DETAILED ACTION
Applicant’s response filed 10/30/2025 has been fully considered. The following rejections and/or objections are either reiterated or newly applied. This is a Second Non-final action due to grounds of rejection under 35 USC 112 that were not necessitated by Applicant’s claim amendments.
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 3, 5, 8, 15, 17, 25, 27 and 29 are cancelled by Applicant.
Claims 34-35 are newly added by Applicant.
Claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are currently pending and are herein under examination.
Claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are rejected.
Claims 1, 13 and 32-33 are objected.
Priority
The instant application claims domestic benefit as a 371 of PCT/GB2020/051549 filed 06/26/2020 and claims foreign priority to UK Application No. GB1909925.8 filed 07/10/2019. However, neither of these applications disclose a computer system capable of performing step (e) as recited in instant claim 13. Thus, the claims to the benefit of priority for claims 1-2, 4, 6-7, 9-12, 26, 28 and 31-35 are acknowledged but are not acknowledged for claims 13-14, 16, 18-24 and 30. As such, the effective filing date for claims 1-2, 4, 6-7, 9-12, 26, 28 and 31-35 is 07/10/2019. The effective filing date for claims is 13-14, 16, 18-24 and 30 is 08/08/2024, which is the date of original disclosure for the computer system of claim 13 to perform step (e).
Withdrawn Rejections
35 USC 101
The rejection of claims 13-14, 16, 18-24 and 30 under 35 USC 101 is withdrawn in view of Applicant’s amendments.
35 USC 103
The rejection of claims 1-2, 4, 6-7, 9-12, 26, 28 and 31 under 35 U.S.C. 103 as being unpatentable over Duan et al. in view of Lim et al., Zhang et al., Hughes et al., and Napolitano et al. is withdrawn in view of claim amendments.
The rejection of claim 32 under 35 U.S.C. 103 as being unpatentable over Duan et al. in view of Lim et al., Zhang et al., Hughes et al., and Napolitano et al., as applied in the rejection above to claim 1, and in further view of Urban et al. is withdrawn in view of claim amendments.
The rejection of claims 13-14, 16, 18-24, 30 and 33 under 35 U.S.C. 103 as being unpatentable over Duan et al. in view of Lim et al., Zhang et al., and Parenti et al. is withdrawn in view of claim amendments.
Claim Objections
Claims 1, 13 and 32-33 are objected to because of the following informalities:
Claim 1, lines 3-4, recites the phrase “one or more first target genes” which should be “the one or more first target genes” to correspond to the same phrase in the preamble.
Claim 13, lines 7-8, recites the phrase “one or more first target genes” which should be “the one or more first target genes” to correspond to the same phrase in the preamble.
Claim 13 step (d) recites the phrase “and wherein the binding of the first optimum compound to the one or more first target genes” appears to be out of place as a result of claim amendment. Delete the phrase or change its grammar to fit better in step (d).
Claim 32, line 5, recites the phrase “and second optimum compound” which should be “the second optimum compound” to clarify that it refers to “a second optimum compound” in claim 32, line 3.
Claim 33, lines 3-4, recites the phrase “one or more first target genes” which should be “the one or more first target genes” to correspond to the same phrase in the preamble.
Claim 33 step (e) recites the word “use” which should be “using” to maintain consistency in verb tense.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
35 USC 112(a)
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 13-14, 16, 18-24 and 30 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the claims and disclosure.
Claim 1 recites new matter. Claim 1 step (e) tests whether the first optimum compound upregulates or inhibits one or more first target genes as part of a disease-target hypothesis during drug discovery. The specification discloses targeting a gene with a compound [1] [38], predicting association data between a compound and a target gene [46], and in silico generation of metrics such as IC50 and EC50. However, neither the specification nor the drawings disclose testing (e.g., in vitro or in vivo) whether the optimum compound inhibits or upregulates the target genes.
Claim 13 recites new matter. Claim 13 step (e) uses the system to test whether the first optimum compound targets one or more first target genes as part of a disease-target hypothesis during drug discovery. However, neither the specification nor the drawings disclose that the system of claim 13 performs the function of step (e). Rather, the specification discloses in para. [38] that a scientist performs the testing for disease-target hypothesis rather than the system of claim 13.
Furthermore, claims 14, 16, 18-24 and 30 are also rejected because they depend on claim 13, which is rejected.
35 USC 112(b)
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the claims.
Claim 1 step (c), lines 20-23, recites the phrase “(IC50) of the compound or … the compound (EC50) … the compound affects … the compound for a gene” which renders the claim indefinite. It is unclear which compound is being referenced because claim step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a first candidate compound as recited in step (b). To overcome this rejection, clarify which compound is being referenced.
Furthermore, claims 2, 4, 6-7, 9-12, 26, 28, 31-32 and 34-35 are also rejected because they depend on claim 1, which is rejected, and because they do not resolve the issue of indefiniteness.
Claim 2 recites the phrase “the polypharmacology fingerprint … the candidate compound” which renders the claim indefinite. It is unclear which polypharmacology fingerprint of which first candidate compound is being referenced because step (c) recites that each first candidate compound comprises a polypharmacology fingerprint.
Claim 7 recites the phrase “most similar” which is a relative phrase that renders the claim indefinite. The term “most similar” 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 how to clearly distinguish which first candidate compound is “most similar” to the theoretical tool compound because the scope of “most similar” is subjective.
Claim 12 step (b)(3) recites the phrase “the genes returned by the search and the predicted genes” which renders the claim indefinite. It is unclear if the phrase refers to claim 1 step (b)(1) and (b)(2) or if the phrase refers to claim 12 step (b)(1) and (b)(2) because both claims recite searching the database for genes and predicting genes. To overcome this rejection, clarify what the phrase refers to.
Claim 13 step (c), lines 24-27, recites the phrase “(IC50) of the compound or … the compound (EC50) … the compound affects … the compound for a gene” which renders the claim indefinite. It is unclear which compound is being referenced because step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a first candidate compound as recited in claim 1 step (b). To overcome this rejection, clarify which compound is being referenced.
