DETAILED ACTION
Applicant's response, filed 8/19/2025, has been fully considered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 8/19/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Status
Claims 31-38 and 40-50 are pending.
Claim 39 is cancelled.
Claims 31-38 and 40-50 are rejected.
Specification
Response to Amendment
In response to applicant’s amendments to the specification, previous objections to the specification are withdrawn.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 43 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Specifically, determination of the predicted state satisfying a predefined condition and then determining whether or not to administer the product based on said state.
Claim Rejections - 35 USC § 101
Response to Amendment
In response to applicant’s amendments to the claims, previous rejections under 35 U.S.C. 101 are withdrawn.
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 31-38, and 40-50 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more. The claims recite a CRM and system for scoring the stability of chemical compounds produced in batch in order to determine a predicted preservation state at a particular time point for the chemical product. The judicial exception is not integrated into a practical application because while claims 49 and 50 attempt to integrate the exception into a practical application, said application is either generically recited computer elements that do not add a meaningful limitation to the abstract idea or it is insignificant extra solution activity and simply implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the computer elements only store and retrieve information in memory as well as perform basic calculations that are known to be well-understood, routine and conventional computer functions as recognized by the decisions listed in MPEP § 2105.05(d).
Framework with which to Analyze Subject Matter Eligibility:
Step 1: Are the claims directed to a category of statutory subject matter (a process, machine, manufacture, or composition of matter)? [See MPEP § 2106.03]
Claims are directed to statutory subject matter, specifically a CRM (claim 49) and a system (claim 50).
Step 2A Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? [See MPEP § 2106.04(a)]
The claims herein recite abstract ideas, mental processes and mathematical concepts.
With respect to the Step 2A Prong One evaluation, the instant claims are found herein to recite abstract ideas that fall into the grouping of mental processes and mathematical concepts.
Claims 31, 49, and 50: Selecting a chemical stability model, processing the model input, determining quality scores, selecting the stability model in part on the quality scores, and determining a preservation state, are processes of identifying, calculating comparing/contrasting, and evaluating that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 32: The chemical product being a drug is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 33: The chemical product being a vaccine is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 34: The attribute of the chemical product comprising a concentration is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 35: The set of experimental stability data comprising a collection of experimental measurements is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 36: The measurements specifying temperature, time, and an attribute value at a specified temperature and time is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 37: Optimizing values of model parameters to minimize error between experimental and predicted attribute values is a verbal articulation of a mathematical process, and therefore an abstract idea, specifically a mathematical concept.
Claim 38: Generating a quality score for the chemical stability model is a process of calculating and comparing/contrasting that can be performed via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 40: Generating a quality score for the chemical stability model based on a confidence interval is a verbal articulation of a mathematical process, and therefore an abstract idea, specifically a mathematical concept.
Claim 41: Determining a predicted value, and determining the predicted preservation state are processes of calculating and comparing/contrasting that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 42: Determining a predicted value of the attribute at a final time point, and determining the predicted value of the attribute at the current time point are processes of calculating and comparing/contrasting that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 43: Determining whether to administer the chemical product based on the predicted preservation state is a process of calculating and comparing/contrasting that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Claim 44: Determining modified experimental stability data based on the temperature profile is a process of calculating and comparing/contrasting that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process. Training the chemical stability model to derive values of model parameters is a verbal articulation of a mathematical process, and therefore an abstract idea, specifically a mathematical concept.
Claim 45: The model input defining an input residual moisture and a predicted value of the attribute of the chemical product is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 46: The model input defining an input radiation state and a predicted value of the attribute of the chemical product is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 47: The model input defining an input lighting state and a predicted value of the attribute of the chemical product is merely further limiting the information itself, which is an abstract idea, specifically a mental process.
Claim 48: Identifying a chemical stability model having the highest value of a quality score is a process of calculating and comparing/contrasting that can be done via pen and paper or within the human mind and is therefore an abstract idea, specifically a mental process.
