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 1-6 and 8-13 are pending.
Claims 1-6 and 8-13 have been examined.
Claims 1-6 and 8-13 are rejected.
Priority
The present application does not claim priority from any earlier application. As result, the application is afforded the effective filing date of 01 December 2021.
Claim Rejections - 35 USC § 101
Applicant’s arguments, see remarks, filed 18 August 2025, with respect to the rejection of claims 1-6 and 8-13 have been fully considered in view of the amendments to the claims and are persuasive. The rejection of claims 1-6 and 8-13 as being directed to non-statutory subject matter has been withdrawn.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(d):
(d) REFERENCE IN DEPENDENT FORMS.—Subject to subsection (e), a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
The following is a quotation of pre-AIA 35 U.S.C. 112, fourth paragraph:
Subject to the following paragraph [i.e., the fifth paragraph of pre-AIA 35 U.S.C. 112], a claim in dependent form shall contain a reference to a claim previously set forth and then specify a further limitation of the subject matter claimed. A claim in dependent form shall be construed to incorporate by reference all the limitations of the claim to which it refers.
This is a new rejection necessitated by applicant’s amendment.
Claims 3-6 and 10-13 are rejected under 35 U.S.C. 112(d) or pre-AIA 35 U.S.C. 112, 4th paragraph, as being of improper dependent form for failing to further limit the subject matter of the claim upon which it depends, or for failing to include all the limitations of the claim upon which it depends. Claims 3-6 and 10-13 depend from claims 1 and 8, respectively. Claims 1 and 8 are limited to the subject matter also claimed in claims 3-6 and 10-13.
Claim 1 and claim 8 both, as currently amended, require that literature mining is used to fetch targets of an existing drug that is similar to the input drug, these limitations are also similarly found in claim 3 and claim 10. Thus, claims 3 and 10 fail to further limit the subject matter of claims 1 and 8.
Claim 1 and claim 8 both, as currently amended, require that a chemical similarity algorithm is applied to identify an existing drug that is similar to the input drug, these limitations are also similarly found in claim 4 and claim 11. Thus, claims 4 and 11 fail to further limit the subject matter of claims 1 and 8.
Claim 1 and claim 8 both, as currently amended, require that a machine learning algorithm is applied to predict targets of the input drug from a list of targets that bind the similar existing drug, these limitations are also similarly found in claim 5 and claim 12. Moreover claims 1 and 8 requires both machine learning and docking to predict targets, however because both claim 5 and 12 only require machine learning this makes clm. 5 and clm. 12 broader than the claims from which they depend. Thus, claims 5 and 12 fail to further limit the subject matter of claims 1 and 8.
Claim 1 and claim 8 both, as currently amended, require that a molecular docking algorithm is applied to predict targets of the input drug from a list of targets that bind the similar existing drug, these limitations are also similarly found in claim 6 and claim 13. Moreover claims 1 and 8 requires both machine learning and docking to predict targets, however because both claim 6 and 13 only require molecular docking this makes clm. 6 and clm. 13 broader than the claims from which they depend. Thus, claims 6 and 13 fail to further limit the subject matter of claims 1 and 8
Applicant may cancel the claim(s), amend the claim(s) to place the claim(s) in proper dependent form, rewrite the claim(s) in independent form, or present a sufficient showing that the dependent claim(s) complies with the statutory requirements.
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.
The following rejection is reiterated and modified as has been necessitated by amendment.
Claim(s) 1,3-6, 8 and 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over Xie (WO 2015013367) in view of Luo et al (NATURE COMMUNICATIONS, 8: 573, 2017), Agarwal et al (BRIEFINGS IN BIOINFORMATICS. VOL 9. NO 6. 479-492, 2008), Iwata et al (Mol. Inf. 2020, 39, 1900096) and Lin et al (Journal of Biomedical Semantics (2017) 8:50).
Claims 1,3-6, 8 and 10-13 are directed to computational methods and systems for a drug discovery algorithm in which a drug name is received, targets that bind compounds similar in structure to the putative drug are identified by using a chemical similarity search to identify structural similar known drugs, predicting targets through machine learning and molecular docking, and data mining the literature for the predicted targets, identify phenotypes for the putative drug shared by 2 or more identified targets, generate a network with the putative drug, the targets and phenotypes, group similar phenotypes by disease or pathway, determine expression of the phenotypes from protein and tissue expression data and identify the tissue and disease impacted by the putative drug.
