DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-16 are currently pending and examined on the merits.
Priority
Applicant’s claim for the benefit of a prior-filed application 63/376,179 filed 19 September 2022 is acknowledged and accepted. The effective filing date is September 19th, 2022.
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.
Claims 1-16 are 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
Claims 1 and 9 recite “treating the subject based on the predicted response to the medical treatment”, however, neither the specification nor the claims recite what explicitly the method of treatment claimed is. Additionally, neither the specification nor the claims recite sufficient structure to conduct such a treatment, nor a connection to the system (comprising a non-transitory computer readable medium) with which to administer said treatment.
The Applicant’s specification describes the claimed invention in Figure 1, but the system described does not detail an administration apparatus in light of the system described, nor is a relationship to the system described. The description of the treatment in paragraphs 0047-0048 (which state “treatment can mean preventing…disease…preventing the disease involves administering…”) of the specification does not sufficiently claim a method of treatment or administration as the claimed invention (regarding the method of claim 1), nor do the paragraphs relate an explicitly claimed treatment method to the system of claim 9 (regarding the system of claim 9). Claims 2-8 and 10-16 are dependent upon claims 1 and 9 respectively and inherit the rejection under 35 U.S.C. 112(a).
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-16 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites “calculating, on a test dataset comprising genome data of a subject, a predicted clinical outcome from a medical treatment on a subject based on a subset of the set of classifiers having a high performance level on the validation dataset”. A “high performance level” is interpreted as:
A relative term of degree (see MPEP 2173.05(b)), and
not known in the art of bioinformatics, as one of ordinary skill in the art would not have clarity as to what “high” means.
The Examiner interprets “high performance” as an area under the curve (AUC) above 0.80.
Claims 9-16 recite both “treating the subject based on the predicted response to the medical treatment” and “A system for predicting…”
A single claim which claims both an apparatus and the method steps of using the apparatus is indefinite under 35 U.S.C. 112(b) or pre-AIA 35 U.S.C. 112, second paragraph. See MPEP 2173.05(p) and In re Katz Interactive Call Processing Patent Litigation, 639 F.3d 1303, 1318, 97 USPQ2d 1737, 1748-49 (Fed. Cir. 2011).
In Katz, a claim directed to "[a] system with an interface means for providing automated voice messages…to certain of said individual callers, wherein said certain of said individual callers digitally enter data" was determined to be indefinite because the italicized claim limitation is not directed to the system, but rather to actions of the individual callers, which creates confusion as to when direct infringement occurs. Katz, 639 F.3d at 1318, 97 USPQ2d at 1749 (citing IPXL Holdings v. Amazon.com, Inc., 430 F.3d 1377, 1384, 77 USPQ2d 1140, 1145 (Fed. Cir. 2005), in which a system claim that recited "an input means" and required a user to use the input means was found to be indefinite because it was unclear "whether infringement … occurs when one creates a system that allows the user [to use the input means], or whether infringement occurs when the user actually uses the input means."); Ex parte Lyell, 17 USPQ2d 1548 (Bd. Pat. App. & Inter. 1990) (claim directed to an automatic transmission workstand and the method of using it held ambiguous and properly rejected under 35 U.S.C. 112, second paragraph).
Claims 2-8 and 10-16 as dependent claims inherit the rejection under 35 U.S.C. 112(b).
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.
Claim(s) 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea of mental steps, mathematic concepts, organizing human activity, or a natural law without significantly more.