Step 2A Prong Two: If the claims recite a judicial exception under prong one, then is the judicial exception integrated into a practical application? [See MPEP § 2106.04(d) and MPEP § 2106.05(a)-(c) & (e)-(h)]
Because the claims do recite judicial exceptions, direction under Step 2A Prong Two provides that the claims must be examined further to determine whether they integrate the abstract ideas into a practical application.
The following claims recite the following additional elements in the form of non-abstract elements:
Claims 31, 49, and 50: Receiving a model input, and training the chemical stability model are insignificant extra solution activities, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)]. A non-transitory computer storage media, instructions, computers, system, and storage devices are all generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Generating an output that causes administering the instance of the chemical product is merely intended use as no structure is recited within either claim that is capable of providing such administration (See In re Otto, 312 F.2d 937, 938, 136 USPQ 458, 459 (CCPA 1963)) [See MPEP § 2111.02].
Claim 42: Receiving a temperature profile is an insignificant extra solution activity, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? [See MPEP 2106.05]
Because the additional claim elements do not integrate the abstract ideas into a practical application, the claims are further examined under Step 2B, which evaluates whether the additional elements, individually and in combination, amount to significantly more than the judicial exception itself by providing an inventive concept.
The claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are generic, conventional or nonspecific. These additional elements include:
The additional elements of receiving a model input (Conventional: Li et al., and Liu et al., each receive data from by downloading the COMDECOM dataset), receiving a temperature profile (Conventional: Specification – page 12, line 23 Conventional method for aggregating data and page 12, line 18 Conventional computer storage for said data) and training the chemical stability model (Conventional: Conventional: Li et al., and Liu et al., each train their respective models (Methods Sections)) are insignificant extra solution activities, specifically necessary data gathering (See Mayo, 566 U.S. at 79, 101 USPQ2d at 1968; OIP Techs., Inc. v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1092-93 (Fed. Cir. 2015) (presenting offers and gathering statistics amounted to mere data gathering), 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) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of a non-transitory computer storage media, instructions, computers, system, and storage devices are all generic and nonspecific elements of a computer that are well-understood, routine and conventional within the art and therefore do not improve the functioning of any computer or technology described therein (Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values), and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)) [See MPEP § 2106.05(d)(II)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 49-50, when the limitations are considered individually and as a whole, are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Response to Arguments
Applicant’s arguments, see page 3, paragraph 3 of Remarks, filed 8/19/2025, with respect to claims 31-48 have been fully considered and are not persuasive. Applicant asserts similarity to Example 39 in so far as the limitations are not practically performable in the human mind. However, Example 39 is directed to facial detection and computer vision, specifically the manipulation/interpretation of data for which the human mind cannot process. The instant application recites data such as temperature, pressure, time, and light exposure, all of which along with structure and machine learning algorithms are performable within the human mind.
Additionally, applicant asserts an improvement to technology through the improvement to “accurate and reliable determination of a product’s preservation state”. However, applicant’s assertion is to an improvement to the judicial exception, the “determining of a preservation state”, not the additional elements of the system, CRM, or process and MPEP 2106.05(a) states It is important to note, the judicial exception alone cannot provide the improvement.
Finally, the administration step is a contingent limitation, MPEP 2111.04(II) The broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. Therefore, the claim is not directed to a practical application.
Claim Rejections - 35 USC § 103
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 103 are withdrawn and new ground of rejections are set forth below.
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 31-38, 40-43, and 48-50 are rejected under 35 U.S.C. 103 as being unpatentable over Liu et al. (Journal of Computationally Aided Molecular Design (2014) 941-950; previously cited) in view of Li et al. (Journal of Chemical Information and Modeling (2019) 1044-1049; previously cited), and Waterman et al. (International Journal of Pharmaceutics (2005) 101-25; newly cited).
Claim 31 is directed to a method of predicting chemical stability using model input of chemical stability attributes, training a model and selecting a model to produce quality scores which can then be used to determine chemical stability.
