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 the Claims
Claims 1-2 and 5-11 are currently pending and under exam herein.
Claims 1-2 and 5-11 are rejected.
Drawings
The Drawings filed on 7/14/2022 were considered.
Information Disclosure Statement
The information disclosure statement (IDS) was previously submitted on 07/14/2022 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement was considered by the examiner in the past office action.
Response to Arguments 112
Applicant amendment overcomes the rejection. The rejections for claims 4 and 12 are withdrawn.
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 and 5-11 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite: (a) mathematical concepts, (e.g., mathematical relationships, formulas or equations, mathematical calculations); and (b) mental processes, i.e., concepts performed in the human mind, (e.g., observation, evaluation, judgement, opinion).
Subject matter eligibility evaluation in accordance with MPEP 2106:
Eligibility Step 1: Claims 1-2 and 5-11 are directed to a machine learning drug evaluation using liquid chromatographic testing
[Step 1: YES]
Eligibility Step 2A: First it is determined in Prong One whether a claim recites a judicial exception, and if
so, then it is determined in Prong Two whether the recited judicial exception is integrated into a
practical application of that exception.
Eligibility Step 2A Prong One: In determining whether a claim is directed to a judicial exception,
examination is performed that analyzes whether the claim recites a judicial exception, i.e., whether a
law of nature, natural phenomenon, or abstract idea is set forth or described in the claim.
Independent claim 1 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
a processor configured to: execute a machine learning model trained using the database to establish an association between the physicochemical property and liquid chromatography retention time of the reference molecules (mental process and/or mathematical process)
apply the retention time of the candidate small molecule to a machine learning model to generate a predicted lipophilicity value for the candidate small molecule, wherein the experimentally measured retention time of the candidate small molecule is provided as an input descriptor to the machine learning model for predicting lipophilicity; (mathematical concept)
selecting one or more candidate small molecules having the predicted lipophilicity value ranging from 1 to 3; and (mental process and/or mathematical process)
output the selected one or more candidate small molecules for pharmaceutical activity testing. (mental process, under the BRI one just needs to select the drugs for more testing as output can be simply writing the names down on a piece of paper as the candidates for more testing)
Dependent claim 2 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the database of small molecule physicochemical properties is a small molecule retention time (SMRT) dataset including International Chemical Identifier (InChi) codes, and extracted data are converted to Simplified Molecular Input Line Entry System (SMILES) notation to extract physico-chemical properties as a query to a ChEMBL database (mathematical concept, this just limits what the math is done on, or the database the machine learning model is trained on).
Dependent claim 5 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
where the database of includes acid dissociation constant (pKa) and polar surface area (mathematical concept, this just limits what the math is done on, or the database the machine learning model is trained on).
Dependent claim 6 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the machine learning model comprises a Random Forest Regression algorithm (mathematical concept, this just limits the type of math being done when training the machine learning model).
Dependent claim 7 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the machine learning model comprises a Gradient Boosting algorithm (mathematical concept, this just limits the type of math being done when training the machine learning model).
Dependent claim 8 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the machine learning model comprises a Support Vector Machine algorithm (mathematical concept, this just limits the type of math being done when training the machine learning model).
Dependent claim 10 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the machine learning model is further trained by one or more indicators of computed molecular descriptors for the candidate small molecule
Dependent claim 11 recites the following steps which fall within the mental processes and/or mathematical concepts groupings of abstract ideas:
wherein the indicators of computed molecular descriptors include one or more computed parameters of mass, dipole moment, atomic composition, Morgan fingerprint, Tanimoto similarity (mathematical concept, this just limits how the machine learning model is trained).
The abstract ideas recited in the claims are evaluated under the broadest reasonable interpretation (BRI) of the claim limitations when read in light of and consistent with the specification. As noted in the foregoing section, the claims are determined to contain limitations that can practically be performed in the human mind with the aid of a pencil and paper, and therefore recite judicial exceptions from the mental process grouping of abstract ideas. Additionally, the recited limitations that are identified as judicial exceptions from the mathematical concepts grouping of abstract ideas are abstract ideas irrespective of whether or not the limitations are practical to perform in the human mind.
Therefore, claims 1-2 and 5-11 recite an abstract idea as the dependent claims will inherit the abstract ideas from the independent claims.
