DETAILED ACTION
Applicant’s response, filed 05 November 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 is being examined under the pre-AIA first to invent provisions.
Claim Status
Claims 1-3, 5-19, and 21 are pending and examined herein.
Claims 1-3, 5-19, and 21 are rejected.
Claim 21 is objected to.
Priority
Claims 1-3, 5-19, and 21 are granted the claim to the benefit of priority to foreign application GB0920382.9 filed 20 November 2009. Thus, the effective filling date of claims 1-3, 5-19, and 21 is 20 November 2009.
Drawings
The drawings received 12 August 2019 are objected to. The drawings are objected to because Figure 2, Figure 3, Figure 11, Figure 12, Figure 13, and Figure 14 contains partial views that are incorrectly labeled and should be labeled Fig. 2A, Fig. 2B, Fig. 3A, Fig. 3B, Fig. 11A, Fig. 11B, Fig. 12A, Fig. 12B, Fig. 13A, Fig. 13B, Fig. 14A, and Fig. 14B (see MPEP 608.02(V) section 37 C.F.R. 1.84(u)(1)). Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
The objection of claim 2 for reciting “optionally and wherein the linear distance” in line 2 in Office action mailed 26 August 2025 is withdrawn in view of the amendment which removes this limitation received 05 November 2025.
Claim 21 is objected to because of the following informalities: claim 21 recites “upon determining that the predefined stop condition is not satisfied… a predefined stop condition” in lines 18 and 19 of the claim should read “upon determining that the predefined stop condition is not satisfied… the predefined stop condition” which would provide consistent language (by mirroring the language recited in independent claim 1) and increase clarity. Appropriate correction is required.
Claim Rejections - 35 USC § 112
The rejection on the ground of 112/b of claims 12-15 for reciting "wherein optionally evaluating the population (PG) against at least one achievement objective…" in Office action mailed 26 August 2025 is withdrawn in view of the amendment of "further comprising optionally evaluating the population (PG) against at least one achievement objective…" received 05 November 2025.
Claim Rejections - 35 USC § 101
The rejection on the ground of 101 of claims 1-3, 5-19, and 21 in Office action mailed 26 August 2025 is withdrawn in view of the amendment of “determining, based on the shortest vector distance, that at least the first ranked member of the initial or further evaluated population is an optimized molecule and synthesizing, in vitro, the drug compound based on the optimized molecule” received 05 November 2025. The claims now recite an additional element which integrates the judicial exceptions into a practical application. The MPEP states at 2106.05(a) “It is important to note, the judicial exception alone cannot provide the improvement. The improvement can be provided by one or more additional elements… In addition, the improvement can be provided by the additional element(s) in combination with the recited judicial exception”. The instant claims now recite an improvement which is provided by the additional element of “synthesizing, in vitro, the drug compound based on the optimized molecule” in combination with the recited judicial exception of “determining, based on the shortest vector distance, that at least the first ranked member of the initial or further evaluated population is an optimized molecule”. The provided improvement is realized in drug technology by synthesizing a drug that is an optimal solution in a multi-objective optimization process which is an optimized drug for predetermined achievement objectives.
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 pre-AIA 35 U.S.C. 103(a) which forms the basis for all obviousness rejections set forth in this Office action:
(a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negated by the manner in which the invention was made.
The rejection below has been modified necessitated by amendment.
Claims 1-3, 5-19, and 21 are rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Nicolaou et al. (J. Chem. Inf. Model. Vol 49(2), pp. 295-307, 2009; previously cited) in view Kasprzak et al. (Structural and Multidisciplinary Optimization, 2001, vol. 22, Issue 3, pp. 208-218; previously cited) in view of Warrington et al. (US 20090209759 A1; previously cited).
