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 currently pending and examined on the merits.
Claims 1-20 are rejected.
Claims 9 and 15 are objected to.
Priority
The instant application claims priority to U.S. Provisional Application 62/890,976 filed on 23 August 2019. At this point in examination, the effective filing date of claims 1-20 is 23 August 2019.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 6 August 2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements have been considered by the examiner.
Drawings
The drawings are objected to because "protien" 404 in Fig. 4 is misspelled and should read "protein". 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 Objections
Claims 9 and 15 are objected to because of the following informalities:
In claim 9, line 8, the punctuation of a semicolon ";" should be replaced with a punctuation of a period "."
In claim 15, line 8, “leraning model” should read “learning model”
These are typographical errors. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-2 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.
The term “desired” in claim 1, line 6, and claim 2, line 5 is a relative term which renders the claim indefinite. The term “desired” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. It is unclear what is "desired" in terms of characteristics. The specification is also silent as to what is considered "desired" for a set of characteristics. One skilled in the art would not recognize what a set of "desired" characteristics means. Therefore, claim 1 is rendered indefinite and rejected under 35 U.S.C. 112(b).
Claim Rejections - 35 USC § 101
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgement, opinion).
Subject matter eligibility evaluation in accordance with MPEP 2106:
Eligibility Step 1: Claims 1-7 are directed to a system (machine). Claims 8-14 are directed to a method of generating a predicted electrostatic solvation free energy of a protein. Claims 15-20 are directed to a system (machine). Therefore, these claims are encompassed by the categories of statutory subject matter, and thus satisfy the subject matter eligibility requirements under Step 1.
[Step 1: YES]
Eligibility Step 2A: First, it is determined in Prong One whether a claim recites a judicial exception, and if so, then it is determined in Prong Two whether the recited judicial exception is integrated into a practical application of that exception.
Eligibility Step 2A, Prong One: In determining whether a claim is directed to a judicial exception, examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a law of nature, natural phenomenon, or abstract idea is set forth described in the claim.
Claims 1-20 recite the following steps which fall within the mental processes and/or mathematical concepts groups of abstract ideas, as noted below.
Independent claim 1 further recites:
identify a set of compounds based on one or more of a defined target clinical application, a set of desired characteristics, and a defined class of compounds (i.e., mental processes);
pre-process each compound of the set of compounds to generate respective sets of feature data (i.e., mental processes);
process the sets of feature data with a trained Poisson-Boltzmann machine learning model to produce a plurality of predicted electrostatic solvation free energies for each compound of the set of compounds, wherein the sets of feature data include multi-weighted colored subgraph centralities (i.e., mental processes, mathematical concepts);
identify a subset of the set of compounds based on the plurality of predicted electrostatic solvation free energies (i.e., mental processes).
Dependent claim 2 further recites:
assign rankings to each compound of the set of compounds, wherein assigning a ranking to a given compound of the set of compounds for a given characteristic of the set of desired characteristics (i.e., mental processes);
comparing a first predicted electrostatic solvation free energy corresponding to the given compound to other predicted electrostatic solvation free energies of other compounds of the set of compounds, wherein the ordered list is ordered according to the assigned rankings (i.e., mental processes).
Dependent claim 3 further recites:
calculate a plurality of multi-weighted colored subgraph centralities for the first protein (i.e., mental processes, mathematical concepts);
generate a feature vector that includes the multi-weighted colored subgraph centralities, wherein one of the sets of feature data includes the feature vector (i.e., mental processes);
process the feature vector with the Poisson-Boltzmann machine learning model to generate a predicted electrostatic solvation free energy of the first protein (i.e., mental processes, mathematical concepts).
Dependent claim 4 further recites:
to calculate a first multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the first protein (i.e., mental processes, mathematical concepts);
define vertices for atoms of the first protein (i.e., mental processes);
define first edges corresponding to pairwise atomic interactions between the atoms of the first protein using a generalized Lorentz function (i.e., mental processes, mathematical concepts);
calculate first atomic centralities for each of the atoms of the first protein (i.e., mental processes, mathematical concepts);
sum the first atomic centralities to generate the first multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
Dependent claim 5 further recites:
to calculate a second multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the first protein (i.e., mental processes, mathematical concepts);
define second edges corresponding to pairwise atomic interactions between the atoms of the first protein using a generalized exponential function (i.e., mental processes, mathematical concepts);
calculate second atomic centralities for each of the atoms of the first protein (i.e., mental processes, mathematical concepts);
sum the second atomic centralities to generate the second multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
Dependent claims 6, 13, and 19 further recite:
wherein the generalized exponential function and the generalized Lorentz function are weighted based on atomic rigidity (i.e., mental processes, mathematical concepts).
Dependent claims 7, 14, and 20 further recite:
wherein the generalized exponential function and the generalized Lorentz function are weighted based on atomic charge (i.e., mental processes, mathematical concepts).
Independent claim 8 further recites:
calculating, by a processor, a plurality of multi-weighted colored subgraph centralities for a protein (i.e., mental processes, mathematical concepts);
generating, by the processor, a feature vector that includes the multi-weighted colored subgraph centralities (i.e., mental processes);
executing, by the processor, a Poisson-Boltzmann machine learning model to process the feature vector to generate a predicted electrostatic solvation free energy of the protein (i.e., mental processes, mathematical concepts).
Dependent claim 9 further recites:
calculating, by the processor, a second plurality of multi-weighted colored subgraph centralities for a second protein (i.e., mental processes, mathematical concepts);
generating, by the processor, a second feature vector that includes the second multi-weighted colored subgraph centralities (i.e., mental processes);
executing, by the processor, a Poisson-Boltzmann machine learning model to process the second feature vector to generate a second predicted electrostatic solvation free energy of the second protein (i.e., mental processes, mathematical concepts).
Dependent claim 10 further recites:
assigning, by the processor, rankings to the protein and the second protein based on the first predicted electrostatic solvation free energy and the second predicted electrostatic solvation free energy (i.e., mental processes);
generating, by the processor, an ordered list that includes the protein and the second protein based on the rankings (i.e., mental processes).
