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 .
Status of Claims
This action is in reply to the claims filed on June 6, 2025. Claim(s) 1-20 are currently pending and have been examined.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-20: Step 1
Claims 1-11, 12, 13-17, 18-20 are drawn to methods, and of which are within the four statutory categories (i.e., a process). Claims 1-20 are further directed to an abstract idea on the grounds set out in detail below.
Claim 1: Step 2A Prong One
Claim 1 recite(s):
(a) accessing with a computer system, a list of candidate drugs for treating a medical condition;
(b) accessing with the computer system, patient health data acquired from a patient with the medical condition;
(c) accessing with the computer system, a machine learning algorithm that has been trained on training data to generate predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient, wherein the predictive scores indicate at least one of a therapeutic efficacy of the candidate drugs, a safety of the candidate drugs, or a tolerability of the candidate drugs;
(d) inputting the patient health data to the machine learning algorithm using the computer system, generating output data as predictive scores for reprioritizing the list of candidate drugs; and
(e) inputting the list of candidate drugs and the predictive scores to a drug recommendation algorithm implemented by the computer system, generating an output as an updated list of candidate drugs that is optimized for the patient based on their patient health data
These limitations, as drafted, given the broadest reasonable interpretation but for the recitation of generic computer components, encompass limitations that can practically be performed in the human mind, including for example, observations, evaluations, judgments, and opinions (“collecting information, analyzing it, and displaying certain results of the collection and analysis,” where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016)), which is a subgrouping of Mental Processes. That is, other than reciting, “a computer system”, “the computer system, a machine learning algorithm that has been trained on training data”, “a drug recommendation algorithm” to perform these functions, nothing in the claim precludes the limitations from practically being performed by a person to access a list of candidate drugs and patient health data to evaluate predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient, and determining output data as predictive scores for reprioritizing the list of candidate drugs and an output as an updated list of candidate drugs that is optimized for the patient.
Claim 1: Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform
the abstract idea and generally linking the abstract idea to a particular technological environment.
This judicial exception is not integrated into a practical application because “a computer system”, “the computer system, a machine learning algorithm that has been trained on training data”, “a drug recommendation algorithm” are recited at a high-level of generality. As set forth in the MPEP 2106.04(d) "merely including instructions to implement an abstract idea on a computer" is an example of when an abstract idea has not been integrated into a practical application.
Additionally, the claims recite “the computer system, a machine learning algorithm that has been trained on training data” at a high degree of generality, amount no more than generally linking the abstract idea to a particular technical environment. The recitation is also similar to adding the words "apply it" to the abstract idea. As set forth in MPEP 2106.05(f), merely reciting the words "apply it" or an equivalent, is an example of when an abstract idea has not been integrated into a practical application.
Claim 1: Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer configured to perform above identified functions amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible. See Alice 573 U.S. at 223 ("mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention".)
Additionally, generally linking the abstract idea to a particular technological environment does not amount to significantly more than the abstract idea (See MPEP 2106.05(h) and Affinity Labs of Texas v. DirectTV, LLC, 838 F.3d 1253, 120 USP12d 1201 (Fed. Cir. 2016)). The claim is not patent eligible.
Claims 2-11 incorporate the abstract idea identified above and recite additional limitations that expand on the abstract idea. For example, claims 2, 7-11 further describe the generic computer components. Similarly, claims 3-4 further describe the patient health data. Similarly, claim 5 further describes the medical condition. Finally, claim 6 further describes the predictive scores.
Dependent claims 2-11 recite additional subject matter which amount to limitations consisted with the additional elements in independent claim 1 (such as claim 11 further recites additional limitations that amount to generic computer components).
Looking at the limitations as an ordered combination adds nothing that is not already
present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
The claims are not patent eligible.
Claim 12: Step 2A Prong One
Claim 12 recite(s):
(a) accessing with a computer system, group medical data acquired from a plurality of patients associated with a group;
(b) accessing with the computer system, a first machine learning algorithm, wherein the first machine learning algorithm is an unsupervised learning algorithm;
(c) inputting the group medical data to the first machine learning algorithm using the computer system, generating cluster data as an output, wherein the cluster data comprise clusters of group medical data associated with a candidate drug characteristic;
(d) accessing with the computer system, new patient health data acquired from a new patient;
(e) accessing with the computer system, a second machine learning algorithm, wherein the second machine learning algorithm is a supervised learning algorithm;
(f) inputting the new patient health data and the cluster data to the second machine learning algorithm using the computer system, generating classified feature data as an output;
(g) accessing a drug recommendation model with the computer system, wherein the drug recommendation model is configured to determine a drug treatment recommendation based on patient health data;
(h) updating the drug recommendation model using the classified feature data; and
(i) inputting the new patient health data to the drug recommendation model, generating an optimized drug selection for the new patient
These limitations, as drafted, given the broadest reasonable interpretation but for the recitation of generic computer components, encompass limitations that can practically be performed in the human mind, including for example, observations, evaluations, judgments, and opinions (“collecting information, analyzing it, and displaying certain results of the collection and analysis,” where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016)), which is a subgrouping of Mental Processes. That is, other than reciting, “a computer system”, “a first machine learning algorithm”, “the first machine learning algorithm is an unsupervised learning algorithm”, “a second machine learning algorithm, wherein the second machine learning algorithm is a supervised learning algorithm”, “a drug recommendation model with the computer system” to perform these functions, nothing in the claim precludes the limitations from practically being performed by a person to access group medical data and new patient health data to determine cluster data, classified feature data, and a drug treatment recommendation, and updating the results to determine an optimized drug selection for the new patient.