Claim 1 is directed to defining a set of n achievement objectives (OAl-n), where n is at least one, defining a population (PG=o)of at least one molecule, selecting an initial population (Pparent) of at least one molecule (Ii-In) from the population (PG=o), wherein the initial population (Pparent) is selected to include one or more of: an existing drug compound; an existing lead compound, and one or more molecules having a predicted value of activity greater than a defined threshold value against a specific target molecule;
Nicolaou et al. shows a multi-objective evolutionary algorithm that initiates with a supply of the implemented objectives to be used for scoring and a set of molecules to be used as the initial population (Nicolaou et al. page 299 left col.). Nicolaou et al. shows utilizing two sets of data for multi-objective optimization that are Estrogen Receptor ligands and molecules in an Estrogen Receptor-alpha Coactivator Binding inhibitor dataset (Nicolaou et al. page 301 right col.).
and evaluating, by a computer device, members (Ii-In) of the initial population (Pparent) against at least one of the n achievement objectives (OA1-x), where x is from 1 to n, wherein the evaluation comprises a calculation of a linear distance from the member (Ii-In) to the at least one achievement objective (OA1-x);
Nicolaou et al. shows performing a Pareto-ranking procedure on calculated scores for members of a population (Nicolaou et al. page 299 left col.). Nicolaou et al. shows a Pareto-ranking procedure which evaluates a population to determine nondominated solutions (Nicolaou et al. page 296 right col). Nicolaou et al. shows a graph of solutions which are ranked with lines connecting the nondominated solutions to each objective considered which represent the distance of the solution to each objective (Nicolaou et al. page 296 Figure 1). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions.
determining whether a predefined stop condition is satisfied, upon determining that a the predefined stop condition is not satisfied, generating further populations (PG; PG+1) of molecules and evaluating each one by an iterative process until the a predefined stop condition is satisfied, comprising performing a first iteration (G=1) of an evolutionary algorithm to generate and evaluate a new population (PG) of at least one molecule, the method comprising: transforming at least one member of the initial population (Pparent) to generate a transformed population (Ptransformed)of at least one molecule, defining a new population (PG) of at least one molecule, the new population (PG) comprising at least one member of the transformed population
Nicolaou et al. shows the algorithm checks for the termination conditions, typically if the number of preset allowed iterations has been reached and if satisfied the process terminates (Nicolaou et al. page 299 right col). Nicolaou et al. shows if the process is not terminated (i.e. the stop condition is not satisfied), then a new population is generated through modifications which are then used in the next iteration of the algorithm (Nicolaou et al. page 299 right col).
identifying at least one desired activity of the drug compound and defining a strategy function to score each member of the new population against one or more of the at least one desired activity, calculating parameters of each member of the population for at least one of the achievement objectives relevant to the one or more desired activity, determining a predicted activity (Prediction 1 to Prediction n) of each member of the population (PG) for the one or more desired activity (Ai-n),
Nicolaou et al. shows the new population is subjected to a fitness calculation against all objectives, performing Pareto-ranking using scores of molecules against objectives, and calculating a multi-objective fitness function based on Pareto-ranking (i.e. the strategy function) (Nicolaou et al. page 299). Nicolaou et al. shows objective scorers as binding affinity scorers, molecular similarity scorers, and chemical structure scorers that are used to calculate parameters for each member of the population for achievement objectives relevant to desired activities which are used for assessing the activity of a molecule (Nicolaou et al. page 300 right col.).
selecting a sub-population (Pelite) of molecules of the new population (PG) that satisfy the strategy function (S),
Nicolaou et al. shows selecting a subset of molecules that are pareto-solutions which are non-dominated solutions of a population (i.e. rank 1 from the Pareto ranking) to archive (Nicolaou et al. page 299 right col.). These molecules satisfy the strategy function by being non-dominated solutions (i.e. there are no other solutions that are better than them in all of the objectives considered) (Nicolaou et al. page 296 right col.).
defining a further new population (PG+1) of at least one molecule (Ii-In), the further new population (PG+1) comprising at least one of the molecules in the selected sub-population (Pelite),
Nicolaou et al. shows merging the archived Pareto-solutions with the current population which defines a new population (Nicolaou et al. page 299 right col.).
and evaluating members (Ii-In) of the further new population (PG+1) against the at least one achievement objective (OAl-x) wherein the evaluating comprises the calculation of linear distance to the at least one achievement objective (OA1-x) and optionally a Pareto frontier for the members (Ii-In) of the further new population (PG+1),
Nicolaou et al. shows the recalculation of the Pareto-rank is performed on the extended set. Nicolaou et al. shows a graph of solutions which are ranked with lines connecting the nondominated solutions to each objective considered which represent the distance of the solution to each objective (Nicolaou et al. page 296 Figure 1). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions.