Claim 13 steps (d) and (e) recite three times the phrase “the one or more first target genes” which renders the claim indefinite. It is unclear which “one or more first target genes” is being referenced because step (a) recites that each first candidate compound targets “one or more first target genes”. To overcome this rejection, clarify which one or more first target genes is being referenced.
Furthermore, claims 14, 16, 18-24 and 30 are also rejected because they include the limitations of claim 13, which has been rejected directly above, and because they do not resolve the issue of indefiniteness.
Claim 14 recites the phrase “the polypharmacology fingerprint … the candidate compound” which renders the claim indefinite. It is unclear which polypharmacology fingerprint of which first candidate compound is being referenced because step (c) recites that each first candidate compound comprises a polypharmacology fingerprint. To overcome this rejection, clarify which polypharmacology fingerprint of which first candidate compound is being referenced.
Claim 19 recites the phrase “most similar” which is a relative phrase that renders the claim indefinite. The term “most similar” 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 how to clearly distinguish which first candidate compound is “most similar” to the theoretical tool compound because the scope of “most similar” is subjective.
Claim 20 recites the phrase “most similar” which is a relative phrase that renders the claim indefinite. The term “most similar” 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 how to clearly distinguish which first candidate compound is “most similar” to the theoretical tool compound because the scope of “most similar” is subjective.
Claim 24 step (b)(3) recites the phrase “the genes returned by the search and the predicted genes” which renders the claim indefinite. It is unclear if the phrase refers to claim 13 step (b)(1) and (b)(2) or if the phrase refers to claim 24 step (b)(1) and (b)(2) because both claims recite searching the database for genes and predicting genes. To overcome this rejection, clarify what the phrase refers to.
Claim 24, lines 23-25, recites the phrase “(IC50) of the compound or … the compound (EC50) … the compound affects … the compound for a gene” which renders the claim indefinite. It is unclear which compound is being referenced because claim 24 step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a first candidate compound as recited in claim 1 step (b). To overcome this rejection, clarify which compound is being referenced.
Claim 28 recites the phrase “the compound” which renders it indefinite. It is unclear which compound is being referenced because claim 1 step (b)(3) recite that the machine learning model predicted interactions between “compounds” and gene binding sites using 3D interaction data. To overcome this rejection, clarify which compound is being referenced.
Claim 30 recites the phrase “the compound” which renders it indefinite. It is unclear which compound is being referenced because claim 13 step (b)(3) recite that the machine learning model predicted interactions between “compounds” and gene binding sites using 3D interaction data. To overcome this rejection, clarify which compound is being referenced.
Claim 32, line 5, line 6, lines 7-8, recite the phrases “the first optimum compound” and “the first and ... optimum compounds” which render the claim indefinite. It is unclear if the phrase refers to “a first optimum compound” in claim 1 step (c), or if it refers to “a first optimum compound” in claim 32, lines 2-3. To overcome this rejection, clarify what the phrase refers to.
Claim 32, lines 7-8, recites the phrase “the one or more off-target genes that differ between the first and second optimum compounds” which lacks antecedent basis. To overcome this rejection, change the phrase to “one or more off-target genes that differ between the first and second optimum compounds.”
Claim 33 step (c), lines 20-23, recites the phrase “(IC50) of the compound or … the compound (EC50) … the compound affects … the compound for a gene” which renders the claim indefinite. It is unclear which compound is being referenced because claim step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a first candidate compound as recited in step (b). To overcome this rejection, clarify which compound is being referenced.
Claim 33 steps (d) and (e) recite the phrase “the one or more first target genes” which renders the claim indefinite. It is unclear which “one or more first target genes” is being referenced because the preamble recites “one or more first target genes” and because there is a set of “one or more first target genes” for each first candidate compound in step (a). To overcome this rejection, clarify what the phrase refers to.
Claim 34, line 3, recites the phrase “the compound ... the compound” which renders the claim indefinite. It is unclear which compound is being referenced because claim 1 step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a respective first candidate compound as recited in claim 1 step (b). To overcome this rejection, clarify which compound is being referenced.
Claim 35, line 3, recites the phrase “the compound affects ... the compound for a gene” which renders the claim indefinite. It is unclear which compound is being referenced because claim 1 step (c) recites that the metrics are generated from the first fingerprints, wherein each first fingerprint corresponds to a respective first candidate compound as recited in claim 1 step (b). To overcome this rejection, clarify which compound is being referenced.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
This rejection is newly recited is necessitated in view of further consideration of the claims.
Step 2A, Prong 1:
In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomena (Step 2A, Prong 1). In the instant application, claims 1-2, 4, 6-7, 9-12, 26, 28, 31-32 and 34-35, claims 13-14, 16, 18-24 and 30 recite a system, and claim 33 recites a method. The instant claims recite the following limitations that equate to one or more categories of judicial exception:
Claims 1, 13 and 33 recite “(a) search/searching a database for first candidate compounds that each target one or more first target genes; (b) automatically generate/generating a first fingerprint for each first candidate compound, by (1) searching the database for genes associated with the first candidate compound, (2) predicting genes associated with the first candidate compound using a machine learning model trained to predict a gene interaction profile for a range of compounds, and (3) building the first fingerprint using the genes returned by the search and the predicted genes, wherein the machine learning model predicts interactions between compounds and gene binding sites using three-dimensional (3D) interaction data;(c) automatically filter/filtering the first candidate compounds using the first fingerprints to identify a first optimum compound for targeting the one or more first target genes, wherein, filtering the first candidate compounds comprises combining filtering by comparing each of the first fingerprints to an ideal fingerprint of a theoretical tool compound and filtering by using metrics generated from the first fingerprints, wherein the metrics comprise one or more of molar weight (MW), a number of hydrogen bond acceptors or donors, enzyme activity comprising at least one of values of a half maximal inhibitory concentration (IC50) of the compound or a half maximal effective concentration of the compound (EC50) in assay, selectivity of a compound for a target gene, number of unwanted genes that the compound affects, potency of the compound for a gene, or cell data providing an indication of an activity of a compound in a cellular assay, and each of the first fingerprints and the ideal fingerprint comprises a polypharmacology fingerprint that describes with which genes the compound is associated; (d) outputting/output the first optimum compound, wherein the first optimum compound binds/targets the one or more first target genes.”
