DETAILED ACTION
1. This office action is in response to an amendment filed on 06/25/2026. Claims 1-20 are pending. Claims 1, 9 and 15 are independent. Each independent claim is amended.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statements (IDS) submitted on 08/20/2026 has been considered. The submission is in-compliance with the provisions of 37 CFR 1.97. Form PTO-1449 is signed and attached hereto.
Response to Arguments
4. Applicant’s arguments filed on June 25, 2026, with regarding to the 35 U.S.C. 102 rejection directed to the independent claims 1, 9 and 15 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
5. Thus, in response to the 35 U.S.C. 102 rejections set forth in the previous office action, applicant amended at least each independent claim 1, 9 and 15, presumably to overcome the 35 U.S.C. 102 rejections set forth in the previous office action. Since the newly amended claims changed the scope and necessitated new grounds of rejection, applicant’s arguments are moot. The analysis of the claims under consideration, as amended, follows in the corresponding section below.
Claim Rejections - 35 USC § 103
6. 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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 non-obviousness.
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 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.
7. Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over NPL document, titled, “PostSV: A Post–Processing Approach for Filtering Structural Variations” by Eman Alzaid et al (herein after referred as Alzaid) (Vol. 14: 2020) (This prior art is cited and provided with the IDS]
in view of Jason Perera (Perera) (US Publication No. 20200258597A1, Pub. Date: August 13, 2020) (This reference is also submitted with the IDS)
The following is referring to independent claims 1, 9 and 15:
As per independent claim 1, Alzaid discloses a system comprising: at least one processor; and a non-transitory computer readable medium comprising instructions that, when executed by the at least one processor, cause the system to ; [Page 6, column 2, paragraph 2, Page 6, right column, “supercomputer”, This describes a computer-implemented PostSV pipeline involving read-alignment software and trained random-forest, support-vector-machine, and logistic regression models. It also identifies the supercomputer used for the work. Executing these software models necessarily involves at least one processor and stored computer-executable instructions on computer-readable storage];
determine, for one or more genomic coordinates of a genomic sample, an initial structural variant call based on nucleotide reads corresponding to the genomic sample [“the SV predictions as a 3-tuple: chromosome name, start position and end position”, at least page 2, column 1, paragraph 2, left column, “The proposed Method: PostSV, This describes receives structural variant predictions together with a BAM file containing aligned nucleotide reads and represents each prediction using chromosome and breakpoint coordinates. These input predictions constitute the initial structure-variant calls at genomic coordinates based on the sequencing reads]
identify sequencing metrics corresponding to one or more of the initial structural variant call or the one or more genomic coordinates [“read-depth”; page 3, column 1, paragraph 3, page 3, Feature Extraction, “30 binary features”, This annotates each candidate structural variant with features based on rea-pair signatures, clipped reads, alignment scores, and read depth at the variant breakpoints. These are the claimed,” other sequencing metrics” corresponding to the initial call and its coordinates];
generate, utilizing a structural variant refinement machine-learning model based on the sequencing metrics, a false positive likelihood indicating a likelihood that the initial structural variant call is a false positive (“Classification of SV predictions into true positive and false positives”, page 3, column 2, paragraph 3, the likelihood for false positive has to be determined in order to perform classification. This combines its sequencing features into a feature matrix and supplies the matrix to random-forest, support-vector machine, and logistic-regression classifiers. The classifiers determine whether a candidate structural variant prediction is a true positive or false positive. A false-positive classification constitutes an indication of the likelihood that the initial call is false]; and
determine a modified structural variant call for the one or more genomic coordinates of the genomic sample based on the false positive likelihood [See abstract, “Several classifiers are employed to classify the candidate predictions and remove false positive” “filter SV predications” Page 4, right column, “Experimental Results and Discussion” paragraph 4. Note: PostSV applies the trained classifiers to the initial structural-variant predictions and filters predictions classified as false positive. Removing or changing a positive call based on the classifier’s output produces a modified structural-variant call or modified structural variant call set.]
Although Alzaid uses alignment score; read-pair, read depth, and breakpoint-distance features, its threshold concern insert size, breakpoint distance, read support, coverage, and sequence-alignment scores.
Alzaid does not expressly determine a coordinate-specific metric representing the degree to which nucleotide calls satisfy read-quantity or base call-quality thresholds.