Dependent claim 11 further recites:
calculating, by the processor, a first multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the protein (i.e., mental processes, mathematical concepts);
defining, by the processor, vertices for atoms of the protein (i.e., mental processes);
defining, by the processor, first edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized Lorentz function (i.e., mental processes, mathematical concepts);
defining, by the processor, first atomic centralities for each of the atoms of the protein (i.e., mental processes);
summing, by the processor, the first atomic centralities to generate the first multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
Dependent claim 12 further recites:
calculating, by the processor, a second multi-weighted colored subgraph centrality for the protein (i.e., mental processes, mathematical concepts);
defining, by the processor, second edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized exponential function (i.e., mental processes, mathematical concepts);
calculating, by the processor, second atomic centralities for each of the atoms of the protein (i.e., mental processes, mathematical concepts);
summing, by the processor, the second atomic centralities to generate the second multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
Independent claim 15 further recites:
generate feature data corresponding to the protein (i.e., mental processes);
process the feature data with a trained Poisson-Boltzmann machine leraning model to produce a predicted electrostatic solvation free energy of the protein (i.e., mental processes, mathematical concepts).
Dependent claim 16 further recites:
calculate multi-weighted colored subgraph centralities for the protein (i.e., mental processes, mathematical concepts);
generate a feature vector that includes the multi-weighted colored subgraph centralities, wherein the feature data includes the feature vector (i.e., mental processes);
process the feature vector with the Poisson-Boltzmann machine learning model to generate the predicted electrostatic solvation free energy of the protein (i.e., mental processes, mathematical concepts).
Dependent claim 17 further recites:
to calculate a first multi-weighted colored subgraph centrality of the multi-weighted colored subgraph centralities (i.e., mental processes, mathematical concepts);
define vertices for atoms of the protein (i.e., mental processes);
define first edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized Lorentz function (i.e., mental processes, mathematical concepts);
calculate the first atomic centralities for each of the atoms of the protein (i.e., mental processes, mathematical concepts);
sum the first atomic centralities to generate the first multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
Dependent claim 18 further recites:
to calculate a second multi-weighted colored subgraph centrality of the multi-weighted colored subgraph centralities (i.e., mental processes, mathematical concepts);
define second edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized exponential function (i.e., mental processes, mathematical concepts);
calculate second atomic centralities for each of the atoms of the protein (i.e., mental processes, mathematical concepts);
sum the second atomic centralities to generate the second multi-weighted colored subgraph centrality (i.e., mental processes, mathematical concepts).
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pencil and paper, and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Therefore, claims 1-20 recite an abstract idea.
[Step 2A, Prong One: YES]
Eligibility Step 2A, Prong Two: In determining whether a claim is directed to a judicial exception, further examination is performed that analyzes if the claim recites additional elements that, when examined as a whole, integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements are analyzed to determine if the abstract idea is integrated into a practical application (MPEP 2106.04(d)(I); MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A, Prong One are not integrated into a practical application because of the reasons noted below.
Claims 1, 10, and 15 recite the additional non-abstract elements of data gathering:
display an ordered list of the subset of the set of compounds via an electronic display (claim 1);
causing, by the processor, the ordered list to be displayed at a user device (claim 10);
receive an identifier corresponding to a protein (claim 15).
which are each a data gathering step, or a description of the data gathered.
Data gathering steps are not an abstract idea, they are extra-solution activity, as they collect the data needed to carry out the JE. The data gathering does not impose any meaningful limitation on the JE, or how the JE is performed. The additional limitation (data gathering) must have more than a nominal or insignificant relationship to the identified judicial exception. (MPEP 2106.04/.05, citing Intellectual Ventures LLC v. Symantee Corp, McRO, TLI communications, OIP Techs. Inc. v. Amason.com Inc., Electric Power Group LLC v. Alstrom S.A.).
Claims 1, 10, and 15 recite the additional non-abstract element (EIA) of a general-purpose computer system or parts thereof:
a system comprising: a non-transitory computer-readable memory and a processor configured to execute instructions stored on the non-transitory computer-readable memory (claims 1 and 15);
an electronic display (claim 1);
a user device (claim 10).
The EIA do not provide any details of how specific structures of the computer elements are used to implement the JE. The claims require nothing more than a general-purpose computer to perform the functions that constitute the judicial exceptions. The computer elements of the claims do not provide improvements to the functioning of the computer itself (as in DDR Holdings, LLC v. Hotels.com LP); they do not provide improvements to any other technology or technical field (as in Diamond v. Diehr); nor do they utilize a particular machine (as in Eibel Process Co. v. Minn. & Ont. Paper Co.). Hence, these are mere instructions to apply the JE using a computer, and therefore the claim does not recite integrate that JE into a practical application.
Thus, the additionally recited elements merely invoke a computer as a tool, and/or amount to insignificant extra-solution data gathering activity, and as such, when all limitations in claims 1-20 have been considered as a whole, the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application. Claims 1, 10, and 15 contain additional elements that would not integrate a judicial exception into a practical application and are further probed for inventive concept in Step 2B.
[Step 2A, Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
With respect to claims 1, 10, and 15: The limitations identified above as non-abstract elements (EIA) related to data gathering do not rise to the level of significantly more than the judicial exception. Activities such as data gathering do not improve the functioning of a computer, or comprise an improvement to any other technical field. The limitations do not require or set forth a particular machine, they do not affect a transformation of matter, nor do they provide an unconventional step (citing McRO and Trading Technologies Int’l v. IBG). Data gathering steps constitute a general link to a technological environment. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception are insufficient to provide significantly more (as discussed in Alice Corp.,).
With respect to claims 1, 10, and 15: The limitations identified above as non-abstract elements (EIA) related to general-purpose computer systems do not rise to the level of significantly more than the judicial exception. These elements do not improve the functioning of the computer itself, or comprise an improvement to any other technical field (Trading Technologies Int’l v. IBG, TLI Communications). They do not require or set forth a particular machine (Ultramercial v. Hulu, LLC., Alice Corp. Pty. Ltd v. CLS Bank Int’l), they do not affect a transformation of matter, nor do they provide an unconventional step. Simply appending well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception are insufficient to provide significantly more (as discussed in Alice Corp., CyberSource v. Retail Decisions, Parker v. Flook, Versata Development Group v. SAP America).
