DETAILED ACTION
The applicant’s response, from 27 July 2026, has been fully considered. Amendments to the claims, from 27 July 2026, were received and entered. The following rejections and/or objections are either reiterated or newly applied. They constitute the complete set presently being applied to the instant application.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Status
Claims 2, 6, 8, 11, 12, 14, 16, 17, and 20 are cancelled.
Claims 21-29 are newly added.
Claims 1, 3-5, 7, 9-10, 13, 15, 18-19, 21-29 are currently pending and under examination herein.
Claims 1, 3-5, 7, 9-10, 13, 15, 18-19, 21-29 are rejected.
Priority
The instant application claims priority as a 371 of PCT/US20/59977 filed 11 November 2020 and to US Provisional Application 63104323 filed 22 October 2020 and US Provisional Application 62934848 filed on 13 November 2019. The effective filing date of claims 1, 3-5, 7, 9-10, 13, 15, 18-19, 21-29 in this action is therefore established to be 13 November 2019. In future actions, the effective filing date of one or more claims may change, due to amendments to the claims, or further analysis of the disclosures of the priority applications.
Drawings
The drawling’s filed on 12 May 2022 are accepted.
Claim Rejections - 35 USC § 112
The previously issued 112(b) rejections are withdrawn in response to the amended claim set. The clarity issues of the unamended claims were addressed by the claim amendments.
Claim Rejections - 35 USC § 101
The previously issued 101 rejection is withdrawn in response to the amended claims integrating the judicial exceptions into a practical application. Particularly, the amended limitations of the independent claims, “selecting, by the one or more processors, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and providing, by the one or more processors, an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer”, are considered to recite a particular treatment (selected based on the predicted cancer origin) that is administered to the subject, as described by MPEP 2106.04(d)(2). Therefore, the judicial exceptions are integrated into a practical application under Step 2A, Prong Two (YES) of the subject matter eligibility analysis.
Claim Rejections - 35 USC § 102
The previously issued 102 rejection did not address all of the amended limitations. Therefore, the following rejection is reiterated and modified as has been necessitated by amendment.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1, 3, 5, 7, 9, 10, 15, 18, and 21-29 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Abdueva (US 20190352695 A1). Italicized text from reference art. Underlined text correspond to amendment.
Applicable claims include:
Claim 1. A method for classifying tumor origin sites, the method comprising: (Claim 1.i) acquiring, by one or more processors, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer; (Claim 1.ii) generating, by the one or more processors, using the sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes; (Claim 1.iii) applying, by the one or more processors, a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated from sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii)a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort; (Claim 1.iv) determining, by the one or more processors, based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject; (Claim 1.v) selecting, by the one or more processors, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and providing, by the one or more processors, an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer.
Claim 3. The method of claim 1, wherein a feature set for the predictive model comprises one or more of mutations, indels, focal amplifications and deletions, broad copy number gains and losses, structural rearrangements, mutation signatures, mutation rate, or sex.
Claim 5. The method of claim 1, further comprising training the predictive model using supervised or unsupervised learning.
Claim 7. The method of claim 1, wherein generating the training dataset further comprises acquiring, from a sequencing device, the sequence reads corresponding to the genetic material from the cohort of study subjects, and using the sequence reads to generate the training dataset.
Claim 9. The method of claim 1, wherein the training dataset comprises gene alteration categories comprising one or more selected from a group consisting of gene amplification (AMP), chromosome gain, homozygous deletion, hotspot, allele, chromosome loss, promoter, signature, structural variant (SV), truncation, and variant of unknown significance (VUS).
Claim 10. The method of claim 1, wherein the set of labels indicate whether a set of genes in the training dataset is from a respective subject diagnosed with cancer in the cohort of study subjects.
Claim 15. (Currently Amended) A system for classifying tumor origin sites, the system comprising a computing device having one or more processors configured to: (Claim 15.i) acquire, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer; (Claim 15.ii) generate, using the subject sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes; (Claim 15.iii) apply a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated using sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii) a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort; (Claim 15.iv) determine, based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject; (Claim 15.v) select, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and provide an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer.