Claim 12: Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform
the abstract idea.
This judicial exception is not integrated into a practical application because “a computer system”, “a first machine learning algorithm”, “the first machine learning algorithm is an unsupervised learning algorithm”, “a second machine learning algorithm, wherein the second machine learning algorithm is a supervised learning algorithm”, “a drug recommendation model with the computer system” are recited at a high-level of generality. As set forth in the MPEP 2106.04(d) "merely including instructions to implement an abstract idea on a computer" is an example of when an abstract idea has not been integrated into a practical application.
Claim 12: Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer configured to perform above identified functions amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible. See Alice 573 U.S. at 223 ("mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention".) The claim is not patent eligible.
Claim 13: Step 2A Prong One
Claim 13 recite(s):
(a) generating, with a computer system, data clusters by inputting patient health data to a first machine learning algorithm using unsupervised learning, the patient health data being acquired from a group of subjects having the medical condition;
(b) training, with the computer system, a second machine learning algorithm on a second training data set using supervised learning, the second training data set comprising data clusters generated using the first machine learning algorithm, wherein the second machine learning algorithm is trained on the second training data set to generate classified feature data indicating a presence or absence of a characteristic in the data clusters that is indicative of at least one or therapeutic efficacy or tolerability of a candidate drug for treating the medical condition; and
(c) storing the second machine learning algorithm with the computer system
These limitations, as drafted, given the broadest reasonable interpretation but for the recitation of generic computer components, encompass limitations that can practically be performed in the human mind, including for example, observations, evaluations, judgments, and opinions (“collecting information, analyzing it, and displaying certain results of the collection and analysis,” where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016)), which is a subgrouping of Mental Processes. That is, other than reciting, “a computer system”, “a first machine learning algorithm using unsupervised learning”, “the computer system, a second machine learning algorithm on a second training data set using supervised learning” to perform these functions, nothing in the claim precludes the limitations from practically being performed by a person to determine data clusters, using a computer to train a software program, and store the software program on a computer.
Claim 13: Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform
the abstract idea and generally linking the abstract idea to a particular technological environment.
This judicial exception is not integrated into a practical application because “a computer system”, “a first machine learning algorithm using unsupervised learning” are recited at a high-level of generality. As set forth in the MPEP 2106.04(d) "merely including instructions to implement an abstract idea on a computer" is an example of when an abstract idea has not been integrated into a practical application.
Additionally, the claims recite ““the computer system, a second machine learning algorithm on a second training data set using supervised learning” at a high degree of generality, amount no more than generally linking the abstract idea to a particular technical environment. The recitation is also similar to adding the words "apply it" to the abstract idea. As set forth in MPEP 2106.05(f), merely reciting the words "apply it" or an equivalent, is an example of when an abstract idea has not been integrated into a practical application.
Claim 13: Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer configured to perform above identified functions amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible. See Alice 573 U.S. at 223 ("mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention".)
Additionally, generally linking the abstract idea to a particular technological environment does not amount to significantly more than the abstract idea (See MPEP 2106.05(h) and Affinity Labs of Texas v. DirectTV, LLC, 838 F.3d 1253, 120 USP12d 1201 (Fed. Cir. 2016)). The claim is not patent eligible.
Claims 14-17 incorporate the abstract idea identified above and recite additional limitations that expand on the abstract idea. For example, claims 14-15 further describe the group of subjects. Finally, claims 16-17 further describe the generic computer components.
Dependent claims 14-17 recite additional subject matter which amount to limitations consisted with the additional elements in independent claim 13 (such as claim 16 further recites additional limitations that amount to generic computer components).
Looking at the limitations as an ordered combination adds nothing that is not already
present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
The claims are not patent eligible.
Claim 18: Step 2A Prong One
Claim 18 recite(s):
(a) determining, with a computer system, functional pathway data as functional molecular cascades impacted by each of a plurality of candidate drugs for treating a medical condition of a subject;
(b) accessing, with the computer system, genomic data for the subject;
(c) determining, with the computer system, single nucleotide polymorphisms (SNPs) in the genomic data;
(d) determining, using the computer system, treatment pathway data comprising pathways affected by variations in the SNPs associated with at least one of treatment response or non-treatment response;
(e) determining an overlap of the functional pathway data and the treatment pathway data; and
(f) selecting a candidate drug for the subject based on the determined overlap
These limitations, as drafted, given the broadest reasonable interpretation as drafted, but for the recitation of generic computer components, encompass limitations that can practically be performed in the human mind, including for example, observations, evaluations, judgments, and opinions (“collecting information, analyzing it, and displaying certain results of the collection and analysis,” where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, Electric Power Group v. Alstom, S.A., 830 F.3d 1350, 1353-54, 119 USPQ2d 1739, 1741-42 (Fed. Cir. 2016)), which is a subgrouping of Mental Processes. That is, other than reciting, “a computer system” to perform these functions, nothing in the claim precludes the limitations from practically being performed by a person to determine functional pathway data, access genomic data to determine SNPs, treatment pathway data, and identify an overlap of the functional pathway data and the treatment pathway to select a candidate drug for the subject.