[Step 2B: NO]
Therefore, claims 1-20 are patent ineligible under 35 U.S.C. § 101.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-5, 8-12, and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Nguyen et al. (Journal of Computer-Aided Molecular Design, 2019, 33, 1-22), as provided in the IDS filed 8/6/2025; refer to as Nguyen [A].
With respect to claim 1:
Claim 1 recites a system comprising a non-transitory computer-readable memory and a processor configured to execute instructions stored on the non-transitory computer-readable memory.
Broadly claiming an automated means to replace a manual function to accomplish the same result does not distinguish over the prior art. See Leapfrog Enters., Inc. v. Fisher-Price, Inc., 485 F .3d 1157, 1161, 82 USPQ2d 1687, 1691 (Fed. Cir. 2007) (“Accommodating a prior art mechanical device that accomplishes [a desired] goal to modern electronics would have been reasonably obvious to one of ordinary skill in designing children’s learning devices. Applying modern electronics to older mechanical devices has been commonplace in recent years.”); In re Venner, 262 F. 2d 91, 95, 120 USPQ 193, 194 (CCPA 1958); see also MPEP § 2144.04. Furthermore, implementing a known function on a computer has been deemed obvious to one of ordinary skill in the art if the automation of the known function on a general purpose computer is nothing more than the predictable use of prior art elements according to their established functions. KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 417, 82 USPQ2d 1385, 1396 (2007); see also MPEP § 2143, Exemplary Rationales D and F. Likewise, it has been found to be obvious to adapt an existing process to incorporate Internet and Web browser technologies for communicating and displaying information because these technologies had become commonplace for those functions. Muniauction, Inc. v. Thomson Corp., 532 F.3d 1318, 1326-27, 87 USPQ2d 1350, 1357 (Fed. Cir. 2008).
With respect to the recited identify a set of compounds based on one or more of a defined target clinical application, a set of desired characteristics, and a defined class of compounds, Nguyen [A] discloses “Subchallenge 3 involved the binding affinity ranking and free energy prediction of target JAK2. It consisted of a relatively small dataset with 17 ligands having similar chemical structures.” (pg. 3, para. 3, lines 9-11). This indicates a small dataset of compounds with desired characteristics of having similar chemical structures to each other.
With respect to the recited pre-process each compound of the set of compounds to generate respective sets of feature data, Nguyen [A] discloses “Weighted colored subgraph (WCS) method describes intermolecular and intramolecular interactions as pairwise atomic correlations [24]. To apply the WCS for analyzing the protein-ligand interactions, we convert all the atoms and their pairwise interactions at the binding site of a protein-ligand complex with a cutoff distance
d
into a colored subgraph
G
(
V
d
,
E
)
with vertices
V
d
and edge
E
.” (pg. 5-6, para. 8, lines 1-5). Also, further discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests converting compounds into weighted colored subgraphs that describe feature data such as intermolecular and intramolecular interactions, which also provide descriptors when determining multiscale centralities.
With respect to the recited process the sets of feature data with a trained Poisson-Boltzmann machine learning model to produce a plurality of predicted electrostatic solvation free energies for each compound of the set of compounds, wherein the sets of feature data include multi-weighted colored subgraph centralities, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests that MWCG feature data, which includes multi-weighted colored subgraph centralities, was processed through machine learning models to produce free energy predictions on ligands with experiment structures.
With respect to the recited identify a subset of the set of compounds based on the plurality of predicted electrostatic solvation free energies, Nguyen [A] discloses “In each bin, we clustered decoys into 10 clusters based on their internal similarities. The docking poses having the smallest free energy were selected as the candidate for their clusters.” (pg. 4, para. 6, lines 8-10). This indicates that a subset of compound docking poses were identified based on smallest free energy of the predicted free energies.
With respect to the recited display an ordered list of the subset of the set of compounds via an electronic display, Nguyen [A] discloses “We employed the machine learning based scoring function to select the best poses for all prediction tasks, i.e., docking Protocol 1. The free energy values were predicted by scheme EP1. Although our pose ranking power was not impressive, the free energy predictions of our model performed pretty well. Specifically, our submission with receipt ID 5bvwx was ranked the second place in the free energy set 1 of stage 1 with
R
M
S
E
c
=
0.68
k
c
a
l
/
m
o
l
. In stage 2, our models improved the accuracy of the energy prediction of compounds in the aforementioned free energy set. In fact, we obtained the first place in term of Kendall’s tau value (
τ
=
0.41
) with receipt ID 4rbjk. That was also the highest Kendall’s tau value among all submissions in two stages for the free energy set 1. Figure 3 plots the performance of all submissions on the free energy set 1 in stage 2.” (pg. 13, para. 4, lines 1-10). Submissions in this list indicate free energy predictions of the compounds in order from highest to lowest Kendall’s tau value, which measures the relationship between the prediction and the actual free energy in Grand Challenge 2. Therefore, this suggests an ordered list of compounds. The performance plot in Figure 3 implies that the list is displayed with an electronic display.
With respect to claim 2:
With respect to the recited assign rankings to each compound of the set of compounds, wherein assigning a ranking to a given compound of the set of compounds for a given characteristic of the set of desired characteristics, Nguyen [A] discloses “We developed a machine learning-based scoring function to select the poses generated by GOLD [46], GLIDE [47], and Autodock Vina [42]. Given a ligand target, we at first formed a training data of complexes taken from the PDB. The criteria for such selections are based on the similarity coefficient, measured by fingerprint 2 (FP2) in Open Babel v2.3.1 [48], of ligand in the complex. Then, we utilized docking software packages such as GOLD, GLIDE, and Autodock Vina to redock ligands to protein in those selected complexes. A variety of docking poses was distributed into 10 different RMSD bins as follows: [0,1], (1,2], …, (9,10]
Å
. In each bin, we clustered decoys into 10 clusters based on their internal similarities. The docking poses having the smallest free energy were selected as the candidate for their clusters. As a result, one may end up with a total of 100 poses for each given complex. We employed all these decoy poses to form a training set with labels defined by their RMSDs. Our topological based deep learning models were utilized to learn this training set. Finally, we employed this established scoring function to re-rank the poses of the target ligand produced by docking software packages.” (pg. 4-5, para. 6, lines 8-15). This suggests that the target ligand docking poses were assigned rankings based on similarity to the training set of docking poses with smallest free energy.