Claim 18. The system of claim 15, wherein the one or more processors are further configured to generate the training dataset using the sequence reads corresponding to the genetic material from the study subjects in the cohort.
Claim 21. The method of claim 1, wherein the plurality of therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy.
Claim 22. The method of claim 1, wherein the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma.
Claim 23. The method of claim 1, wherein the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject.
Claim 24. The method of claim 1, wherein selecting the therapy further comprises changing from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification.
Claim 25. The method of claim 1, wherein the predictive model defines a feature space corresponding to the set of subject genes and the set of subject gene alteration categories.
Claim 26. The system of claim 15, wherein the plurality of therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy.
Claim 27. The system of claim 15, wherein the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma.
Claim 28. The system of claim 15, wherein the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject.
Claim 29. The system of claim 15, wherein the one or more processors are further configured to change from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification.
Regarding Claims 1 and 15, Abdueva teaches (Claim 1.i) acquiring, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer (Paragraph 0004: uses of cell-free nucleic acids (e.g., DNA or RNA). Such uses include detecting, monitoring and determining treatment for a subject having or suspected of having a health condition, such as a disease (e.g., cancer). use sequence information to assess a fragmentome; Paragraph 0138: The biological sample can be derived from any tissue; Paragraph 0178: sequencing using HiSeq (Illumina)). Abdueva teaches (Claim 1.ii) generating, using the sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes (Paragraph 0009: an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0026: structural variation consisting of: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation). Abdueva teaches (Claim 1.iii) applying a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated from sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii) a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort (Paragraph 0009: the classifier comprises a machine learning engine. the classifier further comprises an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0015: providing a training set comprising a set of reference classifications for each of the populations of cell-free DNA obtained from control subjects; a set of phenotypic classifications for each of the populations of cell-free DNA obtained from subjects having observed phenotypes; and training, by a computer, the classifier using the training set; Paragraph 0016: the subjects having an observed phenotype comprise subjects with a tissue-specific cancer; Paragraph 0036: detecting a deviation between the cell-free DNA from the subject and one or more reference populations of cell-free DNA, wherein the deviation is indicative of the presence of a condition or property in the subject. the analysis comprises tissue of origin analysis). Abdueva teaches (Claim 1.iv) determining based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject (Paragraph 0036: detecting a deviation between the cell-free DNA from the subject and one or more reference populations of cell-free DNA, wherein the deviation is indicative of the presence of a condition or property in the subject. the analysis comprises tissue of origin analysis). Abdueva teaches (Claim 1.v) selecting, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and providing an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer (Paragraph 0032-0033: disclosed herein is a method of classifying a test sample from a subject, comprising: classifying the test population of cell-free DNA using a trained classifier. the method further comprises performing a therapeutic intervention on the subject based on the classification of the population of cell-free DNA). The classification includes tumor origin site (see 1.iv above). Additionally, Abdueva teaches the methods are performed by computer processing system, which include processors (Paragraph 0312: The present disclosure provides computer systems that are programmed to implement methods of the disclosure; Paragraph 0313: The computer system includes a central processing unit, which can be a plurality of processors). Claim 15 recites the limitations of claim 1 directed to a system.
Regarding Claim 3, Abdueva teaches a feature set for the predictive model comprises one or more of mutations, indels, focal amplifications and deletions, broad copy number gains and losses, structural rearrangements, mutation signatures, mutation rate, or sex (Paragraph 0026: the structural variation is selected from: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation).
Regarding Claim 5, Abdueva teaches training the predictive model using supervised or unsupervised learning (Paragraph 0014: the classifier trained using a training set; Paragraph 0150: Machine learning algorithms may be supervised or unsupervised).
Regarding Claims 7 and 18, Abdueva teaches generating the training dataset further comprises acquiring, from a sequencing device, the sequence reads corresponding to the genetic material from the cohort of study subjects, and using the sequence reads to generate the training dataset (Paragraph 0009: the classifier comprises a machine learning engine. the classifier further comprises an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0282: A method is provided for creating a trained classifier, comprising providing a plurality of different classes, wherein each class represents a set of subjects with a shared characteristic (e.g., from one or more cohorts)).
