2106.05(I)(A)).
Regarding the above cited limitations in claim 1 of B) and B)i) and the limitation in B)ii) of the target model comprising a scorer, these limitations are WURC as disclosed by Jimenez et al. (“Jimenez”; Journal of Chemical Information and Modeling 2018, 58(2), pages 287-296; previously cited on PTO892 mailed 09/01/2023), Ragoza et al. (Journal of Chemical Information and Modeling 2017, 57(4), pages 942-957; previously cited on PTO892 mailed 09/01/2023), and Hochuli et al. (Journal of Molecular Graphics and Modeling 2018, 84, pages 96-108; previously cited on PTO892 mailed 09/01/2023). The paragraphs below discuss the teachings of these references.
Jimenez predicts protein-ligand binding affinities using 3D-convolutional neural networks (3D CNN) that contain a scoring function, and states that it is an important step in accelerating drug discovery for virtual screening and lead optimization (abstract). Databases such as PDPbind, CSAR NRC-HiQ, CSAR2012, and BindingMOAD (pg. 288, col. 1, para. 3; pg. 290, col. 1, para. 1), wherein subsets of the data were used (pg. 288, col. 2, para. 1). The 3D CNN uses a 3D voxel representation of both proteins and ligands to predict binding affinity (pg. 290, col. 2, para. 3; Figure 3). Figure 2 shows the voxel representation of the protein-ligand complex.
Ragoza discloses a how protein-ligand scoring is a keystone of structure-based drug design (pg. 942, col. 1, para. 1), and teaches a convolutional neural network (CNN) scoring function that receives as input a 3D representation of a protein-ligand interaction (abstract). Pose prediction was performed using a subset of the CSAR-NRC HiQ data set, wherein ligands were redocked up to 20 distinct poses (pg. 943, col. 2, para. 4). The CNN scoring function was trained and optimized to discriminate between correct and incorrect binding poses (abstract; pg. 948, col. 1, last para.; Figure 8). The 3D structural data of protein-ligand structures were discretized into a grid for input in the CNN (pg. 944, col. 1, para. 2). Figures 17 and 18 shows different ligand poses with the same ligand against a target protein. All generated poses were scored and the best score for each ligand was used to assess virtual screening performance (pg. 945, col. 2, para. 3).
Hochuli discloses three methods for visualizing how individual protein-ligand complexes are interpreted by 3D convolutional neural networks (abstract). Figure 1 shows an input to the CNN that are voxelized grid of atom type densities and includes a pose score and affinity prediction. Sets of poses were generated by redocking ligands of the 2016 PDBind refined set using AutoDock Vina scoring function (pg. 97, col. 2, para. 3). Figure 6 shows protein-ligand complex by atom type with associated affinity and pose score. Hochuli also discusses how protien0ligand scoring is a crucial step in structure-based drug design pipelines (abstract; pg. 96, col. 1, para. 1).
When these additional elements are considered individually and in combination, they do not provide an inventive concept because they all equate to WURC functions/components of a generic computer, to mere instructions to apply the judicial exception, and to a WURC method for using convolutional neural networks to predict binding affinities as taught above by Jimenez, Ragoza, and Hochuli. Therefore, these additional elements do not transform the claimed judicial exception into a patent-eligible application of the judicial exception and do not amount to significantly more than the judicial exception itself (Step 2B: No).
As such, claims 1, 3-10, 18-19, 23-26, 31-42, 45, 48-51 and 55-57 are not patent eligible.
Response to Arguments under 35 USC 101
Applicant's arguments filed 06/20/2025 have been fully considered but they are not persuasive.
Applicant appears to argue that that claim 1 confers a practical application of an improvement in the field of virtual screening at least in part by reducing screening costs and time screening (pg. 24, para. 4 – pg. 27, last para. of Applicant’s remarks). Applicant’s arguments are not persuasive for the following reasons:
MPEP 2106.04(d)(1) recites:
“A claim reciting a judicial exception is not directed to the judicial exception if it also recites additional elements demonstrating that the claim as a whole integrates the exception into a practical application. One way to demonstrate such integration is when the claimed invention improves the functioning of a computer or improves another technology or technical field. The application or use of the judicial exception in this manner meaningfully limits the claim by going beyond generally linking the use of the judicial exception to a particular technological environment, and thus transforms a claim into patent-eligible subject matter. Such claims are eligible at Step 2A because they are not "directed to" the recited judicial exception.”
