DETAILED ACTION
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 7/1/2026 has been entered.
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 .
Priority
The instant application does not claim the benefit of priority to any earlier filed applications. As such, the effective filing date of claims 1-18, and 21-22 is 02/16/2022.
Claim Status
Claims 1-18, and 21-22 are pending.
Claims 19-20 are cancelled.
Claims 1-18, and 21-22 are rejected.
Withdrawn Rejections/Objections
The objection to the specification in the Office Action mailed 9/15/2025 is withdrawn in view of the amendments filed 12/15/2025.
The objection to the drawings in the Office Action mailed 9/15/2025 is withdrawn in view of the amendments filed 12/15/2025.
Claim Rejections - 35 USC § 101
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 101 have been reviewed, updated, and provided below. Previous rejections of claims 15-20 as being non-statutory are withdrawn.
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-18, and 21-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract ideas without significantly more. The claims recite a method for segmenting and labeling an amino acid sequence during single molecule sequencing. The judicial exception is not integrated into a practical application because while claims 1-18, and 21-22 attempt to integrate the exception into a practical application, said application is either generically recited computer elements that do not add a meaningful limitation to the abstract idea or it is insignificant extra solution activity and merely implementing the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the computer elements only store and retrieve information in memory as well as perform basic calculations that are known to be well-understood, routine and conventional computer functions as recognized by the decisions listed in MPEP § 2106.05(d).
Framework with which to Analyze Subject Matter Eligibility:
Step 1: Are the claims directed to a category of stator subject matter (a process, machine, manufacture, or composition of matter)? [See MPEP § 2106.03]
Claims are directed to statutory subject matter, specifically a method (Claims 1-7, and 21-20), an apparatus (Claims 8-14), and a CRM (Claims 15-18).
Step 2A Prong One: Do the claims recite a judicially recognized exception, i.e., an abstract idea, a law of nature, or a natural phenomenon? [See MPEP § 2106.04(a)]
The claims herein recite abstract ideas, specifically mental processes and mathematical concepts.
With respect to the Step 2A Prong One evaluation, the instant claims are found herein to recite abstract ideas that fall into the grouping of mental processes and mathematical concepts.
Claim 1: Segmenting the training signal, determining signal characteristics, and generating an HMM signal to segment and label a signal are processes of grouping, classifying, and calculating that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes. Additionally generating an HMM signal to segment and label a signal is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 2: Determining probabilities that signal characteristics correspond to events is a process of calculating values which can be done with pen and paper or in the human mind and is therefore an abstract idea, specifically a mental process. Additionally, determining probabilities that signal characteristics correspond to events are verbal articulations of a mathematical processes and are thus abstract ideas, specifically mathematical concepts.
Claim 3: Assigning probabilities to each HMM node and edge is a process of classifying that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes.
Claim 4: Applying a Viterbi algorithm to the HMM and segmenting the signal is the application of a way of thinking which is an abstract idea, specifically a mental process. Additionally, applying a Viterbi algorithm to the HMM and segmenting the signal are verbal articulations of a mathematical processes and are thus abstract ideas, specifically mathematical concepts.
Claim 5: Estimating a likelihood that the signal characteristics correspond to events based on probabilities is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 8: Segmenting the training signal, determining signal characteristics, determine a first set of event labels, and generating an HMM signal to segment and label a signal are processes of grouping, classifying, training, and calculating that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes. Additionally generating an HMM signal to segment and label a signal is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 9: Determining that a single characteristic corresponds to an individual event is a process of classifying that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes.
Claim 10: Assigning probabilities to each HMM node and edge is a process of classifying that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes.
Claim 11: Applying a Viterbi algorithm to the HMM and segmenting the signal is the application of a way of thinking which is an abstract idea, specifically a mental process.
Claim 12: Estimating a likelihood that the signal characteristics correspond to events based on probabilities is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 13: The training signal including signal noise selected from the specified group is merely limiting the information/data we are using which is itself an abstract idea, specifically a mental process.
Claim 14: The training signal including known amino acid sequences and unknown amino acid sequences is merely limiting the information/data we are using which is itself an abstract idea, specifically a mental process.