With respect to the recited comparing a first predicted electrostatic solvation free energy corresponding to the given compound to other predicted electrostatic solvation free energies of other compounds of the set of compounds, wherein the ordered list is ordered according to the assigned rankings, Nguyen [A] discloses “We developed a machine learning-based scoring function to select the poses generated by GOLD [46], GLIDE [47], and Autodock Vina [42]. Given a ligand target, we at first formed a training data of complexes taken from the PDB. The criteria for such selections are based on the similarity coefficient, measured by fingerprint 2 (FP2) in Open Babel v2.3.1 [48], of ligand in the complex. Then, we utilized docking software packages such as GOLD, GLIDE, and Autodock Vina to redock ligands to protein in those selected complexes. A variety of docking poses was distributed into 10 different RMSD bins as follows: [0,1], (1,2], …, (9,10]
Å
. In each bin, we clustered decoys into 10 clusters based on their internal similarities. The docking poses having the smallest free energy were selected as the candidate for their clusters. As a result, one may end up with a total of 100 poses for each given complex. We employed all these decoy poses to form a training set with labels defined by their RMSDs. Our topological based deep learning models were utilized to learn this training set. Finally, we employed this established scoring function to re-rank the poses of the target ligand produced by docking software packages.” (pg. 4-5, para. 6, lines 1-15). The selection of compound docking poses based on smallest free energy suggests that there was a comparison between a first predicted free energy and other predicted free energies. The target ligand docking poses were then assigned rankings based on the similarity to the selection of docking poses, which implies an ordered list.
With respect to claim 3:
With respect to the recited wherein the set of compounds includes proteins, Nguyen [A] discloses “Subchallenge 3 involved the binding affinity ranking and free energy prediction of target JAK2. It consisted of a relatively small dataset with 17 ligands having similar chemical structures.” (pg. 3, para. 3, lines 9-11). This indicates a small dataset of ligands for binding affinity ranking and free energy prediction to target JAK2, which suggests that these ligands can include proteins.
With respect to the recited calculate a plurality of multi-weighted colored subgraph centralities for the first protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating multi-weighted colored subgraph centralities for a protein.
With respect to the recited generate a feature vector that includes the multi-weighted colored subgraph centralities, wherein one of the sets of feature data includes the feature vector, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “The combination of MWCS and algebraic topological descriptors was utilized as the features in the random forest and deep learning methods. Also, we were interested in seeing how the docking features can enhance our mathematical descriptors by including the Autodock Vina scoring terms in some submissions.” (pg. 11-12, para. 4, lines 6-10). This suggests generating feature vectors that include multiscale centralities because these are MWCS descriptors utilized as feature data in the machine learning methods.
With respect to the recited process the feature vector with the Poisson-Boltzmann machine learning model to generate a predicted electrostatic solvation free energy of the first protein, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). This suggests that MWCG feature vectors were processed in machine learning models to generate a predicted free energy value of a protein.
With respect to claim 4:
With respect to the recited to calculate a first multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the first protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating a multi-weighted colored subgraph centrality for a protein.
With respect to the recited define vertices for atoms of the first protein, Nguyen [A] discloses “Weighted colored subgraph (WCS) method describes intermolecular and intramolecular interactions as pairwise atomic correlations [24]. To apply the WCS for analyzing the protein-ligand interactions, we convert all the atoms and their pairwise interactions at the binding site of a protein-ligand complex with a cutoff distance
d
into a colored subgraph
G
(
V
d
,
E
)
with vertices
V
d
and edge
E
. As such, the
i
t
h
atom is labeled by its position
r
i
, element type
a
i
and co-crystal type
β
i
. Thus, we can express vertices
V
d
as
V
d
=
r
i
,
α
i
,
β
i
|
r
i
∈
R
3
,
α
i
∈
C
,
β
i
∈
S
,
r
i
-
r
j
<
d
f
o
r
s
o
m
e
1
≤
j
≤
N
s
u
c
h
t
h
a
t
β
i
+
β
j
=
1
,
i
=
1
,
2
,
…
,
N
” (pg. 5-6, para. 8, lines 1-8). This suggests defining vertices for atoms of a protein.
With respect to the recited define first edges corresponding to pairwise atomic interactions between the atoms of the first protein using a generalized Lorentz function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized Lorentz function.
With respect to the recited calculate first atomic centralities for each of the atoms of the first protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). This suggests calculating atomic centralities for atoms of a protein.
With respect to the recited sum the first atomic centralities to generate the first multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities.
With respect to claim 5:
With respect to the recited to calculate a second multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the first protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating a multi-weighted colored subgraph centrality for a protein.
With respect to the recited define second edges corresponding to pairwise atomic interactions between the atoms of the first protein using a generalized exponential function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized exponential function.
With respect to the recited calculate second atomic centralities for each of the atoms of the first protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). This suggests calculating atomic centralities for atoms of a protein.
With respect to the recited sum the second atomic centralities to generate the second multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities.