Claims 2 and 14 recite “wherein the polypharmacology fingerprint indicates genes that are inhibited by the candidate compound and an extent to which they are inhibited.”
Claims 4 and 16 recite “automatically predict genes associated with a given first candidate compound only when there is no association data available in the database.”
Claims 6 and 18 recite “wherein the comparing of each of the first fingerprints to an ideal fingerprint of a theoretical tool compound comprises calculating a similarity score.”
Claims 7 and 19 recite “automatically identify one or more of the first candidate compounds which are most similar to the theoretical tool compound as the first optimum compound.”
Claim 9 recites “wherein generating one or more of the first fingerprints comprises obtaining metadata about one or more of the first candidate compounds.”
Claim 20 recites “automatically select, as the first optimum compound, the first candidate compound that is the most similar to the theoretical tool compound.”
Claim 21 recites “automatically obtain metadata about one or more of the first candidate compounds.”
Claims 10 and 22 recite “wherein the metadata comprises at least one of clinical trial phase data, a drug name, or a drug property.”
Claims 11 and 23 recites “automatically use a library evaluation framework to retrieve an indication of how many targets each first candidate compound has.”
Claims 12 and 24 recite “(a) search the database for second candidate compounds that each target one or more second target genes; (b) automatically generate a second fingerprint for each second candidate compound by (1) searching the database for genes associated with the second candidate compound, (2) predicting genes associated with the second candidate compound using the machine learning model trained to predict a gene interaction profile for a range of compounds or another machine learning model trained to predict a gene interaction profile for a range of compounds, and (3) building the second fingerprint using the genes returned by the search and the predicted genes; and (c) automatically filter a group of candidate compounds comprising the first candidate compounds and the second candidate compounds using the first fingerprints and the second fingerprints to identify the first optimum compound and to identify a second optimum compound for targeting the one or more second target genes, wherein, filtering the group of first candidate compounds and second candidate compounds comprises combining filtering by comparing each of the first fingerprints and the second fingerprints to the ideal fingerprint of a theoretical tool compound or another ideal fingerprint of a theoretical tool compound and filtering by using metrics generated from the first fingerprints, wherein the metrics comprise one or more of: molar weight (MW), a logarithm of a partition coefficient (logP), a number of hydrogen bond acceptors or donors, enzyme activity comprising at least one of values of a half maximal inhibitory concentration (IC50) of the compound or a half maximal effective concentration of the compound (EC5O) in assay, selectivity of a compound for a target gene, number of unwanted genes that the compound affects, potency of the compound for a gene, solubility, or cell data providing an indication of an activity of a compound in a cellular assay, and each of the second fingerprints and the another ideal fingerprint comprises a polypharmacology fingerprint that describes with which genes the compound is associated.”
Claim 26 recites “wherein each fingerprint for a compound represents the extent to which each of a number of genes are inhibited by the compound.”
Claims 28 and 30 recites “wherein the 3D interaction data comprise: data relating to a confirmation of the compound in three spatial dimensions, or data relating to a structure of at least part of a gene in three dimensions.”
Claim 32 recites “comprising automatically filtering the first candidate compounds using the first fingerprints to identify a first optimum compound and a second optimum compound that both target the one or more first target genes and have a beneficial effect in treating a disease, wherein the method further comprises using the first optimum compound and second optimum compound to identify one or more off-target genes that are affected by the first optimum compound and the second optimum compound and identifying the one or more off-target genes that differ between the first and second optimum compounds, thereby determining that the one or more first target genes is involved in a treatment mechanism of the disease.”
Claim 34 recites “wherein the metrics comprise enzyme activity comprising at least one of values of a half maximal inhibitory concentration (IC50) of the compound or a half maximal effective concentration of the compound (EC50) in assay.”
Claim 35 recites “wherein the metrics comprise one or more of: selectivity of a compound for a target gene, number of unwanted genes that the compound affects, potency of the compound for a gene, or cell data providing an indication of an activity of a compound in a cellular assay.”
Limitations reciting a mental process.
Claims 1, 4, 7, 9-13, 16, 19-23 and 32-33 recite limitations that are recited at such a high level of generality that they equate to a mental process because they are similar to the concepts of collecting information, analyzing it, and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), which the courts have identified as concepts that can be practically performed in the human mind. The paragraphs below discuss the limitations in these claims that recite a mental process under their broadest reasonable interpretation (BRI).
This paragraph discusses the BRI of claims 1, 12-13, 24 and 33. Steps (a) and (b)(1) include a human manually searching a database. Step (b)(2) includes perform calculations using a logistic regression. Step (b)(3) includes compiling information. Step (c) includes manually filtering compounds based on metrics associated with fingerprints. Step (d) includes writing down information on pen and paper as output. These limitations require analyzing, comparing, and organizing data at a high level of generality, and thus a human could perform them whether with their mind or using pen and paper.
The BRI of claims 4 and 16 include performing calculations with a trained machine learning model which may be a logistic regression.
The BRI of claims 6 and 18 include performing calculations to derive a similarity score on pen and paper.
The BRI of claims 7 includes analyzing data.
The BRI of claims 9-11 and 21-23 include collecting and analyzing information.
The BRI of claims 19-20 include making a determination based upon analyzing data and making a selection.
The BRI of claim 32 includes filtering data manually by analyzing data and identifying data based on analysis.
Limitations reciting a mathematical concept.
Claims 1, 6, 12-13, 18, 24 and 33 recite limitations that equate to a mathematical concept because they are similar to the concepts of organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)), which the courts have identified as mathematical concepts. The BRI of step (b)(2) in claims 1, 12-13, 24 and 33 includes performing calculations using a trained logistic regression. The BRI of claims 6 and 18 include performing calculations to derive a numerical similarity score.
Limitations included in the judicial exception.
The following claims recite limitations that further limit components recited in the judicial exception, but do not change the fact that the components are part of the judicial exception. Claims 2, 14, 26, 28, 30 and 34-35 further limit the polypharmacology fingerprint in claims 1/13, each fingerprint in claim 1, the 3D interaction data in claims 1/13, and the metrics in claim 1.
As such, claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 recite an abstract idea (Step 2A, Prong 1: Yes).