Claim 49 is directed to a computer implemented method of predicting chemical stability using model input of chemical stability attributes, training a model and selecting a model to produce quality scores which can then be used to determine chemical stability.
Claim 50 is directed to a computer implemented method of predicting chemical stability using model input of chemical stability attributes, training a model and selecting a model to produce quality scores which can then be used to determine chemical stability.
Liu et al. teaches on page 942, column 1, paragraph 2 “The COMDECOM data contain 12,810 structurally diverse compounds and their stability data” and on page 942, column 1, paragraph 1 “based upon the COMDECOM data measured from DMSO/H2O solutions stored at 50 C for 105 days”, reading on receive a model input defining an input temperature and an input duration of time. Li et al. teaches on page 1045, column 1, paragraph 5 “COMDECOM data consists of chemical structures and compound purity data measured at days 0, 14, 35, and 105”, Figure 7 on page 946 provides a “flow chart for the rule-embedded naive Bayesian classifier”, and on page 941, column 2, paragraph 1 “Stability is affected by a number of factors: chemical features, solvent types, temperature, humidity, freeze–thaw resistance, storage time, etc.”, the last of which would render obvious the use of such information in the prediction of stability, reading on processing the model input in accordance with the set of model parameters of the chemical stability model to generate a model output that comprises a predicted value of an attribute of the chemical product resulting from storing the chemical product at temperatures within a tolerance of the input temperature for the input duration of time. Liu et al. teaches on page 946, column 1, paragraph 2 “To further validate the performance of the classifier, additional tests were executed by dividing the COMDECOM dataset (containing 9,746 compounds) into two groups: the training set (about 2/3 of the compounds), and the testing set (about 1/3 of the compounds)”, reading on training the chemical stability model on a set of experimental stability data for the chemical product, using a numerical optimization technique, to determine trained values of the set of model parameters of the chemical stability model. Liu et al. teaches on page 946, column 2, paragraph 2 “In this work, the bayesian score ranges from 0 to 1 and 0.5 is the cutoff value to distinguish the unstable or stable compounds”, reading on determining one or more quality scores for the chemical stability model based on the trained values of the set of model parameters of the chemical stability model and determining a predicted preservation state of an instance of the chemical product using the chemical stability model selected for the chemical product. Liu et al. further teaches on page 942, column 1, paragraph 1 “The prediction will be run in the backend and the unstability score will be provided and the predicted potential reactive site will be highlighted”, reading on generating a quality score for the chemical stability model.
Liu et al. does not teach multiple models or the selection of a single model from a group of models.
Li et al. teaches in the abstract “In this paper, we report DeepChemStable, a model employing an attention-based graph convolution network based on the COMDECOM data”, on page 1044, column 1, paragraph 2 “COMDECOM data contain structurally diverse compounds whose stabilities were measured experimentally in a mixture of DMSO and H2O”, and on page 1046, column 1, paragraph 1 “As shown in Figure 2, instead of simply combining all learned fragment features with a global pooling step after several graph convolution layers, an attention layer is applied to capture the different importance of fragments in determination of stability. The attention mechanism captures the influence on an individual fragment of other fragments” along with the cost functions which denote y-hat as the prediction generated for the fragment features, which in view of Li et al. from above reads on generating a quality score for the chemical stability model based on an accuracy of predicted attribute values generated by the chemical stability model in accordance with the trained values of the set of model parameters of the chemical stability model, wherein the accuracy of predicted attribute values generated by the chemical stability model is measured.
Liu et al. and Liu et al. do not teach the administration of the chemical product in response to determining said product’s stability.