Nicolaou et al. does not show upon determining that a the predefined stop condition is satisfied, ranking members (Ii-In) of the initial or further evaluated population (Pparent; PG; PG+l) according to shortest linear distance, wherein the shortest linear distance is a shortest vector distance between a member of the initial or further evaluated population and the set of n achievement objectives (OAl-n) and optionally Pareto frontier to the set of n achievement objectives (OAl-n), wherein the shortest linear distance is different than the Pareto frontier, determining, based on the shortest vector distance, that at least the first ranked member (Ii-In) of the initial or further evaluated population (Pparent; PG; PG+l), is an optimized molecule
When combined with Nicolaou et al., Kasprzak et al. shows utilizing the set of nondominated solutions (i.e. the Pareto-frontier) outputted as solutions when the multi-objective evolutionary algorithm satisfies a stop condition to identify the optimal solution using a linear distance between a member in a Pareto set to an ideal solution. Kasprzak et al. shows the identification of a first ranked member in a population by minimizing the distance from the Pareto set to an ideal solution (i.e. utopia point) to find the optimal solution (Kasprzak et al. page 210 left col., page 210 right col., page 210 figure 2). Thus, the optimal solution will have the shortest linear distance to the ideal solution (the first ranked member) and all other members will have linear distances in increasing order to the ideal solution.
Nicolaou et al. in view of Kasprzak et al. does not show synthesizing, in vitro, the drug compound based on the optimized molecule
When combined with Nicolaou et al. in view of Kasprzak et al., Warrington et al. synthesizing the drug compound based on the identified at least first ranked member of the evaluated initial or further population. Warrington et al. shows a candidate chooser which choses a compound to synthesize based on generated scores for that compound and then synthesizes the chosen compound (Warrington et al. [023] and [027]).
Claim 2 is directed to identifying an additional sub-population of the new population (PG) that fail the strategy function (S), transforming the additional sub-population to generate an additional transformed population, scoring using the strategy function, each member of the additional transformed population according to the at least one desired activity (A1-n), selecting at least one member of the additional transformed population that satisfies the strategy function (S), and evaluating the at least one member of the additional transformed population against the at least one achievement objective (OA1-X).
Nicolaou et al. shows a process of parent selection using a roulette method on the fitness scores of the solutions where the roulette method selects solutions via a probabilistic mechanism that assigns higher selection probability to solutions with higher transformed Pareto-rank which shows that pareto-rank has been performed which provides dominated solutions (a sub-population that fail the strategy function/fitness function) in addition to the non-dominated solutions (Nicolaou et al. page 299 right col.). This roulette method is a probabilistic method which may select these dominated solutions which are added to the new parent population which is then used in the next iteration for optimization which includes transforming (which includes mutation and crossover) which are then evaluated using a fitness function and evaluated against achievement objectives (Nicolaou et al. page 299 right col. and page 300 Figure 4).
Claim 3 is directed to calculating parameters of each member of the initial population for each of the at least one achievement objective or each of the n achievement objectives and calculating the linear distance of each member of the initial population to the at least one achievement objective or to each of the n achievement objectives.
Nicolaou et al. shows calculating parameters (scores) for each achievement objective and using these scores for performing a Pareto-ranking procedure (Nicolaou et al. page 299 left col.). Nicolaou et al. shows a Pareto-ranking procedure which evaluates a population to determine nondominated solutions (Nicolaou et al. page 296 right col). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions (Nicolaou et al. page 296 Figure 1).