Claim 15: Segmenting the training signal, determining signal characteristics, determining a first set of event labels, generating an HMM signal to segment and label a signal are processes of grouping, classifying, and calculating that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes. Additionally generating an HMM signal to segment and label a signal is a verbal articulation of a mathematical process and is therefore an abstract idea, specifically a mathematical concept.
Claim 16: Determining that a single characteristic corresponds to an event is a process of classifying that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes.
Claim 17: Assigning probabilities to each HMM node and edge is a process of classifying that can be done with a pen and paper or in the human mind and are therefore abstract ideas, specifically mental processes.
Claim 18: Applying a Viterbi algorithm to the HMM and segmenting the signal is the application of a way of thinking which is an abstract idea, specifically a mental process.
Claim 21: Assigning a monomer identity corresponding to an event and updating model parameters are processes of identifying and calculating information that can be done via pen and paper or within the human mind and are therefore abstract ideas, specifically mental processes.
Claim 22: The signal comprising the specified measurements and the characteristics corresponding to variations in the electrical measurements are merely further limiting the data itself which are abstract ideas, specifically mental processes.
Step 2A Prong Two: If the claims recite a judicial exception under prong one, then is the judicial exception integrated into a practical application? [See MPEP § 2106.04(d) and MPEP § 2106.05(a)-(c) & (e)-(h)]
Because the claims do recite judicial exceptions, direction under Step 2A Prong Two provides that the claims must be examined further to determine whether they integrate the abstract ideas into a practical application.
The following claims recite the following additional elements in the form of non-abstract elements:
Claim 1: Receiving a training signal, training an HMM, inputting a second signal, and providing an output signal are insignificant extra solution activities, specifically mere data gathering and outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 6: The training signal including signal noise selected from the specified group are insignificant extra solution activities, specifically mere data gathering and outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 7: The training signal including known amino acid sequences and unknown amino acid sequences are insignificant extra solution activities, specifically mere data gathering and outputting (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 8: A receiver circuit, and a processing circuit are generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Receiving a training signal, training an HMM, inputting a second signal, and providing an output signal are insignificant extra solution activities, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Claim 15: A memory device, instructions, and a processor are generic and nonspecific elements of a computer that do not improve the functioning of any computer or technology described herein [See MPEP § 2106.04(d)(1) and MPEP § 2106.05(d)]. Receiving a training signal, training an HMM, inputting a second signal, and providing an output signal are insignificant extra solution activities, specifically mere data gathering (See Performing clinical tests on individuals to obtain input for an equation, In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989) and Determining the level of a biomarker in blood, Mayo, 566 U.S. at 79, 101 USPQ2d at 1968. See also PerkinElmer, Inc. v. Intema Ltd., 496 Fed. App'x 65, 73, 105 USPQ2d 1960, 1966 (Fed. Cir. 2012) (assessing or measuring data derived from an ultrasound scan, to be used in a diagnosis)) [See MPEP § 2106.05(g)].
Step 2B: If the claims do not integrate the judicial exception, do the claims provide an inventive concept? [See MPEP § 2106.05]
Because the additional claim elements do not integrate the abstract idea into a practical application, the claims are further examined under Step 2B, which evaluates whether the additional elements, individually and in combination, amount to significantly more than the judicial exception itself by providing an inventive concept.
The claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception because the claims recite additional elements that are generic, conventional or nonspecific. These additional elements include:
The additional elements of receiver circuit, a processing circuit, a memory device, instructions, and a processor are generic and nonspecific elements of a computer that are well-understood, routine and conventional within the art and therefore do not improve the functioning of any computer or technology described therein (Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information), Performing repetitive calculations, Flook, 437 U.S. at 594, 198 USPQ2d at 199 (recomputing or readjusting alarm limit values), and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)) [See § MPEP 2106.05(d)(II)]. Therefore, taken both individually and as a whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
The additional elements of receiving a training signal (Conventional: Thompson et al. 2011 – Figure 2), training an HMM (Conventional: Rabiner et al. Page 261, column 2, Paragraphs 2-3), inputting a second signal (Conventional: Thompson et al. 2011 – Figure 2), the training signal including signal noise selected from the specified group (the type of data doesn’t change this as a data gathering step or change it from a conventional computer function), the training signal including known amino acid sequences and unknown amino acid sequences (the type of data doesn’t change this as a data gathering step or change it from a conventional computer function), and providing an output signal, are insignificant extra solutional activities, specifically mere data gathering, that are recognized as well understood, routine and conventional by the courts (See Analyzing DNA to provide sequence information or detect allelic variants, Genetic Techs. Ltd., 818 F.3d at 1377; 118 USPQ2d at 1546, and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information)) [See MPEP § 2106.05(g)]. Therefore, taken both individually and as whole, the additional elements do not amount to significantly more than the judicial exception by providing an inventive concept.