Step 2A, Prong 2:
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). The judicial exception is not integrated into a practical application because the claims do not recite additional elements that reflect an improvement to a computer, technology, or technical field (MPEP § 2106.04(d)(1) and 2106.5(a)), require a particular treatment or prophylaxis for a disease or medical condition (MPEP § 2106.04(d)(2)), implement the recited judicial exception with a particular machine that is integral to the claim (MPEP § 2106.05(b)), effect a transformation or reduction of a particular article to a different state or thing (MPEP § 2106.05(c)), nor provide some other meaningful limitation (MPEP § 2106.05(e)). Rather, the claims include limitations that equate to an equivalent of the words “apply it” and/or to instructions to implement an abstract idea on a computer (MPEP § 2106.05(f)), insignificant extra-solution activity (MPEP § 2106.05(g)), and generally linking the use of the judicial exception in a particular technological environment (MPEP § 2106.05(h)). The instant claims recite the following additional elements:
Claim 1 recites “A computer-implemented method of identifying a compound for targeting one or more first target genes, the method comprising: (e) using the first optimum compound to test whether the first optimum compound upregulates or inhibits the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Claims 2, 4, 6-7, 9-12, 26, 28, -3132 and 34-35 recite “The computer-implemented method of claim 1/9”
Claim 13 recites “A system for identifying a compound for targeting one or more target genes, the system comprising: one or more computer processors and associated non-transitory processor readable storage medium; and processor executable instructions stored in the storage medium that when executed by the one or more processors cause the system to: (e) use the first optimum compound to test whether the first optimum compound targets the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Claims 14, 18, 22 and 30 recite “The system of claim 13/21 …”
Claims 16, 19-21 and 23-34 recite “The system of claim 13, wherein, when executed by the one or more processors, the instructions cause the system to …”
Claim 31 recites “wherein the machine learning model comprises a neural network.”
Claim 33 recites “A system for identifying a compound for targeting one or more target genes, the system comprising: one or more computer processors and associated non-transitory processor readable storage medium; and processor executable instructions stored in the storage medium that when executed by the one or more processors cause the system to: (e) use the first optimum compound to test whether the first optimum compound binds to the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Regarding the above cited limitations in claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 a computer-implemented method and a system comprised of processors and non-transitory memory, there are no limitations requiring anything other than a generic computing system. Therefore, these limitations equate to mere instructions to implement an abstract idea on a generic computer which the courts have established does not render an abstract idea eligible in Alice Corp., 573 U.S. at 223, 110 USPQ2d at 1983. See also 573 U.S. at 224, 110 USPQ2d at 1984.
Claim 31 equates to insignificant, extra solution activity of necessary data gathering because the neural network is used to make predictions which are used to perform the judicial exception in claim 1 step (b)(3).
Step (e) in claims 1, 13 and 33 equates to insignificant extra-solution activity, mere instructions to apply the judicial exception, and generally linking a judicial exception to a particular technological environment. The three paragraphs below discuss why for each consideration:
First, regarding insignificant extra-solution activity. The recitation of “(e) using the first optimum compound to test whether the first optimum compound upregulates/inhibits, targets, or binds the one or more first target genes” does not impose meaningful limits on the claim (MPEP 2106.05(g)(2). The optimum compound is already filtered using metrics such as IC50. Thus, step (e) appears to confirm the abstract ideas performed in steps (b) and (c) by, for example, performing a wet-lab assay.
Second, regarding mere instructions to apply the judicial exception. The recitation of “(e) using the first optimum compound to test whether the first optimum compound upregulates/inhibits, targets, or binds the one or more first target genes” recites only the idea of a solution or outcome i.e., it fails to recite details of how a solution to a problem is accomplished (MPEP 2106.05(f)(1)). This recitation encompasses all forms (e.g., any suitable wet-lab technique) to determine whether the optimum compound targets, upregulates/inhibits, or binds a target gene. It also attempts to cover any target gene associated with any disease.
Third, regarding generally linking a judicial exception to a particular technological environment. The recitation in step (e) of “as part of a disease-target hypothesis during drug discovery” merely limits use of the abstract idea in steps (a)(d) to testing in a particular technological environment (i.e., disease-target hypothesis during drug discovery).
As such, claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are directed to an abstract idea (Step 2A, Prong 2: No).
Step 2B:
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). These claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because these claims recite additional elements that equate to instructions to apply the recited exception in a generic way and/or in a generic computing environment (MPEP § 2106.05(f)) and to well-understood, routine and conventional (WURC) limitations (MPEP § 2106.05(d)). The instant claims recite the following additional elements:
Claim 1 recites “A computer-implemented method of identifying a compound for targeting one or more first target genes, the method comprising: (e) using the first optimum compound to test whether the first optimum compound upregulates or inhibits the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Claims 2, 4, 6-7, 9-12, 26, 28, -3132 and 34-35 recite “The computer-implemented method of claim 1/9”
Claim 13 recites “A system for identifying a compound for targeting one or more target genes, the system comprising: one or more computer processors and associated non-transitory processor readable storage medium; and processor executable instructions stored in the storage medium that when executed by the one or more processors cause the system to: (e) use the first optimum compound to test whether the first optimum compound targets the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Claims 14, 18, 22 and 30 recite “The system of claim 13/21 …”
Claims 16, 19-21 and 23-34 recite “The system of claim 13, wherein, when executed by the one or more processors, the instructions cause the system to …”
Claim 31 recites “wherein the machine learning model comprises a neural network.”
Claim 33 recites “A system for identifying a compound for targeting one or more target genes, the system comprising: one or more computer processors and associated non-transitory processor readable storage medium; and processor executable instructions stored in the storage medium that when executed by the one or more processors cause the system to: (e) use the first optimum compound to test whether the first optimum compound binds to the one or more first target genes as part of a disease-target hypothesis during drug discovery.”