Claim 5 is directed to calculating the parameters of each member (Ii-In) of the new population (PG+1) for each of the at least one achievement objective (OA1-x) or for each of the n achievement objectives (OAl-n); and calculating the linear distance of each member (Ii-In) of the new population (PG+1) to the at least one achievement objective (OA1-x) or to each of the n achievement objectives (OAl-n). Claim 6 is directed to determining whether a stop condition is satisfied, and if the stop condition is not satisfied: defining the evaluated new population (PG+1) as a new parent population (Pparent) of at least one molecule (Ii-In); and performing a second iteration (G=2) of the evolutionary algorithm by repeating the steps of Claim 5.
Nicolaou et al. shows the process then iterates, and the new population is subjected to fitness calculation against all objectives (calculating parameters) and Pareto-ranking (Nicolaou et al. page 299 right col.). Nicolaou et al. shows calculating parameters (scores) for each achievement objective and using these scores for performing a Pareto-ranking procedure (Nicolaou et al. page 299 left col.). Nicolaou et al. shows a Pareto-ranking procedure which evaluates a population to determine nondominated solutions (Nicolaou et al. page 296 right col). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions (Nicolaou et al. page 296 Figure 1).
Claim 7 is directed to applying at least one filter (F) to remove molecules that fail a solubility requirement before evaluating the population (PG) against at least one achievement objective (OA1-x).
Nicolaou et al. shows using scorers set to values generally in line to the Rule-of-Five for oral bioavailability (which includes a solubility requirement) were applied as hard filters in each generation to remove potentially problematic designs from further consideration (Nicolaou et al. page 303 left col.). Nicolaou et al. shows these hard-filters are applied before evaluating populations against at least one achievement objective (Nicolaou et al. page 300 Figure 4).
Claim 8 is directed to wherein PG = Pparent + Ptransformed
Nicolaou et al. the parents are then subjected to mutation and crossover according to the probabilities indicated by the user. The new population is formed by merging the original population and the newly produced mutants and crossover children (Nicolaou et al. page 299 right col.).
Claim 9 is directed to applying at least one filter to remove molecules that fail at least one predefined criteria of the filter.
Nicolaou et al. shows an algorithm that utilizes filters to remove molecules that have scores outside a range allowed (Nicolaou et al. page 299 left col.).
Claim 10 is directed to applying at least one filter to remove molecules that fail at least one predefined criteria of the filter, wherein the filter is applied to molecules of the population before ranking members of the new population.
Nicolaou et al. shows an algorithm that utilizes filters to remove molecules that have scores outside a range allowed (Nicolaou et al. page 299 left col.). Nicolaou et al. further shows this filtering step is done before performing Pareto-ranking (Nicolaou et al. page 300 Figure 4)
Claim 11 is directed to wherein the at least one predefined criteria is selected form at least one of molecular weight, H-bond donors, H-bond acceptors, and number of rotatable bonds.
Nicolaou et al. shows a collection of chemical structure scorers, e.g. molecular weight, hydrogen bond donors and acceptors, and number of rotatable bonds, were also used as hard filters (Nicolaou et al. page 303 left col.).
Claim 12 is directed to further comprising optionally evaluating the population (PG) against at least one achievement objective (OA1-x), and selecting molecules from the evaluated population (PG) by applying the a strategy function (S), comprises: identifying at least one desired activity (A) of an optimized molecule and defining the a strategy function (S) to score each member (Ii-In) of the population (PG) against one or more of the at least one desired activity (A1.n);calculating the parameters of each member (Ii-In) of the population (PG) for at least one of the achievement objectives (OA1-x) relevant to the one or more desired activity (A1-n);determining the predicted activity (Prediction 1 to Prediction n) of each member (Ii-In) of the population (PG) for the one or more desired activity (A1-n); selecting the sub-population (Pelite) of molecules of the population (PG) that satisfy the strategy function (S); and optionally selecting a sub-population (Prandom) of at least one molecule from a the sub- population (Pnonelite) of molecules that do not satisfy the strategy function (S).
This claim is interpreted as being an optional step and is not required to be practiced. Therefore, claim 12 is obvious over Nicolaou et al. in view Kasprzak et al. in view of Warrington et al..
Claim 13 is directed to wherein the new population (PG+1) of at least one molecule (Ii-In) comprises Pelite or Pelite + Prandom.