Therefore, claims 1-20, when the limitations are considered individually and as a whole, are rejected under 35 USC § 101 as being directed to non-statutory subject matter.
Response to Arguments
Applicant's arguments filed 7/1/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 8 of the Remarks filed 7/1/2026 that the claims do not recite an abstract idea, but are rather require the “handling of complex, high-frequency electrical measurements generated by specialized molecular detection hardware, as well as the application of probabilistic modeling techniques across large datasets”. Furthermore, applicant asserts on page 8 of the Remarks filed 7/1/2026 that the claims do not recite a mathematical concept, as “although an HMM involves mathematical constructs, the recited steps are directed to a specific application of these constructs to process signals” and the HMM is “a component of a concrete signal-processing pipeline”. However, examiner reminds applicant that mere size and scale of an abstract idea does not escape the realm of abstract idea groupings nor does mere use of computers to perform existing abstract ideas as seen in MPEP sections 2106.04(a)(2), and 2106.05(a), as well as current case precedent such as Intellectual Ventures I LLC v. Captial One Bank (USA) (Fed. Cir. 2015), Electrical Power Group, LLC v. Alstom S.A. (Fed. Cir. 2016), and FairWarning IP, LLC v. latric Systems, Inc. (Fed. Cir. 2016).
Applicant asserts on page 8 of the Remarks filed 7/1/2026 that the claims integrate any recited abstract idea into a practical application, citing an improvement “the claimed method improves molecular sequencing workflows by enabling automated, accurate segmentation and labeling of molecular signals using a trained HMM. This improvement reduces error and increases efficiency compared to the conventional manual or heuristic approaches”. However, examiner reminds applicant that according to MPEP 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, meaning the asserted improvement to accuracy and efficiency is merely an improvement to the judicial exception alone, and therefore cannot be the basis for a practical application or solution to a technical problem.
Applicant asserts on page 5 of the Remarks filed 7/1/2026 that the newly recited claim 21 recites a specific improvement in processing molecular detection signals. However, applicant asserts this improvement to be in the event-level associations between the signal events and monomer identities which are part of the abstract idea, however any improvements must be directed to the additional elements or additional elements in conjunction with the judicial exception, MPEP 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.
Claim Rejections - 35 USC § 103
Response to Amendment
In view of applicant’s amendments to the claims, previous rejections under 35 U.S.C. 103 have been reviewed, updated, and provided below.
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-5, 7-12, and 14-18 are rejected under 35 U.S.C. 103 as being unpatentable over Sgouralis et al. (Biophysical Journal (2017) 2021-2029; previously cited), Schreiber et al. (Bioinformatics (2015) 1897-1903; previously cited), and Van Rooyen et al. (EP 3608913 A1; previously cited).
Claim 1 is directed to a method of segmentation and labeling in single molecule sequencing using a trained Hidden Markov Model to automatically segment and label signals.
Claim 8 is directed to an apparatus for segmentation and labeling in single molecule sequencing using a trained Hidden Markov Model to automatically segment and label signals.
Claim 15 is directed to a CRM that stores instructions that performs segmentation and labeling in single molecule sequencing using a trained Hidden Markov Model to automatically segment and label signals.