Waterman et al. teaches in the abstract “Methods are discussed, with the appropriate caveats, for accelerated aging of liquid and solid dosage forms, including small and large molecule active pharmaceutical ingredients. In particular, this review covers general thermal methods, as well as accelerated aging methods appropriate to oxidation, hydrolysis, reaction with reactive excipient impurities, photolysis and protein denaturation”, and on page 101, column 1, paragraph 1 “In the development of pharmaceutical dosage forms, one of the persistent challenges is assuring acceptable stability. While classically stability refers to the ability to withstand loss of a chemical due to decomposition, in the pharmaceutical world, the term “stability” more often refers to the storage time allowed before any degradation product in the dosage form achieves a sufficient level to represent a risk to the patient. Based on this time, the expiration date (shelf-life) of a product is determined. The allowable level of any given impurity will depend on the dose and likelihood of toxicity; however, for most drugs, the allowable levels of a single impurity permissible without explicit toxicological clinical testing are generally well less than 1% based on the drug”, which renders obvious administering the instance of the chemical product to a subject in response to a determination that the predicted preservation state of the instance of the chemical product satisfies a predefined condition, as the determination of stability of a pharmaceutical would then render obvious the administration of said pharmaceutical.
It would have been obvious at the time of filing to modify the teachings of Li et al. and Liu et al. for the overall method of claims 31, 49, and 50, with the teachings of Waterman et al. for the predicting of pharmaceutical stability as both are chemical compounds with the same features of stability affecting both, i.e. pharmaceuticals are merely a sub-category of chemicals. Additionally, Li et al. and Liu et al. would be obvious to combine as they are specifically from the same lab, on the same subject, using the same data, and similar methods. It would also be obvious to a person skilled within the art to give users a choice from multiple models to predict chemical stability based upon each model’s performance on the data given, especially as these two papers come from the same lab on the same topic each attempting to address issues with modeling chemical stability. One would have had a reasonable expectation of success using the teachings of each as again two of these papers come from the same lab on the same topic each attempting to address issues with modeling chemical stability, and the third is merely focusing on a subcategory of the data. Therefore, it would be obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Claim 32 is directed to the method of claim 31 but further specifies that the chemical product be a drug.
Liu et al. teaches on page 944, column 1, paragraph 5 “A scaffold-based classification approach (SCA) was employed to compare the structural diversities of the COMDECOM, Drug Bank, and WDI databases”.
Li et al. teaches in the abstract “In the drug discovery process, unstable compounds in storage can lead to false positive or false negative bioassay conclusions”.
Waterman et al. teaches in the abstract “Methods are discussed, with the appropriate caveats, for accelerated aging of liquid and solid dosage forms, including small and large molecule active pharmaceutical ingredients”.
All prior art pieces teach the chemical product being a drug.
Claim 33 is directed to the method of claim 32 and therefore claim 31, but further specifies that the chemical product be a vaccine.
Liu et al. teaches on page 944, column 1, paragraph 5 “A scaffold-based classification approach (SCA) was employed to compare the structural diversities of the COMDECOM, Drug Bank, and WDI databases”.
Li et al. teaches in the abstract “In the drug discovery process, unstable compounds in storage can lead to false positive or false negative bioassay conclusions”.
It would be obvious to a person skilled in the art that the use of a stability model for chemical stability of drugs would also be useful for the chemical stability of vaccines, as they are in fact a form of drug.
Claim 34 is directed to the method of claim 33 and therefore claim 31, but further specifies that the attribute of the chemical product comprise a concentration of an active component of the chemical product.
Li et al. teaches on page 1045, column 1, paragraph 5 “COMDECOM data consists of chemical structures and compound purity data measured at days 0, 14, 35, and 105”, reading on wherein the attribute of the chemical product comprises a concentration of an active component in the chemical product.
Claim 35 is directed to the method of claim 31 but further specifies that the experimental stability data for the chemical product comprise a collection of measurements from physical experiments.
Li et al. teaches on page 1044, column 1, paragraph 2 “COMDECOM data contain structurally diverse compounds whose stabilities were measured experimentally in a mixture of DMSO and H2O”, reading on wherein the set of experimental stability data for the chemical product comprises a collection of experimental measurements generated by way of one or more physical experiments.
