DETAILED ACTION
This action is in reference to the communication filed on 24 AUG 2026.
Amendments to claims 1, 15, 26, entered and considered, as is the cancellation of claims 9, 22, 33.
Claims 1-8, 10-21, 23-32, 34-36 pending and examined.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-8, 10-21, 23-32, 34-36 rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. As explained below, the claim(s) are directed to an abstract idea without significantly more.
Step One: Is the Claim directed to a process, machine, manufacture or composition of matter? YES
With respect to claim(s) 1-8, 10-21, 23-32, 34-36 the independent claim(s) 1, 15, 26 recite(s) a method, a system, and a computer readable media, each of which is a statutory category of invention.
Step 2A – Prong One: Is the claim directed to a law of nature, a natural phenomenon (product of nature) or an abstract idea? YES
With respect to claim(s) 1-8, 10-21, 23-32, 34-36, the independent claim(s) (claims 1, 15, 26 ) is/are directed, in part, to:
A
given peptide sequence and binding value pair data set comprises peptide sequence information and peptide binding values of one or more antibodies to one or more peptides that comprises the peptide sequence information which antibodies are form a sample obtained from a given reference subject n the population and which antibodies are indicative of one or more disease states, thereby obtaining a final set of weight and bias values of
applying a clustering algorithm to the final set of weight and bias values of the wherein the disease map comprises clusters of the disease states represented in a two or more dimensional space , and;
determining whether a test subject has at least one of the disease states using a peptide sequence and binding value pair data set obtained from the test subject and the trained electronic neural network and/or the disease map.
These claim elements are considered to be abstract ideas because they are directed to mathematical concepts including relationships, formulas, equations or calculations. Applying a “clustering algorithm” to weights and bias values from an existing trained neural network, is categorically an example of such mathematical concepts. Examiner finds that the limitations regarding the prior training of the algorithm are descriptive of the data in general.
Examiner also finds that the claims recite examples of mental processes, such as concepts performed in the human mind including observation, evaluation, judgement, and opinion. Examiner notes that while the limitations read “clustering algorithm,” to be applied to a set of data about disease and/or populations, to create a risk map, no specific algorithm is explicitly disclosed. As such, Examiner find that considering the relationships between a set of data about disease and population(s) to create a risk map is, to be broadly at least, an example of observations of data, evaluating the data, and presenting the opinion in the form of the risk map.
If a claim limitation, under its broadest reasonable interpretation, covers mathematical relationships, formulas, equations, and/or calculations, then it falls within the “mathematical concepts” grouping of abstract ideas. If a claim limitation falls into concepts performed in the human mind, then I falls within the “mental processes” category of abstract ideas. Accordingly, the claims recite an abstract idea.
Step 2A – Prong Two: Does the claim recite additional elements that integrate the judicial exception into a practical application? NO.
This judicial exception is not integrated into a practical application. In particular, the claim(s) recite(s) additional elements: Claim 1 recites that the method is “computer implemented,” claim 15 – “a system comprising a processor, a memory communicatively coupled ” and claim 26 recites “ a computer readable media comprising non- transitory computer executable instructions, executed by at least one processor” to perform the claim steps. Claims 1, 15, 26 also recite the active “training” of an “electronic neural network.” Examiner finds that the processors and memory/media in claims 15, 26, and by extension/BRI, the computer in claim 1, are all recited at a high level of generality and as such amount to no more than adding the words “apply it” to the judicial exception, or mere instructions to implement the abstract idea on a computer, or merely uses the computer as a tool to perform the abstract idea (see MPEP 2106.05f), or generally links the use of the judicial exception to a particular technological field of use/computing environment (see MPEP 2106.05h). Examiner finds similarly with respect to training of the neural network as claimed – the neural network and the training therein are “applied” to the abstract idea(s). Examiner notes that the claim itself, as well as the specification, appear to be more focused on the descriptive aspects of the training set rather than the training process itself. Examiner finds no improvement to the functioning of the computer or any other technology or technical field in the elements identified above, including the computing elements, the training of the neural network(s), nor the use of the neural networks as claimed (see MPEP 2106.05a), nor any other application or use of the judicial exception in some meaningful way beyond a general like between the use of the judicial exception to a particular technological environment (see MPEP 2106.05e).