With respect to claim 8:
With respect to the recited calculating, by a processor, a plurality of multi-weighted colored subgraph centralities for a protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests calculating multi-weighted colored subgraph centralities for a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited generating, by the processor, a feature vector that includes the multi-weighted colored subgraph centralities, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “The combination of MWCS and algebraic topological descriptors was utilized as the features in the random forest and deep learning methods. Also, we were interested in seeing how the docking features can enhance our mathematical descriptors by including the Autodock Vina scoring terms in some submissions.” (pg. 11-12, para. 4, lines 6-10). Nguyen [A] discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests generating feature vectors that include multiscale centralities because these are MWCS descriptors utilized as feature data in the machine learning methods. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited executing, by the processor, a Poisson-Boltzmann machine learning model to process the feature vector to generate a predicted electrostatic solvation free energy of the protein, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). Nguyen [A] discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests that MWCG feature vectors were processed in machine learning models to generate a predicted free energy value of a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to claim 9:
With respect to the recited calculating, by the processor, a second plurality of multi-weighted colored subgraph centralities for a second protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests calculating multi-weighted colored subgraph centralities for a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited generating, by the processor, a second feature vector that includes the second multi-weighted colored subgraph centralities, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “The combination of MWCS and algebraic topological descriptors was utilized as the features in the random forest and deep learning methods. Also, we were interested in seeing how the docking features can enhance our mathematical descriptors by including the Autodock Vina scoring terms in some submissions.” (pg. 11-12, para. 4, lines 6-10). Nguyen [A] discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests generating feature vectors that include multiscale centralities because these are MWCS descriptors utilized as feature data in the machine learning methods. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited executing, by the processor, the Poisson-Boltzmann machine learning model to process the second feature vector to generate a second predicted electrostatic solvation free energy of the second protein, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). Nguyen [A] discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests that MWCG feature vectors were processed in machine learning models to generate a predicted free energy value of a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to claim 10:
With respect to the recited assigning, by the processor, rankings to the protein and the second protein based on the first predicted electrostatic solvation free energy and the second predicted electrostatic solvation free energy, Nguyen [A] discloses “We developed a machine learning-based scoring function to select the poses generated by GOLD [46], GLIDE [47], and Autodock Vina [42]. Given a ligand target, we at first formed a training data of complexes taken from the PDB. The criteria for such selections are based on the similarity coefficient, measured by fingerprint 2 (FP2) in Open Babel v2.3.1 [48], of ligand in the complex. Then, we utilized docking software packages such as GOLD, GLIDE, and Autodock Vina to redock ligands to protein in those selected complexes. A variety of docking poses was distributed into 10 different RMSD bins as follows: [0,1], (1,2], …, (9,10]
Å
. In each bin, we clustered decoys into 10 clusters based on their internal similarities. The docking poses having the smallest free energy were selected as the candidate for their clusters. As a result, one may end up with a total of 100 poses for each given complex. We employed all these decoy poses to form a training set with labels defined by their RMSDs. Our topological based deep learning models were utilized to learn this training set. Finally, we employed this established scoring function to re-rank the poses of the target ligand produced by docking software packages.” (pg. 4-5, para. 6, lines 1-15). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). The selection of compound docking poses based on smallest free energy suggests that there was a comparison between a first predicted free energy and a second predicted free energies. The target ligand docking poses were then assigned rankings based on the similarity to the selection of docking poses. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited generating, by the processor, an ordered list that includes the protein and the second protein based on the rankings, Nguyen [A] discloses “We employed the machine learning based scoring function to select the best poses for all prediction tasks, i.e., docking Protocol 1. The free energy values were predicted by scheme EP1. Although our pose ranking power was not impressive, the free energy predictions of our model performed pretty well. Specifically, our submission with receipt ID 5bvwx was ranked the second place in the free energy set 1 of stage 1 with
R
M
S
E
c
=
0.68
k
c
a
l
/
m
o
l
. In stage 2, our models improved the accuracy of the energy prediction of compounds in the aforementioned free energy set. In fact, we obtained the first place in term of Kendall’s tau value (
τ
=
0.41
) with receipt ID 4rbjk. That was also the highest Kendall’s tau value among all submissions in two stages for the free energy set 1. Figure 3 plots the performance of all submissions on the free energy set 1 in stage 2.” (pg. 13, para. 4, lines 1-10). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). Submissions in this generated list indicate free energy predictions of protein compounds in order from highest to lowest Kendall’s tau value, which measures the relationship between the prediction and the actual free energy in Grand Challenge 2. Therefore, this suggests an ordered list that includes the protein and a second protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited causing, by the processor, the ordered list to be displayed at a user device, Nguyen [A] discloses “We employed the machine learning based scoring function to select the best poses for all prediction tasks, i.e., docking Protocol 1. The free energy values were predicted by scheme EP1. Although our pose ranking power was not impressive, the free energy predictions of our model performed pretty well. Specifically, our submission with receipt ID 5bvwx was ranked the second place in the free energy set 1 of stage 1 with
R
M
S
E
c
=
0.68
k
c
a
l
/
m
o
l
. In stage 2, our models improved the accuracy of the energy prediction of compounds in the aforementioned free energy set. In fact, we obtained the first place in term of Kendall’s tau value (
τ
=
0.41
) with receipt ID 4rbjk. That was also the highest Kendall’s tau value among all submissions in two stages for the free energy set 1. Figure 3 plots the performance of all submissions on the free energy set 1 in stage 2.” (pg. 13, para. 4, lines 1-10). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). Submissions in this list indicate free energy predictions of protein compounds in order from highest to lowest Kendall’s tau value, which measures the relationship between the prediction and the actual free energy in Grand Challenge 2. Therefore, this suggests an ordered list of compounds. The performance plot in Figure 3 implies that the list is displayed with a user device. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to claim 11:
With respect to the recited calculating, by the processor, a first multi-weighted colored subgraph centrality of the plurality of multi-weighted colored subgraph centralities for the protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests calculating a multi-weighted colored subgraph centrality for a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited defining, by the processor, vertices for atoms of the protein, Nguyen [A] discloses “Weighted colored subgraph (WCS) method describes intermolecular and intramolecular interactions as pairwise atomic correlations [24]. To apply the WCS for analyzing the protein-ligand interactions, we convert all the atoms and their pairwise interactions at the binding site of a protein-ligand complex with a cutoff distance
d
into a colored subgraph
G
(
V
d
,
E
)
with vertices
V
d
and edge
E
. As such, the
i
t
h
atom is labeled by its position
r
i
, element type
a
i
and co-crystal type
β
i
. Thus, we can express vertices
V
d
as
V
d
=
r
i
,
α
i
,
β
i
|
r
i
∈
R
3
,
α
i
∈
C
,
β
i
∈
S
,
r
i
-
r
j
<
d
f
o
r
s
o
m
e
1
≤
j
≤
N
s
u
c
h
t
h
a
t
β
i
+
β
j
=
1
,
i
=
1
,
2
,
…
,
N
” (pg. 5-6, para. 8, lines 1-8). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests defining vertices for atoms of a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited defining, by the processor, first edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized Lorentz function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized Lorentz function. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited defining, by the processor, first atomic centralities for each of the atoms of the protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests defining atomic centralities of a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited summing, by the processor, the first atomic centralities to generate the first multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to claim 12:
With respect to the recited calculating, by the processor, a second multi-weighted colored subgraph centrality for the protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests calculating a multi-weighted colored subgraph centrality for a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited defining, by the processor, second edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized exponential function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized exponential function. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited calculating, by the processor, second atomic centralities for each of the atoms of the protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests calculating atomic centralities for atoms of a protein. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to the recited summing, by the processor, the second atomic centralities to generate the second multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “all the receptor structures in GC3 are supplied in the protein sequence format. We utilized the homology modeling task in Maestro of Schrödinger software [44] to obtain 3D structure predictions.” (pg. 4, para. 4, lines 1-3). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities. The use of a software to obtain resulting predictions implies that the overall method is using a computer, which is inherently a processor.