[Step 2A Prong One: YES]
Eligibility Step 2A Prong Two: In determining whether a claim is directed to a judicial exception, further
examination is performed that analyzes if the claim recites additional elements that when examined as a
whole integrates the judicial exception(s) into a practical application (MPEP 2106.04(d)). A claim that
integrates a judicial exception into a practical application will apply, rely on, or use the judicial exception
in a manner that imposes a meaningful limit on the judicial exception. The claimed additional elements
are analyzed to determine if the abstract idea is integrated into a practical application (MPEP
2106.04(d)(I); MPEP 2106.05(a-h)). If the claim contains no additional elements beyond the abstract
idea, the claim fails to integrate the abstract idea into a practical application (MPEP 2106.04(d)(III)).
The judicial exceptions identified in Eligibility Step 2A Prong One are not integrated into a practical application because of the reasons noted below.
The additional element in independent claim 1 includes:
A machine learning system for predicting a physicochemical property of candidate small molecules for pharmaceuticals comprising
a liquid chromatography column configured to receive a candidate small molecule having an unknown lipophilicity value and measure a retention time of the candidate small molecule, generating an experimentally measured retention time of the candidate small molecule;
receive the experimentally measured retention time of the candidate small molecule
a database storing lipophilicity values and retention times of reference molecules
The additional element in dependent claim 9 includes:
wherein the machine learning model comprises a Deep Neural Network algorithm.
The additional elements of receive the experimentally measured retention time of the candidate small molecule (Claim 1), a liquid chromatography column configured to receive a candidate small molecule having an unknown lipophilicity value and measure a retention time of the candidate small molecule, generating an experimentally measured retention time of the candidate small molecule (Claim 1) are insignificant extra-solution activity that are part of the data gathering process used in the recited judicial exceptions (see MPEP 2106.05(g)).
The additional elements of a database storing lipophilicity values and retention times of reference molecules (Claim 1), A machine learning system for predicting a physicochemical property of candidate small molecules for pharmaceuticals comprising (Claim 1), wherein the machine learning model comprises a Deep Neural Network algorithm (Claim 9) fail to integrate a judicial exception into a practical application merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). Additionally, it also does not improve the function of a generic computer.
The additionally recited elements merely invoke a computer as a tool, and/or amount to insignificant extra-solution data gathering activity, and as such, when all limitations in claims 1-2 and 5-11have been considered as a whole, the claims are deemed to not recite any additional elements that would integrate a judicial exception into a practical application, and therefore claims 1-2 and 5-11are directed to an abstract idea (MPEP 2106.04(d)).
[Step 2A Prong Two: NO]
Eligibility Step 2B: Because the claims recite an abstract idea, and do not integrate that abstract idea into a practical application, the claims are probed for a specific inventive concept. The judicial exception alone cannot provide that inventive concept or practical application (MPEP 2106.05). Identifying whether the additional elements beyond the abstract idea amount to such an inventive concept requires considering the additional elements individually and in combination to determine if they amount to significantly more than the judicial exception (MPEP 2106.05A i-vi).
The claims do not include any additional elements that are sufficient to amount to significantly more than the judicial exception(s) because of the reasons noted below.
The additional elements recited in claim 1 and claim 9 are identified above, and carried over from Step 2A: Prong Two along with their conclusions for analysis at Step 2B. Any additional element or combination of elements that was considered to be insignificant extra-solution activity at Step 2A: Prong Two was re-evaluated at Step 2B, because if such re-evaluation finds that the element is unconventional or otherwise more than what is well-understood, routine, conventional activity in the field, this finding may indicate that the additional element is no longer considered to be insignificant; and all additional elements and combination of elements were evaluated to determine whether any additional elements or combination of elements are other than what is well-understood, routine, conventional activity in the field, or simply append well-understood, routine, conventional activities previously known to the industry, specified at a high level of generality, to the judicial exception, per MPEP 2106.05(d).