Step 2A, Prong 1
Claims 1-16 are drawn to a process (For example, “A Method”, clms. 1-8 and 10-16. “A system”, clm. 9.). In accordance with MPEP § 2106, claims found to recite statutory subject matter (Step 1: YES) are then analyzed to determine if the claims recite any concepts that equate to an abstract idea, law of nature or natural phenomenon (Step 2A, Prong 1). In the instant application, the claims (italicized) recite the following limitations that equate to an abstract idea (abstract idea in parenthesis):
Claims 1 recites:
selecting a set of biological processes; (which is a mental step, i.e. can be performed with pen and paper)
selecting a training dataset and a validation dataset, each dataset comprising a set of genome data and clinical outcomes; (mental step)
grouping a set of mutations into groups each corresponding to a biological process of the set of biological processes; (mental step)
generating a set of classifiers, each comprising a combination of mutations, to predict a clinical outcome from one of the groups of mutations; (mathematical process of a mathematical calculation)
training the set of classifiers on the training dataset; (mathematical calculation)
calculating, with the validation dataset, a performance level of each classifier in the set of classifiers; (mathematical calculation)
calculating, on a test dataset comprising genome data of a subject, a predicted clinical outcome from a medical treatment on a subject based on a subset of the set of classifiers having a high performance level on the validation dataset; and… (mathematical calculation)
Claim 2 states: the step of generating the set of classifiers comprises a Greedy forward feature selection algorithm. (mathematical calculation)
Claim 3 states: the step of generating the set of classifiers comprises a randomized forward feature selection algorithm (mathematical calculation)
Claim 4 states: the step of generating the set of classifiers comprises a genetic algorithm. (mathematical calculation)
Claim 5 states: the step of generating the set of classifiers comprises a random forest algorithm. (mathematical calculation)
Claim 6 states: the step of generating the set of classifiers comprise a gradient boosted tree. (mathematical calculation)
Claim 7 states: at least one classifier of the set of classifiers comprises a Forward Neural Network model. (mathematical calculation)
Claim 8 states: at least one classifier of the set of classifiers comprises a Long Short-Term Memory Recurrent Neural Network model (mathematical calculation)
The claims recite an abstract idea of analyzing genomic data (See MPEP 2106.07(a)).
These recitations are similar to the concepts of collecting information, analyzing it and displaying certain results of the collection and analysis in Electric Power Group, LLC, v. Alstom (830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016)), organizing and manipulating information through mathematical correlations in Digitech Image Techs., LLC v Electronics for Imaging, Inc. (758 F.3d 1344, 111 U.S.P.Q.2d 1717 (Fed. Cir. 2014)) and comparing information regarding a sample or test to a control or target data in Univ. of Utah Research Found. v. Ambry Genetics Corp. (774 F.3d 755, 113 U.S.P.Q.2d 1241 (Fed. Cir. 2014)) and Association for Molecular Pathology v. USPTO (689 F.3d 1303, 103 U.S.P.Q.2d 1681 (Fed. Cir. 2012)) that the courts have identified as concepts that can be practically performed in the human mind or mathematical relationships. Therefore, these limitations fall under the “Mental process” and “Mathematical concepts” groupings of abstract ideas.
While claims 1-16 recite performing some aspects of the analysis using a “model”, there are no additional limitations that indicate that this model requires anything other than carrying out the recited mental process or mathematical concept in a generic computer environment. Merely reciting that a mental process is being performed in a generic computer environment does not preclude the steps from being performed practically in the human mind or with pen and paper as claimed. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then if falls within the “Mental processes” grouping of abstract ideas. As such, claim(s) 1-16 recite(s) an abstract idea/law of nature/natural phenomenon (Step 2A, Prong 1: YES).