Accordingly, this/these additional element(s) do(es) not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? NO.
The independent claim(s) is/are additionally directed to claim element: Claim 1 recites that the method is “computer implemented,” claim 15 – “a system comprising a processor, a memory communicatively coupled ” and claim 26 recites “ a computer readable media comprising non- transitory computer executable instructions, executed by at least one processor.” Claims 1, 15, 26 also recite the active “training” of an “electronic neural network.” When considered individually, the identified claim elements only contribute generic recitations of technical elements to the claims. It is readily apparent, for example, that the claim is not directed to any specific improvements of these elements. Examiner looks to Applicant’s specification in:
[0043] In some embodiments, the one or more electronic neural networks could include a feedforward neural network. In such embodiments, the electronic neural networks could be trained using back propagation, as is known in the technical field. In some embodiments, the machine learning system could be trained on a subset of the peptide sequence and binding paired data and the resulting machine learning system and/or individual machine learning models thereof could then be validated on the remaining subset of the peptide data, as is known in the technical field.
[0050] Computer 201 may be implemented as any of a desktop computer, a laptop computer, can be incorporated in one or more servers, clusters, or other computers or hardware resources, or can be implemented using cloud-based resources. Computer 201 includes volatile memory 214 and persistent memory 212, the latter of which can store computer-readable instructions, that, when executed by electronic processor 210, configure computer 201 to perform any of the methods disclosed herein, including method 100, and/or form or store any electronic neural network, and/or perform any classification technique as described herein. Computer 201 further includes network interface 208, which communicatively couples computer 201 to training corpus source 202 via network 204. Other configurations of system 200, associated network connections and other hardware, software, and service resources are possible.
[0051] The computer programs can exist in a variety of forms both active and inactive. For example, the computer programs can exist as software program(s) comprised of program instructions in source code, object code, executable code or other formats; firmware program(s), or hardware description language (HDL) files. Any of the above can be embodied on a transitory or non-transitory computer readable medium, which include storage devices and signals, in compressed or uncompressed form. Exemplary computer readable storage devices include conventional computer system RAM (random access memory), ROM (read-only memory), EPROM (erasable, programmable ROM), EEPROM (electrically erasable, programmable ROM), and magnetic or optical disks or tap.
[0056] Recently, our group used an unbiased approach to develop sequence-based predictive models for the binding data of nine different, well-characterized isolated proteins to the peptide arrays described above. Binding patterns of each protein were recorded, and a simple feed-forward, back propagation neural network (NN) model was used to relate the amino acid sequences on the array to the binding values. Remarkably, it was possible to train the network with 90% of the sequence/binding value pairs and predict the binding of the remaining sequences with accuracy equivalent to the noise in the measurement (the Pearson correlation coefficients (R) between the observed and predicted binding values were equivalent to that between measured binding values of multiple technical replicates, and in some cases as high as R=0.99). In fact, accurate binding predictions (R>0.9) for some protein targets could be achieved by training on as little as a few hundred randomly chosen sequence/binding value pairs from the array. In addition, the binding predictions were specific; the neural networks captured not only the bulk binding of individual proteins but the differential binding between proteins.
[0062] The encoder vectors for each amino acid in the sequence were then concatenated together in the same order as the sequence. A feed-forward, back-propagation neural network was then trained on a fraction of the peptide sequence/binding value pairs and the resulting model was used to predict the binding value of the remaining peptide sequences not involved in the training (the test set). An L2 loss function (sum of squared error) was used for the training. The model performance was assessed by calculating the Pearson correlation coefficient between the measured and predicted binding values in the test dataset. Unless otherwise stated, the neural networks used in this work were trained on all samples simultaneously (the output layer and target matrix each consisted of a number of columns equal to the number of different samples, so for every sequence input, one value was predicted for each sample).