The additional elements of receive the experimentally measured retention time of the candidate small molecule (Claim 1), a liquid chromatography column configured to receive a candidate small molecule having an unknown lipophilicity value and measure a retention time of the candidate small molecule, generating an experimentally measured retention time of the candidate small molecule (Claim 1) are are conventional and part of the data gathering process used in the recited judicial exceptions (see MPEP 2106.05(g)). Evidence for conventionality is shown by by Munro et al. (Munro, K. et al. Artificial Neural Network Modelling of Pharmaceutical Residue Retention Times in Wastewater Extracts Using Gradient Liquid Chromatography-High Resolution Mass Spectrometry Data. Journal of Chromatography A 2015, 1396, 34–44) (abstract) which train a deep neural network to predict retention time of pharmaceutical compounds. Additional evidence for conventionality is shown by Taskinen et al. (Taskinen, J.; Yliruusi, J. Prediction of Physicochemical Properties Based on Neural Network Modelling. Advanced Drug Delivery Reviews 2003, 55 (9), 1163–1183.) which uses neural networks to predict physicochemical properties. Additional evidence for conventionality is shown by Fu et al. (Fu, Y.; Luo, J.; Qin, J.; Yang, M. Screening Techniques for the Identification of Bioactive Compounds in Natural Products. Journal of Pharmaceutical and Biomedical Analysis 2019, 168, 189–200.) (abstract) which is a review for screening methods of determining bioactivity of natural products. Additional evidence for conventionality is shown by, Bouwmeester et al. (Bouwmeester, R.; Martens, L.; Degroeve, S. Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction. Analytical Chemistry 2019, 91 (5), 3694–3703.) (abstract), a review for machine learning prediction of retention times in liquid chromatography. Examiner also asserts it is routine and conventional.
The additional elements of a database storing lipophilicity values and retention times of reference molecules (Claim 1), A machine learning system for predicting a physicochemical property of candidate small molecules for pharmaceuticals comprising (Claim 1), wherein the machine learning model comprises a Deep Neural Network algorithm (Claim 9) are conventional fail to integrate a judicial exception into a practical application merely reciting the words "apply it" (or an equivalent) with the judicial exception, or merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, as discussed in MPEP § 2106.05(f). MPEP states that for example, if the additional limitations only store and retrieve information in memory, explain that these are well-understood, routine, conventional computer functions as recognized by the court decisions listed in MPEP § 2106.05(d). It also does not improve the functioning of a generic computer.
When taken alone, all additional elements in claims 1-2 and 5-11 do not amount to significantly more than the above-identified judicial exception(s). Even when evaluated as a combination, the additional elements fail to transform the exception(s) into a patent-eligible application of that exception. Thus, claims 1-13 are deemed to not contribute an inventive concept, i.e., amount to significantly more than the judicial exception(s) (MPEP 2106.05(II)).
[Step 2B: NO]
Response to Arguments 101[AltContent: rect]
The MPEP states that performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989); is an example of activities that the courts have found to be insignificant extra-solution Mere Data Gathering.
Examiner asserts that applicants argument of “expressly recites a liquid chromatography column, a database, and a processor, all of which are supported by the originally filed Specification. In particular, the Specification repeatedly describes a laboratory-integrated workflow in which candidate small molecules are physically processed through a liquid chromatography system, experimentally analyzed, and subsequently evaluated for pharmaceutical purposes.” Is mere data gathering that is well understood, routine, and conventional. As well as all other arguments towards the data gathering step.
“(1) applying a candidate small molecule to a liquid chromatography column; (2) experimentally measuring the retention time of the candidate small molecule;” Are data gathering steps which can then be placed in a mathematical equation of “(3) providing the measured retention time to a trained machine learning model;” which examiner asserts under the broadest reasonable interpretation “machine learning model” includes simple mathematical models such as linear regression which is a mathematical concept.
Examiner asserts that “(4) selecting one or more candidate molecules based on the predicted physicochemical property generated by the model” is a mental process.
The MPEP also states “The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. See, e.g., Benson, 409 U.S. at 67, 65, 175 USPQ at 674-75, 674 (noting that the claimed "conversion of [binary-coded decimal] numerals to pure binary numerals can be done mentally," i.e., "as a person would do it by head and hand."); Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1139, 120 USPQ2d 1473, 1474 (Fed. Cir. 2016) (holding that claims to a mental process of "translating a functional description of a logic circuit into a hardware component description of the logic circuit" are directed to an abstract idea, because the claims "read on an individual performing the claimed steps mentally or with pencil and paper").”
“Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. As the Federal Circuit has explained, "[c]ourts have examined claims that required the use of a computer and still found that the underlying, patent-ineligible invention could be performed via pen and paper or in a person’s mind." Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015). See also Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘‘[W]ith the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’); Mortgage Grader, Inc. v. First Choice Loan Servs. Inc., 811 F.3d 1314, 1324, 117 USPQ2d 1693, 1699 (Fed. Cir. 2016) (holding that computer-implemented method for "anonymous loan shopping" was an abstract idea because it could be "performed by humans without a computer"). (Fed. Cir. 2017); [AltContent: rect]
Examiner asserts that “(5) performing pharmaceutical testing on the selected candidate molecules.” Is generic, well under stood routine and conventional extra solution activity. The MPEP also states that “ii. Using well-known standard laboratory techniques to detect enzyme levels in a bodily sample such as blood or plasma, Cleveland Clinic Foundation v. True Health Diagnostics, LLC, 859 F.3d 1352, 1355, 1362, 123 USPQ2d 1081, 1082-83, 1088
The MPEP also states “A step of administering a drug providing 6-thioguanine to patients with an immune-mediated gastrointestinal disorder, because limiting drug administration to this patient population did no more than simply refer to the relevant pre-existing audience of doctors who used thiopurine drugs to treat patients suffering from autoimmune disorders, Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 78, 101 USPQ2d 1961, 1968 (2012”
Applicants argument of “Additionally, the presently claimed invention is not directed merely to mathematical calculations or data analysis performed in the abstract. Rather, the claimed system is specifically integrated with a physical analytical instrument, namely the liquid chromatography column, which obtains experimentally measured retention times of candidate molecules. These experimentally measured values are then utilized by the machine learning model to predict physicochemical properties of the candidate molecules and to facilitate selection of compounds having desired characteristics.“ is mere data gathering please see above.
Examiner asserts applicant gathers data, performs mental and mathematical processes, and then does nothing significantly more as that “performing pharmaceutical testing on the selected candidate molecules.” Is just generic well under stood routine and conventional extra solution activity.
The argument of “Claim 1 is directed to a practical application in pharmaceutical discovery and candidate screening. The claimed system ultimately identifies candidate molecules having target physicochemical properties and further subjects the selected molecules to pharmaceutical activity testing. Accordingly, the claimed invention transforms experimentally obtained chromatographic measurements into actionable compound-selection prediction/selection for downstream pharmaceutical evaluation. Therefore, the claimed invention is directed to a specific technological application that integrates machine learning with physical laboratory instrumentation, experimentally measured data, and pharmaceutical testing procedures. The claims recite significantly more than a mathematical concept or abstract data analysis and instead define a practical laboratory- based screening system that produces a tangible and useful teleological, result.” Is not persuasive as applicant gathers data and then performs an abstract idea, then tests the compounds in a generic way well understood routine way. Please see MPEP passages above.
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 and 5,6, 8-11 are rejected under 35 U.S.C. 103 as being unpatentable over Domingo-Almenara et al. (Domingo-Almenara et al. The METLIN Small Molecule Dataset for Machine Learning-Based Retention Time Prediction. Nature Communications 2019, 10 (1)) in further view of Valkó (Valkó, K. L. Lipophilicity and Biomimetic Properties Measured by HPLC to Support Drug Discovery. Journal of Pharmaceutical and Biomedical Analysis 2016, 130, 35–54) in further view of Wijewardhane et al. (ChemRxiv, 2021, Graph Neural Networks Bootstrapped for Synthetic Selection and Validation of Small Molecule Immunomodulators) in further view of Datta et al. (Datta, R.; Das, D.; Das, S. Efficient Lipophilicity Prediction of Molecules Employing Deep-Learning Models. Chemometrics and Intelligent Laboratory Systems 2021, 213, 104309.). The italicized text corresponds to the instant claim limitations.