Claim 36 is directed to the method of claim 35 and therefore claim 31 but further specifies that the experimental measure be an experimental temperature, duration of time and attribute value for the chemical product.
Liu et al. teaches on page 941, column 2, paragraph 1 “Stability is affected by a number of factors: chemical features, solvent types, temperature, humidity, freeze–thaw resistance, storage time, etc.”
Li et al. teaches on page 1044, column 1, paragraph 2 “COMDECOM data contain structurally diverse compounds whose stabilities were measured experimentally in a mixture of DMSO and H2O. The compound purity was monitored at 0-, 14-, 35-, and 105-day time points, and models were built from these data”.
It would be obvious to a person skilled in the art that measurements of stability over time would include a temperature and therefore be an attribute (stability), with both corresponding time and temperature data.
Claim 37 is directed to the method of claim 36 and thus claim 31, but further specifies optimizing the model parameters based upon minimizing an error between the experimental and the predicted values.
Li et al. teaches on page 1044, column 1, paragraph 2 “COMDECOM data contain structurally diverse compounds whose stabilities were measured experimentally in a mixture of DMSO and H2O”, and on page 1046, column 1, paragraph 1 “As shown in Figure 2, instead of simply combining all learned fragment features with a global pooling step after several graph convolution layers, an attention layer is applied to capture the different importance of fragments in determination of stability. The attention mechanism captures the influence on an individual fragment of other fragments” along with the cost functions which denote y-hat as the prediction generated for the fragment features, reading on wherein for each chemical stability model in the library of chemical stability models, training the chemical stability model comprises, for each experimental measurement in the collection of experimental measurements: optimizing values of the set of model parameters of the chemical stability model to minimize an error between: (i) the experimental attribute value specified by the experimental measurement, and (ii) a predicted attribute value generated by the chemical stability model by processing the experimental temperature and the experimental duration of time specified by the experimental measurement.
Claim 38 is directed to the method of claim 31 but further specifies that trained model parameters be compared to a target range of values for the model parameter.
Li et al. teaches on page 1046, column 2, paragraph 2 “Table 3 lists the hyperparameters to be optimized and their search range”, and on page 1047, column 1, paragraph 1 “the DeepChemStable model generated four graph convolution layers and output atom embedding size of 200. The best learning rate is 10−4. The best positive rate is 1.5, and the best L2 regulation parameter is 10−4”, reading on generating a quality score for the chemical stability model by comparing a trained value of a model parameter of the chemical stability model to a target range of values for the model parameter of the chemical stability model.
Claim 40 is directed to the method of claim 31 but further specifies that the quality score for the model be based on a confidence interval associated with a trained value of a model parameter.
Li et al. teaches on page 1046, column 2, paragraph 2 “Table 3 lists the hyperparameters to be optimized and their search range”, and on page 1047, column 1, paragraph 1 “the DeepChemStable model generated four graph convolution layers and output atom embedding size of 200. The best learning rate is 10−4. The best positive rate is 1.5, and the best L2 regulation parameter is 10−4”.
It would be obvious that any model’s performance would be associated the values of the trained hyperparameters, if any. Therefore, a confidence interval, which dictates the number of times you know a value will fall within the range specified, of a hyperparameter, would necessarily be associated with the performance of said model, and be an obvious way of determining model selection.
Claim 41 is directed to the method of claim 31 but further specifies determining a predicted value at a current time point, and determining a preservation state based upon a range of values.
Liu et al. teaches on page 942, column 2, paragraph 1 “compound purity measured at the 0th day is denoted as p0, which usually ranges from 90 to 100 %”, on page 942, column 1, paragraph 2 “The COMDECOM data contain 12,810 structurally diverse compounds and their stability data”, and on page 1045, column 1, paragraph 5 “COMDECOM data consists of chemical structures and compound purity data measured at days 0, 14, 35, and 105”, reading on wherein determining a predicted preservation state of an instance of the chemical product using the chemical stability model selected for the chemical product comprises: determining a predicted value of the attribute of the instance of the chemical product at a current time point using the chemical stability model selected for the chemical product; and determining the predicted preservation state of the instance of the chemical product based on whether the predicted value of the attribute of the instance of the chemical product is included in a predefined range of attribute values.