Regarding Claim 9, Abdueva teaches the training dataset comprises gene alteration categories comprising one or more selected from a group consisting of gene amplification (AMP), chromosome gain, homozygous deletion, hotspot, allele, chromosome loss, promoter, signature, structural variant (SV), truncation, and variant of unknown significance (VUS) (Paragraph 0026: the structural variation is a variation in nucleosomal positioning selected from the group consisting of: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation. In some embodiments, the cluster is a hotspot; Paragraph 0214: a classifier (e.g., a machine learning engine) that is trained to classify said sample as having or not having each of a set of single nucleotide variants (SNVs) or other genetic variants)
Regarding Claim 10, Abdueva teaches the set of labels indicate whether a set of genes in the training dataset is from a respective subject diagnosed with cancer in the cohort of study subjects (Paragraph 0031: each of the plurality of different classes is selected from the group consisting of: healthy, breast cancer, colon cancer, lung cancer, pancreatic cancer, prostate cancer, ovarian cancer, melanoma, and liver cancer; Paragraph 0085: providing training data from a plurality of training subject, including a plurality subjects from a first class and a plurality of subjects from a second class, and wherein the training data includes, from a training sample from each training subject, a multi-parametric distribution of cfDNA molecules mapping to one or more selected genomic loci; and training a machine learning algorithm to develop a classification model that, based on test data from a test sample from a test subject, including the multi-parametric distribution of cfDNA molecules mapping to the selected genomic loci, classifies the subject as having cancer or not having cancer).
Regarding Claim 21 and 26, Abdueva teaches the therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy (Paragraph 0195: a treatment may be a targeted treatment such as a tyrosine kinase inhibitor).
Regarding Claim 22 and 27, Abdueva teaches the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma (Paragraph 0031: each of the plurality of different classes is selected from the group consisting of: healthy, breast cancer, colon cancer, lung cancer, pancreatic cancer, prostate cancer, ovarian cancer, melanoma, and liver cancer).
Regarding Claim 23 and 28, Abdueva teaches the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject (Paragraph 0138: biological sample refers to a tissue or fluid sample derived from a subject; Paragraph 0328: Cell-Free DNA Fragmentation Patterns Reveal Changes Associated with Somatic Mutations in the Primary Tumors).
Regarding Claim 24 and 29, Abdueva teaches selecting the therapy further comprises changing from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification (Paragraph 0209: classification can be used to identify patients to be given a certain therapy, to be taken off a therapy treatment; Paragraph 0220: may yield insight into tumor status of a subject from which the cell-free DNA sample was acquired, such as tissue of origin, tumor druggability, and tumor resistance to treatment).
Regarding Claim 25, Abdueva teaches the predictive model defines a feature space corresponding to the set of subject genes and the set of subject gene alteration categories (Paragraph 0336: A fragmentome profile can be modeled in 3D coordinate space as a density of observed fragment starts and length associated with specific conditions (e.g., malignant or non-malignant).
Claim Rejections - 35 USC § 103
The previously issued 103 rejection did not address all of the amended limitations. Therefore, the following rejection is reiterated and modified as has been necessitated by amendment.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 5, 7, 9, 10, 13, 15, 18, 19 and 21-29 are rejected under 35 U.S.C. 103 as being unpatentable over Abdueva (US 20190352695 A1), as applied to claims 1, 3, 5, 7, 9, 10, 15, 18, and 21-29 in the 102 Rejection above, in view of Marquard et al. (2015, BMC Medical Genomics, Vol. 8: 1-13, previous action). Italicized text from reference art. Underlined text correspond to amendment.
Applicable claims include:
Claim 1. A method for classifying tumor origin sites, the method comprising: (Claim 1.i) acquiring, by one or more processors, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer; (Claim 1.ii) generating, by the one or more processors, using the sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes; (Claim 1.iii) applying, by the one or more processors, a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated from sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii)a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort; (Claim 1.iv) determining, by the one or more processors, based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject; (Claim 1.v) selecting, by the one or more processors, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and providing, by the one or more processors, an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer.