Alzaid does not disclose the following underlined amended claim limitations:
identify one or more variant region quality metrics …. the one or more variant region quality metrics indicating a degree to which nucleotide base calls from the nucleotide reads satisfy one or more read quality thresholds or base call quality thresholds at the one or more genomic coordinates
identify other sequencing metrics corresponding to one or more of the initial structural variant call or the one or more genomic coordinates,
machine-learning model based on to process the one or more variant region quality metrics and the other sequencing metrics,
However, Perera discloses the above underlined claim limitations:
read quality requirement to nucleotide reads associated with genomic coordinates [Para. 0016, “predefined mapping quality threshold” and para. 0085, “not qc_fail”. This expressly evaluates sequencing reads against mapping-quality and quality-control requirements. Para. 0085 and 0088 further describe filtering based on quality-control status, edit distance, insertions, deletions, unique mapping and mapping likelihood. These are read-level quality criteria applied before calculating positional metrics]
identify one or more variant region quality metrics …. the one or more variant region quality metrics indicating a degree to which nucleotide base calls from the nucleotide reads satisfy one or more read quality thresholds or base call quality thresholds at the one or more genomic coordinates [para. 0090-0091, “number of reads that uniquely map”. Note: after applying the read filters, it calculates positional coverage representing the number of qualifying reads mapping to each nucleotide position. Because this count is calculated from the filtered reads, it indicates the amount or degree of qualifying nucleotide-read support at each genomic coordinate. It therefore corresponds to the claimed variant-region quality metric]
identify other sequencing metrics corresponding to one or more of the initial structural variant call or the one or more genomic coordinates [para. 0093, “allelic frequencies”, “log ratios”; “areas of low sequencing coverage”, In addition to positional coverage, Perera calculates allelic frequencies tumor-to-normal coverage ratios, coverage depth, low coverage regions, and related summary statistics. These constitute other sequencing metrics associated with the relevant genomic region]
machine-learning model based on to process the one or more variant region quality metrics and the other sequencing metrics [Para. 0098, “machine learning classification model” and para 0092-0093, create combined coverage and summary-statistics tables containing the positional coverage and other sequencing metrics. para. 0098 supplies features from the summary-statistics table to the machine-learning model. Para. 0099 identifies the model as a shallow decision tree, while para. 0100 additionally identifies random-forest implementation. Thus, Perera teaches processing the quality -derived positional metrics together with the other sequencing metrics using machine learning]
Alzaid and Perera are analogous arts and are in the same field of endeavor as they both pertain and are directed to sequencing nucleotides and determining nucleotide base calls for genomic samples.
It would have been obvious to one having ordinary skill in the art, before the effective filing of the claimed invention, to supplement Alzaid’s existing feature matrix with Perera’s quality-filtered, nucleotide-position coverage metrics so that Alaid’s classifier would operate on more reliable read evidence and more accurately distinguish true structural-variant calls from false-positive calls. The combination would have involved the predictable use of Perera’s known quality-control and feature-extraction technique as an additional input to Alzaid’s existing machine learning classifier, with a reasonable expectation of reducing false positives.
As per independent claim 9, independent claim 9 is rejected for same reason as that of the above independent claim 1.
As per independent claim 15, independent claim 15 is rejected for same reason as that of the above independent claim 1.
The following is referring to dependent claims 2-8, 10-14 and 16-20:
As per dependent claim 2, the combination of Alzaid and Perera discloses the method/system as applied to claim 1 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to determine the initial structural variant call by determining a deletion of more than a threshold number of base pairs, an insertion of more than the threshold number of base pairs, a duplication of more than the threshold number of base pairs, an inversion, a translocation, or a copy number variation (CNV) [Page 1, column 1, paragraph 1, under introduction, “These rearrangements have several forms including insertions, deletions, translocations, inversions, duplications, and copy number variations (CNVs)”].
As per dependent claim 3, the combination of Alzaid and Perera discloses the method/system as applied to claim 1 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to determine the initial structural variant call by determining a structural variant call of a number of base pairs within a threshold range of base pairs [Page 2, column 2, paragraph 3, “(2) the distance between the breakpoints of a single-end signature and the corresponding SV breakpoints does not exceed a defined threshold”].