With respect to claim 16:
With respect to the recited calculate multi-weighted colored subgraph centralities for the protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating multi-weighted colored subgraph centralities for a protein.
With respect to the recited generate a feature vector that includes the multi-weighted colored subgraph centralities, wherein the feature data includes the feature vector, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). Also, further discloses “The combination of MWCS and algebraic topological descriptors was utilized as the features in the random forest and deep learning methods. Also, we were interested in seeing how the docking features can enhance our mathematical descriptors by including the Autodock Vina scoring terms in some submissions.” (pg. 11-12, para. 4, lines 6-10). This suggests generating feature vectors that include multiscale centralities because these are MWCS descriptors utilized as feature data in the machine learning methods.
With respect to the recited process the feature vector with the Poisson-Boltzmann machine learning model to generate the predicted electrostatic solvation free energy of the protein, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). This suggests that MWCG feature vectors were processed in machine learning models to generate a predicted free energy value of a protein.
With respect to claim 17:
With respect to the recited to calculate a first multi-weighted colored subgraph centrality of the multi-weighted colored subgraph centralities, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating a multi-weighted colored subgraph centrality for a protein.
With respect to the recited define vertices for atoms of the protein, Nguyen [A] discloses “Weighted colored subgraph (WCS) method describes intermolecular and intramolecular interactions as pairwise atomic correlations [24]. To apply the WCS for analyzing the protein-ligand interactions, we convert all the atoms and their pairwise interactions at the binding site of a protein-ligand complex with a cutoff distance
d
into a colored subgraph
G
(
V
d
,
E
)
with vertices
V
d
and edge
E
. As such, the
i
t
h
atom is labeled by its position
r
i
, element type
a
i
and co-crystal type
β
i
. Thus, we can express vertices
V
d
as
V
d
=
r
i
,
α
i
,
β
i
|
r
i
∈
R
3
,
α
i
∈
C
,
β
i
∈
S
,
r
i
-
r
j
<
d
f
o
r
s
o
m
e
1
≤
j
≤
N
s
u
c
h
t
h
a
t
β
i
+
β
j
=
1
,
i
=
1
,
2
,
…
,
N
” (pg. 5-6, para. 8, lines 1-8). This suggests defining vertices for atoms of a protein.
With respect to the recited define first edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized Lorentz function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized Lorentz function.
With respect to the recited calculate first atomic centralities for each of the atoms of the protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). This suggests calculating atomic centralities for atoms of a protein.
With respect to the recited sum the first atomic centralities to generate the first multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities.
With respect to claim 18:
With respect to the recited to calculate a second multi-weighted colored subgraph centrality of the multi-weighted colored subgraph centralities, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests calculating a multi-weighted colored subgraph centrality for a protein.
With respect to the recited define second edges corresponding to pairwise atomic interactions between the atoms of the protein using a generalized exponential function, Nguyen [A] discloses “For each set of element pairs
P
k
,
k
=
1
,
2
,
…
,
36
, a set of vertices
V
P
k
is a subset of
V
d
containing all atoms that belong to a pair in
P
k
. Therefore, the edges in such WCS describing potential pairwise atomic interactions are defined by
E
P
k
σ
,
τ
,
ζ
=
Ф
τ
,
ζ
σ
r
i
-
r
j
|
(
α
i
,
β
i
α
j
,
β
j
)
∈
P
k
;
i
,
j
=
1
,
2
,
…
,
N
, where
r
i
-
r
j
defines a Euclidean distance between
i
t
h
and
j
t
h
atoms,
σ
indicates the type of radial basic functions (e.g.,
σ
= L for Lorentz kernel,
σ
= E for exponential kernel),
τ
is a scale distance factor between two atoms, and
ζ
is a parameter of power in the kernel (i.e.,
ζ
=
κ
when
σ
= E,
ζ
=
v
when
σ
= L). The kernel
Ф
τ
,
ζ
σ
characterizes a pairwise correlation satisfying the following conditions
Ф
τ
,
ζ
σ
r
i
-
r
j
=
1
a
s
r
i
-
r
j
→
0
,
Ф
τ
,
ζ
σ
r
i
-
r
j
=
0
a
s
r
i
-
r
j
→
∞
. Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
” (pg. 6, para. 1, lines 14-28). This suggests defining edges describing pairwise atomic interactions between atoms using a generalized exponential function.
With respect to the recited calculate second atomic centralities for each of the atoms of the protein, Nguyen [A] discloses “Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair. In the current work, we choose
w
i
j
=
1
i
f
β
i
+
β
j
=
1
,
o
t
h
e
r
w
i
s
e
w
i
j
=
0
, for all calculations to reduce dimension of the parameter space. To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 1, lines 6-19). This suggests calculating atomic centralities for atoms of a protein.