Claim 18: Step 2A Prong Two
This judicial exception is not integrated into a practical application because the remaining elements amount to no more than general purpose computer components programmed to perform
the abstract idea and generally linking the abstract idea to a particular technological environment.
This judicial exception is not integrated into a practical application because “a computer system” are recited at a high-level of generality. As set forth in the MPEP 2106.04(d) "merely including instructions to implement an abstract idea on a computer" is an example of when an abstract idea has not been integrated into a practical application.
Claim 18: Step 2B
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer configured to perform above identified functions amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible. See Alice 573 U.S. at 223 ("mere recitation of a generic computer cannot transform a patent-ineligible abstract idea into a patent-eligible invention".) The claim is not patent eligible.
Claims 19-20 incorporate the abstract idea identified above and recite additional limitations that expand on the abstract idea. For example, claim 19 further describes that the functional pathway data is generated by a generic computer component. Finally, claim 20 further describes the treatment pathway data.
Dependent claims 19-20 recite additional subject matter which amount to limitations consisted with the additional elements in independent claim 18 (such as claim 19 further recites additional limitations that amount to generic computer components).
Looking at the limitations as an ordered combination adds nothing that is not already
present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application.
The claims are not patent eligible.
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 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Lefkofsky et al. (U.S. Patent Pre-Grant Publication No. 2021/0012882) in view of Cutillas (U.S. Patent Pre-Grant Publication No. 2023/0245743).
As per independent claim 1, Lefkofsky discloses a method for generating an updated list of candidate drugs for treating a medical condition of a patient, the method comprising:
(a) accessing with a computer system, a list of candidate drugs for treating a medical condition (See [0175]: Exemplary analytics using one or more analytics modules may include one or more therapy engines that can generate reports listing predicted drugs that may be used to effectively treat a patient, which the Examiner is interpreting effectively treat a patient to encompass treating a medical condition);
(b) accessing with the computer system, patient health data acquired from a patient with the medical condition (See Fig. 1 and [0121], [0155]: Patient data includes clinical records, lab results, and/or imaging data, which the Examiner is interpreting patient data to encompass patient health data);
(e) inputting the list of candidate drugs and the predictive scores to a drug recommendation algorithm implemented by the computer system, generating an output as an updated list of candidate drugs that is optimized for the patient based on their patient health data (See [0158], [0173]-[0175]: Exemplary analytics using one or more analytics modules may include one or more therapy engines that can generate reports listing predicted drugs that may be used to effectively treat a patient, predicted effective dosage amounts for one or more drugs, potential drug side effects, and/or other treatment predictions based on patient genetic data and real-world clinical data, which the Examiner is interpreting the generated reports listing predicted drugs that may be used to effectively treat a patient to encompass generating an output as an updated list of candidate drugs that is optimized for the patient based on their patient health data when combined with Cutillas’ disclosure below of “a ranking of the drugs from said plurality of drugs d.sub.n in order of their predicted efficacy in said sample taken from said patient” in [0032]-[0033] to be input into the therapy engine as inputting the predictive scores.)
While Lefkofsky teaches the method as described above, Lefkofsky may not explicitly teach (c) accessing with the computer system, a machine learning algorithm that has been trained on training data to generate predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient, wherein the predictive scores indicate at least one of a therapeutic efficacy of the candidate drugs, a safety of the candidate drugs, or a tolerability of the candidate drugs; and
(d) inputting the patient health data to the machine learning algorithm using the computer system, generating output data as predictive scores for reprioritizing the list of candidate drugs.
Cutillas teaches a method comprising:
(c) accessing with the computer system, a machine learning algorithm that has been trained on training data to generate predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient, wherein the predictive scores indicate at least one of a therapeutic efficacy of the candidate drugs, a safety of the candidate drugs, or a tolerability of the candidate drugs (See [0032]-[0033]: The one or more trained predictive models (such as machine learning models) have been trained to provide a ranking of the drugs from said plurality of drugs d.sub.n in order of their predicted efficacy in said sample taken from said patient, which the Examiner is interpreting a ranking of the drugs to encompass predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient as this ranking is after the initial obtainment of a plurality of drugs, and interpreting predicted efficacy in said sample taken from said patient to encompass a therapeutic efficacy of the candidate drugs); and
(d) inputting the patient health data to the machine learning algorithm using the computer system, generating output data as predictive scores for reprioritizing the list of candidate drugs (See [0032]-[0033]: The one or more trained predictive models (such as machine learning models) have been trained to provide a ranking of the drugs from said plurality of drugs d.sub.n in order of their predicted efficacy in said sample taken from said patient, which the Examiner is interpreting a ranking of the drugs to encompass predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed to modify the method of Lefkofsky to include (c) accessing with the computer system, a machine learning algorithm that has been trained on training data to generate predictive scores for reprioritizing candidate drugs for treating the medical condition of the patient, wherein the predictive scores indicate at least one of a therapeutic efficacy of the candidate drugs, a safety of the candidate drugs, or a tolerability of the candidate drugs; and (d) inputting the patient health data to the machine learning algorithm using the computer system, generating output data as predictive scores for reprioritizing the list of candidate drugs as taught by Cutillas. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Lefkofsky with Cutillas with the motivation of fulfils a core aim of precision medicine (See Detailed Description of the Invention of Cutillas in [0056]).