Claim 3. The method of claim 1, wherein a feature set for the predictive model comprises one or more of mutations, indels, focal amplifications and deletions, broad copy number gains and losses, structural rearrangements, mutation signatures, mutation rate, or sex.
Claim 5. The method of claim 1, further comprising training the predictive model using supervised or unsupervised learning.
Claim 7. The method of claim 1, wherein generating the training dataset further comprises acquiring, from a sequencing device, the sequence reads corresponding to the genetic material from the cohort of study subjects, and using the sequence reads to generate the training dataset.
Claim 9. The method of claim 1, wherein the training dataset comprises gene alteration categories comprising one or more selected from a group consisting of gene amplification (AMP), chromosome gain, homozygous deletion, hotspot, allele, chromosome loss, promoter, signature, structural variant (SV), truncation, and variant of unknown significance (VUS).
Claim 10. The method of claim 1, wherein the set of labels indicate whether a set of genes in the training dataset is from a respective subject diagnosed with cancer in the cohort of study subjects.
Claim 13. The method of claim 1, wherein the predictive model is further configured to generate a confidence score corresponding to a likelihood of the tumor origin site identified by the classification.
Claim 15. (Currently Amended) A system for classifying tumor origin sites, the system comprising a computing device having one or more processors configured to: (Claim 15.i) acquire, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer; (Claim 15.ii) generate, using the subject sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes; (Claim 15.iii) apply a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated using sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii) a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort; (Claim 15.iv) determine, based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject; (Claim 15.v) select, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and provide an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer.
Claim 18. The system of claim 15, wherein the one or more processors are further configured to generate the training dataset using the sequence reads corresponding to the genetic material from the study subjects in the cohort.
Claim 19. (Currently Amended) The system of claim 15, wherein the predictive model is further configured to generate a confidence score for the classification, wherein the confidence score corresponds to a likelihood of the cancer origin site in the subject.
Claim 21. The method of claim 1, wherein the plurality of therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy.
Claim 22. The method of claim 1, wherein the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma.
Claim 23. The method of claim 1, wherein the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject.
Claim 24. The method of claim 1, wherein selecting the therapy further comprises changing from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification.
Claim 25. The method of claim 1, wherein the predictive model defines a feature space corresponding to the set of subject genes and the set of subject gene alteration categories.
Claim 26. The system of claim 15, wherein the plurality of therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy.
Claim 27. The system of claim 15, wherein the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma.
Claim 28. The system of claim 15, wherein the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject.
Claim 29. The system of claim 15, wherein the one or more processors are further configured to change from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification.
Regarding Claims 1 and 15, Abdueva teaches (Claim 1.i) acquiring, via a sequencing device, subject sequence reads corresponding to genetic material in a tissue sample from a subject with cancer (Paragraph 0004: uses of cell-free nucleic acids (e.g., DNA or RNA). Such uses include detecting, monitoring and determining treatment for a subject having or suspected of having a health condition, such as a disease (e.g., cancer). use sequence information to assess a fragmentome; Paragraph 0138: The biological sample can be derived from any tissue; Paragraph 0178: sequencing using HiSeq (Illumina)). Abdueva teaches (Claim 1.ii) generating, using the sequence reads, a subject sample dataset comprising (i) a set of subject genes and (ii) a set of subject gene alteration categories corresponding to the set of subject genes (Paragraph 0009: an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0026: structural variation consisting of: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation). Abdueva teaches (Claim 1.iii) applying a predictive model to the subject sample dataset, wherein the predictive model is trained using a training dataset generated from sequence reads corresponding to genetic material from a cohort of study subjects with known cancers, the training dataset comprising (i) a set of genes, (ii) a set of gene alteration categories corresponding to the set of genes, and (iii) a set of labels characterizing tumor origin sites for the known cancers of the study subjects in the cohort (Paragraph 0009: the classifier comprises a machine learning engine. the classifier further comprises an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0015: providing a training set comprising a set of reference classifications for each of the populations of cell-free DNA obtained from control subjects; a