Nicolaou et al. shows merging the archive Pareto-solutions (i.e. Pelite) with the current population which defines a new population (Nicolaou et al. page 299 right col.).
Claim 14 is directed to wherein the strategy function (S) is satisfied for molecules of the population (PG) that satisfy one of: the molecule is part of a subset of the population PG where each molecule in the subset has a higher predicted activity (Prediction 1) than each molecule in a remainder of the population PG
Nicolaou et al. shows selecting a subset of molecules that are pareto-solutions which are non-dominated solutions of a population (i.e. rank 1 from the Pareto ranking) to archive (Nicolaou et al. page 299 right col.). These molecules satisfy the strategy function by being non-dominated solutions (i.e. there are no other solutions that are better than them in all of the objectives considered) which shows a higher predicted activity than each molecule in a remainder of the population (Nicolaou et al. page 296 right col.)
Claim 15 is directed to wherein the at least one desired activity (A) of an optimized molecule is selected from one or more of: predicted activity against one or more target molecule (e.g. specificity, binding affinity, inhibition constant); predicted relative activity against one target molecule compared to another molecule; predicted selectivity for one or more target molecule over another molecule; predicted relative selectivity for more than one target molecule; predicted drug-like properties / scores (e.g. ADME); prioritization of one or more ADME property; prioritization of drug-like properties over one or more activity or specificity; and prioritization of vector optimization over Pareto frontier.
Nicolaou et al. shows a desired activity which are used for multi-objective optimization is binding affinity of a designed molecule to a target protein (Nicolaou et al. page 300 right col.).
Claim 16 is directed to wherein the transformations are derived from one or both of a database of known chemical transformations and a library of genetic algorithm operators.
Nicolaou et al. shows utilizing genetic algorithm operators of mutation and crossover for the transformations (Nicolaou et al. page 301 left col.)
Claim 17 is directed to wherein the initial population (Pparent) of at least one molecule is one of: a larger population (PG=o) of molecules based on at least one predetermined selection criteria; a population of molecules selected using one or more selection criteria selected from at least one of: 3D virtual docking, chemical similarity, database searching, Bayesian activity modelling, and an algorithm; or a population of one molecule.
Nicolaou et al. shows utilizing an Estrogen Receptor-alpha Coactivator Binding inhibitor dataset which was selected by database searching (Nicolaou et al. page 301 right col.).
Claim 18 is directed to wherein the set of n achievement objectives comprises a plurality of parameter values that define properties of a desired optimized molecule and includes binding affinity to a target molecule.
Nicolaou et al. shows a the calculation of binding affinity values of a designed molecule to a target protein for use in the multi-objective optimization algorithm (Nicolaou et al. page 300 right col.).
Claim 19 is directed to wherein the stop condition is selected from a number of iterations of the evolutionary algorithm.
Nicolaou et al. shows the algorithm checks for the termination conditions, typically if the number of preset allowed iterations has been reached and if satisfied the process terminates.
Claim 21 is directed to defining a set of n achievement objectives (OAl-n), where n is at least one, wherein the achievement objectives include at least one of: inhibition activity against the specific target molecule; binding affinity to the specific target molecule; specificity for the specific target molecule; and selectivity for the specific target molecule over a non-target molecule, defining a population (PG=o)of at least one molecule, selecting an initial population (Pparent) of at least one molecule (Ii-In) from the population (PG=o),
Nicolaou et al. shows a multi-objective evolutionary algorithm that initiates with a supply of the implemented objectives to be used for scoring and a set of molecules to be used as the initial population (Nicolaou et al. page 299 left col.). Nicolaou et al. shows using the multi-objective evolutionary algorithm to design molecules exhibiting selectivity between to receptors (Nicolaou et al. page 302 left col.).