With respect to the limitations of Claims 1,2, 5, 6, 8, 9, 10, 11, Domingo-Almenara et al. teaches that machine learning (ML) has played and still plays a key role at different levels in fields as diverse as quantum mechanics, physical chemistry, biophysics or physiology. In chemoinformatics, ML has been widely adopted in the design of quantitative structure–activity relationship (QSAR) models aimed at predicting specific properties such as bioactivity, toxicity or small molecule-protein binding affinity. These models enable screening for molecules with specific properties and their development has been possible given the availability of public datasets. In that sense, datasets with a wide set of examples from which an ML model can learn are necessary to build accurate ML-based prediction models (pg. 2, Introduction paragraph 1, A machine learning system for predicting a physicochemical property of candidate small molecules for pharmaceuticals (Claim 1)). Domingo-Almenara et al. also teaches the METLIN’s SMRT dataset includes the RT in seconds, the PubChem numbers, the molfile containing the structures (SDF format), and molecular descriptors and extended connectivity fingerprints (ECFP) calculated with Dragon 7. ECFP together with their respective RT were used as input data for the deep-learning regression model. (pg. 2, Results, paragraph 1-2, apply the retention time of the candidate small molecule to a machine learning model to generate a predicted lipophtilicity value for the candidate small molecule, wherein the experimentally measured retention time of the candidate small molecule is provided as an input descriptor to the machine learning model for predicting lipophilicity (Claim 1) Examiner asserts that Domingo- Almenara was used to teach the principal of machine learning and the well known relationship between structure and retention time and that this relationship can be modeled using machine learning. A person of ordinary skill in the art would recognize how to modify this machine learning model with using retention time as an input.
Valko teaches a strong relationship on retention time and lipophilicity, as well as other properties. Any person having ordinary skill in the art would recognize that retention time is a direct result of the structure of the molecule and the interactions between the analyte and the column. This robust amount of information that any person having ordinary skill in the art would recognize as useful to include retention time in a machine learning method.
Examiner asserts that Domingo- Almenara in view of Valko does teach the following: experimentally measuring liquid chromatography retention time and using the measured retention time as an input feature for a machine-learning model (ii) predicting lipophilicity from the measured retention time. As it is extremely common in chemical machine learning to inverse machine learning algorithms and Domingo- Almenara already taught the machine learning captures the relationship between structure and retention time. A person of ordinary skill in the art would understand the use of retention time would improve a machine learning model that is meant to predict lipophilicity. A person of ordinary skill in the art when trying to predict lipophilicity from structure would naturally look at Valko and conclude it is obvious to try to include retention time. As retention time would be obvious to try “(iii) identifying retention time as the most influential predictive descriptor;” Examiner asserts that any person of ordinary skill in the art would find the importance of retention time during normal experimentation and trial and error. Additionally, Examiner asserts that the data does not show that retention time as the most influential predictive descriptor. Domingo-Almenara et al. also teaches RP chromatography with high performance liquid chromatography–mass spectrometry (HPLC–MS) was used to acquire RT data for a total of 80,038 small molecules (pg. 2, Results, paragraph 1, a liquid chromatography column configured to receive a candidate small molecule having an unknown lipophilicity value and measure a retention time of the candidate small molecule (Claim 1)) Domingo-Almenara et al. also teaches the METLIN’s SMRT dataset includes the RT in seconds, the PubChem numbers, the molfile containing the structures (SDF format), and molecular descriptors and extended connectivity fingerprints (ECFP) calculated with Dragon 7. ECFP together with their respective RT were used as input data for the deep-learning regression model. The MELTIN database also contains smiles and inchi codes of the corresponding molecules. (pg. 2, Results, paragraph 1-2, wherein the database of small molecule physicochemical properties is a small molecule retention time (SMRT) dataset including International Chemical Identifier (InChi) codes, and extracted data are converted to Simplified Molecular Input Line Entry System (SMILES) notation to extract physico-chemical properties as a query to a ChEMBL database (Claim 2)). Domingo-Almenara et al. also teaches RP chromatography with high performance liquid chromatography–mass spectrometry (HPLC–MS) was used to acquire RT data for a total of 80,038 small molecules. See MPEP 2111.05 and Lowry, 32 F.3d at 1583-84, 32 USPQ2d at 1035. When the computer-readable medium merely serves as a support for information or data, no functional relationship exists (pg. 2, Results, paragraph 1, where the database of small molecule physicochemical properties includes acid dissociation constant (pKa) and polar surface area (Claim 5)). Domingo-Almenara et al. also teaches other non-deep ML methods such as random forest regression using fingerprints. The random forest regression yielded a lower accuracy than the DLM (pg. 2, Application of deep learning for RT prediction, paragraph 2, wherein the machine learning model comprises a Random Forest Regression algorithm (Claim 6)). Domingo-Almenara et al. also teaches a deployed deep-learning regression model (DLM) (pg. 2, Application of deep learning for RT prediction, paragraph 1, wherein the machine learning model comprises a Deep Neural Network algorithm (Claim 9)) Domingo-Almenara et al. also teaches the METLIN’s SMRT dataset includes the RT in seconds, the PubChem numbers, the molfile containing the structures (SDF format), and molecular descriptors and extended connectivity fingerprints (ECFP) calculated with Dragon 7. ECFP together with their respective RT were used as input data for the deep-learning regression model. (pg. 2, Results, paragraph 1-2, wherein the machine learning model is further trained by one or more indicators of computed molecular descriptors for the candidate small molecule (Claim 10)). Domingo-Almenara et al. also teaches the METLIN’s SMRT dataset includes the RT in seconds, the PubChem numbers, the molfile containing the structures (SDF format), and molecular descriptors and extended connectivity fingerprints (ECFP) calculated with Dragon 7. ECFP together with their respective RT were used as input data for the deep-learning regression model. ECFP are equivalent to morgan fingerprints (pg. 2, Results, paragraph 1-2, wherein the indicators of computed molecular descriptors include one or more computed parameters of mass, dipole moment, atomic composition, Morgan fingerprint, Tanimoto similarity (Claim 11)).