Regarding the above cited limitations in claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 a computer-implemented method and a system comprised of processors and non-transitory memory, there are no limitations requiring anything other than a generic computing system. These limitations equate to mere instructions to implement an abstract idea on a generic computing system, which the courts have established does not provide an inventive concept in Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363, 1367, 115 USPQ2d 1636, 1639 (Fed. Cir. 2015). Additionally, storing instructions in a non-transitory computer readable medium as stated in claim 13 equates to storing information in memory, which the courts have established as a WURC function of a generic computer in Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
As discussed above in Step 2A, Prong 2, step (e) in claims 1, 13 and 33 equates to insignificant extra-solution activity, mere instructions to apply the judicial exceptions, and generally linking a judicial exception to a particular technological environment; all of which do not provide an inventive concept.
Regarding claim 31, this limitation is WURC as taught by Si et al. (International journal of molecular sciences 16, no. 3 (2015): 5194-5215; newly cited). Si et al. discloses a review on predicting protein DNA-binding sites (title). Protein 3-D structure and DNA-binding site motifs are used to propose DNA-binding residues and locate DNA-binding residues in 3D structure (Figure 1). 3D structural data on protein-DNA complexes are used (sec. 2.1 and sec. 2.3.2). This data is used in neural networks to make predictions (sec. 2.4.3). The predictions also include transcription factors (sec. 2.6).
When these additional elements are considered individually and in combination, they do not provide an inventive concept. This is because the additional elements equate to WURC functions and components of a generic computing system, WURC limitations as taught by Si et al., mere instructions to apply the judicial exception, and generally link the use of a judicial exception to a particular technological environment. Therefore, these additional elements do not transform the claimed judicial exception into a patent-eligible application of the judicial exception and do not amount to significantly more than the judicial exception itself (Step 2B: No).
As such, claims 1-2, 4, 6-7, 9-14, 16, 18-24, 26, 28 and 30-35 are not patent eligible.
Response to Arguments under 35 USC 101
Applicant's remarks filed 10/30/2025 have been fully considered but they are not persuasive.
Applicant argues that claim 13 integrates the judicial exception by improving a method for identifying associations between a compound and a target gene for use in drug discovery (pg. 12, para. 3 – pg. 14, para. 3 of Applicant’s remarks). Applicant’s arguments are not persuasive for the following reasons:
Claim 13 does not integrate the judicial exception into a practical application. Steps (a)(d) have been identified as reciting a judicial exception. MPEP 2106.05(a) recites “the judicial exception alone cannot provide the improvement.” A practical application is determined by evaluating the additional elements alone or in combination (2106.04(d).I) as well as evaluating how the additional elements use or interact with the judicial exception (MPEP 2106.04(d).III). The additional elements in claim 13 are the system and step (e). The system is a generic computer and thus equates to implementing the abstract idea on a generic computer, which does not integrate into a practical application (MPEP 2106.05(f). Step (e) does not integrate into a practical application for the reasons described in the rejection above. Specifically, step (e) imposes no meaningful limitations as it confirms through wet-lab experimentation what was already predicted in-silico in steps (a)-(c) (i.e., the optimum compound was already filtered based on IC50 for target genes, thus indicating that it already targets the target genes). Additionally, step (e) appears to encompass all forms (i.e., any suitable wet lab technique) of determining whether the target compound targets the target genes, wherein the target genes are associated with any disease.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-2, 4, 6-7, 9-14, 18-24, 26, 28, 30, 33 and 35 are rejected under 35 U.S.C. 103 as being unpatentable over Duan et al. (“Duan”; NPJ systems biology and applications, 2(1), 1-12; previously cited on PTO892 mailed 04/04/2023) in view of Li et al. (“Li”; Molecular Genetics and Genomics 289, no. 3 (2014): 489-499; previously cited on PTO892 mailed 06/30/2025).
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the references.
The bold and italicized text below are the limitations of the instant claims, and the italicized text serves to map the prior art onto the instant claims.
Claims 1, 13 and 33:
A computer-implemented method of identifying a compound for targeting one or more first target genes, the method comprising:
A system for identifying a compound for targeting one or more target genes, the system comprising: one or more computer processors and associated non-transitory processor readable storage medium; and processor executable instructions stored in the storage medium that when executed by the one or more processors cause the system to:
A computer-implemented method of identifying a compound for targeting one or more first target genes, the method comprising:
Duan discloses a method called characteristic direction (CD) that improves upon current methods for computing signatures from the library of integrated network-based cellular (LINCS) L1000 data set (abstract). The L1000 signatures are processed with the CD method by use of a search engine application called L1000CDS. The application predicts whether a small-molecule signature will either mimic or reverse an input gene expression signature and also predicts gene drug targets for the small molecule profiles that were profiled by the L1000 assays (abstract).
Duan states that L1000CDS is a web-based search engine software application (pg. 4, col. 2) that can be accessed via a server (pg. 11, col. 1, para. 4), thus indicating that the method/system is performed on a computer that contains processors and memory.
(a) searching a database for first candidate compounds that each target one or more first target genes;
Duan states that the LINCS-L1000 data set (database) comprises over a million gene expression profiles (target genes) of chemically perturbed cell lines (abstract), which was obtained by determining the response of ~50 human cell lines to ~20,000 compounds (candidate compounds) (pg. 1, col. 1, para. 2).
(b) automatically generating a first fingerprint for each first candidate compound by
Duan states differential gene expression signatures for each compound in the LINCS-L1000 dataset were computed as a CD signature (fingerprint) (pg. 1, col. 2 – pg. 2, col. 2, para. 1) (pg. (pg. 10, col. 2, para. 2). The CD signature also associates the compounds’ structure and gene expression signature (Figure 2a) (pg. 3, col. 2, para. 2).
(1) searching the database for genes associated with the first candidate compound,
Duan teaches that a user can search through the L1000CDS database by specifically searching for a compound, wherein a CD signature for the compound appears which differentially expressed genes associated with the compound from the cell line perturbations (abstract) (Figure 4, column “signature”). The CD signatures describe the way in which gene expression changes in response to the compound (pg. 3, col. 2, para. 2).
(2) predicting genes associated with the first candidate compound using a machine learning model trained to predict a gene interaction profile for a range of compounds, and (3) building the first fingerprint using the genes returned by the search and the predicted genes, wherein the machine learning model predicts interactions between compounds and gene binding sites using three-dimensional (3D) interaction data;
Duan teaches that the L1000CDS search engine predicts target genes of the small molecules profiled by the L1000 assay (predicting genes associated with the first candidate compound … to predict a gene interaction profile for a range of compounds) (abstract) (pg. 5, col. 1, last para.) (pg. 11, col. 1, para. 3). Duan states that the CD signatures are generated for each compound in the LINCS-L1000 data (building the first fingerprint using the genes returned by the search) (pg. 10, col. 2, para. 2).