Claim 42 is directed to the method of claim 41 and thus claim 31, but further specifies the use of temperature as a predicted attribute.
Liu et al. teaches on page 941, column 2, paragraph 1 “Stability is affected by a number of factors: chemical features, solvent types, temperature, humidity, freeze–thaw resistance”.
Li et al. teaches on page 1044, column 1, paragraph 1 “Many factors contribute to the chemical instability of compounds in a repository and include chemical substructures, storage conditions, solvents, and temperature”.
It would be obvious to a person skilled in the art to use temperature as a predicted attribute, specifically when Li et al. is predicting features to then predict stability, and the data they are using is the COMDECOM dataset which is time based. This would then render obvious receiving a temperature profile that defines, for each time interval in a sequence of time intervals preceding the current time point, a respective temperature at which the instance of the chemical product was stored during the time interval; and for each time interval in the sequence of time intervals starting from a first time interval in the sequence of time intervals: determining a predicted value of the attribute of the instance of the chemical product at a final time point in the time interval, using the chemical stability model selected for the chemical product, based on: (i) a predicted value of the attribute of the instance of the chemical product at a first time point in the time interval, and (ii) a duration of the time interval; and determining the predicted value of the attribute of the instance of the chemical product at the current time point based on a predicted value of the attribute of the instance of the chemical product at a final time point in a final time interval in the sequence of time intervals.
Claim 43 is directed to the method of claim 31 but further specifies that it be determined based off the predicted preservation state, whether or not to administer the chemical product.
It would be obvious that if we are examining a drug as previously described that an unstable state would not be administered or kept for administering to a patient.
Claim 48 is directed to the method of claim 31 but further specifies that to identify the best model, said model will have the highest value of a quality score from among the models.
It would have been obvious to a person skilled in the art to identify a model from a group of models as the best model via a score, given a choice of multiple models. Additionally, both Li et al. and Liu et al. provide a score of each model in terms of their AUC to determine precision/recall rates.
Claim 45 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (Journal of Chemical Information and Modeling (2019) 1044-1049; previously cited), Liu et al. (Journal of Computationally Aided Molecular Design (2014) 941-950; previously cited), and Waterman et al. (International Journal of Pharmaceutics (2005) 101-25; newly cited) as applied to claims 31-38, 40-43, and 48-50 above, and further in view of Ahlneck et al. (International Journal of Pharmaceutics (1990) 87-95; previously cited).
Claim 45 is directed to the method of claim 31 but further specifies that the model input defines a residual moisture and the output defines a predicted value of said attribute.
Li et al. and Liu et al. teach the method of claims 31-35, 38, 43, and 48-50 as previous described.
Ahlneck et al. teaches in on page 1, column 1, paragraph 1 “It is well recognized that residual water associated with drugs in the solid state can have significant effects on a variety of physical and chemical properties, such as chemical degradation, dissolution rate, flow and compactibility”, which in view of Li et al. and Liu et al., would render the use of residual moisture as model input, and thereby model output, obvious.
It would have been obvious at the time of invention to modify the teachings of Li et al. and Liu et al. for the method of claim 31, with the teachings of Ahlneck et al. as the latter mere informs that residual water is associated with variety of chemical properties including chemical degradation. One would have had a reasonable expectation of success given that Ahlneck et al. is merely informing a new source of data and not modifying the prior method. Therefore, it would be obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Claim 46 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (Journal of Chemical Information and Modeling (2019) 1044-1049; previously cited), Liu et al. (Journal of Computationally Aided Molecular Design (2014) 941-950; previously cited), and Waterman et al. (International Journal of Pharmaceutics (2005) 101-25; newly cited) as applied to claims 31-38, 40-43, and 48-50 above, and further in view of Lee et al. (Food Science Biotechnology (2013) 279-282; previously cited).