With respect to the recited sum the second atomic centralities to generate the second multi-weighted colored subgraph centrality, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests summing atomic centralities to achieve multiscale centralities, or multi-weighted colored subgraph centralities.
Claims 6, 13, 15, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Nguyen et al. (Journal of Computer-Aided Molecular Design, 2019, 33, 1-22), referred to as Nguyen [A], as applied to claims 1-5, 8-12, and 16-18 above, in view of Bramer et al. (The Journal of Chemical Physics, 2018, 148(5), 1-14).
Nguyen [A] is applied to claims 1-5, 8-12, and 16-18 above.
With respect to claims 6, 13, and 19:
With respect to the recited wherein the generalized exponential function and the generalized Lorentz function are weighted based on atomic rigidity, Nguyen [A] discloses “Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
, where
r
i
and
r
j
are, respectively, the van de Waals radius of the
i
t
h
and
j
t
h
atoms. In the graph theory or network analysis, centrality is widely used to identify the most important nodes [57]. There are various types of centrality such as degree centrality [58], closeness centrality [59], harmonic centrality [60], etc. Specifically, while the degree centrality is measured as a number of edges upon a node, closeness and harmonic centralities depend on the length of edges and are defined as
1
/
∑
j
r
i
-
r
j
and
∑
j
1
/
r
i
-
r
j
, respectively. Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair.” (pg. 6-7, para. 4, lines 1-15). This describes a generalized exponential function and a generalized Lorentz function used to calculate a centrality.
However, Bramer et al. discloses “Our previous work has shown that generalized exponential functions,
Ф
k
(
r
i
-
r
j
;
η
i
j
=
e
-
(
r
i
-
r
j
/
η
i
j
)
κ
,
(
α
i
α
j
)
∈
P
k
;
κ
>
0
, and generalized Lorentz functions,
Ф
k
(
r
i
-
r
j
;
η
i
j
=
1
1
+
(
r
i
-
r
j
/
η
i
j
)
v
,
(
α
i
α
j
)
∈
P
k
;
v
>
0
, are good choices which satisfy the assumptions. Centrality is an important concept in graph theory and has many applications. There are many centrality definitions. For example, normalized closeness centrality and Harmonic centrality of node
r
i
in a connected graph are given as
1
/
∑
j
r
i
-
r
j
and
∑
j
1
/
r
i
-
r
j
, respectively. In this context, we extend Harmonic centrality to subgraphs with weighted edges defined by generalized correlation functions,
μ
i
k
=
∑
j
=
1
N
w
i
j
Ф
k
r
i
-
r
j
;
η
i
j
,
α
i
α
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
N
, where
w
i
j
is a weight function related to the element type. The WCG centrality in Eq. (6) describes the atomic specific rigidity which measures the stiffness at the
i
t
h
atom due to the
k
t
h
set of contact atoms.” (pg. 4, col. 2, para. 1, lines 5-22). This suggests a generalized exponential function and a generalized Lorentz function used to calculate a centrality, which is based on atomic specific rigidity.
It would have been prima facie obvious to one of ordinary skill in the art to modify the generalized exponential function and the generalized Lorentz function disclosed by Nguyen [A] to incorporate weighting based on atomic rigidity disclosed by Bramer et al. One would be motivated to make this modification because the present MWCG used in the study of Bramer et al. is over 40% more accurate than GNM and delivers an average Pearson correlation coefficient as high as 0.8 in protein B-factor prediction of 364 proteins, which offers a reliable method for protein flexibility analysis and various applications (pg. 13, col. 2, para. 2, lines 22-26). There is a likelihood of success, since both methods are used to make predictions for protein analysis and are well known in the field of molecular dynamics.
With respect to claim 15:
Claim 15 recites a system comprising a non-transitory computer-readable memory and a processor configured to execute instructions stored on the non-transitory computer-readable memory.
Broadly claiming an automated means to replace a manual function to accomplish the same result does not distinguish over the prior art. See Leapfrog Enters., Inc. v. Fisher-Price, Inc., 485 F .3d 1157, 1161, 82 USPQ2d 1687, 1691 (Fed. Cir. 2007) (“Accommodating a prior art mechanical device that accomplishes [a desired] goal to modern electronics would have been reasonably obvious to one of ordinary skill in designing children’s learning devices. Applying modern electronics to older mechanical devices has been commonplace in recent years.”); In re Venner, 262 F. 2d 91, 95, 120 USPQ 193, 194 (CCPA 1958); see also MPEP § 2144.04. Furthermore, implementing a known function on a computer has been deemed obvious to one of ordinary skill in the art if the automation of the known function on a general purpose computer is nothing more than the predictable use of prior art elements according to their established functions. KSR Int’l Co. v. Teleflex Inc., 550 U.S. 398, 417, 82 USPQ2d 1385, 1396 (2007); see also MPEP § 2143, Exemplary Rationales D and F. Likewise, it has been found to be obvious to adapt an existing process to incorporate Internet and Web browser technologies for communicating and displaying information because these technologies had become commonplace for those functions. Muniauction, Inc. v. Thomson Corp., 532 F.3d 1318, 1326-27, 87 USPQ2d 1350, 1357 (Fed. Cir. 2008).
With respect to the recited generate feature data corresponding to the protein, Nguyen [A] discloses “To describe a centrality for the whole graph
G
(
V
P
k
,
E
P
k
σ
,
τ
,
ζ
)
, we take into account a summation of the node’s centralities
μ
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
μ
j
k
,
σ
,
τ
,
v
. Since we have 36 choices of the set of weighted colored edges
P
k
, we can obtain corresponding 36 bipartite subgraph centralities
μ
k
,
σ
,
τ
,
v
. By varying kernel parameters (
σ
,
τ
,
v
), one can achieve multiscale centralities for multiscale weighted colored subgraph (MWCS) [24]. For a two-scale WCS, we obtain a total of 72 descriptors for a protein-ligand complex.” (pg. 7, para. 2, lines 3-9). This suggests generating feature data, which is comprised of descriptors that correspond to a protein.