As per claim 2, Lefkofsky/Cutillas discloses the method of claim 1 as described above. Lefkofsky further teaches wherein the machine learning algorithm is trained on training data using supervised learning (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering.)
As per claim 3, Lefkofsky/Cutillas discloses the method of claim 1 as described above. Lefkofsky further teaches wherein the patient health data comprise at least one of phenotypic data or genomic data (See [0044], [0121], [0181]: Receiving patient data from a patient's medical record from an electronic health record system, and an exemplary training data set may include the clinical and molecular details of a patient such as those curated from the Electronic Health Record or genetic sequencing reports, which the Examiner is interpreting the Electronic Health Record or genetic sequencing reports to encompass at least one of phenotypic data or genomic data.)
As per claim 4, Lefkofsky/Cutillas discloses the method of claims 1 and 3 as described above. Lefkofsky further teaches wherein the patient health data comprise phenotypic data that include questionnaire response data indicating patient responses to a questionnaire (See [0121]: The term “clinical data” refers to information related to a patient or a cohort subject that is typically obtained by questioning the subject, observing the subject, or testing the subject, which the Examiner is interpreting questioning the subject to encompass questionnaire response data indicating patient responses to a questionnaire.)
As per claim 5, Lefkofsky/Cutillas discloses the method of claims 1 and 3-4 as described above. Lefkofsky further teaches wherein the medical condition is migraines or chronic headaches and the questionnaire response data comprise at least one of a headache frequency reported by the patient, a mean headache functional severity score reported by the patient, a mean headache pain intensity score reported by the patient, and a tolerability score reported by the patient (See [0121]: The term “clinical data” refers to information related to a patient or a cohort subject that is typically obtained by questioning the subject, observing the subject, or testing the subject, and exemplary clinical data include, but are not limited to physical characteristic (e.g., sex, height, weight, age, overall health, etc.), medical history, current and past diagnosis, current and past treatment regimens administered, patient compliance, treatment outcomes, imaging analysis such as x-rays, CT-scans, facial imaging, and body movement recordings, physician observations and notes regarding behavior, thought patterns, sleep cycles, physical conditions, changes, etc., which the Examiner is interpreting physical conditions to encompass the medical condition is migraines or chronic headaches as these are physical conditions), wherein the tolerability score indicates a tolerability of a presently prescribed drug for treating the medical condition (See [0121]: Exemplary clinical data include, but are not limited to physical characteristic (e.g., sex, height, weight, age, overall health, etc.), medical history, current and past diagnosis, current and past treatment regimens administered, patient compliance, treatment outcomes, which the Examiner is interpreting current and past treatment regimens to encompass a tolerability score reported by the patient, wherein the tolerability score indicates a tolerability of a presently prescribed drug for treating the medical condition as the clinical data includes treatment outcomes.)
As per claim 6, Lefkofsky/Cutillas discloses the method of claim 1 as described above. Lefkofsky may not explicitly teach wherein the predictive scores comprise at least one of positive predictive scores that increase a priority of an associated candidate drug in the list of candidate drugs and negative predictive scores that decrease a priority of an associated candidate drug in the list of candidate drugs.
Cutillas teaches a method wherein the predictive scores comprise at least one of positive predictive scores that increase a priority of an associated candidate drug in the list of candidate drugs and negative predictive scores that decrease a priority of an associated candidate drug in the list of candidate drugs (See [0039]-[0041]: Providing training data comprising a plurality of drug response distance values D.sub.n for each of a plurality of drugs d.sub.n, wherein D for each drug d is the difference between the distribution of expression of biological markers of sensitivity to drug d relative to the distribution of expression of biological markers of resistance to drug d, which the Examiner is interpreting the difference between the distribution of expression of biological markers of sensitivity to drug d relative to the distribution of expression of biological markers of resistance to drug d to encompass a positive or negative score to increase or decrease a priority of an associated candidate drug in the list of candidate drugs.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed to modify the method of Lefkofsky to include the predictive scores comprise at least one of positive predictive scores that increase a priority of an associated candidate drug in the list of candidate drugs and negative predictive scores that decrease a priority of an associated candidate drug in the list of candidate drugs as taught by Cutillas. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Lefkofsky with Cutillas with the motivation of fulfils a core aim of precision medicine (See Detailed Description of the Invention of Cutillas in [0056]).
As per claim 7, Lefkofsky/Cutillas discloses the method of claim 1 as described above. Lefkofsky further teaches wherein the machine learning algorithm is trained on a training data set comprising clusters of patient health data corresponding to a study group of patients having the medical condition, wherein the clusters of patient health data are correlated with different characteristics (See [0181]-[0182]: The therapy engines may also comprise one or more machine learning algorithms or neural networks, a machine learning algorithm (MLA) or a neural network (NN) may be trained from a training data set, for a depression disease state, an exemplary training data set may include the clinical and molecular details of a patient such as those curated from the Electronic Health Record or genetic sequencing reports, which the Examiner is interpreting the clinical and molecular details of a patient to encompass clusters of patient health data corresponding to a study group of patients having the medical condition, wherein the clusters of patient health data are correlated with different characteristics.)