Xie describes methods and systems to apply a systems pharmacology approach for drug discovery. Xie provides a systems pharmacology paradigm for drug discovery. Systems pharmacology focuses on searching for multi-target drugs to perturb diseased-associated networks rather than designing a selective ligand to target an individual receptor [0014]. With respect to the limitations of claims 1 and 8 in which an input drug is received Xie shows given a query drug, the query drug is linked to the drug similarity network by the chemical similarity [0018]. Xie shows output of the algorithm is the list of all proteins in the network (or a subset thereof), ranked by the probability py for the query chemical to reach the protein [0018], reading on fetching targets of similar drugs. Xie shows functional similarity (phenotypes) is evaluated by semantic similarity of Gene Ontology (GO) terms [0023], reading on determine phenotypes based on association from an ontological database. With respect to the limitation of generating a network comprising the drug, target and phenotype, Xie shows a drug-target coherent ranking is assessed for each pair of drug-drug and protein-protein similarity networks [0024].
Xie does not show a step in which chemical similarity is combined with machine learning, molecular docking and literature data mining to identify targets.
Luo et al, like Xie, is directed to a drug discovery workflow. Luo et al show a computational pipeline. Luo et al shows that an input compound is received(p. 3, 2nd col.). Luo et al show the input compound is compared to other compounds to identify structural similarities between the compounds, as a comparison of drug features (fig 1.) In figure 1, shows the machine learning is applied to the drug features, and target/protein features to result in a prediction scores. Luo et al shows the features used to produce the prediction scores include phenotypic data, such as drug disease interactions (p.10, 2nd column). Luo et al shows the predictions can also be supported by the previously known experimental or clinical evidence in the literature, suggesting literature mining (p. 7, 2nd col). With respect to the limitation of generating a network comprising the compound, targets and phenotypes, Luo et al shows a novel network integration pipeline for DTI prediction (p.3, 1st col.). Luo et al shows the relational properties (e.g., similarity), association information and topological context of each drug (or protein) node in the heterogeneous network (p.3, 2nd col). Luo et al show the molecular docking of compounds to COX1 and COX2 targets each was predicted to have an inhibition phenotype on COX1/2 (p.9, 1st col). Luo et al shows the
Agarwal et al is directed to literature mining to identify targets of drugs from the literature (p. 480, col 2).Agrarwal shows the basic tools of text search and retrieval have been available for decades and are familiar to researchers in a variety of domain-specific implementations(p480, col 2).Agarwal states narrowly focusing on a pharmaceutical target in isolation can lead to problems, and that it is necessary to consider the action of drugs and their targets in an overall pathway and systems context, beginning with the direct interactors of the target but extending to all manner of relations, direct and indirect (p 480, col 1)
Similar to Xie and Luo et al, Iwata et al also describes a target-based approach to drug discovery. Reading on the limitation selecting phenotypes associated with at least 2 targets, Iwata et al shows the combination of the target-based approach, as in Xie, and phenotypic approach, such as in Luo et al, to select targets related to a phenotype (fig. 3 ). Iwata et al show associations can be accessed from ontological databases(p 10/11).
Lin et al is directed to an ontological framework to integrate, navigate, and analyze drug discovery data based on formalized and standardized classifications and annotations of druggable protein targets, the Drug Target Ontology (DTO)(abstract). With respect to the limitation of determining a phenotype grouping by disease or process, Lin et al shows we categorized important disease targets by inference based on the protein - disease association, which were modeled as ‘strong’, ‘at least some’, or ‘at least weak’ evidence (p. 8, col 2). Lin et al further show DTO classifies (groups) the four major drug target protein families, GPCRs, kinases, ion channels and nuclear receptors, based on phylogenecity, function, target development level, disease association, tissue expression, chemical ligand and substrate characteristics, and target-family specific characteristics (abstract). Lin et al shows a target is also associated with some organ, tissue, or cell line using some evidence from TISSUES database, reading the limitation of expression in tissues based of protein and expression data accessed from a data base (p.7 col 1).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify, and one would have been motivated to do so with a reasonable expectation of success, the system of Xie for screening drugs with the ontological framework of Lin et al because Lin et al show their framework will further facilitate the challenging integration and formal linking to biological assays, phenotypes, disease models, drug poly-pharmacology, binding kinetics and many other processes, functions and qualities that are at the core of drug discovery (p. 14, col 2). It would have been further obvious to one of ordinary skill in the art at the time of invention to modify, and one would have been motivated to do so with a reasonable expectation of success, the system of Xie for screening drugs with Luo et al because Luo et al show their approach can achieve better and more robust prediction performance (e.g., with less false-positive predictions) by considering diverse information from various types of network features. Luo et al continue showing DTINet is a scalable framework in that more additional networks can be easily incorporated into the current prediction pipeline. Other biological entities of different types, such as gene expression, pathways, symptoms and Gene Ontology (GO) annotations, can also be integrated into the heterogeneous network for DTI prediction (p. 10). It would have been further obvious to one of ordinary skill in the art at the time of invention to modify, and one would have been motivated to do so with a reasonable expectation of success, the system of Xie for screening drugs with Iwata et al because Iwata et al shows that their probabilistic framework enables the ability to computationally execute target deconvolution considering polypharmacology, which cannot be solved by conventional experimental approaches (p. 10/11, col 1).