However, Duan does not disclose using a trained machine learning model that predicts interaction between compounds and gene binding sites using 3D interaction data.
Li predicts DNA-binding sites in DNA-binding proteins using an SVM based on sequential and 3D structure information (abstract). Table 1 shows the training and testing datasets containing 3D structural features used in the SVM (trained machine learning model). Data was taken from the Protein Data Bank (PDB) which contains protein-DNA complexes (gene binding sites) (pg. 490, col. 2, para. 3).
It would have been prima facie obvious to one of ordinary skill in the art to have modified the CD signatures of Duan by predicting DNA-binding sites in compounds/proteins used to treat diseases as taught by Li. The motivation for doing so is taught by Li who states identifying DNA-binding residues contribute to drug design and discovery (pg. 489, col. 2, last para.). Duan also states that knowing potential targets of molecules is very useful for many drug discovery applications (pg. 4, col. 1).
One of ordinary skill in the art would have a reasonable expectation of success because LINCS contains antibodies which could be used to make DNA-binding site predictions. The 3D data for predictions could be acquired from PDB. There also would have been a reasonable expectation of success to associate DNA-binding sites to specific genes because Li states that their method can be used to design artificial transcription factors (pg. 489, col. 2, last para. – pg. 490, col. 1, para. 1).
(c) automatically filtering the first candidate compounds using the first fingerprints to identify a first optimum compound for targeting the one or more first target genes,
Duan teaches that the L1000CDS application outputs the top 50 CD signatures (pg. 4, col. 2) (Figure 3). L1000CDS contains the compound (first candidate compounds) and their associated CD signatures (first fingerprints) (abstract) (Figure 4). Figure 4 show the top ranked compound (first optimum compound). The top 50 output is considered a filtering step because the L1000CDS contains ~20,000 compounds (pg. 1, col. 1, para. 1).
wherein, filtering the first candidate compounds comprises combining filtering by comparing each of the first fingerprints to an ideal fingerprint of a theoretical tool compound and
Duan shows in Figure 3 that a user can specify an up/down gene expression list (ideal fingerprint of a theoretical tool compound) that is used to calculate a similarity between the up/down gene expression list and a differential gene expression profile a compound captured in the CD signatures (first candidate compound) (pg. 4, col. 2) (pg. 6, col. 1, para. 1-3). The CD signature that has the highest similarity to the inputted up/down gene list is ranked number 1 and is outputted as shown in Figure 4. The L1000CDS database is filtered from ~20,000 compounds down to the top 50 ranked compounds for the inputted up/down gene expression list (pg. 1, col. 1, para. 1) (pg. 4, col. 2).
filtering by using metrics generated from the first fingerprints, wherein the metrics comprise one or more of: molar weight (MW), a logarithm of a partition coefficient (logP), a number of hydrogen bond acceptors or donors, enzyme activity comprising at least one of values of a half maximal inhibitory concentration (IC50) of the compound or a half maximal effective concentration of the compound (EC5O) in assay, selectivity of a compound for a target gene, number of unwanted genes that the compound affects, potency of the compound for a gene, solubility, or cell data providing an indication of an activity of a compound in a cellular assay,
Duan teaches that the CD signatures contain a differential gene expression profile for a compound used to perturb cell lines (abstract). Figure 4 shows single drug and small-molecule results from the L1000CDS application, which shows the chemical compounds used to perturb human cell lines and have associated differential gene expression data (Figure 4, column “signature”). This equates to potency of the compound for a gene and cell data providing an indication of an activity of a compound in a cellular assay. Compound potency is measured in cells by quantifying differential gene expression after perturbation. The L1000CDS database is filtered from ~20,000 compounds down to the top 50 ranked compounds for the inputted up/down gene expression list (pg. 1, col. 1, para. 1) (pg. 4, col. 2).
and each of the first fingerprints and the ideal fingerprint comprises a polypharmacology fingerprint that describes with which genes the compound is associated;
In Duan, both the inputted up/down genes and the differentially expressed genes associated with a compound are considered a polypharmacology fingerprint.
Claim 1: (d) outputting the first optimum compound, wherein the first optimum compound targets the one or more first target genes;
Claim 33: (d) outputting the first optimum compound, wherein the first optimum compound targets the one or more first target genes; and
Duan shows in Figure 4 L1000CDS outputting a number 1 ranked compound. The compound is ranked on whether it mimics or reverses an input gene expression signature and has associated gene targets (the first optimum compound) (abstract) (Figure 4). Duan gives an example of using their method to predict drugs and small molecules that inhibit Ebola infection (pg. 7, col. 1, para. 2-3). Tables 1 and 2 show a ranked list of the predicted drugs and small molecules to inhibit Ebola infection, wherein the number one ranked prediction is kenpaullone (Tables 1 and 2).
Claim 13: (d) output the first optimum compound, wherein the first optimum compound binds to the one or more first target genes and wherein the binding of the first optimum compound to the one or more first target genes;
Duan teaches that the predicted targets for all small-molecule signatures using the CD method were added as predictions in the L1000CDS application (pg. 4, col. 1). However, Duan does not teach that the drug gene target predictions determine whether the compound binds to the target genes. As discussed above, Li teaches using protein-DNA complexes to predict DNA-binding residues in DNA-binding proteins (abstract). Together Duan and Li teach outputting an optimum compound that binds to a target gene.
Claim 1: (e) using the first optimum compound to test whether the first optimum compound upregulates or inhibits the one or more first target genes as part of a disease-target hypothesis during drug discovery.
Claim 13: (e) use the first optimum compound to test whether the first optimum compound targets the one or more first target genes as part of a disease-target hypothesis during drug discovery.