As per claim 8, Lefkofsky/Cutillas discloses the method of claims 1 and 7 as described above. Lefkofsky further teaches wherein the different characteristics comprise therapeutic efficacy of candidate drugs for treating the medical condition or tolerability of candidate drugs by patients in the study group of patients (See [0180]-[0182]: The criteria can include the presence of sufficient evidence to determine that a given enzyme is the primary metabolizing enzyme for a given drug, presence of sufficient evidence to determine the effect of pharmacogenomic variation in the gene on pharmacokinetic parameters of the drug, presence of sufficient evidence to determine the effect of pharmacogenomic variation in the gene on PD parameters of the drug, presence of sufficient evidence to determine the clinical implications of pharmacogenomic variation on the drug (e.g. dosing, efficacy, tolerability, adverse drug events), presence of evidence for the involvement of multiple genes in the metabolism of the drug, whether or not a multi-gene algorithm is likely needed to best approximate the disposition and clinical outcomes of the medication, which the Examiner is interpreting pharmacogenomic variation on the drug (e.g. dosing, efficacy, tolerability, adverse drug events) to encompass therapeutic efficacy of candidate drugs for treating the medical condition or tolerability of candidate drugs by patients in the study group of patients.)
As per claim 9, Lefkofsky/Cutillas discloses the method of claims 1 and 7 as described above. Lefkofsky further teaches wherein the training data set is generated by inputting the patient health data for each patient in the study group of patients to an unsupervised learning algorithm, generating an output as the clusters of patient health data (See [0161], [0181]-[0182]: A medical provider may use these tools to analyze the data in semi-supervised and unsupervised manners to define clusters, separations or stratifications among patients based on clinical, molecular, and treatment patterns through a series of interactive learning from the data in aggregate, and unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines, which the Examiner is interpreting the unsupervised machine learning algorithm to encompass an unsupervised learning algorithm, and interpreting the clustering and aggregating to encompass generating an output as the clusters of patient health data.)
As per claim 10, Lefkofsky/Cutillas discloses the method of claim 1 as described above. Lefkofsky further teaches wherein the machine learning algorithm is a supervised learning-based machine learning algorithm (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering.)
As per claim 11, Lefkofsky/Cutillas discloses the method of claims 1 and 10 as described above. Lefkofsky further teaches wherein the supervised learning-based machine learning algorithm is a mixed models algorithm (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering; unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines, which the Examiner is interpreting the various MLAs to encompass a mixed models algorithm.)
As per independent 12, Lefkofsky discloses a method for generating a drug selection for treating a medical condition of a patient, the method comprising:
(a) accessing with a computer system, group medical data acquired from a plurality of patients associated with a group (See [0049]-[0051], [0175]: Exemplary analytics using one or more analytics modules may include one or more therapy engines that can generate reports listing predicted drugs that may be used to effectively treat a patient, which the Examiner is interpreting effectively treat a patient to encompass treating a medical condition, and cohort data to encompass group medical data);
(b) accessing with the computer system, a first machine learning algorithm, wherein the first machine learning algorithm is an unsupervised learning algorithm (See [0161], [0181]-[0182]: A medical provider may use these tools to analyze the data in semi-supervised and unsupervised manners to define clusters, separations or stratifications among patients based on clinical, molecular, and treatment patterns through a series of interactive learning from the data in aggregate, and unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines, which the Examiner is interpreting the unsupervised machine learning algorithm to encompass a first machine learning algorithm, wherein the first machine learning algorithm is an unsupervised learning algorithm);
(c) inputting the group medical data to the first machine learning algorithm using the computer system, generating cluster data as an output, wherein the cluster data comprise clusters of group medical data associated with a candidate drug characteristic (See [0049]-[0051], [0181]-[0182]: The therapy engines may also comprise one or more machine learning algorithms or neural networks, a machine learning algorithm (MLA) or a neural network (NN) may be trained from a training data set, for a depression disease state, an exemplary training data set may include the clinical and molecular details of a patient such as those curated from the Electronic Health Record or genetic sequencing reports, which the Examiner is interpreting the cohort data set to encompass the cluster data comprise clusters of group medical data associated with a candidate drug characteristic);
(d) accessing with the computer system, new patient health data acquired from a new patient (See Fig. 1 and [0121], [0155]: Patient data includes clinical records, lab results, and/or imaging data, which the Examiner is interpreting patient data to encompass new patient health data);
(e) accessing with the computer system, a second machine learning algorithm, wherein the second machine learning algorithm is a supervised learning algorithm (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering);
(g) accessing a drug recommendation model with the computer system, wherein the drug recommendation model is configured to determine a drug treatment recommendation based on patient health data (See [0158], [0173]-[0175]: Exemplary analytics using one or more analytics modules may include one or more therapy engines that can generate reports listing predicted drugs that may be used to effectively treat a patient, predicted effective dosage amounts for one or more drugs, potential drug side effects, and/or other treatment predictions based on patient genetic data and real-world clinical data, which the Examiner is interpreting the generated reports listing predicted drugs that may be used to effectively treat a patient to encompass the drug recommendation model is configured to determine a drug treatment recommendation based on patient health data);
(i) inputting the new patient health data to the drug recommendation model, generating an optimized drug selection for the new patient (See [0158], [0173]-[0175]: Exemplary analytics using one or more analytics modules may include one or more therapy engines that can generate reports listing predicted drugs that may be used to effectively treat a patient, predicted effective dosage amounts for one or more drugs, potential drug side effects, and/or other treatment predictions based on patient genetic data and real-world clinical data, which the Examiner is interpreting the generated reports listing predicted drugs that may be used to effectively treat a patient to encompass generating an optimized drug selection for the new patient.)