Claim 46 is directed to the method of claim 31 but further specifies that the model input defines a radiation state and the output defines a predicted value of said attribute.
Li et al. and Liu et al. teach the method of claims 31-35, 38, 43, and 48-50 as previous described.
Lee et al. teaches on page 1, column 1, paragraph 1 “Curcumin, a yellow pigment from turmeric (Curcuma longa), has shown various health beneficial effects. In the present study, changes in the chemical stability and bioactivities of curcumin by UV radiation were investigated. Curcumin degradation in water or phosphate buffered saline was accelerated under UV radiation (254 nm); the residual levels of curcumin were 36.9 and 16.8%, respectively, after 24 h radiation.”, which in view of Li et al. and Liu et al., would render the use of radiation state as model input, and thereby model output, obvious.
It would have been obvious at the time of invention to modify the teachings of Li et al. and Liu et al. for the method of claim 31, with the teachings of Lee et al. as the latter mere informs that UV radiation is associated with variety of chemical properties including chemical degradation of curcumin. One would have had a reasonable expectation of success given that Lee et al. is merely informing a new source of data and not modifying the prior method. Therefore, it would be obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Claim 47 is rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (Journal of Chemical Information and Modeling (2019) 1044-1049; previously cited), Liu et al. (Journal of Computationally Aided Molecular Design (2014) 941-950; previously cited), and Waterman et al. (International Journal of Pharmaceutics (2005) 101-25; newly cited) as applied to claims 31-38, 40-43, and 48-50 above, and further in view of Anarjan et al. (Journal of the American Oil Chemists' Society (2013) 1223-1227; previously cited).
Claim 47 is directed to the method of claim 31 but further specifies that the model input defines a lighting state and the output defines a predicted value of said attribute.
Li et al. and Liu et al. teach the method of claims 31-35, 38, 43, and 48-50 as previous described.
Anarjan et al. teaches in the abstract “Since astaxanthin is sensitive to oxidative damage, its degradations kinetics in the prepared nanodispersion systems were investigated as a function of storage temperature, atmosphere and light. The results showed that astaxanthin degradation followed a first-order kinetic and, in most cases, astaxanthin was more stable in optimum-formulated three-component-stabilized nanodispersions as compared to nanodispersion systems stabilized by individual stabilizers. In addition, high storage temperature and intense illumination significantly (P\0.05) increased the degradation of astaxanthin”, which in view of Li et al. and Liu et al., would render the use of lighting state as model input, and thereby model output, obvious.
It would have been obvious at the time of invention to modify the teachings of Li et al. and Liu et al. for the method of claim 31, with the teachings of Anarjan et al. as the latter mere informs that intense illumination is associated with increased chemical degradation of specific chemicals. One would have had a reasonable expectation of success given that Anarjan et al. is merely informing a new source of data and not modifying the prior method. Therefore, it would be obvious to one with ordinary skill in the art to incorporate the teachings of each and to be successful.
Subject Matter Potentially Free from the Prior Art
Claim 44 contains subject matter that is potentially free from the prior. More specifically claim 44 sets out the determination not of stability data but of modified stability data using the method of claim 42 and thus claim 31, and that the data used is to exclude measurements relating to at least one temperature higher than any temperature included in the temperature profile. While the second portion of the claim is not novel, the use of modified experimental data, specifically modified in such a way as is described, the claim as a whole is not read on by any prior thus found.
Response to Arguments
Applicant's arguments filed 8/19/2025 have been fully considered but they are not persuasive. Applicant asserts that due to current amendments, prior rejections under 35 U.S.C. 103 are traversed, however the newly cited rejection includes newly cited prior art which reads on the current amendments.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
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.
/K.N.A./Examiner, Art Unit 1687
/OLIVIA M. WISE/Supervisory Patent Examiner, Art Unit 1685