Step 2A, Prong 2
Claims found to recite a judicial exception under Step 2A, Prong 1 are then further analyzed to determine if the claims as a whole integrate the recited judicial exception into a practical application or not (Step 2A, Prong 2). This judicial exception is not integrated into a practical application because the claims do not recite an additional element that reflects an improvement to technology or applies or uses the recited judicial exception to affect a particular treatment for a condition. Rather, the instant claims recite additional elements that amount to mere instructions to implement the abstract idea in a generic computing environment or mere instructions to apply the recited judicial exception via a generic treatment. Specifically, the claims recite the following additional elements:
Claim 1 states: …treating the subject based on the predicted response to the medical treatment
In order to qualify as a "treatment" or "prophylaxis" limitation, the claim limitation in question must affirmatively recite an action that effects a particular treatment or prophylaxis for a disease or medical condition. An example of such a limitation is a step of "administering amazonic acid to a patient" or a step of "administering a course of plasmapheresis to a patient." If the limitation does not actually provide a treatment or prophylaxis, e.g., it is merely an intended use of the claimed invention or a field of use limitation, then it cannot integrate a judicial exception under the "treatment or prophylaxis" consideration. For example, a step of "prescribing a topical steroid to a patient with eczema" is not a positive limitation because it does not require that the steroid actually be used by or on the patient, and a recitation that a claimed product is a "pharmaceutical composition" or that a "feed dispenser is operable to dispense a mineral supplement" are not affirmative limitations because they are merely indicating how the claimed invention might be used. See MPEP 2106.04(d)(2). As such, claims 1-16 are directed to an abstract idea (Step 2A, Prong 2: NO).
Step 2B
Claims found to be directed to a judicial exception are then further evaluated to determine if the claims recite an inventive concept that provides significantly more than the judicial exception itself (Step 2B). The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that do not actually provide a treatment or prophylaxis. The instant claims recite the following additional elements:
Claim 1 states: …treating the subject based on the predicted response to the medical treatment
As discussed above, there are no additional limitations to indicate a particular treatment for a particular disease. See MPEP 2106.04(d)(2).
Additionally, the claims are directed to well-understood, routine, and conventional activity as evidenced by Stern et al. (Open Biol. 2018 May;8(5):180031.), who teaches prediction of response to drug therapy in psychiatric disorders.
The additional elements do not comprise an inventive concept when considered individually or as an ordered combination that transforms the claimed judicial amount to significantly more than the judicial exception itself (Step 2B: No). As such, claims 1-16 is/are not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, and 5-9 are are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Nike T. Beaubier et al. (US11367508B2) as evidenced by Khan et al. (Artif Intell Rev 53, 5455–5516 (2020).)
References to claim limitations will be italicized.
Regarding claims 1 and 9, “high performance level” is interpreted as an AUC of at least 0.80.
Regarding claims 1 and 9, Beaubier et al. teaches systems methods and compositions to determine cellular pathway disruption, including computational embodiments as disclosed in the specification (“The process 502 can be implemented as computer readable instructions…”) and including methods to discover pathway signatures that predict treatment response and disease outcomes (Spec, “Uses of Systems and Methods”: “…the systems and methods discover integrative, multi-omic pathway signatures that predict treatment response and disease outcomes…, re: clm. 1, …A method of predicting a response to a medical treatment in a subject…clm. 9, … A system for predicting a response to a medical treatment in a subject, comprising a non- transitory computer-readable medium with instructions stored thereon, which when executed by a processor perform steps comprising)
Beaubier et al. further teaches the section of a pathway from a database (Spec, “For example, the pathway selected may be the RTK/RAS pathway…, Fig 1. Illustrates signaling pathways; re: clm. 1, … selecting a set of biological processes…clm. 9, … selecting a set of biological processes from a database of biological processes…)
Beaubier et al. further discloses in the specification machine learning models and further details in the specification and in Fig. 2B an embodiment in which “Training data for the pathway disruption models includes transcriptomic data and may further include genomic data… Training data and/or biological validation data…may further include structured clinical or organoid data, including any evidence of a therapy slowing the growth of cancer in a patient or tumor organoid…”. Beaubier et al. additionally discloses in the spec that computer-readable media includes computer storage and communication media (re: clm. 1, … selecting a training dataset and a validation dataset, each dataset comprising a set of genome data and clinical outcomes…, clm. 9, … storing a training dataset and a validation dataset on the non-transitory computer-readable medium, each dataset comprising a set of genome data and clinical outcomes).