Duan predicts kenpaullone as the top ranked drug (first optimum compound) to inhibit Ebola infection then treats tissue cultures with kenpaullone (pg. 7, col. 1, para. 3). Kenpaullone was observed to inhibit Ebola infection (Figure 6a) (pg. 7, col. 1, para. 3). Duan also teaches that their observations of differential gene expression after treating cells with kenpaullone are consistent with the predictions of kenpaullone as the top mimicking drug (first optimum compound upregulates or inhibits the one or more first target genes) (pg. 10, col. 1, para. 1).
Claim 33: (e) use the first optimum compound to test whether the first optimum compound binds to the one or more first target genes as part of a disease-target hypothesis during drug discovery.
Duan teaches predicting which genes are targeted by the small molecules and compounds (abstract). However, Duan does not test compounds for whether they bind to the target genes.
Li teaches using protein-DNA complexes to predict DNA-binding residues in DNA-binding proteins (abstract). Li also teaches that their predictions allow for experimental validation of the DNA-binding sites (pg. 497, col. 1, last para.) (pg. 497, col. 2, para. 2).
It would have been prima facie obvious to one of ordinary skill in the art to have experimentally validated whether a top ranked compound directly targets/binds a gene of interest in Duan because Li states that characterizing DNA-binding sites contributes to drug design and discovery. One of ordinary skill in the art would have had a reasonable expectation of success to experimentally validate whether a protein/compound binds a target gene because Li provides several examples of experimental validations (pg. 497, col. 1, last para. – col. 2, last para.).
Claims 2 and 14:
Duan states that the CD signatures contain gene expression data after treatment with a compound (pg. 3, col. 2, para. 2). These appear in the Target column of Figure 4.
Claim 4:
MPEP 2111.04.II recites “The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met.” Claim 4 is a contingent limitation because it is only required when there is no association data available in the database. As such, claim 4 is not required to be performed and is rejected because of its dependency on claim 1, which is rejected.
Claims 6-7 and 18-20:
Duan states that when a user inputs the up/down genes (theoretical tool compound) into the system, as shown in Figure 3, the system outputs a ranked listed of compounds (candidate compounds) that have a similar gene expression signature to the input up/down genes (similarity score), as shown in Figure 4 (pg. 4, col. 2; pg. 6, col. 1, para. 2). The number 1 ranked compound is the optimum compound, i.e., kenpaullone in Figure 4.
Claims 9-10 and 21-22:
Duan states that each of the expression entries are associated with the name of the compound used (pg. 6, col. 1, para. 1; Figure 4). Other metadata may be associated (pg. 4, col. 2) (pg. 6, col. 1, para. 1).
Claims 11 and 23:
Duan states that their method can also predict targets of the identified compound (pg. 9, col. 2 – pg. 10, col. 1, para. 1). Figure 4 contains a column called Targets that displays the number of target genes.
Claims 12 and 24:
Claims 12 and 24 perform the same steps as claims 1 and 13, respectively, which have been taught above, except that in step (c) both first and second candidate compounds are compared to the theoretical tool compound. Duan shows in Figure 4 that multiple compounds are ranked when the up/down genes are inputted into L1000CDS.
Claim 26:
Duan teaches that the CD signatures describe the way in which expression of a gene changes in response to the compound (pg. 1, col. 2).
Claims 28 and 30:
Duan does not disclose using 3D interaction data to predict interactions between compounds and genes. However, as taught above regarding claim 1, Li uses 3D structural features derived from protein-DNA complexes derived from PDB (conformation). (pg. 490, col. 2, para. 2).
Claim 35:
Duan states differential gene expression signatures for each compound in the LINCS-L1000 dataset were computed as a CD signature (pg. 1, col. 2 – pg. 2, col. 2, para. 1) (pg. (pg. 10, col. 2, para. 2). The CD signature associates a compound’s structure with the gene expression signature of the cell line that it perturbed (Figure 2a) (pg. 3, col. 2, para. 2). This is part of the L1000 assays which are cell data indicating effects of compounds on cell line gene expression.
Claims 16 and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Duan et al. (“Duan”; NPJ systems biology and applications, 2(1), 1-12; previously cited on PTO892 mailed 04/04/2023) in view of Li et al. (“Li”; Molecular Genetics and Genomics 289, no. 3 (2014): 489-499; previously cited on PTO892 mailed 06/30/2025), as applied above to claims 1 and 13, and in further view of Lim et al. (“Lim”; arXiv preprint arXiv:1904.08144, pg. 1-20; previously cited on PTO892 mailed 05/08/2024).
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the references. The italicized text serves to map the prior art onto the instant claims.
The limitations of claims 1 and 13 have been taught in the rejection above by Duan and Li.
Claim 16:
Duan states that the LINCS-L100 data set comprises over a million gene expression profiles of chemically perturbed cell lines (abstract) (pg. 1, col. 1, para. 2). Duan also teachings predicting which genes the compounds target (abstract) However, Duan and Li do not teach predicting genes when there is no associated data available in the database.
Lim discloses using a graph neural network to predict drug-target interactions, wherein graph features are extracted from intermolecular interactions taken directly from the 3D structural information of the protein-ligand binding pose (abstract). This model is then used for virtual screening and pose prediction (abstract). Lim discloses that a molecular library can be screened with proteins (pg. 13, para. 2 – pg. 14, para. 2; Figure 2).
It would have been prima facie obvious to one of ordinary skill in the art to have modified the method of Duan and Li for detecting targets of compounds/proteins by performing virtual screening on compounds/proteins that do not have associated interactions in a database as taught by Lim. The motivation for doing so is taught by Lim who states that accurate prediction of drug-target interaction is essential for in silico drug discovery (pg. 2, para. 1) and knowing potential targets of molecules is very useful for many drug discovery applications (pg. 4, col. 1). One of ordinary skill in the art would have a reasonable expectation of success because virtual screening attempts to find novel applications for therapeutics that do not have known associations.
Claim 31:
Li discloses an SVM that predicts DNA-binding sites on DNA-binding proteins using protein-DNA complexes and 3D structural data (abstract). However, neither Duan nor Li disclose using a neural network.
Lim discloses a trained graph neural network that predicts drug-target interactions based on 3D structural information of the protein-ligand binding pose (abstract).