As per dependent claim 4, the combination of Alzaid and Perera discloses the method/system as applied to claim 1 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to identify other the sequencing metrics corresponding to the initial structural variant call by identifying one or more of read-based sequencing metrics, reference-based sequencing metrics, [ Page 3, column 1, paragraph 2-3: read depth, genome mean coverage, page 3 Feature Extraction and Read Depth. Alzaid derives features from reads, including read-pair, clipped-read and read-depth information at candidate breakpoints. Read depth is expressly calculated from reads so it is read-based sequencing metric].
As per dependent claim 11, dependent claim 11 is rejected for same reason as that of the above dependent claim 4.
As per dependent claim 5, the combination of Alzaid and Perera discloses the method/system as applied to claim 4 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to identify the read-based sequencing metrics by determining, for the initial structural variant call, one or more of: one or more base-call quality scores; a fraction of nucleotide reads supporting an alternate contiguous sequence from a reference genome; a number of split nucleotide reads from the nucleotide reads corresponding to the initial structural variant call; a coverage depth of the nucleotide reads corresponding to the initial structural variant call; an additional structural variant call located within a threshold number of base pairs from the initial structural variant call within the genomic sample; an alignment of a contiguous sequence corresponding to the nucleotide reads with a reference sequence of a reference genome modified to include a structural variant corresponding to the initial structural variant call; a deletion length in nucleotide bases based on one or more soft clipped nucleotide reads; a number of the nucleotide reads exhibiting a mapping quality metric that fails to satisfy a threshold mapping quality metric; an insert size representing a length of nucleotide-read fragments corresponding to the initial structural variant call; or a structural-variant likelihood representing a ratio of the initial structural variant call to a reference call for the one or more genomic coordinates based on the insert size [Page 1, column 2, paragraph 1, “split reads (SRs), are one of the main sources of information used to refine SV breakpoints” Page 3, column 1, paragraph 2-3: read depth, genome mean coverage].
As per dependent claim 12, dependent claim 12 is rejected for same reason as that of the above dependent claim 5.
As per dependent claim 6, the combination of Alzaid and Perera discloses the method/system as applied to claim 4 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to identify the variant region quality metrics by determining one or more of: a number of nucleotide reads that comprise at least a threshold number of base calls and correspond to a target genomic region for the initial structural variant call; or a number of nucleotide bases in an alternate contiguous sequence corresponding to the target genomic region from a reference genome for which base calls for the nucleotide reads fail to satisfy a threshold base call quality score [ Page1, column 1, paragraph 2: minimum and maximum thresholds for insert sizes for identifying SV regions].
As per dependent claim 13, dependent claim 13 is rejected for same reason as that of the above dependent claim 6.
As per dependent claim 7, the combination of Alzaid and Perera discloses the method/system as applied to claim 4 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to identify the reference-based sequencing metrics by identifying, within one or more genomic regions of a reference genome corresponding to the one or more genomic coordinates of the genomic sample, one or more of: a tandem repeat length in nucleotide bases; a permutation entropy of nucleotide bases; a cytosine quadruplex (C-quadruplex); or a guanine quadruplex (G-quadruplex) [Page 4, column 1, paragraph 4].
As per dependent claim 14, dependent claim 14 is rejected for same reason as that of the above dependent claim 7.
As per dependent claim 8, the combination of Alzaid and Perera discloses the method/system as applied to claim 4 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the system to: generate the false positive likelihood by determining the initial structural variant call is a false positive call or a true positive call based on the one or more variant region quality metrics and the other sequencing metrics; and determine the modified structural variant call by: changing the initial structural variant call from a positive structural variant call to a negative structural variant call based on the initial structural variant call being the false positive call; or changing the initial structural variant call from a negative structural variant call to a positive structural variant call based on the initial structural variant call being the true positive call and generate a variant call file comprising the modified structural variant call by modifying one or more data fields for one or more metrics associated with the initial structural variant call [“Classification of SV predications into true positives and false positives” page 3, column 2, paragraph 3, the likelihood for false positive has to be determined in order to perform classification and See abstract, “Several classifiers are employed to classify the candidate predictions and remove false positive. See also Perera maps ML processing and the existence of a VCF] .
As per dependent claim 17, dependent claim 17 is rejected for same reason as that of the above dependent claim 8.