set of phenotypic classifications for each of the populations of cell-free DNA obtained from subjects having observed phenotypes; and training, by a computer, the classifier using the training set; Paragraph 0016: the subjects having an observed phenotype comprise subjects with a tissue-specific cancer; Paragraph 0036: detecting a deviation between the cell-free DNA from the subject and one or more reference populations of cell-free DNA, wherein the deviation is indicative of the presence of a condition or property in the subject. the analysis comprises tissue of origin analysis). Abdueva teaches (Claim 1.iv) determining based on applying the predictive model to the subject sample dataset, a classification identifying a tumor origin site associated with the cancer in the subject (Paragraph 0036: detecting a deviation between the cell-free DNA from the subject and one or more reference populations of cell-free DNA, wherein the deviation is indicative of the presence of a condition or property in the subject. the analysis comprises tissue of origin analysis). Abdueva teaches (Claim 1.v) selecting, for the subject, a therapy from a plurality of therapies for the cancer based on the tumor origin site; and providing an output based on an association between the subject with the classification and the therapy, wherein the subject is administered with the therapy for the cancer (Paragraph 0032-0033: disclosed herein is a method of classifying a test sample from a subject, comprising: classifying the test population of cell-free DNA using a trained classifier. the method further comprises performing a therapeutic intervention on the subject based on the classification of the population of cell-free DNA). The classification includes tumor origin site (see 1.iv above). Additionally, Abdueva teaches the methods are performed by computer processing system, which include processors (Paragraph 0312: The present disclosure provides computer systems that are programmed to implement methods of the disclosure; Paragraph 0313: The computer system includes a central processing unit, which can be a plurality of processors). Claim 15 recites the limitations of claim 1 directed to a system.
Regarding Claim 3, Abdueva teaches a feature set for the predictive model comprises one or more of mutations, indels, focal amplifications and deletions, broad copy number gains and losses, structural rearrangements, mutation signatures, mutation rate, or sex (Paragraph 0026: the structural variation is selected from: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation).
Regarding Claim 5, Abdueva teaches training the predictive model using supervised or unsupervised learning (Paragraph 0014: the classifier trained using a training set; Paragraph 0150: Machine learning algorithms may be supervised or unsupervised).
Regarding Claims 7 and 18, Abdueva teaches generating the training dataset further comprises acquiring, from a sequencing device, the sequence reads corresponding to the genetic material from the cohort of study subjects, and using the sequence reads to generate the training dataset (Paragraph 0009: the classifier comprises a machine learning engine. the classifier further comprises an input of a set of genetic variants at one or more loci of the genome. the set of genetic variants comprises one or more loci of reported tumor markers; Paragraph 0282: A method is provided for creating a trained classifier, comprising providing a plurality of different classes, wherein each class represents a set of subjects with a shared characteristic (e.g., from one or more cohorts)).
Regarding Claim 9, Abdueva teaches the training dataset comprises gene alteration categories comprising one or more selected from a group consisting of gene amplification (AMP), chromosome gain, homozygous deletion, hotspot, allele, chromosome loss, promoter, signature, structural variant (SV), truncation, and variant of unknown significance (VUS) (Paragraph 0026: the structural variation is a variation in nucleosomal positioning selected from the group consisting of: an insertion, a deletion, a translocation, a gene rearrangement, methylation status, a micro-satellite, a copy number variation, a copy number-related structural variation, or any other variation which indicates differentiation. In some embodiments, the cluster is a hotspot; Paragraph 0214: a classifier (e.g., a machine learning engine) that is trained to classify said sample as having or not having each of a set of single nucleotide variants (SNVs) or other genetic variants)
Regarding Claim 10, Abdueva teaches the set of labels indicate whether a set of genes in the training dataset is from a respective subject diagnosed with cancer in the cohort of study subjects (Paragraph 0031: each of the plurality of different classes is selected from the group consisting of: healthy, breast cancer, colon cancer, lung cancer, pancreatic cancer, prostate cancer, ovarian cancer, melanoma, and liver cancer; Paragraph 0085: providing training data from a plurality of training subject, including a plurality subjects from a first class and a plurality of subjects from a second class, and wherein the training data includes, from a training sample from each training subject, a multi-parametric distribution of cfDNA molecules mapping to one or more selected genomic loci; and training a machine learning algorithm to develop a classification model that, based on test data from a test sample from a test subject, including the multi-parametric distribution of cfDNA molecules mapping to the selected genomic loci, classifies the subject as having cancer or not having cancer).