An invention would have been prima facie obvious to one of ordinary skill in the art if there was a finding that the prior art contained a method/system that differed from the instant invention by the substitution of some components with other components, wherein the results of the substitution would have been predictable. It would have been prima facie obvious to substitute the SVM of Li with the graph neural network of Lim for predicting DNA-binding sites. The result of this substitution would have yielded predictable results because both the SVM and graph neural network use 3D structural data to make binding predictions.
Claim 32 is rejected under 35 U.S.C. 103 as being unpatentable over Duan et al. (“Duan”; NPJ systems biology and applications, 2(1), 1-12; previously cited on PTO892 mailed 04/04/2023) in view of Li et al. (“Li”; Molecular Genetics and Genomics 289, no. 3 (2014): 489-499; previously cited on PTO892 mailed 06/30/2025), as applied above to claim 1, and in further view of Urban et al. (“Urban”; Toxicology Research 3, no. 6 (2014): 433-444; previously cited on PTO892 mailed 06/30/2025).
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the references.
The bold and italicized text below are the limitations of the instant claims, and the italicized text serves to map the prior art onto the instant claims.
The limitations of claim 1 have been taught in the rejection above by Duan and Li.
Claim 32:
comprising automatically filtering the first candidate compounds using the first fingerprints to identify a first optimum compound and a second optimum compound that both target the one or more first target genes and have a beneficial effect in treating a disease,
Duan shows in Figure 3 that L1000CDS allows a user to input specific gene target combinations that a desired compound should target, wherein the target genes can be selected as up-regulated or down-regulated.
wherein the method further comprises using the first optimum compound and second optimum compound to identify one or more off-target genes that are affected by the first optimum compound and the second optimum compound and identifying the one or more off target genes that differ between the first and second optimum compounds, thereby determining that the one or more first target genes is involved in a treatment mechanism of the disease.
Duan discloses optimum compounds that target specific genes, but does not disclose determining off-target genes of the compounds to then compare off-target genes affected by different compounds.
Urban discloses predicting adverse drug reactions by an integrated experimental and computational approach, specifically predicting translations of off-target genes (abstract). Figure 1 shows off-target associated with adverse drug response in two anti-Parkinson drugs, Pergolide and Ropinirole. If a test compound is highly similar to a known off-target ligand, it is predicted to modulate that target as well (Figure 2) (pg. 438, col. 2, para. 2).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the instant invention to have modified the L1000CDS method of Duan for predicting effect of drugs on gene expression to include an assessment of off-target gene effects of compounds as taught by Urban because Urban states that adverse drug reactions are associated with most drugs and are often discovered late in drug development and sometimes only during extended course of clinical use (abstract). One of ordinary skill in the art would have had a reasonable expectation of success for combining Urban to Duan because Urban states that there are in silico models for predicting off-target effects of compounds (pg. 438, col. 1, para. 4-5).
Claim 34 is rejected under 35 U.S.C. 103 as being unpatentable over Duan et al. (“Duan”; NPJ systems biology and applications, 2(1), 1-12; previously cited on PTO892 mailed 04/04/2023) in view of Li et al. (“Li”; Molecular Genetics and Genomics 289, no. 3 (2014): 489-499; previously cited on PTO892 mailed 06/30/2025), as applied above to claim 1, and in further view of Kalliokoski et al. (“Kalliokoski”; PloS one 8, no. 4 (2013): e61007; newly cited).
This rejection is newly recited as necessitated by claim amendment and in view of further consideration of the references. The italicized text serves to map the prior art onto the instant claims.
The limitations of claim 1 have been taught in the rejection above by Duan and Li.
Claim 34:
Duan ranks compounds based on their CD signature, wherein out of thousands of compounds only the top 50 are returned (Figure 4) (abstract). However, neither Duan nor Li disclose ranking compounds based on an IC50 value.
Kalliokoski discusses uses of IC50 data (title). Kalliokoski recites that IC50 “is the most commonly used metric for on-target activity in lead optimization. It is used to guide lead optimization, build large-scale chemogenomics analysis, off-target activity and toxicity models based on public data” (abstract). Kalliokoski writes “proper usage of IC50 data facilitates the development of useful methods for drug discovery” (pg. 1, col. 1, para. 1).
It would have been prima facie obvious to one of ordinary skill in the art to have further filtered the ranked compounds by using an IC50 value because IC50 is the most common metric for lead optimization in drug discovery as taught by Kalliokoski (abstract). There would have been a reasonable expectation of success to further rank molecules by IC50 because it is another metric used to sort/rank molecules.
Response to Arguments under 35 USC 103
Applicant's arguments filed 10/30/2025 have been fully considered but they are not persuasive.
Applicant argues that the cited references do not disclose the specific metrics recited in amended step (c) of claims 1, 13 and 33 (pg. 14, last para. – pg. 19, last para.). Applicant’s argument is not persuasive for the following reasons:
In view of further consideration of Duan, it appears that Duan does teach metrics recited in step (c). For example, Duan teaches the metric of “cell data providing an indication of an activity of a compound in a cellular assay”. Duan recites that the CD signatures contain differential gene expression profiles of cell lines perturbed by compounds (abstract) (Figure 4, column “Signature”). This also broadly reads on the metric in step (c) of “selectivity of a compound for a target gene” because the CD signatures show differential expression of genes predicted to be targeted by the compound (Figure 4, column “Target”).
Conclusion
No claims are allowed.
Notable, but not relied upon, prior art includes: Contreras-Moreira et al. (Nucleic acids research 38, no. suppl_1 (2010): D91-D97; newly cited) who teaches a database of binding specificity for all protein-DNA complexes in Protein Data Bank. Zamanighomi et al. (Nucleic acids research 45, no. 10 (2017): 5666-5677; newly cited) who teaches associating known DNA binding motifs to transcription factors with no known binding motifs. Pujato et al. (Nucleic acids research 42, no. 22 (2014): 13500-13512; newly cited) who teaches predicting which genes are regulated by transcription factors based on 3D models of transcription factored derived from TF-DNA complexes.
Inquiries
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Noah A. Auger whose telephone number is (703)756-4518. The examiner can normally be reached M-F 7:30-4:30 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached on (571) 272-9047. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.A.A./Examiner, Art Unit 1687
/KAITLYN L MINCHELLA/Primary Examiner, Art Unit 1685