While Lefkofsky discloses the method as described above, Lefkofsky may not explicitly teach (f) inputting the new patient health data and the cluster data to the second machine learning algorithm using the computer system, generating classified feature data as an output;
(h) updating the drug recommendation model using the classified feature data.
Cutillas teaches a method for (f) inputting the new patient health data and the cluster data to the second machine learning algorithm using the computer system, generating classified feature data as an output (See Fig. 3 and [0143]-[0144]: The EMDR sets grouped drugs based on their mode of action when analyzed by unsupervised classification methods, thus suggesting that EMDRs, used by DRUML as input, reflect the biological mechanisms of responses to the different drugs, which the Examiner is interpreting the DRUML to encompass the second machine learning algorithm, and unsupervised classification methods to encompass classified feature data);
(h) updating the drug recommendation model using the classified feature data (See [0032]-[0033]: The one or more trained predictive models (such as machine learning models) have been trained to provide a ranking of the drugs from said plurality of drugs d.sub.n in order of their predicted efficacy in said sample taken from said patient, which the Examiner is interpreting a ranking of the drugs to encompass updating the drug recommendation model using the classified feature data when combined with Lefkofsky.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed to modify the method of Lefkofsky to include (f) inputting the new patient health data and the cluster data to the second machine learning algorithm using the computer system, generating classified feature data as an output; (h) updating the drug recommendation model using the classified feature data as taught by Cutillas. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Lefkofsky with Cutillas with the motivation of fulfils a core aim of precision medicine (See Detailed Description of the Invention of Cutillas in [0056]).
As per independent claim 13, Lefkofsky discloses a method for training a machine learning algorithm for reprioritizing a list of candidate drugs for treating a medical condition based on patient data acquired from a patient with the medical condition, the method comprising:
(a) generating, with a computer system, data clusters by inputting patient health data to a first machine learning algorithm using unsupervised learning (See [0161], [0181]-[0182]: A medical provider may use these tools to analyze the data in semi-supervised and unsupervised manners to define clusters, separations or stratifications among patients based on clinical, molecular, and treatment patterns through a series of interactive learning from the data in aggregate, and unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines, which the Examiner is interpreting the unsupervised machine learning algorithm to encompass a first machine learning algorithm, wherein the first machine learning algorithm is an unsupervised learning algorithm), the patient health data being acquired from a group of subjects having the medical condition (See [0049]-[0051], [0181]-[0182]: The therapy engines may also comprise one or more machine learning algorithms or neural networks, a machine learning algorithm (MLA) or a neural network (NN) may be trained from a training data set, for a depression disease state, an exemplary training data set may include the clinical and molecular details of a patient such as those curated from the Electronic Health Record or genetic sequencing reports, which the Examiner is interpreting the cohort data set to encompass the cluster data and the cluster data is the patient health data being acquired from a group of subjects having the medical condition);
(b) training, with the computer system, a second machine learning algorithm on a second training data set using supervised learning (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering), the second training data set comprising data clusters generated using the first machine learning algorithm (See [0181]: A machine learning algorithm (MLA) or a neural network (NN) may be trained from a training data set, an exemplary training data set may include the clinical and molecular details of a patient such as those curated from the Electronic Health Record or genetic sequencing reports, and MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering; unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering), wherein the second machine learning algorithm is trained on the second training data set to generate classified feature data indicating a presence or absence of a characteristic in the data clusters that is indicative of at least one or therapeutic efficacy or tolerability of a candidate drug for treating the medical condition; and
(c) storing the second machine learning algorithm with the computer system (See [0319]: The process can be stored in a non-transitory computer-readable medium. In some embodiments, the process can be stored as executable instructions in a non-transitory computer-readable medium (e.g., at least one memory) and executed by at least one processor coupled to the computer-readable medium. In some embodiments, the process can be implemented in the system.)
While Lefkofsky discloses a method for (b) training, with the computer system, a second machine learning algorithm on a second training data set using supervised learning, the second training data set comprising data clusters generated using the first machine learning algorithm, Lefkofsky may not explicitly teach wherein the second machine learning algorithm is trained on the second training data set to generate classified feature data indicating a presence or absence of a characteristic in the data clusters that is indicative of at least one or therapeutic efficacy or tolerability of a candidate drug for treating the medical condition.