These passages, as well as others, makes it clear that the invention is not directed to a technical improvement. When the claims are considered individually and as a whole, the additional elements noted above, appear to merely apply the abstract concept to a technical environment in a very general sense – i.e. a generic computer receives information from another generic computer, processes the information and then sends information back. The most significant elements of the claims, that is the elements that really outline the inventive elements of the claims, are set forth in the elements identified as an abstract idea. The fact that the generic computing devices are facilitating the abstract concept is not enough to confer statutory subject matter eligibility.
As per dependent claims 2-8, 10-14, 16-21, 23-25, 27-32, 34-36:
Dependent claims 6, 20 recite specific clustering algorithms. Examiner finds that the algorithms themselves are a further recitation of the mathematical concepts as identified above with respect to claims 1, 15, 26. In the interest of compact prosecution, Examiner notes that these algorithms do not provide a practical application nor significantly more than the abstract idea(s) identified above. No improvement to the functioning of the computer or anything pertaining to the algorithms themselves is noted. Instead, the specification appears to rely on the known existence of said algorithms as clustering algorithms, and further relies on their known capabilities and application therein. As such these claims are not found to recite significantly more.
Dependent claims 2-5, 7-14, 16-19, 21-25, 27-30, 32- 36 are not directed any additional abstract ideas and are also not directed to any additional non-abstract claim elements. Rather, these claims offer further descriptive limitations of elements found in the independent claims and addressed above – such as the calculations, the weights, the outcomes, and the variables, as well as generating a therapy and different elements regarding the map itself as created per the clustering. While these descriptive elements may provide further helpful context for the claimed invention these elements do not serve to confer subject matter eligibility to the invention since their individual and combined significance is still not heavier than the abstract concepts at the core of the claimed invention.
Non-Obvious Subject Matter
Claims 1-36 are believed to be free from the prior art.
The closest prior art is believed to be:
US20170103172, to Fink et al: discloses a means of generating a disease map using a differential equation means of modeling in order to determine the risk of a disease spreading over a given population. The modeling is specifically executed using a neural network model in order to provide temporal mapping and development of the map over a plurality of levels of granularity and scale.
US20200294680, to Gupta et al: discloses a means of mapping and predicting the spread of an infectious disease, using a model and applying it to a given population. Using machine learning and AI, the reference can use the disease mapping to predict and create an appropriate response to the threat of spread using the actual magnitude of the risk to a given location/population.
US10573003, to Sethi: discloses a pre-trained machine learning model such as a penalized logistic regression model which is used to classify infectious diseases locally and as compared to a point of interest. The pre-trained model is trained to reduce the difference between the classifier output and the “known” or actual rate of infection/spread in a given area. This information is used the quantify the extent of the risk of the spread for future modeling. Sethi further teaches the use of a clustering algorithm for the purposes of mapping.
US20140087963 to Johnston et al: discloses a means of using a peptide sequencing/binding values process to train a regressor, and wherein the peptide sequence/binding data and values are used to represent a plurality of conditions.
US20040153249, to Zhang et al, also teaches a means of using peptide sequencing to train a modeling process to be used in disease prediction methods.
US 10140835, to Padhye: uses vector mapping and a predictive algorithm in order to determine the risk of spread of the vectors transporting the disease itself, thereby mapping the risk of the spread by mapping vectors over a given area rather than the specific spread of the disease itself. Historical machine learning techniques are used to make these predictions of vector movement.
US20210319847, to Min: discloses a neural network trained on data comprising peptide binding property predictors, using the positive bonding sequences only as this allows for optimized training. A discriminator is used to update the training data to represent the sampled positive peptide sequences. An encoding vector may be used to represent the training sequences themselves. Min further teaches that the inputs to the training process may be weighed based on the connection between pairs.
However, the cited references when taken separately or in any combination, does not specifically teach applying a clustering algorithm to the weights and bias values of the neural network, and specifically does not teach the specific training of the neural network as claimed, wherein the sequence and the binding value pair data comprise sequence/binding values of one or more antibodies to the peptides, from a reference subject with antibodies. Simplified, Examiner finds that the means through which the neural network is trained for the predictive clustering is not fairly taught in the references, particularly in view of the specific peptide sequence information and peptide binding values as applied to the one or more antibodies.