Sgouralis et al. teaches in figure 7 “We may use the iHMM to estimate portions of the complete state space such as those contained in different segments… Estimated noiseless traces for two cases: 1) using a limited segment of the full trace”, on page 2022, column 2, paragraph 2 “Thus, we label with n the states of the system as it evolves through time”, on page 2022, column 1, paragraph 3 “all transitions out of state sigma are fully described by a probability vector”, on page 2023, column 1, paragraph 2 “the goals of the HMM are to estimate 1) the underlying state sequence, which is unobserved during the measurements; and 2) the model parameters, which include…and the state transition probabilities, associated with the states…”, and on page 2022, column 2, paragraph 1 “It is often practical to model the emission distributions by a general family and use state-specific parameters, psi , to distinguish its members”, furthermore it is inherent to any hidden Markov model that it be necessarily trained to correctly estimate parameters for event prediction, reading on segmenting the training signal into a set of events, determining signal characteristics of the training signal for each event of the first set of events, and training a Hidden Markov Model (HMM) using the set of events and the signal characteristics. Sgouralis et al. teaches in figure 4 the outputting of distributions of various states of a biomolecule that are a priori unknown, reading on providing the output signal having a sequence corresponding to a set of events and corresponding labels generated by the HMM. Furthermore, Sgouralis et al. teaches on page 2026, in Figure 4 “Synthetic data sets resembling a hypothetical biomolecule undergoing transitions between discrete states that we analyzed with the iHMM”.
Sgouralis et al. does not teach generating the HMM signal to the second signal to automatically segment and label the second signal to generate an output signal.
Schreiber et al. teaches in the abstract “We propose an automated method for aligning nanopore data to a reference through the use of hidden Markov models”, on page 1898, column 1, paragraph 6 “To model nanopore data, we first perform event detection on the data, detecting all regions of ionic current which are longer than 500 ms, below 90 pA and above 0 pA. We then segment each event by recursively splitting at the ionic current sample, which best splits a region into two Gaussian distributions until a threshold in probabilistic gain is reached, representing each time interval as a segment with a mean current, a standard deviation and a duration…Each match state in our HMM uses a Gaussian distribution to assign emission probabilities to the segments, with parameters l and r having initial values derived from a hand-analyzed reference sequence. Insert states, which correspond to unpredicted currents, have a uniform distribution from 0A to 90 pA, which are the limits for event detection. Initial transition probabilities inside each module were estimated by hand from a small number of events”, reading on determining a first set of event labels for the first set of events, each event label identifying a monomer of the sequence of monomers corresponding to an event of the first set of events and, in view of the teachings of Sgouralis et al., generating, using the trained HMM responsive to the inputting, an output signal, wherein the HMM segments the second signal into a second set of events and labels the second signal to yield a labeled second signal by assigning a predicted monomer identity to each event of the second set of events.
Van Rooyen et al. teaches in claim 2 “a database connected with the cloud computing cluster for receiving result data”, reading on receiving a training signal generated by molecular detection. Van Rooyen et al. also teaches “in certain instances, a training mode may be implemented employing a training sequence so as to further refine transition probability accuracy”, and “In various instances, the integrated circuit and/or chip may be a component within a sequencer, such as an automated sequencer or other genetic analysis apparatus, such as a mapper and/or aligner, and/or in other embodiments, the integrated circuit and/or expansion card may be accessible via the internet, e.g., cloud”, reading on applying the HMM to the second signal to automatically segment and label the second signal to generate an output signal.
It would have been obvious at the time of the effective filing date of the invention to a person skilled in the art to modify the teachings of Van Rooyan et al. for segmenting and labeling sequence data via HMMs with the teachings of Sgouralis et al. for using modified HMMs in single molecule data analysis as both are using similar models as well as similar data to classify segmented signal information via trained HMMs. Furthermore, it would have been obvious to combine the teachings of the previous two with the teachings of Schreiber et al. for determining event labels of monomers of a sequence and assigning predicted monomer identities as the latter teaches in the abstract “We validated our automated methodology on a subset of that data by automatically calculating an error rate for the distinction between the three cytosine variants and show that the automated methodology produces a 2–3% error rate, lower than the 10% error rate from previous manual segmentation and alignment”. One would have had a reasonable expectation of success given that all three are in the same field, using the same data and the same methods, merely slight variations of each. Therefore, it would have been obvious at the time of invention to modify the teachings of each and to be successful.