Beaubier et al. further discloses in Fig. 1B grouping mutations and genes by color group, stating in a description in the specification: “The color codes illustrate the different functional components of the pathways, meaning that a mutation in any gene in a color group could be predicted to have the same effect on pathway function as a mutation in another gene in the same color group.” (re: clm. 1, 9 … grouping a set of mutations into groups each corresponding to a biological process of the set of biological processes…)
Beaubier et al. further teaches pathway disruption engines, which comprise a plurality of trained machine learning models (clm. 1), and further discloses in the specification that “A patient data store…may include…a collection of features available for every patient…in the system. These features…may be used to generate the artificial intelligence classifiers (for example, pathway engines 200 n) in the system.”
Beaubier et al. additionally states in the specification specific machine learning predictive models the pathway engines are comprised of, and states they may be used to predict clinical outcomes, stating:
“The system 10 may comprise one or more data inputs 100, one or more pathway engines 200, …Data inputs 100 may comprise transcriptome value sets and one or more dysregulation indicators (as described in FIG. 4). Data inputs 100 may further comprise DNA variant data, methylation data, cancer type, and/or proteomics data.”,
“In various embodiments, pathway engine 200 n predicts pathway disruption status based on RNA data. In various embodiments, pathway engine 200 n comprises a predictive model. In various embodiments, pathway engine 200 n comprises a support vector machine, random forest, and/or k-nearest neighbor model. In some embodiments, pathway engine 200 n comprises a logistic regression model…” (re: clm. 1, 9, … generating a set of classifiers, each comprising a combination of mutations…)
“The pathway disruption score(s) may be used to determine a degree of confidence in predicting a particular treatment response based on clinical data and/or therapy response data associated with other generated pathway disruption scores…” (re: clm. 1, 9, … to predict a clinical outcome…), and,
Grouping of variants (
(“At 756, the process 750 can label samples as positive samples or negative samples and/or remove samples from the sample group based on the variants, the VAF, and the LOR of the copy number of each gene in the sample.”) And
(“…the degree of dysregulation caused by a nucleic acid variant can be indicated by classifying a variant or set of variants in the module as…” [in Multi-Gene Modules, Pathways]) re: clm. 1, 9, … from one of the groups of mutations…))
Therefore, Beaubier et al. teaches generating a set of classifiers using groups of mutations to predict clinical outcomes (re: clm. 1, 9, … generating a set of classifiers, each comprising a combination of mutations, to predict a clinical outcome from one of the groups of mutations…)
Beaubier et al. further teaches in claim 2 that the machine learning models (classifiers) used in pathway modules are trained with the training data (clm. 2, re: clm. 1, 9, … training the set of classifiers on the training dataset…)
Beaubier et al. further discloses cross-validation of pathway engines in the specification (“In one example, at 610, the process 602 may perform optional cross-validation of the pathway engine…”) in which data (which may be transcriptome data) is split such that a portion is used for training and validation for the generation of a precision score (Spec, re: clm. 1, 9, … calculating, with the validation dataset, a performance level of each classifier in the set of classifiers…)
Beaubier et al. further teaches pathway engines with an AUC of 90% in the specification and in Fig. 17C (“A logistic regression model…using DEGs…separates STK11 (FIGS. 17C-D) mutation carriers from pathway WT groups.”), stating:
“The final models (pathway engines) for both RAS (KRAS, HRAS, NRAS) and PI3K (PIK3CA and PIKCB) disruption were statistically powerful, with AUCs greater than or equal to ≈0.84. In one example, the AUC was 0.90.”
As stated above, the applicant’s specification defines a classifier with a “high performance level” as “at least 90% of the training performance” in the specification. Beaubier et al. further discloses in Fig. 12A that the pathway engines may be used with genomic data and are used to predict treatment efficacy via the output of pathway disruption scores, which are related to treatments, as Beaubier states in the specification (“The pathway disruption score(s) may be used in the development of models for the prediction of patient outcome/treatment response.”).
Beaubier et al. further teaches in the specification an exemplary process that can select an alpha parameter to train a pathway engine “…and determine the performance of the trained pathway engine”. Beaubier et al. therefore teaches validation of classifiers within said pathway engines disclosed (re: clm. 1, 9, … calculating, on a test dataset comprising genome data of a subject, a predicted clinical outcome from a medical treatment on a subject based on a subset of the set of classifiers having a high performance level on the validation dataset).