As per dependent claim 10, the combination of Alzaid and Perera discloses the method/system as applied to claim 9 above. Furthermore, Alzaid discloses the method/device: determining the initial structural variant call comprises utilizing a call generation model to determine base calls corresponding to the one or more genomic coordinates of the genomic sample indicate a structural variant in relation to a reference genome; and determining the modified structural variant call comprises correcting the initial structural variant call for the one or more genomic coordinates based on the false positive likelihood generated by the structural variant refinement machine-learning model [See at least abstract, “Several classifiers are employed to classify the candidate predictions and remove false positive].
As per dependent claim 16, the combination of Alzaid and Perera discloses the method/system as applied to claim 15 above. Furthermore, Alzaid discloses the method/device, wherein the structural variant refinement machine-learning model comprises one or more gradient boosted decision trees [gradient boosted decision tree are an obvious alternative to random forests as used by page 3, paragraph 4].
As per dependent claim 18, the combination of Alzaid and Perera discloses the method/system as applied to claim 15 above. Further Alzaid discloses the system further comprising instructions that, when executed by the at least one processor, cause the computing device to: determine, from a truth dataset, a ground truth structural variant call corresponding to the modified structural variant call is incorrectly labeled as a false positive instead of a true positive based on one or more truth set nucleotide reads for the ground truth structural variant call satisfying structural variant criteria; change a label for the ground truth structural variant call from false positive to true positive; and adjust parameters of the structural variant refinement machine-learning model based on a comparison of the modified structural variant call and the ground truth structural variant call.[See at least page 3-4]
As per dependent claim 19, the combination of Alzaid and Perera discloses the method/system as applied to claim 15 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the computing device to determine the ground truth structural variant call is incorrectly labeled based on the structural variant criteria by: parsing a Concise Idiosyncratic Gapped Alignment Report (CIGAR) string to identify a truth set nucleotide read of the truth dataset that satisfies a threshold mapping quality metric; determining a portion of the CIGAR string comprising a starting index of a corresponding structural variant call generated by a call generation model; and determining that the starting index corresponds to a structural variant and matches a length of the corresponding structural variant call generated by the call generation model [See page 14, paragraph 3: CIGAR string].
As per dependent claim 20, the combination of Alzaid and Perera discloses the method/system as applied to claim 15 above. Furthermore, Alzaid discloses the method/device, further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the false positive likelihood utilizing the structural variant refinement machine-learning model based on one or more variant region quality metrics the other the sequencing metrics and the initial structural variant call as inputs [Classification of SV predications into true positives and false positives” page 3, column 2, paragraph 3, the likelihood for false positive has to be determined in order to perform classification and page 6, paragraph 2 and see Perera at least para. 0090-0091, “number of reads that uniquely map”. Note: after applying the read filters, it calculates positional coverage representing the number of qualifying reads mapping to each nucleotide position. Because this count is calculated from the filtered reads, it indicates the amount or degree of qualifying nucleotide-read support at each genomic coordinate. It therefore corresponds to the claimed variant-region quality metric]
Conclusion
8. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
a. US Publication No. 20200286587 A1 Israeli et al discloses methods, systems, and computer program products that use deep learning models to classify candidate mutations detected in sequencing data, particularly suboptimal sequencing data. The methods, systems, and programs provide for increased efficiency, accuracy, and speed in identifying mutations from a wide range of sequencing data.
b. US Publication No. 2019/0220704 A1 SCHULZ-TRIEGLAFF et al discloses Deep Learning-Based Variant Classifier, On para. 0087 teaches structural variation within variant. “variant” refers to a nucleic acid sequence that is different from a nucleic acid reference. Typical nucleic acid sequence variant includes without limitation single nucleotide polymorphism (SNP), short deletion and insertion polymorphisms (Indel), copy number variation (CNV), microsatellite markers or short tandem repeats and structural variation”
c. US Publication No. 2020/0321076 A1 Putnam et al discloses methods, systems, and algorithms to identify and report genome or chromosome level structural information, such as the presence of structural variations. In some cases, structural variations include copy number variations, inversions, deletions, tandem duplications, or inverted duplications. Further provided herein are methods, systems and algorithms for assembling read-paired genomic data, including creating and optimizing scaffold models.
d. See the other cited references.
9. Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAMSON B LEMMA whose telephone number is 571-272-3806. The examiner can normally be reached on M-F 8am-10pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor Yin-Chen Shaw can be reached on 571-272-8878. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/SAMSON B LEMMA/
Primary Examiner, Art Unit 2498
Prosecution Insights