Claim 2 is directed to the method of claim 1 but further specifies determining probabilities that signal characteristics correspond to sets of events.
Claim 9 is directed to the apparatus of claim 8 but further specifies determining probabilities that signal characteristics correspond to an individual event.
Claim 16 is directed to the CRM of claim 15 but further specifies determining probabilities that an individual signal characteristic corresponds to an event.
Sgouralis et al. teaches on page 2023, column 1, paragraph 2 “the goals of the HMM are to estimate 1) the underlying state sequence, which is unobserved during the measurements; and 2) the model parameters, which include…and the state transition probabilities, associated with the states…”, reading on further comprising determining the signal characteristics for the set of events includes determining probabilities that the signal characteristics correspond to the set of events.
Claim 3 is directed to the method of claim 1 but further specifies assigning probabilities to each HMM node and edge to predict correspondence to an event or transition to another node.
Claim 10 is directed to the apparatus of claim 8 but further specifies assigning probabilities to each HMM node and edge to predict correspondence to an event or transition to another node.
Claim 17 is directed to the CRM of claim 16 and thus claim 15, but further specifies assigning probabilities to each HMM node and edge to predict correspondence to events.
Van Rooyen et al. teaches “In such an instance, the initial path score through the matrix will be the sum of all edge likelihoods in the path. For example, the edge likelihood may be a function of likelihoods of all outgoing edges from a given vertex” and “Some primary analysis pipelines often include: Signal processing to amplify, filter, separate, and measure sensor output; Data reduction, such as by quantization, decimation, averaging, transformation, etc.; Image processing or numerical processing to identify and enhance meaningful signals, and associate them with specific reads and nucleotides (e.g. image offset calculation, cluster identification); Algorithmic processing and heuristics to compensate for sequencing technology artifacts (e.g. phasing estimates, cross-talk matrices); Bayesian probability calculations; Hidden Markov models”, reading on further comprising generating the HMM based on the set of events and the signal characteristics includes assigning probabilities to each HMM node and edge that model the node output to predict when the signal characteristics correspond to an event and transitioning to another HMM node when a node does not correspond.
Claim 4 is directed to the method of claim 1 but further specifies applying a Viterbi algorithm to the HMM and segmenting a second signal into a second set of events.
Claim 11 is directed to the apparatus of claim 8 but further specifies applying a Viterbi algorithm to the HMM and segmenting a second signal into a second set of events.
Claim 18 is directed to the CRM of claim 17 and thus claim 15, but further specifies applying a Viterbi algorithm to the HMM and segmenting a second signal into a second set of events.
Van Rooyen et al. teaches “Additionally, such as with respect to variant calling, both Hidden Markov model (HMM) and/or dynamic programming (DP) algorithms, including Viterbi and forward algorithms, may be implemented…”, reading on further comprising automatically segmenting the second signal includes applying a Viterbi algorithm to the HMM and responsively segmenting the second signal into a second set of events.
Claim 5 is directed to the method of claim 4 and thus claim 1, but further specifies estimating a likelihood that the signal characteristics correspond to a set of events based on the probabilities of the HMM.
Claim 12 is directed to the apparatus of claim 8 but further specifies estimating a likelihood that the signal characteristics correspond to a set of events based on the probabilities of the HMM.
Van Rooyen et al. teaches “In such an instance, the initial path score through the matrix will be the sum of all edge likelihoods in the path. For example, the edge likelihood may be a function of likelihoods of all outgoing edges from a given vertex” and “Some primary analysis pipelines often include: Signal processing to amplify, filter, separate, and measure sensor output; Data reduction, such as by quantization, decimation, averaging, transformation, etc.; Image processing or numerical processing to identify and enhance meaningful signals, and associate them with specific reads and nucleotides (e.g. image offset calculation, cluster identification); Algorithmic processing and heuristics to compensate for sequencing technology artifacts (e.g. phasing estimates, cross-talk matrices); Bayesian probability calculations; Hidden Markov models”, reading on further comprising labeling the second set of events based on the signal characteristics by estimating a likelihood that the signal characteristics correspond to the second set of events based on probabilities indicated by the HMM.