With respect to the recited process the feature data with a trained Poisson-Boltzmann machine leraning model to produce a predicted electrostatic solvation free energy of the protein, Nguyen [A] discloses “To make use of both MWCG and algebraic topology features, we carried out two different schemes for the energy prediction. In the first approach, we used random forest to learn the biomolecular structure represented by MWCG, and used CNNs with topological features. The final predictions for this method was the consensus results between the energy values predicted by two aforementioned machine learning strategies. We named this method EP1. In the second approach, MWCG and topological features were mixed and fed into the CNNs model. The energy value predicted by these deep learning networks was submitted. We name this model EP2.” (pg. 11, para. 2, lines 1-8). Also, further discloses “The best free energy predictions on the ligands with experiment structures were also attained by our predictions.” (pg. 12, para. 3, lines 10-11). This suggests that MWCG feature data was processed in machine learning models to generate a predicted free energy value of a protein.
Nguyen [A] does not disclose receive an identifier corresponding to a protein.
However, Bramer et al. discloses “The study uses two data sets, one from Refs. 35 and 38 and the other from the work of Park, Jernigan, and Wu. The first contains 364 proteins and the second contains 3 subsets of small, medium, and large proteins.” (pg. 9-10, col. 2, para. 1, lines 1-4). This describes data sets comprising of Protein Databank IDs, which are also depicted in Tables II-V under the column titled “PDB ID” (pg. 6-10, Tables II-V).
Claims 7, 14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Nguyen et al. (Journal of Computer-Aided Molecular Design, 2019, 33, 1-22), referred to as Nguyen [A], as applied to claims 1-5, 8-12, and 16-18 above, in view of Nguyen et al. (International Journal for Numerical Methods in Biomedical Engineering, 2018, 35(3), 1-28); refer to as Nguyen [B].
Nguyen [A] is applied to claims 1-5, 8-12, and 16-18 above.
With respect to claims 7, 14, and 20:
With respect to the recited wherein the generalized exponential function and the generalized Lorentz function are weighted based on atomic charge, Nguyen [A] discloses “Commonly used radial basis functions include generalized exponential functions
Ф
τ
,
x
E
=
e
-
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
κ
,
κ
>
0
, and generalized Lorentz functions
Ф
τ
,
v
L
r
i
-
r
j
=
1
1
+
(
r
i
-
r
j
/
τ
(
r
i
+
r
j
)
)
v
,
v
>
0
, where
r
i
and
r
j
are, respectively, the van de Waals radius of the
i
t
h
and
j
t
h
atoms. In the graph theory or network analysis, centrality is widely used to identify the most important nodes [57]. There are various types of centrality such as degree centrality [58], closeness centrality [59], harmonic centrality [60], etc. Specifically, while the degree centrality is measured as a number of edges upon a node, closeness and harmonic centralities depend on the length of edges and are defined as
1
/
∑
j
r
i
-
r
j
and
∑
j
1
/
r
i
-
r
j
, respectively. Our centrality used in the current work is an extension of the harmonic formulation by our correlation functions
μ
i
k
,
σ
,
τ
,
v
=
∑
j
=
1
V
P
k
w
i
j
Ф
τ
,
v
σ
r
i
-
r
j
,
α
i
,
β
i
α
j
,
β
j
∈
P
k
,
∀
i
=
1
,
2
,
…
,
V
P
k
, where
w
i
j
is a weight function assigned to each atomic pair.” (pg. 6-7, para. 4, lines 1-15). This describes a generalized exponential function and a generalized Lorentz function.
However, Nguyen [B] discloses “Let
X
=
{
r
1
,
r
2
,
…
,
r
N
,
}
be a finite set for
N
atomic coordinates in a molecule and
q
j
be the partial charge on the
j
t
h
atom, and
r
-
r
j
the Euclidean distance between the
j
t
h
atom and a point
r
∈
R
3
. The unnormalized molecular number density and molecular charge density are given by a discrete-to-continuum mapping
ρ
r
,
η
j
,
w
j
=
∑
j
=
1
N
w
j
Ф
(
r
-
r
j
;
η
j
)
, where
w
j
=
1
for molecular number density and
w
j
=
q
j
for molecular charge density. Here,
η
j
are characteristic distances and
Ф
is a
C
2
correlation kernel or a density estimator that satisfies the following admissibility conditions
Ф
r
-
r
i
;
η
j
|
|
=
1
,
a
s
r
-
r
j
→
0
,
Ф
r
-
r
j
;
η
j
|
|
=
0
,
a
s
r
-
r
j
→
∞
. Monotonically decaying radial basis functions are all admissible. Commonly used correlation kernels include generalized exponential functions
Ф
(
r
-
r
j
;
η
j
|
|
)
=
e
-
(
r
-
r
j
/
η
j
)
κ
,
κ
>
0
; and generalized Lorentz functions
Ф
r
-
r
j
;
η
j
=
1
1
+
(
r
-
r
j
/
η
j
)
v
,
v
>
0
. Many other functions, such as
C
2
delta sequences of the positive type discussed in an earlier work can be employed as well. Note that
ρ
r
,
η
j
,
w
j
depends on scale parameters
η
j
and possible charges
q
j
.” (pg. 4-5, para. 4, lines 1-18). This suggests a multiscale discrete-to-continuum mapping function that utilizes a generalized exponential function and a generalized Lorentz function, which depends on possible atomic charges.
It would have been prima facie obvious to one of ordinary skill in the art to modify the generalized exponential function and the generalized Lorentz function disclosed by Nguyen [A] to incorporate weighting based on atomic charges disclosed by Nguyen [B]. One would be motivated to make this modification because extensive numerical experiments indicate that the proposed DG-GL strategy of Nguyen [B] is able to outperform other state-of-the-art methods in drug toxicity, molecular solvation, and protein-ligand binding affinity predictions (pg. 15, para. 2, lines 17-19). There is a likelihood of success, since both methods are used to make predictions for molecular solvation free energy and are well known in the field of molecular dynamics.
Conclusion
No claims are allowed.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jammy Luo whose telephone number is (571)272-2358. The examiner can normally be reached Monday - Friday, 9:00 AM - 5:00 PM 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, Larry D Riggs can be reached at (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.
/J.N.L./Examiner, Art Unit 1686
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686