and evaluating, by a computer device, members (I1-In) of the initial population (Pparent) against at least one of the n achievement objectives (OA1-x), where x is from 1 to n, wherein the evaluation comprises a calculation of a linear distance from the member (Ii-Im) to the at least one achievement objective (OA1-x);
Nicolaou et al. shows performing a Pareto-ranking procedure on calculated scores for members of a population (Nicolaou et al. page 299 left col.). Nicolaou et al. shows a Pareto-ranking procedure which evaluates a population to determine nondominated solutions (Nicolaou et al. page 296 right col). Nicolaou et al. shows a graph of solutions which are ranked with lines connecting the nondominated solutions to each objective considered which represent the distance of the solution to each objective (Nicolaou et al. page 296 Figure 1). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions.
determining whether a predefined stop condition is satisfied, upon determining that a the predefined stop condition is not satisfied, generating further populations (PG; PG+1) of molecules and evaluating each one by an iterative process until the a predefined stop condition is satisfied, comprising performing a first iteration (G=1) of an evolutionary algorithm to generate and evaluate a new population (PG) of at least one molecule, the method comprising: transforming at least one member of the initial population (Pparent) to generate a transformed population (Ptransformed)of at least one molecule, defining a new population (PG) of at least one molecule, the new population (PG) comprising at least one member of the transformed population
Nicolaou et al. shows the algorithm checks for the termination conditions, typically if the number of preset allowed iterations has been reached and if satisfied the process terminates (Nicolaou et al. page 299 right col). Nicolaou et al. shows if the process is not terminated (i.e. the stop condition is not satisfied), then a new population is generated through modifications which are then used in the next iteration of the algorithm (Nicolaou et al. page 299 right col).
identifying at least one desired activity of the drug compound and defining a strategy function to score each member of the new population against one or more of the at least one desired activity, calculating parameters of each member of the population for at least one of the achievement objectives relevant to the one or more desired activity, determining a predicted activity (Prediction 1 to Prediction n) of each member of the population (PG) for the one or more desired activity (Ai-n),
Nicolaou et al. shows the new population is subjected to a fitness calculation against all objectives, performing Pareto-ranking using scores of molecules against objectives, and calculating a multi-objective fitness function based on Pareto-ranking (i.e. the strategy function) (Nicolaou et al. page 299). Nicolaou et al. shows objective scorers as binding affinity scorers, molecular similarity scorers, and chemical structure scorers that are used to calculate parameters for each member of the population for achievement objectives relevant to desired activities which are used for assessing the activity of a molecule (Nicolaou et al. page 300 right col.).
selecting a sub-population (Pelite) of molecules of the new population (PG) that satisfy the strategy function (S),
Nicolaou et al. shows selecting a subset of molecules that are pareto-solutions which are non-dominated solutions of a population (i.e. rank 1 from the Pareto ranking) to archive (Nicolaou et al. page 299 right col.). These molecules satisfy the strategy function by being non-dominated solutions (i.e. there are no other solutions that are better than them in all of the objectives considered) (Nicolaou et al. page 296 right col.).
defining a further new population (PG+1) of at least one molecule (Ii-In), the further new population (PG+1) comprising at least one of the molecules in the selected sub-population (Pelite),
Nicolaou et al. shows merging the archive Pareto-solutions with the current population which defines a new population (Nicolaou et al. page 299 right col.).
and evaluating members (Ii-In) of the further new population (PG+1) against the at least one achievement objective (OAl-x) wherein the evaluating comprises the calculation of linear distance to the at least one achievement objective (OA1-x) and optionally a Pareto frontier for the members (Ii-In) of the further new population (PG+1),
Nicolaou et al. shows the recalculation of the Pareto-rank is performed on the extended set. Nicolaou et al. shows a graph of solutions which are ranked with lines connecting the nondominated solutions to each objective considered which represent the distance of the solution to each objective (Nicolaou et al. page 296 Figure 1). It is implicitly shown that when performing Pareto-ranking, a linear distance is calculated to each objective to identify nondominated solutions.