The Examiner hereby asserts that the totality of the evidence neither anticipates nor renders obvious the particular combination of elements as claimed. That is, the Examiner emphasizes the claims as a whole and hereby asserts that the totality of the evidence fails to set forth, either explicitly or implicitly, an appropriate rationale for combining or otherwise modifying the available prior art to arrive at the claimed invention. The combination of features as claimed would not be obvious to one of ordinary skill in the art because any combination of the evidence at hand to reach the combination of features as claimed would require a substantial reconstruction of Applicant’s claimed invention relying on improper hindsight bias.
Response to Arguments
Applicant’s remarks as filed on 24 AUG 2026 have been fully considered. Examiner notes these remarks were files with the Response After Final Action on 24 AUG 2026.
Applicant discusses the claim amendments and related support on page 9/10 of the remarks. Examiner appreciates the references to the appropriation portions of the specification.
Applicant begins a discussion of the rejection under 35 USC 101 on page 11, making reference to newly amended training limitation in claim 1. Examiner notes the training limitation is now addressed in the additional elements portion of the analysis as noted above. Examiner respectfully disagrees with Applicant’s analogy to Enfish- the training itself does not appear to recite a technical improvement analogous to the improvement found in the self-referential table. Similarly, Examiner does not find any improvement analogous to McRO in which the claims automated a task previously only a human could perform.
As per Step 2A Prong 2, Examiner respectfully disagrees with Applicant’s characterization of the rejection. Examiner does not find the claim language specifically provides for noise reduction/information aggregation. As per point 2, Examiner finds that detection of unknown disease states may in fact be accomplished using the technical solution presented in the claims, however, the detection itself is not on its face a technical problem. As per point 3, Applicant reiterates the order of the combination as evidence of a technical solution, however, Examiner does not find an actual explanation as to what exactly said improvement is. Examiner does not find that the claims recite an improvement in the functioning of the computer itself. As noted in the rejection above, Examiner finds that the majority of the independent claim is focused on description of the training set characteristics rather than the training process itself.
Applicant turns to a discussion of step 2b/significantly more on page 12. Applicant’s remarks regarding an improvement are again found unpersuasive as any improvements represented by the claimed invention are found in population disease maps/mapping. Again, Examiner notes that there is no improvement to the NN or any other technical elements/technologies in the claim, instead, any improvements are found to non-technical areas, using existing technology. Portions of the specification as cited above discuss that the training occurs through back propagation as is “standard in the art.”
Applicant discusses the prior art on page 13. Examiner notes that prior art/novelty is a separate inquiry from subject matter eligibility. Per MPEP 2106.05d: “The question of whether a particular claimed invention is novel or obvious is "fully apart" from the question of whether it is eligible. Diamond v. Diehr, 450 U.S. 175, 190, 209 USPQ 1, 9 (1981).” Examiner notes that the prior art discussion of the action in no way references an “improvement” per se. Further, the improvement itself must be technical in nature – “In determining patent eligibility, examiners should consider whether the claim "purport(s) to improve the functioning of the computer itself" or "any other technology or technical field." Alice Corp. Pty. Ltd. v. CLS Bank Int’l, 573 U.S. 208, 225, 110 USPQ2d 1976, 1984 (2014).
Examiner notes again that the final limitation is still written to conclude in the alternate, wherein the pair value data set is not even required to have been obtained from the NN, and instead could just be from the disease map itself.
Applicant’s remarks regarding the remaining dependent claims are found unpersuasive for the reasons discussed above with respect to the independent claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KATHERINE KOLOSOWSKI-GAGER whose telephone number is (571)270-5920. The examiner can normally be reached Monday - Friday.
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, Mamon Obeid can be reached at 571-270-1813. 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.
/KATHERINE . KOLOSOWSKI-GAGER/
Primary Examiner
Art Unit 3687
/KATHERINE KOLOSOWSKI-GAGER/Primary Examiner, Art Unit 3687
Prosecution Insights