Claim 7 is directed to the method of claim 1 but further specifies training the signal includes a known amino acid sequence and a second unknown sequence.
Claim 14 is directed to the apparatus of claim 8 but further specifies training the signal includes a known amino acid sequence and a second unknown sequence.
Van Rooyen et al. teaches “In various embodiments, the system may include one or more of an electronic data source that provides digital signals representing a plurality of reads of genomic data, such as where each of the plurality of reads of genomic data include a sequence of nucleotides”, “a training mode may be implemented employing a training sequence so as to further refine transition probability accuracy for a given sequencer run”, and “…for each mapped position, accesses the (internal or external) memory to retrieve a segment of the reference sequence/genome corresponding to the mapped position…”, reading on further comprising the training signal includes a known amino acid sequence and the second signal includes an unknown amino acid sequence.
Claims 6 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Sgouralis et al. (Biophysical Journal (2017) 2021-2029), Schreiber et al. (Bioinformatics (2015) 1897-1903), and Van Rooyen et al. (EP 3608913 A1) as applied to claims 1-5, 7-12, and 14-18 above, and further in view of Jung et al. (Journal of Physical Chemistry B. (2009) 13886-13890) and Wang et al. (IEEE Transactions on Neural Networks (1999) 1511-1517).
Claim 6 is directed to the method of claim 1 but further specifies including signal from the group of correlated noise, spiky noise, and non-Gaussian noise.
Claim 13 is directed to the apparatus of claim 8 but further specifies including signal from the group of correlated noise, spiky noise, and non-Gaussian noise.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. teach the method and apparatus of claims 1 and 8 as described above.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. do not teach the inclusion of a signal from the group of correlated noise, spiky noise, and non-Gaussian noise.
Jung et al. teaches on page 2, paragraph 1 “In this paper, data sets of varying length are generated by pseudo randomly generated transition and emission matrices exhibiting experimentally relevant, Poisson-distributed noise”, reading on further comprising the signal characteristics include signal noise selected from the group of correlated noise, non-Gaussian noise, and spiky noise.
It would have been obvious at the time of the effective filing date of the invention to a person skilled in the art to modify the teachings of Sgouralis et al., Schreiber et al., and Van Rooyan et al. for the method and apparatus of claims 1 and 8, with the teachings of Jung et al. for including Poisson-distributed noise as the inclusion of noise within the training is a well-understood and routine part of training models (Wang et al. 1999 – Page 1511, column 1, paragraph 1 “well known that the two major problems associated with backpropagation learning”, and the abstract “A new global optimization strategy for training adaptive systems such as neural networks”). One would have had a reasonable expectation of success given that Sgouralis et al. and Van Rooyan et al. are both applying HMMs to single molecule data analysis and Jung et al. is attempting to improve the goodness-of-fit of the models being used in such analysis. Therefore, it would have been obvious at the time of invention to modify the teachings of each and to be successful.
Claims 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Sgouralis et al. (Biophysical Journal (2017) 2021-2029; previously cited), Schreiber et al. (Bioinformatics (2015) 1897-1903; previously cited), and Van Rooyen et al. (EP 3608913 A1; previously cited) as applied to claims 1-5, 7-12, and 14-18 above, and further in view of David et al. (Bioinformatics (2017) 49-55; newly cited).
Claim 21 is directed to the method of claim 1 but further specifies assigning a monomer identity to each event, and updating model parameters based on associations between the events.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. teach the method and apparatus of claims 1 and 8 as described above.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. do not teach the assigning of a monomer identity to each event, and updating model parameters based on associations between the events.