In order for a claim to contain an improvement in a technology or technological field, the claim as a whole must integrate the exception into a practical application (MPEP 2106.04(d)(1)). Instant claim 1, when viewed as a whole, does not integrate the recited judicial exception into a practical application. This is because steps F)i)—F)v) in claim 1 are not required because they are contingent limitations. Steps F)i—F)v) are contingent upon the following limitation in claim 1: “F) determining, using a computer system, whether one or more predefined reduction criteria are satisfied, wherein, when the one or more predefined reduction criteria are not satisfied, the method further comprises:” steps F)i)—F)v). The BRI of contingent limitations requires only steps that must be performed and does not include steps that are not required to be performed because the conditions(s) precedent are not met (MPEP 2111.04(II)). In other words, in step F), there is an interpretation where the predefined reduction criteria are satisfied and thus steps F)i)—F)v) are not performed. This is pertinent to claim 1 as a whole not conferring the alleged improvement because Applicant appears to state that the improvement is at least in part conferred by steps F)i)—F)v) (pg. 27, para. 3 – last para. of Applicant’s remarks). If part of the alleged improvement is conferred by limitations that are not required (i.e., steps F)i)—F)v)), then the claim as a whole does not integrate the exception into a practical application.
Applicant appears to argue that the compounds in the dataset with low predictive scores, indicating low binding affinity, are eliminated in step E and the remaining compounds have higher predictive scores (pg. 28, para. 1 – para. 3 of Applicant’s remarks). Applicant’s arguments are not persuasive for the following reasons:
MPEP 2106.04(d)(1) recites:
“Second, if the specification sets forth an improvement in technology, the claim must be evaluated to ensure that the claim itself reflects the disclosed improvement. That is, the claim includes the components or steps of the invention that provide the improvement described in the specification. The claim itself does not need to explicitly recite the improvement described in the specification (e.g., "thereby increasing the bandwidth of the channel").”
Step E) in claim 1 requires eliminating chemical compounds in the plurality of chemical compounds based at least in part on the predictive results, but there is no limitation requiring elimination based upon a low binding affinity nor is there a limitation requiring compounds with a higher predictive score to be retained. Therefore, claim 1 does not contain limitations that reflect the alleged improvement.
Applicant’s reference to the blog post is acknowledged, but is not persuasive for the same reasons discussed in the responses above (pg. 28, last para. – pg. 31, para. of Applicant’s remarks).
Applicant argues that the predictive model increases the number of test objects a computer system can search, which addresses a known problem with virtual screening and thus claim 1 contains an improvement in technology. Applicant’s arguments are not persuasive for the following reasons:
Applicant appears to argue that step D) in claim 1 confers the alleged improvement. However, step D) has been identified as reciting a judicial exception. An improvement in technology cannot be the result of the judicial exception itself (MPEP 2106.05(a)).
Applicant’s arguments regarding claims 3-10, 12-14, 16-42 and 55-56 are not persuasive for the same reasons applied above regarding claim 1 (pg. 32, para. 3 of Applicant’s remark).
Conclusion
No claims are allowed.
Claims 16-17, 43-44, 46-47 and 52-54 were analyzed under 35 USC 101 and were found to be patent eligible under Step 2B for not being well-understood, routine, and conventional (WURC). Specifically, the additional elements of claim 43 when viewed in combination with the additional elements in claim 1 are not WURC. Claims 46 and 52-53 depend on claim 43 and as such are also not WURC when viewed in combination. Claims 16-17, 44, 47 and 54 depend on claim 1 and are not WURC when the additional elements are viewed in combination with claim 1.
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 THREE-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 final action.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Noah A. Auger whose telephone number is (703)756-4518. The examiner can normally be reached M-F 7:30-4:30 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached on (571) 272-9047. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.A.A./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687