(b) training, with the computer system, a second machine learning algorithm on a second training data set using supervised learning, the second training data set comprising data clusters generated using the first machine learning algorithm, wherein the second machine learning algorithm is trained on the second training data set to generate classified feature data indicating a presence or absence of a characteristic in the data clusters that is indicative of at least one or therapeutic efficacy or tolerability of a candidate drug for treating the medical condition (See [0032]-[0033]: The one or more trained predictive models (such as machine learning models) have been trained to provide a ranking of the drugs from said plurality of drugs d.sub.n in order of their predicted efficacy in said sample taken from said patient, which the Examiner is interpreting a ranking of the drugs to encompass indicating a presence or absence of a characteristic in the data clusters, and interpreting predicted efficacy in said sample taken from said patient to encompass a therapeutic efficacy of a candidate drugs.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed to modify the method of Lefkofsky to include the second machine learning algorithm is trained on the second training data set to generate classified feature data indicating a presence or absence of a characteristic in the data clusters that is indicative of at least one or therapeutic efficacy or tolerability of a candidate drug for treating the medical condition as taught by Cutillas. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Lefkofsky with Cutillas with the motivation of fulfils a core aim of precision medicine (See Detailed Description of the Invention of Cutillas in [0056]).
As per claim 14, Lefkofsky/Cutillas discloses the method of claim 13 as described above. Lefkofsky further teaches wherein the group of subjects comprises subjects classified as one of responders or non-responders to at least one candidate drug included in the list of candidate drugs for treating the medical condition (See [0057], [0122]: The listing of prior medications can include at least one patient response to a medication, and the invention disclosed here may be used to capture, ingest, cleanse, structure, and combine robust clinical data and detailed molecular data to determine the significance of correlations, patterns and trends to generate reports for physicians, analyze or confirm the accuracy of a diagnosis, predict the likelihood that a patient responds to a specific treatment, recommend or discourage specific treatments for a patient, support biomarker discovery, bolster clinical research efforts, monitor treatment and dosing decisions, which the Examiner is interpreting the listing of prior medications can include at least one patient response to a medication to encompass the group of subjects comprises subjects classified as one of responders or non-responders to at least one candidate drug.)
As per claim 15, Lefkofsky/Cutillas discloses the method of claim 13 as described above. Lefkofsky further teaches wherein the group of subjects comprises subjects classified as one of tolerators or non-tolerators of at least one candidate drug included in the list of candidate drugs for treating the medical condition (See [0057], [0122]: The listing of prior medications can include at least one patient response to a medication, and the invention disclosed here may be used to capture, ingest, cleanse, structure, and combine robust clinical data and detailed molecular data to determine the significance of correlations, patterns and trends to generate reports for physicians, analyze or confirm the accuracy of a diagnosis, predict the likelihood that a patient responds to a specific treatment, recommend or discourage specific treatments for a patient, support biomarker discovery, bolster clinical research efforts, monitor treatment and dosing decisions, which the Examiner is interpreting the listing of prior medications can include at least one patient response to a medication to encompass the group of subjects comprises subjects classified as one of tolerators or non-tolerators of at least one candidate drug.)
As per claim 16, Lefkofsky/Cutillas discloses the method of claim 13 as described above. Lefkofsky further teaches wherein the first machine learning algorithm is a k- means clustering algorithm (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering; unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines.)
As per claim 17, Lefkofsky/Cutillas discloses the method of claim 13 as described above. Lefkofsky further teaches wherein the second machine learning algorithm is a mixed models algorithm (See [0181]: MLAs include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees, classification and regression trees, Naïve Bayes, nearest neighbor clustering; unsupervised algorithms (such as algorithms where no features/classification in the data set are annotated) using Apriori, means clustering, principal component analysis, random forest, adaptive boosting; and semi-supervised algorithms (such as algorithms where certain features/classifications in the data set are annotated) using generative approach (such as a mixture of Gaussian distributions, mixture of multinomial distributions, hidden Markov models), low density separation, graph-based approaches (such as mincut, harmonic function, manifold regularization), heuristic approaches, or support vector machines.)
As per independent claim 18, Lefkofsky discloses a method for identifying a candidate drug for treating a medical condition of a subject, the method comprising:
(a) determining, with a computer system, functional pathway data as functional molecular cascades impacted by each of a plurality of candidate drugs for treating a medical condition of a subject (See [0049], [0324]: The knowledge database can include data related to interactions between a specific drug or drugs and one or more nucleic acid sequences associated with drug metabolism, primary drug metabolic pathway data, a cohort data set previously derived from a cohort of psychiatric subjects, the cohort data set including drug or drugs used in a treatment, diagnosis before the treatment and/or treatment outcome for patients in the cohort, which the Examiner is interpreting data related to interactions between a specific drug or drugs and one or more nucleic acid sequences associated with drug metabolism, primary drug metabolic pathway data to encompass functional pathway data as functional molecular cascades impacted by each of a plurality of candidate drugs);
(b) accessing, with the computer system, genomic data for the subject (See [0127]-[0128], [0206]: The knowledge database (KDB) may include treatment implications, diagnostic implications, and prognostic implications, and the KDB may include structured data regarding drug-gene interactions, including pharmacogenetic interactions, and precision medicine findings reported in the psychiatric and basic science literature, the KDB may include clinically annotated pharmacogenomic classifications for key pharmacodynamic and pharmacokinetic results related to the treatment of depression and other psychiatric diseases, which the Examiner is interpreting the KDB to include genomic data);
(c) determining, with the computer system, single nucleotide polymorphisms (SNPs) in the genomic data (See [0027]-[0030], [0235]-[0236]: Specific genetic variants at a certain genomic location associated with a gene (such as SNPs at an identified locus) that are detected by these genetic testing panels, sequence analysis, microarray, or another method may be identified according to reference SNP cluster(rs) ID and/or genomic position of the genetic variant);
(d) determining, using the computer system, treatment pathway data comprising pathways affected by variations in the SNPs associated with at least one of treatment response or non-treatment response (See [0161], [0324]: The knowledge database can include data related to interactions between a specific drug or drugs and one or more nucleic acid sequences associated with drug metabolism, primary drug metabolic pathway data, a cohort data set previously derived from a cohort of psychiatric subjects, the cohort data set including drug or drugs used in a treatment, diagnosis before the treatment and/or treatment outcome for patients in the cohort, which the Examiner is interpreting primary drug metabolic pathway data to encompass pathway data comprising pathways affected by variations in the SNPs associated with at least one of treatment response or non-treatment response as the diagnosis before the treatment and/or treatment outcome for patients in the cohort); and
(e) determining an overlap of the functional pathway data and the treatment pathway data (See [0030], [0122], [0159], [0324]: A diagnosis indication may be based on any portion of individual patient data or aggregated data from multiple patients, including clinical data, behavioral data, and molecular data. In one example, individual patient data is normalized, de-identified, and stored collectively in database to facilitate easy query access to the dataset in aggregate to enable a medical provider to use system to compare patients' data, stratify patients, predict therapeutic outcomes, and generate new hypotheses, which the Examiner is interpreting comparing the molecular and clinical data of a patient to an aggregated data set of molecular and/or clinical data from multiple patients to encompass an overlap of the functional pathway data and the treatment pathway data.)