David et al. teaches on page 50, column 1, paragraphs 3-4 “DNA fragments pass through a protein embedded in a membrane via a nanometre-sized channel…As a DNA strand passes through the pore it partially blocks the flow of electric current through the pore. The flow of current is sampled over time which is the observable output of the system. The central idea is that the single-stranded DNA product present in the nanopore affects the current in a way that is strong enough to enable decoding the electric signal data into a DNA sequence. This process, called basecalling, takes as input a list of current measurements, and produces as output a list of DNA bases most likely to have generated those currents… The first part of the decoding process is to segment the sampled current measurements into blocks. The nanopore current measurements are taken at regular time intervals, but the threading of the singlestranded DNA product through the nanopore is a stochastic process controlled by biological enzymes. The segmentation process takes as input the list of current measurements and produces a list of events, each consisting of: start starti, length lengthi, mean meani and standard deviation stdvi. Ideally, each event corresponds to a different DNA context found inside the nanopore, and consecutive events correspond contexts differing by exactly one base”, and on the same page, column 2, paragraph 2-3 “As a further complication, the current measurements have slightly different characteristics between nanopores, and between the times when they are taken by the same nanopore. To account for these variations, Metrichor uses a set of read- and strand-specific scaling parameters: shift, scale, drift, var, scale’ and var’…The core of the decoding process is the basecalling step, performed in the cloud by Metrichor, which infers the DNA sequence most likely to have produced the observed event sequence. Metrichor uses a Hidden Markov Model (HMM) for basecalling data, where the hidden state corresponds to the DNA context present in the nanopore, and where the pore models are used to compute emission probabilities”, reading on wherein determining the first set of event labels comprises assigning, to each event of the first set of events, a monomer identity corresponding to that event, and training the Hidden Markov Model (HMM) comprises updating model parameters based on associations between the events and the assigned monomer identities.
It would have been obvious at the time of the effective filing date of the invention to a person skilled in the art to modify the teachings of Sgouralis et al., Schreiber et al., and Van Rooyan et al. for the method and apparatus of claims 1 and 8, with the teachings of David et al. for the identification of individual nucleotides in a sequence from a nanopore signal using an HMM as David et al. teaches on page 55, column 2, paragraph 2 “Nanocall produces reads comparable in mappability and quality to Metrichor 1D reads with 68% identity. As an important technical difference from Metrichor, with Nanocall we found that double-strand pore model scaling seems to work better than single-strand scaling” and in the abstract “Nanocall is the first open-source, freely available, off-line basecaller for Oxford Nanopore sequencing data”. One would have had a reasonable expectation of success given that all four are in the same field, using the same data and the same methods, merely slight variations of each. Therefore, it would have been obvious at the time of invention to modify the teachings of each and to be successful.
Claim 22 is directed to the method of claim 1 but further specifies that the training and second signal comprise electric measurements from a molecular detection device, and the characteristics correspond to variations in the measurements from successive interactions.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. teach the method and apparatus of claims 1 and 8 as described above.
Sgouralis et al., Schreiber et al., and Van Rooyen et al. do not teach the training and second signal comprise electric measurements from a molecular detection device, and the characteristics correspond to variations in the measurements from successive interactions.
David et al. teaches on page 50, column 1, paragraphs 3-4 “DNA fragments pass through a protein embedded in a membrane via a nanometre-sized channel…As a DNA strand passes through the pore it partially blocks the flow of electric current through the pore. The flow of current is sampled over time which is the observable output of the system. The central idea is that the single-stranded DNA product present in the nanopore affects the current in a way that is strong enough to enable decoding the electric signal data into a DNA sequence. This process, called basecalling, takes as input a list of current measurements, and produces as output a list of DNA bases most likely to have generated those currents… The first part of the decoding process is to segment the sampled current measurements into blocks. The nanopore current measurements are taken at regular time intervals, but the threading of the singlestranded DNA product through the nanopore is a stochastic process controlled by biological enzymes. The segmentation process takes as input the list of current measurements and produces a list of events, each consisting of: start starti, length lengthi, mean meani and standard deviation stdvi. Ideally, each event corresponds to a different DNA context found inside the nanopore, and consecutive events correspond contexts differing by exactly one base”, and on the same page, column 2, paragraph 3 “The core of the decoding process is the basecalling step, performed in the cloud by Metrichor, which infers the DNA sequence most likely to have produced the observed event sequence. Metrichor uses a Hidden Markov Model (HMM) for basecalling data, where the hidden state corresponds to the DNA context present in the nanopore, and where the pore models are used to compute emission probabilities”, reading on wherein the training signal and the second signal comprise electrical measurements generated as a molecule interacts with a sensing region of the molecular detection device, and wherein the signal characteristics correspond to variations in the electrical measurements caused by successive portions of the molecule interacting with the sensing region.