Response to Arguments
Applicant's arguments filed 18 August 2025 have been fully considered but they are not persuasive. Applicant argues the Xie in view of Lin fails to teach the claim amended limitation of a single fetching step that requires three modalities. Applicant’s argument is not persuasive because Luo et al shows the three modalities as described above. Applicant argues Xie in view of Lin fails to teach the selection of phenotypes with 2 or more targets. Applicant's argument is not persuasive. Xie et al shows the shared phenotypes between 2 or more targets in the teaching at [0023] in which Xie shows the functional similarity between two proteins may be determined by comparing their corresponding DAG. Function is a phenotype in view of applicant’s broad characterization of the term “phenotype” at [0063], for example. The rejection has also been further clarified with respect to the limitation of “2 or more targets” by the inclusion of Iwata et al. Applicant argues the rejection fails to show the group of similar phenotypes. The argument is not persuasive. Lin et al further show DTO classifies (groups) the four major drug target protein families, GPCRs, kinases, ion channels and nuclear receptors, based on phylogenecity, function, target development level, disease association, tissue expression, chemical ligand and substrate characteristics, and target-family specific characteristics (abstract). Further, based on the guidance provided in the specification with respect to applicant’s characterization of a phenotype (specification at [0063] ) the groupings in fig 4 supports the teaching of the limitation. Applicant's argument that Xie in view of Lin fails to show phenotypic level tissue expression is not persuasive. Lin incorporates phenotypic tissue and disease expression by extracting data from the DISEASES and TISSUE databases.
Claims 2 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over claims 1,3-6, 8 and 10-13 are rejected under 35 U.S.C. 103 as being unpatentable over Xie in view of Luo et al, Agarwal et al, Iwata et al and Lin et al above, and further in view of Jeong et al (Nature Scientific Reports,(2019) 9:12513, doi.org/10.1038/s41598-019-48989-2).
Claims 2 and 9 are directed to the weightage of individual phenotypes , cumulative weightage of the phenotypes in a group and the visualization of the ratio of weightages.
Xie in view of Luo et al, Agarwal et al, Iwata et al and Lin et al as applied to claims 1,3-6, 8 and 10-13 above show computational methods and systems for predicting the impact a putative drug will have on a phenotype.
Xie in view of Luo et al, Agarwal et al, Iwata et al and Lin et al as applied to claims 11,3-6, 8 and 10-13 do not show the cumulative weightage of phenotypes.
Jeong et al is directed to the analysis of the anticancer effect of the druggable targetome to understand the varied phenotypic outcomes of diverse functional classes of target genes (abstract). With respect to claim 2 and 9, Jeong et al shows in figure 3 a visualization of the functional (phenotypic) similarity between every pair of genes based on the Gene Ontology annotations of genes, called the Tanimoto score (p. 8). Jeong et al shows the Tanimoto score between two genes is simply the ratio of an interaction over a union between two sets (p. 8).
It would have been obvious to one of ordinary skill in the art at the time of invention to modify and one would have been motivated to do so with a reasonable expectation of success, the systems and methods of Xie in view of Luo et al, Agarwal et al, Iwata et al and Lin et al as applied to claims 1,3-6, 8 and 10-13 for screening drugs with the visualization and analysis of phenotypic similarities of Jeong et al because Jeong shows physiological relevance has critical importance in developing in vitro assays for screening anticancer targets (p. 5). Jeong further shows that multiplexing the cell count and viability measures provides a useful strategy for better evaluation of anticancer efficacy in target screening (p. 5).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KARLHEINZ R SKOWRONEK whose telephone number is (571)272-9047. The examiner can normally be reached Mon-Fri 8:00-16:30.
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, Daniel Sullivan can be reached at (571)272-0779. 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.
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687
KARLHEINZ R. SKOWRONEK
Supervisory Patent Examiner
Art Unit 1631