While Lefkofsky discloses the method as described above, Lefkofsky may not explicitly teach (f) selecting a candidate drug for the subject based on the determined overlap.
Cutillas teaches a method for (f) selecting a candidate drug for the subject based on the determined overlap (See [0037]: The method of the first aspect of the present invention may include an additional step f. of identifying a drug with which to treat a patient by selecting one of the highest-ranking drugs according to the ranking of the drugs from said plurality of drugs do in order of their predicted efficacy, which the Examiner is interpreting selecting one of the highest-ranking drugs to encompass selecting a candidate drug for the subject based on the determined overlap when combined with Lefkofsky.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed to modify the method of Lefkofsky to include (f) selecting a candidate drug for the subject based on the determined overlap as taught by Cutillas. One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to modify Lefkofsky with Cutillas with the motivation of fulfils a core aim of precision medicine (See Detailed Description of the Invention of Cutillas in [0056]).
As per claim 19, Lefkofsky/Cutillas discloses the method of claim 18 as described above. Lefkofsky further teaches wherein the functional pathway data are generated by an artificial intelligence-driven search for functional molecular cascaded impacted by each of the plurality of candidate drugs binding or non-receptor effects on direct and downstream effects (See [0132], [0180]-[0181], [0325]: The therapy engine can identify relevant drug-gene interactions based on the molecular data and the clinical data, and the process can identify relevant drug-gene interactions based on at least a portion of the nucleic acid sequences included in the molecular data, which the Examiner is interpreting drug-gene interactions to encompass functional molecular cascaded impacted by each of the plurality of candidate drugs binding or non-receptor effects on direct and downstream effects, and the therapy engines comprise one or more machine learning algorithms or neural networks.)
As per claim 20, Lefkofsky/Cutillas discloses the method of claim 18 as described above. Lefkofsky further teaches wherein the treatment pathway data are generated based on determining from the genomic data, using the computer system, SNPs reaching a threshold associated with at least one of a positive outcome or a negative outcome with a treatment response for each of the plurality of candidate drugs (See [0027], [0195]: A subset of patients may respond well to therapies of a drug under a certain dosage threshold and respond negatively to dosage that exceed a certain dosage threshold, which the Examiner is interpreting the certain dosage threshold to encompass a threshold associated with at least one of a positive outcome or a negative outcome with a treatment response for each of the plurality of candidate drugs, and SNPs are one of the most common types of genetic variation.)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sharma et al. (U.S. Patent Pre-Grant Publication No. 2023/0106284), describes system for generating drug compositions for a disease target, the system comprises a database arrangement and a processor, wherein the processor is configured to receive information comprising one or more drugs associated with the disease target, identify a plurality of parameters associated with the disease target, using the database arrangement, construct a matrix to identify at least one of direct and indirect synergies of each of the drug with the plurality of parameters and assign weights thereby to each of the parameters with respect to each of the drug, based on the identified at least one of direct and indirect synergies, calculate a total score of each of the drug and rank the plurality of drugs based on the calculated total score and sort thereby the plurality of drugs.
Morselli Gysi et al. (U.S. Patent Pre-Grant Publication No. 2022/0165352), describes a multi-modal system includes a protein-protein interaction network (PPI), a graph neural network (GNN), a diffusion module, a proximity module, and an aggregation module.
Lunghi et al. (“Strategies and Tools for Supporting the Appropriateness of Drug Use in Older People”), describes three main steps are considered in implementing measures to improve appropriateness: prescription, acceptance by the patient, and continuous monitoring of adherence and risk-benefit profile.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Bennett S Erickson whose telephone number is (571)270-3690. The examiner can normally be reached Monday - Friday: 9:00am - 5:00pm.
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, Robert Morgan can be reached at (571) 272-6773. 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.
/Bennett Stephen Erickson/Primary Examiner, Art Unit 3683
Prosecution Insights