Beaubier et al. further teaches treating a patient via embodiment 153-154 and further teaches treatments in the specification (“In some embodiments, the methods include treating the subject pursuant to the recommended therapeutic/treatment regimen. In some embodiments, a recommended treatment includes administering to the subject an effective amount of one or more of the compounds listed in FIGS. 26A-27P or FIGS. 27Q-V…” (re: clm. 1, 9, … treating the subject based on the predicted response to the medical treatment.).
Beaubier et al. teaches a method using genomic data to predict treatment efficacy in anticipation of claims 1 and 9.
Regarding claims 5 and 13, Beaubier teaches in the specification “In various embodiments, pathway engine 200 n comprises a support vector machine, random forest…” in anticipation of claim 5 (re: clm. 5, 13, … wherein the step of generating the set of classifiers comprises a random forest algorithm.)
Regarding claims 6 and 14, Beaubier et al. teaches in the specification “The above referenced models may be implemented as artificial intelligence engines and may include gradient boosting models…[machine learning algorithms] include supervised algorithms (such as algorithms where the features/classifications in the data set are annotated) using linear regression, logistic regression, decision trees…” (re: clm. 6, 14, … wherein the step of generating the set of classifiers comprise a gradient boosted tree.). Beaubier et al. teaches a gradient boosting model in anticipation of claims 6 and 14.
Regarding claims 7 and 15, Beaubier et al. teaches a forward neural network due to the inherency of a convolutional neural network which Beaubier et al. teaches in the specification (see MPEP 2112 IV).
Beaubier et al. teaches embodiments in which trained pathway disruption engines “…include one or more machine learning models or neural networks.” Beaubier et al. teaches “NNs include conditional random fields, convolutional neural networks, attention based neural networks…” A convolutional neural network is a feed forward neural network as evidenced by Khan et al, pg. 5456 (re: clm. 7, 15 … wherein at least one classifier of the set of classifiers comprises a Forward Neural Network model.).
Therefore, Beaubier et al. teaches a forward neural network model in anticipation of claims 7 and 15.
Regarding claims 8 and 16, Beaubier et al. teaches in the specification “NNs include conditional random fields, convolutional neural networks, attention based neural networks, deep learning, long short term memory networks, or other neural models where the training data set includes a plurality of tumor samples, RNA expression data for each sample, and pathology reports covering imaging data for each sample.” (re: clm. 8, 16… wherein at least one classifier of the set of classifiers comprises a Long Short-Term Memory Recurrent Neural Network model). Beaubier et al. teaches a long short term memory network in anticipation of claims 8 and 16.
Claim Rejections - 35 USC § 103
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.
Claim(s) 2-4, and 10-12 are rejected under 35 U.S.C. 103 as being unpatentable over Beaubier et al. as evidenced by Khan et al. as applied to claims 1, and 5-9 above in view of Rudolf Jagdhuber et al. (BMC Bioinformatics 21, 26 (2020).).
Beaubier et al. as evidenced by Khan et al. is applied to claims 1, and 5-9 above.
Regarding claims 2-4, and 10-12 Beaubier et al. teaches generating a set of classifiers (re: clm. 2, 4, 10, 12 … the step of generating the set of classifiers…), but does not teach:
a Greedy forward feature selection algorithm (re: clm. 2, 10, … generating the set of classifiers comprises a Greedy forward feature selection algorithm.),
nor a randomized forward feature selection algorithm (re: clm. 3, 11, … a randomized forward feature selection algorithm.),
nor a genetic algorithm (re: clm. 4, 12, … generating the set of classifiers comprises a genetic algorithm.).