Response to Arguments
Applicant's arguments filed 7/1/2026 have been fully considered but they are not persuasive.
Applicant asserts on page 10 of the Remarks filed 7/1/2026 that Schreiber et al., Sgouralis et al., and Van Rooyen et al., do not teach the determining of event labels which identify a monomer of the sequence, nor the training of the HMM using the first set of events. Specifically, that Schreiber et al. “does not teach or suggest determining monomer identities for individual signal events as a labeling operation derived from the signal”. Additionally, applicant then asserts “To the extent signal portions are associated with HMM states in Schreiber et al., any corresponding monomer identity is inherited from the predefined reference sequence that defines those states, not determined from the signal on an event-by-event basis” and that Schreiber et al. fails to teach “training a model by comparing predicted monomer identities for signal events against corresponding monomer labels”.
However, the BRI of the claims does not match the limitations set forth in the arguments. Specifically, applicant’s argument that “any corresponding monomer identity is inherited from the predefined reference sequence that defines those states” concedes the fact that monomer identity is given through the predicted state, and while it “does not teach or suggest determining monomer identities for individual signal events as a labeling operation derived from the signal”, this is merely because it is an intrinsic part of ascribing a signal and the corresponding states to a reference, i.e. if you have a reference and ascribe a signal and states to it, you know the monomers. Furthermore, limitations of the claim do not specify the determination from the signal on an event-by-event basis, merely that they be determined. In other words, the use of an HMM has not even entered the picture in the claim limitations yet.
Lastly, regarding the training described in Schreiber et al., page 1901, column 1, paragraphs 4 on, describe the training implemented including the use of labeled data, “the labels were designed to give much larger and more distinctive signal changes than the methylation changes, making a mismatch between the cytosine call and the label call a strong indicator that the cytosine call is incorrect. The 423 events were split into three sets: 207 (49%) in a training set, 89 (21%) in a cross-training set and 127 (30%) in a test set. The test set was set aside and all training and model development done on the training and cross-training sets”. Therefore, Schreiber et al. is not deficient and thus the additional prior art references have nothing to “cure”.
Additionally, applicant asserts on page 12 of the Remarks filed 7/1/2026 that Schreiber et al., Van Rooyen et al., and Sgouralis et al. fail to teach the generating of an output signal that maps events of the second signal to labels corresponding to monomers via segmentation of the second signal. However, Schreiber et al. teaches on page 1898, column 1, paragraph 6 “We then segment each event by recursively splitting at the ionic current sample, which best splits a region into two Gaussian distributions until a threshold in probabilistic gain is reached… Each match state in our HMM uses a Gaussian distribution to assign emission probabilities to the segments, with parameters l and r having initial values derived from a hand-analyzed reference sequence” and while it may be “applying the HMM to compute likelihoods and alignment scores of an observed signal relative to one or more predefined sequence hypotheses” these “predefined sequence hypotheses” as seen in Figure 1, where (a) is the reference and (b) and (c) are the alignments predicted by the HMM, are the monomers being predicted in the sequence. Each of these positions are monomers within the sequence, with each potentially different monomer being a state. And while examiner agrees that the alignment is not a signal, the teachings of Sgouralis et al. do teach the segmenting of a direct signal as seen in Figure 4 on page 2026 depicting “Synthetic data sets resembling a hypothetical biomolecule undergoing transitions between discrete states that we analyzed with the iHMM”. Examiner concedes that this was not previously well articulated or pointed to in the last office action, but has amended the 103 rejections to properly articulate this.
In regards newly recited claims 21 and 22, examiner agrees with applicant in part that the newly recited claim limitations distinguish over the previously cited prior art. As such a new prior art search was performed and newly recited art mapped to the claims.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KEENAN NEIL ANDERSON-FEARS whose telephone number is (571)272-0108. The examiner can normally be reached M-Th, alternate F, 8-5.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Karlheinz Skowronek can be reached at 571-272-9047. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/K.N.A./Examiner, Art Unit 1687
/LARRY D RIGGS II/Supervisory Patent Examiner, Art Unit 1686
Prosecution Insights