Domingo-Almenara et al. does not explicitly teach using retention time as an input to a machine learning model (Claim 1), it also has no mention of lipophilicity (Claim 1), It also does not teach selecting molecules for biological testing (Claim 1), selecting one or more candidate small molecules having the predicted lipophilicity value ranging from 1 to 3, (Claim 1), testing the selected candidate small molecules for pharmaceutical activity (Claim 1), wherein the machine learning model comprises a Support Vector Machine algorithm (Claim 8),
Valkó teaches that the chromatographic properties measured at early stages of the drug discovery process provide an easy assessment of lipophilicity, oral absorption, volume of distribution, drug efficiency. The data is stored in a database. The authors used LC to acquire attention time, (pg. 50, conclusion paragraph 1) They also discuss published LC methods for determining lipophilicity. The values of retention time and lipophilicity are inherently stored in some database. Valkó also teaches that properties, such as lipophilicity, protein binding, phospholipid binding, and acid/base character can be incorporated in the design of molecules with the right biological distribution and pharmacokinetic profile to become an effective drug (abstract) Valkó teaches that the chromatographic properties measured at early stages of the drug discovery process provide an easy assessment of lipophilicity, oral absorption, volume of distribution, drug efficiency (pg. 50, conclusion paragraph 1) Valkó teaches that the chromatographic properties measured at early stages of the drug discovery process provide an easy assessment of lipophilicity, oral absorption, volume of distribution, drug efficiency (pg. 50, conclusion paragraph 1, liquid chromatography column configured to receive a candidate small molecule having an unknown lipophilicity value and measure a retention time of the candidate small molecule, generating an experimentally measured retention time of the candidate small molecule; a database storing lipophilicity values and retention times of reference molecules; receive the experimentally measured retention time of the candidate small molecule (Claim 1) apply the retention time of the candidate small molecule to a machine learning model to generate a predicted lipophilicity value for the candidate small molecule, wherein the experimentally measured retention time of the candidate small molecule is provided as an input descriptor to the machine learning model for predicting lipophilicity; (Claim 1, when viewed in light of other art see argument above it would be obvious to include machine learning to aid the prediction)
Wijewardhane et al. teaches a Bootstrapped EGNN model was used to select compounds for synthesis and experimental validation with predicted high and low potency to inhibit PD-1/PD-L1 interaction (abstract and output the selected one or more candidate small molecules for pharmaceutical activity testing. (Claim 1). Wijewardhane et al. also teaches compared the cross-validated EGNN model with GNN, Support Vector Machine (SVM), and Random Forest (RF) baseline models trained with Incyte training data, using their test set performances (pg. 18, paragraph 2, wherein the machine learning model comprises a Support Vector Machine algorithm (Claim 8))
Datta et al. teaches the optimum range of lipophilicity of compounds to be successful as drugs is found to have logP value between 1 and 3 (pg. 1, Introduction, paragraph 2, selecting one or more candidate small molecules having the predicted lipophilicity value ranging from 1 to 3(Claim 1)).