Nicolaou et al. does not show upon determining that a the predefined stop condition is satisfied, ranking members (Ii-In) of the initial or further evaluated population (Pparent; PG; PG+l) according to shortest linear distance, wherein the shortest linear distance is a shortest vector distance between a member of the initial or further evaluated population and the set of n achievement objectives (OAl-n) and optionally Pareto frontier to the set of n achievement objectives (OAl-n), wherein the shortest linear distance is different than the Pareto frontier, determining, based on the shortest vector distance, that at least the first ranked member (Ii-In) of the initial or further evaluated population (Pparent; PG; PG+l), is an optimized molecule
When combined with Nicolaou et al., Kasprzak et al. shows utilizing the set of nondominated solutions (i.e. the Pareto-frontier) outputted as solutions (when the multi-objective evolutionary algorithm satisfies a stop condition) to identify the optimal solution using a linear distance between a member in a Pareto set to an ideal solution. Kasprzak et al. shows the identification of a first ranked member in a population by minimizing the distance from the Pareto set to an ideal solution (i.e. utopia point) to find the optimal solution (Kasprzak et al. page 210 left col.). Thus, the optimal solution will have the shortest linear distance to the ideal solution (the first ranked member) and all other members will have linear distances in increasing order to the ideal solution.
Nicolaou et al. in view of Kasprzak et al. does not show synthesizing, in vitro, the drug compound based on the optimized molecule.
When combined with Nicolaou et al. in view of Kasprzak et al., Warrington et al. synthesizing the drug compound based on the identified at least first ranked member of the evaluated initial or further population. Warrington et al. shows a candidate chooser which choses a compound to synthesize based on generated scores for that compound and then synthesizes the chosen compound (Warrington et al. [023] and [027]).
An invention would have been obvious to one or ordinary skill in the art if some motivation in the prior art would have led that person to combine reference teachings to arrive at the claimed invention. It would have been obvious to one of ordinary skill in the art before the effective filling date to have combined the multi-objective evolutionary algorithm of Nicolaou et al. with the process of identifying the optimal solution in a Pareto set of Kasprzak et al. because this would allow for a method that outputs multi-objective optimization solutions in a Pareto set and then further uses the Pareto set to identify an optimal solution based on a distance between members of the Pareto set and an ideal solution (Kasprzak et al. page 210 left col.). It would have been further obvious to one of ordinary skill in the art before the effective filling date to have combined the method of identifying an optimal solution from a Pareto set of Nicolaou et al. in view of Kasprzak et al. with synthesizing an identified molecule of Warrington et al. because this would allow for a method that synthesizes optimal solution molecules that have certain desirable properties (Warrington et al. [023] and [027]). One would have a reasonable expectation of success because Nicolaou et al. identifies a Pareto set of the best performing molecules with respect to all achievement objectives while Kasprzak et al. shows utilizing a Pareto set to identify an optimal solution while Warrington et al. synthesizing compounds that have been chosen based on scores.
Response to Arguments
Applicant's arguments filed 05 November 2025 have been fully considered but they are not persuasive.
Applicant argues that Nicolaou whether considered singly or in combination with the other cited reference, fails to describe, teach, or suggest “ranking members (I1-In) of the initial or further evaluated population… wherein the shortest linear distance is different than the Pareto frontier”. Applicant further argues that a utopia point on a Pareto set (which is shown by Kasprzak and is relied upon for showing the ranking process) is not “a shortest vector distance between a member of the initial or further evaluated population and the set of n achievement objectives… wherein the shortest linear distance is different than the Pareto frontier” (Reply p. 17-18).
This argument has been fully considered but found to be not persuasive. It is noted that the utopia point itself is not relied upon as being the shortest linear distance. The utopia point is utilized for finding the optimal compromise solution by calculating the linear distance between the utopia point and the members of the Pareto set and identifying the member of the Pareto set which lies geometrically closest (or shortest linear distance to the utopia point) as the optimal compromise design (Kasprzak page 210 and page 210 Figure 2). It is noted that this linear distance from the utopia point and a member of the Pareto Set is different from the Pareto frontier itself.
Conclusion
No claims are allowed.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN EDWARD HAYES whose telephone number is (571)272-6165. The examiner can normally be reached M-F 9am-5pm.
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, Olivia Wise can be reached at 571-272-2249. 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.
/J.E.H./Examiner, Art Unit 1685
/KAITLYN L MINCHELLA/Primary Examiner, Art Unit 1685