Regarding Claim 21 and 26, Abdueva teaches the therapies comprises at least one of surgery, hormonal therapy, chemotherapy, immunotherapy, or targeted therapy (Paragraph 0195: a treatment may be a targeted treatment such as a tyrosine kinase inhibitor).
Regarding Claim 22 and 27, Abdueva teaches the cancer comprises at least one of bladder cancer, breast cancer, cholangiocarcinoma, colorectal cancer, endometrial cancer, esophagogastric cancer, gastrointestinal stromal tumor, germ cell tumor, glioma, head and neck cancer, melanoma, mesothelioma, neuroblastoma, non-small cell lung cancer, ovarian cancer, pancreatic cancer, pancreatic neuroendocrine tumor, prostate cancer, renal cell cancer, small cell lung cancer, thyroid cancer, or uveal melanoma (Paragraph 0031: each of the plurality of different classes is selected from the group consisting of: healthy, breast cancer, colon cancer, lung cancer, pancreatic cancer, prostate cancer, ovarian cancer, melanoma, and liver cancer).
Regarding Claim 23 and 28, Abdueva teaches the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject (Paragraph 0138: biological sample refers to a tissue or fluid sample derived from a subject; Paragraph 0328: Cell-Free DNA Fragmentation Patterns Reveal Changes Associated with Somatic Mutations in the Primary Tumors).
Regarding Claim 24 and 29, Abdueva teaches selecting the therapy further comprises changing from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification (Paragraph 0209: classification can be used to identify patients to be given a certain therapy, to be taken off a therapy treatment; Paragraph 0220: may yield insight into tumor status of a subject from which the cell-free DNA sample was acquired, such as tissue of origin, tumor druggability, and tumor resistance to treatment).
Regarding Claim 25, Abdueva teaches the predictive model defines a feature space corresponding to the set of subject genes and the set of subject gene alteration categories (Paragraph 0336: A fragmentome profile can be modeled in 3D coordinate space as a density of observed fragment starts and length associated with specific conditions (e.g., malignant or non-malignant).
Abdueva does not explicitly teach a confidence score for the origin prediction (Claim 13 and 19). Marquard et al. teach district but related methods for using machine leaning and sequence data to predict tumor origin.
Regarding Claim 9, Marquard et al. teaches the training dataset comprises gene alteration categories including chromosome gain (copy number aberrations), hotspot (base substitution frequency), chromosome loss (copy number aberrations), structural variant (non-synonymous mutations), truncation (trinucleotide base substitution frequency), and variant of unknown significance (non-synonymous mutations) (Page 3, Column 1, Paragraphs 2-5).
Regarding Claim 10, Marquard et al. teach respective subject diagnosed with cancer in the cohort of study subjects (Page 2, Column 2, Paragraph 3: Sample ID - the same sample name matched to more than one tumor ID; Page 3, Column 1, Paragraph 6: we trained an ensemble of ten classifiers, each intended to discriminate one primary site from the other nine. Based on cross validation accuracy, we found that random forests provided the best performance across the 10 primary sites).
Regarding Claim 13 and 19, Marquard et al. teach the predictive model is further configured to generate a confidence score corresponding to a likelihood of the tumor/cancer origin site identified by the classification. (Page 6, Column 2, Paragraph 2: we defined a “confidence score” as the difference between the individual classification scores for the two highest-scoring tissues. We found that the confidence score was indeed a strong indicator of accuracy, and that a large fraction of tumors could be classified with high confidence).
Regarding Claim 23 and 28, Marquard et al. suggest the tissue sample is obtained from at least one of a primary site or a metastatic site of the subject (Page 11, Column 2, Paragraph 2: Classifiers such as ours may be useful for establishing the primary site in patients with metastatic disease of unknown origin).
Regarding Claim 24 and 29, Marquard et al. suggest the therapy further comprises changing from a second therapy previously identified for the subject to the therapy based on the tumor origin site identified by the classification (Page 11, Column 2, Paragraph 2: Classifiers such as ours may be useful in order to direct patients to the most optimal treatment).
It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to combine Marquard et al. with Abdueva. Marquard et al. teach methods for prediction tumor origin from information derived from sequence data, with enhanced accuracy over other methods, as established through confidence level estimation, allowing it to be useful for medical applications (Page 11, Column 1, Paragraph 4: our method, using the same data, performed better; Page 11, Column 2, Paragraph 4: Our method can be used to identify the likely primary site of a tumor specimen with sufficient accuracy to be clinically useful). Additionally, Marquard et al. suggest using their methods with cell free DNA based analyses, as performed by Abdueva (Page 11, Column 2, Paragraph 4: identify the origin of circulating tumor cells or DNA found in blood-based screens). Furthermore, one of ordinary skill in the art would predict that the methods could be readily combined with a reasonable expectation of success because both are within the same technical field – using information derived from sequence date and machine leaning to predict cancer origin.
Claims 1, 3-5, 7, 9, 10, 13, 15, 18, 19 and 21-29 are rejected under 35 U.S.C. 103 as being unpatentable over Abdueva, in view of Marquard et al., as applied to claims 1, 3, 5, 7, 9, 10, 13, 15, 18, 19 and 21-29 above, and in further view of Soh et al. (2017, Genomic Medicine, Vol. 9: 1-11, previous action). Italicized text from reference art. Underlined text correspond to amendment.
Applicable claims include:
Claims 1, 3, 5, 7, 9, 10, 13, 15, 18, 19 and 21-29 are presented above
Claim 4. The method of claim 3, wherein classifier scores for the predictive model were calibrated using multinomial logistic regression to match empirically observed classification probabilities.
Regarding Claims 1, 3, 5, 7, 9, 10, 13, 15, 18, 19 and 21-29, these limitations are taught by Abdueva and Marquard et al. as indicated above.
Abdueva and Marquard et al. do not explicitly teach multinomial logistic regression (Claim 4). Soh et al. teach district but related methods for using machine leaning and sequence data to predict tumor origin.
Regarding Claim 4, Soh et al. classifier scores for the predictive model were calibrated using multinomial logistic regression to match empirically observed classification probabilities (Page 4, Column 1, Paragraph 3: To select features in the logistic regression model, we used the glmnet implementation of L1-regularised logistic regression, which follows symmetric formulation of multiclass logistic regression; Page 4, Column 2, Paragraph 2: Development of a classifier based on somatic point mutations). Multinomial logistic regression is synonymous with multiclass logistic regression.
It would have been obvious to one of ordinary skill in the art at the time of the effective filing date to combine Soh et al. with Marquard et al. and Abdueva. Soh et al. their machine learning methods, which include model optimization through multiclass regression, are highly efficient while expanding the types of variants assessed (Page 2, Column 2, Paragraph 2: With this optimized approach, we found that a gene panel of as few as 50 genes allows cancer-type prediction with an accuracy of around 77 %; Page 10, Column 1, Paragraph 1: To our knowledge, our work is the first to show systematically that cancer types can also be identified from somatic point mutations and copy number alterations). Furthermore, one of ordinary skill in the art would predict that the methods could be readily combined with a reasonable expectation of success because all are within the same technical field – using information derived from sequence data and machine leaning to predict cancer origin.
Double Patenting
No double patenting rejections are issued.
Conclusion
No claims are allowed.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BLAKE H ELKINS whose telephone number is (571)272-2649. The examiner can normally be reached Monday-Thursday 8-5PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, 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.
/B.H.E./Examiner, Art Unit 1687
/Karlheinz R. Skowronek/Supervisory Patent Examiner, Art Unit 1687
Prosecution Insights