A person having ordinary skill in the art would be motivated to combine the machine learning database and model for retention time prediction taught by Domingo-Almenara et al. with the machine learning models that predict lipophilicity from HPLC retention times with the knowledge of selecting favorable candidates for further testing taught by Wijewardhane et al. because all the works are in the same field of endeavor and all address predicting properties of compounds for drug discovery. A person having ordinary skill in the art would also find an optimal lipophilicity value between 1 and 3 taught by Datta et al. because it limits the range of prediction and will make a better machine learning model as well as being in the same field of endeavor.Therefore a person of ordinary skill in the art would be motivated to combine the prior art. In addition, there is a reasonable expectation of success because the underlying function of each model does not change just the data being used to train the model and the type of machine learning model used.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Domingo-Almenara et al. in further view of Valkó in further view of Wijewardhane et al. in view of Datta et al. as applied to claims 1-2 and 5,6, 8-11 above in further view of Wang et al. (Wang, Y et al. In Silico Prediction of Human Intravenous Pharmacokinetic Parameters with Improved Accuracy. Journal of Chemical Information and Modeling 2019, 59 (9), 3968–3980.) The italicized text corresponds to the instant claim limitations.
The limitations of claims 1-2 and 5,6, 8-11 have been taught by Domingo-Almenara et al. in further view of Valkó in further view of Wijewardhane et al. in view of Datta et al. above.
Domingo-Almenara et al. in further view of Valkó in further view of Wijewardhane et al. in view of Datta et al. does not explicitly teach wherein the machine learning model comprises a Gradient Boosting algorithm (Claim 7). However, these limitations were known in the art at the time of the effective filing date of the invention, as taught by Wang et al. teaches gradient boosting machine is a family of powerful machine-learning techniques whose learning procedure consecutively fits new models to provide more an accurate estimate of the response variable (pg. 3970, Model Building, paragraph 1, wherein the machine learning model comprises a Gradient Boosting algorithm (Claim 7)).
A person having ordinary skill in the art would use the machine learning model to predict chemical properties with retention time taught by Domingo-Almenara et al. in further view of Valkó in further view of Wijewardhane et al. in view of Datta et al. with a gradient boosting algorithm taught by Wang et al. because it would be obvious for a person skilled in the art to try a variety of machine learning models in orderto find the best model. In addition, there is a reasonable expectation of success because gradient boosting is another type of supervised machine learning and therefore can work on the same type of data structure. In addition, Wang et al. teaches gradient boosting machine is a family of powerful machine-learning techniques whose learning procedure consecutively fits new models to provide more an accurate estimate of the response variable (pg. 3970, Model Building, paragraph 1) and therefore a person having ordinary skill in the art would be motivated to use that machine learning model.
Response to Arguments 103
Examiner asserts that Domingo- Almenara was used to teach the principal of machine learning and the well known relationship between structure and retention time and that this relationship can be modeled using machine learning. A person of ordinary skill in the art would recognize how to modify this machine learning model with using retention time as an input. Valko teaches a strong relationship on retention time and lipophilicity, as well as other properties. Any person having ordinary skill in the art would recognize that retention time is a direct result of the structure of the molecule and the interactions between the analyte and the column. This robust amount of information that any person having ordinary skill in the art would recognize as useful to include retention time in a machine learning method.
Examiner asserts that Domingo- Almenara in view of Valko does teach the following: experimentally measuring liquid chromatography retention time and using the measured retention time as an input feature for a machine-learning model (ii) predicting lipophilicity from the measured retention time. As it is extremely common in chemical machine learning to inverse machine learning algorithms and Domingo- Almenara already taught the machine learning captures the relationship between structure and retention time. A person of ordinary skill in the art would understand the use of retention time would improve a machine learning model that is meant to predict lipophilicity. A person of ordinary skill in the art when trying to predict lipophilicity from structure would naturally look at Valko and conclude it is obvious to try to include retention time. As retention time would be obvious to try “(iii) identifying retention time as the most influential predictive descriptor;” Examiner asserts that any person of ordinary skill in the art would find the importance of retention time during normal experimentation and trial and error. Additionally, Examiner asserts that the data does not show that retention time as the most influential predictive descriptor. Wijewardhane taught screening the results of a machine learning model for biological testing therefore a person of ordinary skill in the art would (iv) utilizing the resulting predictions for pharmaceutical candidate selection and screening.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Connor Beveridge whose telephone number is 571-272-2099. The examiner can normally be reached Monday - Thursday 9 am - 5 pm.
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 at 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.
/C.H.B./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687
Prosecution Insights