Jagdhuber et al. teaches a Greedy forward feature selection algorithm (Abstract, Adaptations of greedy forward selection, Methods, pg. 1-3, re: clm. 2, 10, a Greedy forward feature selection algorithm),
a randomized forward feature selection algorithm (which additionally includes, At every step, the option of return with a user defined probability [pStop]; pg. 5-6, “For this purpose, we propose a random forward selection approach…”, Algorithm 2, re: clm. 3, 11, … a randomized forward feature selection algorithm.),
and a genetic algorithm (pg. 3-5, Adaptations on genetic algorithms, Methods, re: clm. 4, 12, … generating the set of classifiers comprises a genetic algorithm.)
Jagdhuber et al. does not teach generating a set of classifiers (re: clm. 2, … The method of claim 1, wherein the step of generating the set of classifiers …)
In KSR Int 'l v. Teleflex, the Supreme Court, in rejecting the rigid application of the teaching, suggestion, and motivation test by the Federal Circuit, indicated that “The principles underlying [earlier] cases are instructive when the question is whether a patent claiming the combination of elements of prior art is obvious. When a work is available in one field of endeavor, design incentives and other market forces can prompt variations of it, either in the same field or a different one. If a person of ordinary skill can implement a predictable variation, § 103 likely bars its patentability.” KSR Int'l v. Teleflex lnc., 127 S. Ct. 1727, 1740 (2007).
Applying the KSR standard of obviousness to Beaubier et al. and Jagdhuber et al., the examiner concludes that the combination of the systems methods and compositions to determine cellular pathway disruption as disclosed by Beaubier et al. with the Greedy forward feature selection algorithm and genetic algorithm as disclosed by Jagdhuber et al. represents a finding that there was some teaching, suggestion, or motivation, either in the references themselves or in the knowledge generally available to one of ordinary skill in the art, to modify the reference or to combine reference teachings.
One of ordinary skill in the art of medical bioinformatics and genomics would be motivated to combine the teachings of Beaubier et al. and Jagdhuber et al. because the combination would lead to a stronger treatment response prediction method. In support of this motivation, Jagdhuber et al. states their art aims to alleviate cost-burden on biomarker testing, stating in their abstract:
“Feature selection is a widely researched preprocessing step to handle huge numbers of biomarker candidates and has special importance for the analysis of biomedical data. Such data sets often include many input features not related to the diagnostic or therapeutic target variable. A less researched, but also relevant aspect for medical applications are costs of different biomarker candidates. These costs are often financial costs, but can also refer to other aspects, for example the decision between a painful biopsy marker and a simple urine test. In this paper, we propose extensions to two feature selection methods to control the total amount of such costs: greedy forward selection and genetic algorithms.” (Abstract, pg. 1).
In additional support, the applicant’s specification discloses application of algorithms “alone or in combination” (para. 0068 ) including those disclosed in Jagdhuber et al., stating: “It was therefore reasoned that greedy feature selection strategy impaired generalization by converging into local optimum. As such, randomized forward feature selection was employed…” (para 0073), and discloses descriptions of said algorithms as applied to biological processes (para. 0094-0096)
There would have been a reasonable expectation of success because the methods of both arts exist in the same field of the invention. In support of this expectation, the Applicant’s specification states on paragraph 0073 the use of both a greedy forward feature selection and genetic algorithm (Spec, para. 0073). Additionally, Beaubier et al. describes the application of machine learning models to detect cellular pathway dysregulation in cancer specimens (Beaubier et al. Specification), and Jagdhuber et al. references cancer datasets in their analysis on pg. 8 and 9.
One skilled in the art of medical bioinformatics and genomics could reasonably apply the algorithms Jagdhuber et al. teaches to the features within the data (inclusive of multi-omic signatures as Beaubier et al. states in the specification) Beaubier et al. obtains from cancer specimens. Therefore, claims 2-4, and 10-12 of the applicant’s invention would have been prima facie obvious to one of skill in the art at the time of filing of the application, absent evidence to the contrary.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN T STUBBS whose telephone number is (571)272-0340. The examiner can normally be reached M-F 8-5 EST.
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, Larry Riggs can be reached at 571-270-3062. 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.T.S./Examiner, Art Unit 1686
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights