Patent Application
20230420134
Recent studies on diverse cancer types indicate that tumors possess an endogenous microbiome that may be harnessed for improved prognosis, diagnosis, therapeutic selection, and to enhance our understanding of intra-tumor biology. Thus far, reports have provided evidence for a tumor-unique microbiome in cancers of the breast, prostate, colon, brain, bone, skin, and pancreas. Just how microbes come to colonize tumors is an area of active debate, but it has been demonstrated that independent of etiology, cancer-specific microbial associations can be exploited for diagnostic purposes via sequencing-based detection of microbial nucleic acids. Indeed, Poore et al., have shown that detection of microbial DNA (mbDNA) fragments in patient plasma samples could correctly discriminate among various cancers and non-cancer samples (PMID: 32214244 and PCT WO 2020/093040).
In Poore et al., metagenomic shotgun sequencing data derived from total plasma cell-free DNA—which, perforce, contains a mixture of human cfDNA and microbial cfDNA—was computationally segregated according to whether the sequencing reads mapped to a human reference genome. All unmapped—i.e., non-human—reads were then classified down to the genus level using a fast k-mer mapping approach (Kraken, PMID: 24580807). The output of the Kraken analysis is a list of taxonomic classifications for the sequencing reads in a sample and the read counts associated with each taxonomic assignment. In Poore al., this paired data (genera and read counts) derived from HIV-negative, healthy donors and cancer cohorts (lung, prostate and melanoma) were used as the inputs for machine learning classification algorithms to identify features unique to each cancer type. One disadvantage of using taxonomy-based classification is that the taxonomy assignment, while useful for cancer classification, does not directly inform one of what, if any, cancer-specific biochemical capacities may be provided by the tumor-associated microbiota. Having a method that can both classify and diagnose cancers while also providing information pertaining to the presence/abundance of biochemical capacities could help elucidate how intratumoral microbiota contribute to tumor-specific biology by either providing or consuming tumor required or produced metabolites, respectively.
Other prior art that is relevant to this field is as follows: U.S. Publication No. 2018/0223338 describes using the solid tissue microbiome or salvia microbiome in identifying and diagnosing head and neck cancer; and U.S. Publication No. 2018/0258495A1 describes using the solid tissue microbiome or fecal microbiome to detect colon cancer, some kinds of mutations associated with colon cancer, and a kit to collect and amplify the corresponding microbes. PCT WO 2019/191649 describes using cell-free microbial DNA and machine learning models to distinguish subjects having advanced adenoma and/or colorectal cancer from healthy subjects, wherein the machine learning algorithms rely upon DNA sequence reads mapping to reference genomes as input for analysis.
The disclosure provided herein describes systems and methods capable of accurately diagnosing or determining the presence or lack thereof cancer and other diseases, its subtypes, and its likelihood to respond to certain therapies solely using nucleic acids of non-human origin from a tissue or liquid biopsy sample. Specifically, the present invention provides methods that may identify the presence and abundance of microbial functional genes (and fragments thereof) and biochemical pathways present in a biopsy sample (e.g., a liquid or tissue biopsy). In some cases, the microbial functional genes and biochemical pathways may be utilized to train one or more models and/or predictive models, described elsewhere herein. Such trained models may output a determination of the presence or lack thereof a subject's cancer or the likelihood of therapeutic response and/or efficacy when a subject receives a treatment.
The methods of the present invention disclosed herein provide a method to generate a diagnostic model capable of diagnosing and classifying cancer whilst also providing information pertaining to the presence and or abundance of biochemical capacities to elucidate intratumoral microbiota contributions to tumor-specific biology. In some cases, tumor-specific biology may pertain to how intratumoral microbiota contribute to consuming tumor required or produced metabolites. For example, pathway-based analysis may help illuminate microbe-catalyzed conversions of therapeutic small molecules, enzymatic activities which may alter the in vivo efficacy of said molecules. To give a specific example using a therapeutic case where microbial activity has been directly implicated—bacterial mediated deamination of the cytidine moiety in the chemotherapeutic gemcitabine: it has been shown that bacteria expressing a long isoform of cytidine deaminase (cdd) can convert the active form of gemcitabine to the less therapeutically efficacious 2′2-difluorodeoxyuridine (PMID: 28912244). With this as biochemical test case, the present invention disclosed herein is aimed to address the unmet need of diagnosing cancer in a subject by way of his/her circulating microbial DNA, as detailed by Poore et al., while simultaneously detecting the presence/absence or abundance of the cancer-associated isoform of cdd. In view of this example, in some embodiments, the methods disclosed herein may not be limited only to diagnosing cancer in a subject but also predicting that the subject, if found to harbor the long isoform of cdd would likely not respond to gemcitabine treatment.
Aspects of the disclosure provided herein, in some embodiments, comprise a method of determining the presence or lack thereof cancer of a subject. In some embodiments, the method comprises: (a) providing one or more sequencing reads of a subject's biological sample; (b) filtering the sequencing reads with a genome database to produce a set of filtered non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) determining the presence or lack thereof cancer of the subject as an output to the trained model when the trained model is provided an input of the set of protein database associations. In some embodiments, the set of protein database associations comprises a set of functional genes, biochemical pathways, or any combination thereof. In some embodiments, the method further comprises decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some embodiments, translating is completed in silico. In some embodiments, the biological sample is a tissue, liquid biopsy, or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the biological sample comprises a nucleic acid composition, wherein the nucleic acid composition comprises DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the trained model is trained with a set of functional gene and biochemical pathway abundances that are present or absent with a characteristic abundance for a cancer of interest. In some embodiments, the non-human sequences originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some embodiments, the trained model is configured to determine a category or tissue-specific location of the cancer of the subject. In some embodiments, the trained model is configured to determine one or more types of cancer of the subject. In some embodiments, the trained model is configured to determine one or more subtypes of the cancer of the subject. In some embodiments, the trained model is configured to determine a stage of cancer of the subject, cancer prognosis of the subject, or any combination thereof. In some embodiments, the trained model is configured to determine the presence or lack thereof cancer at a low-stage (stage I or stage II) tumor. In some embodiments, the trained model is configured to determine an immunotherapy response of the second set of one or more subjects when the second set of one or more subjects are provided the immunotherapy. In some embodiments, the method further comprises outputting with the trained model a therapy for the subject to treat the subject's cancer, wherein the subject will respond with positive therapeutic efficacy when administered the therapeutic. In some embodiments, the cancer of the subject comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof. In some embodiments, the liquid biopsy comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some embodiments, filtering comprises computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some embodiments, the protein database is the UniRef database. In some embodiments, translating is accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some embodiments, the mapping of the non-human proteins to the biochemical pathways is accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some embodiments, the biochemical pathways are generated with the software package MinPath.
Aspects of the disclosure, in some embodiments, describe A method of providing a determination of the presence or lack thereof cancer of a subject, the method comprising: (a) sequencing a nucleic acid compositions of a subject's biological sample thereby generating sequencing reads; (b) filtering the sequencing reads with a genome database to produce a set of filtered non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) providing a determination of the presence or lack thereof cancer of the subject as an output of a trained model when the trained model is provided an input of the set protein database associations. In some embodiments, the set of protein database associations comprises a set of functional genes, biochemical pathways, or any combination thereof. In some embodiments, the method further comprises decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some embodiments, translating is completed in silico. In some embodiments, the biological sample is a tissue, liquid biopsy sample, or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the biological sample comprises a nucleic acid composition, wherein the nucleic acid composition comprises DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the trained model is trained with a set of functional gene and biochemical pathway abundances that are present or absent with a characteristic abundance for a cancer of interest In some embodiments, the non-human sequences originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some embodiments, the trained model is configured to determine a category or tissue-specific location of the cancer of the subject. In some embodiments, the trained model is configured to determine one or more types of the cancer of the subject. In some embodiments, the trained model is configured to determine one or more subtypes of the cancer of the subject. In some embodiments, the trained model is configured to determine a stage of a cancer of the subject, cancer prognosis of the subject, or any combination thereof. In some embodiments, the trained model is configured to determine the presence or lack thereof a cancer at a low-stage (stage I or stage II) tumor. In some embodiments, the trained model is configured to determine an immunotherapy response of the subject when the subject is provided an immunotherapy. In some embodiments, the method further comprises outputting with the trained model a therapy for the subject to treat the subject's cancer, wherein the subject will respond with positive therapeutic efficacy when administered the therapy. In some embodiments, the cancer of the subject comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof. In some embodiments, the liquid biopsy comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some embodiments, filtering comprises computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some embodiments, the protein database is the UniRef database. In some embodiments, translating is accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some embodiments, the mapping of the non-human proteins to the biochemical pathways is accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some embodiments, the biochemical pathways are generated with the software package MinPath.
Aspects of the disclosure provided herein, in some embodiments, describe a method of training a model configured to determine the presence or lack thereof cancer of a subject, the method comprising: (a) providing a dataset comprising nucleic acid sequencing reads of a first set of one or more subjects' nucleic acid compositions and a corresponding one or more cancers of the first set of one or more subjects; (b) filtering the nucleic acid sequencing reads with a build of a genome database to generate non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) training a model with the set of protein database associations and the corresponding one or more cancer states of the first set of one or more subjects, thereby generating a trained model configured to determine the presence or lack thereof cancer of a second set of one or more subjects. In some embodiments, the set of protein database associations comprises a set of functional genes, biochemical pathways, or any combination thereof. In some embodiments, the method further comprises decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some embodiments, translating is completed in silico. In some embodiments, the biological sample is a tissue, liquid biopsy sample or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the biological sample comprises a nucleic acid composition, wherein the nucleic acid composition comprises DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the trained model is trained with a set of functional gene and biochemical pathway abundances that are present or absent with a characteristic abundance for a cancer of interest. In some embodiments, the non-human sequences originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some embodiments, the trained model is configured to determine a category or tissue-specific location of the second set of one or more subjects' cancer. In some embodiments, the trained model is configured to determine one or more types of the second set of one or more subjects' cancer. In some embodiments, the trained model is configured to determine one or more subtypes of the second set of one or more subjects' cancer. In some embodiments, the trained model is configured to determine a stage of the second set of one or more subjects' cancer, cancer prognosis, or any combination thereof. In some embodiments, the trained is configured to determine the presence or lack thereof the second set of one or more subjects' cancer at a low-stage (stage I or stage II) tumor. In some embodiments, the trained model is configured to determine an immunotherapy response of the subject when the subject is provided an immunotherapy. In some embodiments, the method further comprises outputting with the trained model a therapy to treat the second set of one or more subjects' cancer, wherein the second set of one or more subjects will respond with positive therapeutic efficacy when administered the therapy. In some embodiments, the first and second set of one or more subjects' cancer comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof. In some embodiments, the liquid biopsy comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some embodiments, filtering comprises computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some embodiments, the protein database is the UniRef database. In some embodiments, translating is accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some embodiments, the mapping of the non-human proteins to the biochemical pathways is accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some embodiments, the biochemical pathways are generated with the software package MinPath. In some embodiments, the dataset further comprises a corresponding previous or current treatment administered to the first set of one or more subjects. In some embodiments, the dataset further comprises a treatment efficacy of the first set of one or more subjects' previous or current treatment administration.
Aspects of the disclosure provided herein, in some embodiments, describes a computer-implemented method for utilizing a trained predictive model to provide a therapeutic treatment prediction for one or more subjects, the method comprising: (a) receiving a first set of one or more subjects' nucleic acid sequencing reads of a biological sample and corresponding cancer classification; (b) filtering the nucleic acid sequencing reads with a build of a genome database to generate non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) utilizing a trained predictive model to provide a treatment prediction for the first set of one or more subjects when the set of protein database associations are provided as an input to the trained predictive model. In some embodiments, the trained predictive model is trained on a second set of one or more subjects' nucleic acid sequencing reads of a biological sample, corresponding cancer classification, corresponding treatment administered, corresponding treatment response, or any combination thereof. In some embodiments, the second set of one or more subjects are different than the first set of one or more subjects. In some embodiments, the set of protein database associations comprises a set of functional genes, biochemical pathways, or any combination thereof. In some embodiments, the method further comprising decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some embodiments, translating is completed in silico. In some embodiments, the biological sample is a tissue, liquid biopsy sample or any combination thereof. In some embodiments, the first and/or second set of one or more subjects are human or a non-human mammal. In some embodiments, the biological sample nucleic acid composition comprises DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the non-human sequences originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some embodiments, the treatment prediction comprises an immunotherapy response of the first set of one or more subjects when the first set of one or more subjects are administered an immunotherapy. In some embodiments, the treatment prediction comprises a therapeutic efficacy that the first set of one or more subjects will respond with positive efficacy. In some embodiments, the cancer classification comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof. In some embodiments, the liquid biopsy comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some embodiments, filtering comprises computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some embodiments, the protein database is the UniRef database. In some embodiments, translating is accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some embodiments, the mapping of the non-human proteins to the biochemical pathways is accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some embodiments, the biochemical pathways are generated with the software package MinPath.
Aspects of the disclosure provided herein, in some embodiments, comprise a method of changing a subject's cancer treatment with a trained predictive model. In some embodiments, the method comprises: (a) providing one or more sequencing reads of a subject's biological sample with cancer, cancer type, and treatment administered to treat the cancer; (b) filtering the sequencing reads with a genome database to produce a set of filtered non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) changing the subject's cancer treatment when the treatment administered differs from a treatment recommendation outputted by a trained predictive model when inputted with the set of protein database associations. In some embodiments, the trained predictive model is trained on a second set of one or more subjects' nucleic acid sequencing reads of a biological sample, corresponding cancer classification, corresponding treatment administered, corresponding treatment response, or any combination thereof. In some embodiments, the second set of one or more subjects are different than the first set of one or more subjects. In some embodiments, the set of protein database associations comprises a set of functional genes, biochemical pathways, or any combination thereof. In some embodiments, the method further comprises decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some embodiments, translating is completed in silico. In some embodiments, the biological sample is a tissue, liquid biopsy sample or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the biological sample nucleic acid composition comprises DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the non-human sequences originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some embodiments, the treatment recommendation comprises an immunotherapy response of the subject when the subject is administered an immunotherapy. In some embodiments, the treatment recommendation comprises a therapeutic that the subject will respond with positive efficacy. In some embodiments, the subject's cancer comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof. In some embodiments, the liquid biopsy comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some embodiments, filtering comprises computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some embodiments, the protein database is the UniRef database. In some embodiments, the translating is accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some embodiments, the mapping of the non-human proteins to the biochemical pathways is accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some embodiments, the biochemical pathways are generated with the software package MinPath.
Aspects disclosed herein provide a method of creating a diagnostic model for diagnosing cancer in a subject based on taxonomy-independent non-human functional gene abundances in a biological sample comprising: (a) sequencing nucleic acid compositions in the biological sample to generating sequencing reads; (b) filtering the sequencing reads with a build of a genome database to isolate non-human sequencing reads; (c) translating in silico a composition of non-human sequencing reads to identify non-human proteins represented in the non-human sequencing reads; (c) mapping the non-human proteins to a non-human protein database of non-human functional genes and biochemical pathways; (d) mapping the non-human proteins to a non-human protein database of non-human functional genes and biochemical pathways; (e) generating functional gene and biochemical pathway abundance tables with the non-human functional genes and biochemical pathways; (f) analyzing the biochemical pathway abundance tables with a trained machine learning algorithm; and (g) using an output of the trained machine learning algorithm to provide a diagnosis of a presence or absence of the cancer of the subject. In some embodiments, the biological sample is a tissue, liquid biopsy sample or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the nucleic acid composition comprises a total population of DNA, RNA, cell-free DNA (cfDNA), cell-free RNA (cfRNA), exosomal DNA, exosomal RNA or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the output of the trained machine learning algorithm comprises an analysis of the functional gene and biochemical pathway abundance tables. In some embodiments, the trained machine learning algorithm is trained with a set of functional gene and biochemical pathway abundances that are known to be present with a characteristic abundance or absent in a cancer of interest. In some embodiments, the diagnostic model utilizes biochemical pathway abundance information from one or more of the following domains of life: bacterial, archaeal, and/or fungal. In some embodiments, the diagnostic model diagnoses a category or tissue-specific location of cancer. In some embodiments, the diagnostic model is used to diagnose one or more types of cancer in a subject. In some embodiments, the diagnostic model is used to diagnose one more subtypes of cancer in a subject. In some embodiments, the diagnostic model is used to predict the stage of cancer in a subject and/or predict cancer prognosis in the subject. In some embodiments, the diagnostic model is used to diagnose a type of cancer at a low-stage (stage I or stage II) tumor. In some embodiments, the diagnostic model is used to predict immunotherapy response of a subject. In some embodiments, the diagnostic model is utilized to select an optimal therapy for a particular subject. In some embodiments, the diagnostic model is utilized to longitudinally model a course of one or more cancers' response to a therapy and to then adjust a treatment regimen. In some embodiments, the diagnostic model diagnoses one or more of the following: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, or uveal melanoma. In some embodiments, the diagnostic model identifies and removes certain non-human features as contaminants termed noise, while selectively retaining other non-human features termed signal. In some embodiments, the liquid biopsy sample includes but is not limited to one or more of the following: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, or exhaled breath condensate. In some embodiments, the filtering comprises computationally filtering of sequencing reads by bowtie2, Kraken programs or any combination thereof. In some embodiments, the protein database is the UniRef database. In some embodiments, the non-human protein database is queried to identify proteins represented in the non-human sequencing reads is performed with the software package DIAMOND. In some embodiments, the database of biochemical pathways is the KEGG or MetaCyc Database. In some embodiments, generating biochemical pathway abundance tables is performed with the software package MiniPath.
Aspects disclosed herein provide a method of creating a diagnostic model for diagnosing cancer in a subject based on taxonomy-independent non-human functional gene abundances in a biological sample, the method comprising: (a) sequencing nucleic acid compositions in the biological sample to generate sequencing reads; (b) filtering the sequencing reads with a build of a genome database to isolate non-human sequencing reads; (c) mapping the non-human sequencing reads to a database of sequenced genomes; (d) generating a plurality of mapped genomic coordinates between the non-human sequencing reads and the database of sequenced genomes; (e) using the plurality of mapped genomic coordinates to query a database of known non-human proteins to calculate an abundance; (f) mapping the non-human proteins to a database of functional genes and biochemical pathways; (g) generating a plurality of functional gene and biochemical pathway abundance tables; (h) analyzing the functional gene and biochemical pathway abundance tables with a trained machine learning algorithm; and (i) using an output of the trained machine learning algorithm analysis of the plurality of functional gene and biochemical pathway abundance tables to diagnose a presence or absence of the cancer of the subject. In some embodiments, the diagnostic model utilizes a biochemical pathway abundance information from one or more of the following domains of life: bacterial, archaeal, and/or fungal. In some embodiments, the biological sample is a tissue, liquid biopsy sample or any combination thereof. In some embodiments, the subject is human or a non-human mammal. In some embodiments, the nucleic acid composition comprises a total population of DNA, RNA, cell-free DNA (cfDNA), cell-free RNA (cfRNA), exosomal DNA, exosomal RNA or any combination thereof. In some embodiments, the genome database is a human genome database. In some embodiments, the output of the trained machine learning algorithm comprises an analysis of the plurality of functional gene and biochemical pathway abundance tables. In some embodiments, the trained machine learning algorithm is trained with a set of functional gene and biochemical pathway abundances that are known to be present with a characteristic abundance or absent in the cancer of interest. In some embodiments, the diagnostic model diagnoses a category or tissue-specific location of cancer. In some embodiments, the diagnostic model is used to diagnose one or more types of cancer in a subject. In some embodiments, the diagnostic model is used to diagnose one or more subtypes of cancer in a subject. In some embodiments, the diagnostic model is used to predict the stage of cancer in a subject and/or predict cancer prognosis in the subject. In some embodiments, the diagnostic model is used to diagnose a type of cancer at low-stage (stage I or stage II) tumor. In some embodiments, the diagnostic model is used to predict immunotherapy response of a subject. In some embodiments, the diagnostic model is utilized to select an optimal therapy for a particular subject. In some embodiments, the diagnostic model is utilized to longitudinally model a course of one or more cancers' response to a therapy and to then adjust a treatment regime. In some embodiments, the diagnostic model diagnoses one or more of the following: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, or uveal melanoma. In some embodiments, the diagnostic model identifies and removes certain non-human features as contaminants termed noise, while selectively retaining other non-human features termed signal. In some embodiments, the liquid biopsy includes but is not limited to one or more of the following: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, or exhaled breath condensate. In some embodiments, filtering comprises computationally filtering of sequencing reads by botwie2, Kaken programs or any combination thereof. In some embodiments, the database of sequenced genomes is the Web of Life database. In some embodiments, the protein database is the UniRef database. In some embodiments, the database of biochemical pathways is the KEGG or MetaCyc database.
In some embodiments, the invention provides a method for broadly creating patterns of microbial functional gene presence or abundance (‘signatures’) that are associated with the presence and/or type of cancer using liquid biopsy samples. These ‘signatures’ can then be deployed to diagnose the presence, kind, and/or subtype of cancer in a human.
In some embodiments, the invention provides a method for broadly creating patterns of microbial functional gene or abundance that are associated with the presence and/or type of cancer using primary tumor tissues. These ‘signatures’ can then be deployed to diagnose the presence, kind, and/or subtype of cancer in a human using liquid biopsy samples from said human.
In some embodiments, the invention provides a method of broadly diagnosing disease in a mammalian subject comprising: detecting microbial presence or abundance in a liquid biopsy sample from the subject; determining that the detected microbial functional gene or abundance is different than the microbial functional gene or abundance in a normal liquid biopsy sample, and correlating the detected microbial functional gene or abundance with a known microbial functional gene or abundance for a disease, thereby diagnosing the disease.
In some embodiments, the invention provides a method of diagnosing the type of disease in a mammalian subject comprising: detecting microbial presence or abundance in a liquid biopsy sample from the subject; determining that the detected microbial functional gene or abundance is similar or different to the microbial functional gene or abundance in a population of cancer and/or healthy patients with previously studied liquid biopsy samples, and correlating the detected microbial functional gene or abundance with the most similar liquid biopsy samples in this cohort, thereby diagnosing the disease and/or kind of disease.
In some embodiments, the invention provides a method of predicting which subjects will respond or will not respond to a particular treatment for disease, wherein the disease is cancer, wherein the subject is human, wherein the treatment is immunotherapy, wherein the immunotherapy is a PD-1 blockade (e.g. nivolumab, pembrolizumab).
In embodiments, the invention provides a method of diagnosing disease, further comprising treating the disease in the subject based on the identified non-mammalian features of the disease, wherein the disease is cancer, wherein the non-mammalian features are microbial, wherein the subject is human.
In some embodiments, the invention provides a method of diagnosing disease, further comprising longitudinal monitoring of its non-mammalian features to indicate response to treating the disease, wherein the disease is cancer, wherein the non-mammalian features are microbial, wherein the subject is human.
In some embodiments, the invention provides an assay to measure the microbial functional gene or abundance in the specified tissue samples, thereby permitting diagnosis of the disease.
In some embodiments, the invention utilizes a diagnostic model based on a machine learning architecture. In some embodiments, the invention utilizes a diagnostic model based on a regularized machine learning architecture.
In some embodiments, the invention utilizes a diagnostic model based on an ensemble of machine learning architectures. In some embodiments, the invention identifies and selectively removes certain non-mammalian features as contaminants termed noise, while selectively retaining other non-mammalian features as non-contaminants termed signal, wherein non-mammalian features are microbial.
In some embodiments, the invention provides a method of diagnosing disease wherein microbial functional gene or abundance information is combined with additional information about the host (subject) and/or the host's (subject's) cancer to create a diagnostic model that has greater predictive performance than only having microbial functional gene or abundance information alone.
In some embodiments, the diagnostic model utilizes information in combination with microbial functional gene or abundance information from one or more of the following sources: cell-free tumor DNA, cell-free tumor RNA, exosomal-derived tumor DNA, exosomal-derived tumor RNA, circulating tumor cell derived DNA, circulating tumor cell derived RNA, methylation patterns of cell-free tumor DNA, methylation patterns of cell-free tumor RNA, methylation patterns of circulating tumor cell derived DNA, and/or methylation patterns of circulating tumor cell derived RNA.
In some embodiments, microbial functional gene or abundance is detected by nucleic acid detection of one or more of the following methods: metagenomic shotgun sequencing, targeted microbial sequencing, host whole genome sequencing, host transcriptomic sequencing, cancer whole genome sequencing, and cancer transcriptomic sequencing.
In some embodiments, the microbial nucleic acids are detected simultaneously with nucleic acids from the host and subsequently distinguished.
In some embodiments, the host nucleic acids are selectively depleted, and the microbial nucleic acids are selectively retained prior to measurement (e.g. sequencing) of a combined nucleic acid pool.
In some embodiments, the invention provides that the tissue is blood, a constituent of blood (e.g. plasma), or a tissue biopsy, wherein the tissue biopsy may be malignant or non-malignant.
In some embodiments, the microbial functional gene or abundance of the cancer is determined by measuring microbial functional gene or abundance in other locations of the host.
The novel features of the invention are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present invention will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the invention are utilized, and the accompanying drawings of which:
The disclosure provided herein, describes a method to accurately diagnose and/or determine the presence or lack thereof one or more subjects' one or more cancers, subtypes, and/or the cancers likelihood of therapy response. In some cases, the one or more subjects' may be human or non-human mammals. The methods described herein may utilize nucleic acids of non-human origin from a tissue or liquid biopsy sample. This may be achieved by identifying specific patterns of microbial functional units (i.e., proteins including, but not limited to, enzymes, transcription factors, and receptors). In some embodiments, exemplary microbial enzymes that can be used for disease classification are provided in Table 1 and their presence or abundances (‘a signature’) within a sample to assign a certain probability that (1) the individual has cancer, (2) the individual has a cancer from a particular body site, (3) the individual has a particular type of cancer, (4) a cancer, which may or may not be diagnosed at the time, has a high or low likelihood or responding to a particular cancer therapy, (5) a cancer, which may or may not be diagnosed at the time, is found to harbor microbial features (e.g. microbial antigens) that can be targeted for developing a personalized therapeutic to treat the subject's cancer, or any combination thereof probabilities. Other uses for such methods are reasonably imaginable and readily implementable to those skilled in the art.
The methods described herein, may use nucleic acids of non-human origin to diagnose a condition (e.g., cancer) that has been traditionally thought to be a disease of the human genome. In some embodiments, methods may provide better clinical outcomes compared to a typical pathology report because since the methods described herein do not necessarily rely upon observed tissue structure, cellular atypia, or any other subjective measure traditionally used to diagnose cancer. In some cases, the methods may provide a high degree of sensitivity by focusing solely on microbial nucleic acid sources rather than modified human (i.e., cancerous) nucleic acid sources, which are modified often at extremely low frequencies in a background of ‘normal’ nucleic acid sources. In some embodiments, the methods disclosed herein may achieve such outcomes by either solid tissue and/or liquid biopsy samples, the latter of which may require minimal sample preparation and may be minimally invasive. In some embodiments, the liquid biopsy-based assay may overcome challenges posed by circulating tumor DNA (ctDNA) assays, which often suffer from sensitivity issues due to cell-free DNA (cfDNA) that originates from non-malignant human cells. In some instances, the liquid biopsy-based microbial assay may distinguish between cancer types, which ctDNA assays typically are not able to achieve, since most common cancer genomic aberrations are shared between cancer types (e.g., TP53 mutations, KRAS mutations). In some cases, the method described herein may constrain the size of the signatures, the method of which will be expected by someone knowledgeable in the art (e.g., regularized machine learning), the microbial assays may be made clinically available through the use of e.g. multiplexed quantitative polymerase chain reaction (qPCR), and targeted assay panels for multiplexed amplicon sequencing.
In some embodiments, the methods described herein may determine the presence or lack thereof cancer of a subject by utilizing trained models and/or trained predictive models, where the models and/or predictive models may comprise machine learning models trained on non-human functional gene and biochemical pathway abundances (i.e., non-human signatures) that can be deployed on real-time sequencing data or retrospective sequencing data (i.e., sequencing data from a database or repository). In some instances, the non-human signatures may comprise microbial signatures. In some cases, the methods for determining or diagnosing cancer of a subject may comprise a step of sequencing the nucleic acid compositions of a subject. Alternatively, the methods for determining or diagnosing cancer of a subject may comprise a step of accessing sequencing reads of a subject's biological sample nucleic acid compositions.
In some embodiments, the methods described herein may train a model by (a) taking a blood sample from a patient during a routine clinic visit; (b) preparing plasma or serum from that blood sample, extracting the nucleic acids within, and amplifying the sequences for specific microbial genes determined previously, by way of the previously trained machine learning model, to be useful signatures for diagnosing cancer; (c) obtaining a digital read-out of the presence and/or abundance of these microbial signatures; (d) normalizing the presence and/or abundance data on an adjacent computer or cloud computing infrastructure and feeding it into a previously trained machine learning model; and (e) reading out a prediction and a certain degree of confidence for how likely this sample (1) is associated with the presence or absence of cancer, (2) is associated with cancer of a particular type or bodily location, or (3) is associated with a high, intermediate, or low likelihood of response to a range of cancer therapies; and (f) using that sample's microbial information to continue training the machine learning model if additional information is later inputted by the user.
In some instances, the methods described herein may comprise a method of training a model configured to determine the presence or lack thereof cancer of the subject. In some cases, the method may comprise the steps of: (a) providing a dataset comprising nucleic acid sequencing reads of a first set of one or more subjects' nucleic acid compositions and a corresponding one or more cancers of the first set of one or more subjects; (b) filtering the nucleic acid sequencing reads with a build of a genome database to generate non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) training a model with the set of protein database associations and the corresponding one or more cancer states of the first set of one or more subjects, thereby generating a trained model configured to determine the presence or lack thereof cancer of a second set of one or more subjects. In some instances, the set of protein database associations may comprise a set of functional genes, biochemical pathways, or any combination thereof, described elsewhere herein. In some instances, the method may further comprise decontaminating the filtered non-human sequencing reads prior to step (c) to remove contaminant non-human sequencing reads. In some cases, the contaminant non-human sequencing reads may be determined a prior or from a database of contaminant non-human sequencing reads determined from experimental data analysis. In some cases, the translating of step (c) may be completed in silico. In some instances, the method may in place of or in addition to step (a) comprise the step of sequencing nucleic acid compositions of the first set of one or more subjects. In some cases, the method may further comprise outputting with the trained model a therapy to treat the second set of one or more subjects' cancer, wherein the second set of one or more subjects will respond with positive therapeutic efficacy when administered the therapy. In some cases, the dataset may further comprise a corresponding previous or current treatment administered to the first set of one or more subjects. In some cases, the dataset may further comprise a treatment efficacy of the first set of one or more subjects' previous or current treatment administration.
In some cases, the first and/or second set of one or more subjects may be human or non-human mammal. In some cases, the biological sample may comprise a tissue, liquid biopsy sample or any combination thereof. In some cases, the biological sample may comprise a nucleic acid composition, where the nucleic acid composition may comprise DNA, RNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some cases the non-human sequences may originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some instances, the liquid biopsy may comprise plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof.
In some instances, the first and/or second set of one or more subjects may comprise cancer. In some cases, the cancer may comprise acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof.
In some cases, the trained model may be trained with a set of functional gene and biochemical pathway abundances that are present or absent with a characteristic abundance for a cancer of interest. In some instances, the trained model may be configured to determine one or more subtypes of the second set of one or more subjects' cancer. In some cases, the trained model may be configured to determine a stage of the second set of one or more subjects' cancer, cancer prognosis, or any combination thereof. In some instances, the trained model may be configured to determine the presence or lack thereof the second set of one or more subjects' cancer at a low-stage (stage I or stage II) tumor. In some cases, the trained model may be configured to determine an immunotherapy response of the subject when the subject is provided an immunotherapy. In some cases, the trained model may be configured to determine a category or tissue-specific location of the second set of one or more subjects' cancer. In some cases, the trained model may be configured to determine one or more types of the second set of one or more subjects' cancer.
In some instances the genome database may be a human genome database. In some cases step (b) of filtering may comprises computational filter of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some instances, the protein database may be the UniRef database. In some cases, step (c) of translating may be accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some cases, step (d) of mapping of the non-human proteins to the biochemical pathways may be accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank, or any combination thereof databases. In some cases, the biochemical pathways may be generated with the software package MiniPath.
In some cases, the methods of the invention disclosed herein may comprise (a) sequencing the nucleic acid content of a liquid biopsy sample; and (b) generating a diagnostic model. In some embodiments, the sequencing method may comprise next-generation sequencing or long-read sequencing (e.g., nanopore sequencing) or a combination thereof. In some embodiments, the model 110 may comprise a diagnostic model. In some cases, the diagnostic model may comprise a trained machine learning algorithm 109 as shown in
In some embodiments, the machine learning algorithm 109 may be trained with nucleic acid sequencing data 103 derived from nucleic acids from a plurality of known healthy subjects 101 and a plurality of known cancer subjects 102. In some embodiments, the machine learning algorithm 109 may be trained with nucleic acid sequencing data 103 that has been processed through a metagenomic function bioinformatics pipeline 108 consisting of (a) computationally filtering all sequencing reads mapping to the human genome 104; (b) processing the remaining non-human microbial sequencing reads 105 through a decontamination pipeline 106 to remove sequences derived from common microbial contaminants; and (c) analyzing the remaining reads for their translated (i.e., protein) content 107. In some embodiments, computational filtering of all sequencing reads may be accomplished with bowtie2, Kraken programs or any equivalent thereof.
In some embodiments, the machine learning algorithm 109 may be trained resulting in a trained diagnostic model 110, where the trained diagnostic model may determine microbial signatures associated with and/or indicative of healthy subjects 111 and microbial signatures associated with/indicative of subjects with cancer 112.
In some embodiments, the machine learning algorithm 109, as shown in
In some embodiments, the abundance of functional microbial genes is ascertained using the bioinformatics pipeline Web of Life Toolkit App (WolTka) 212 or any equivalent thereof, as shown in
Aspects disclosed herein provide a method of training a diagnostic model (
comprise a machine learning signature indicative of a healthy (i.e., cancer-free) subject 111, or a machine learning derived signature indicative of cancer-positive subject 112 as seen in
In some embodiments, the trained diagnostic model 110 may be used to analyze the nucleic acid samples from subjects of unknown disease status 113 and provide a diagnosis of disease and, where applicable, classification of the state of that disease 115, as seen in
In some instances, the disclosure provided herein describes a method of determining the presence or lack thereof cancer of a subject. In some cases, the method may comprise the steps of: (a) providing one or more sequencing reads of a subject's biological sample; (b) filtering the sequencing reads with a genome database to produce a set of filtered non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) determining the presence or lack thereof cancer of the subject as an output to the trained model when the trained model is provided an input of the set of protein database associations. In some instances, the set of protein database associations may comprise a set of functional genes, biochemical pathways, or any combination thereof, described elsewhere herein. In some instances, the method may further comprise decontaminating the filtered non-human sequencing reads prior to step (c) to remove contaminant non-human sequencing reads. In some cases, the contaminant non-human sequencing reads may be determined a prior or from a database of contaminant non-human sequencing reads determined from experimental data analysis. In some cases, the translating of step (c) may be completed in silico. In some instances, the method may in place of or in addition to step (a) comprise the step of sequencing nucleic acid compositions of the subjects. In some cases, the method may further comprise outputting with the trained model a therapy to treat the subject's cancer, where the subject will respond with positive therapeutic efficacy when administered the therapy.
In some cases, the subject may be human or non-human mammal. In some cases, the biological sample may comprise a tissue, liquid biopsy sample or any combination thereof. In some cases, the biological sample may comprise a nucleic acid composition, where the nucleic acid composition may comprise DNA, RNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some cases the non-human sequences may originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some instances, the liquid biopsy may comprise plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof.
In some instances, the subject may comprise cancer. In some cases, the cancer may comprise acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof.
In some cases, the trained model may be trained with a set of functional gene and biochemical pathway abundances that are present or absent with a characteristic abundance for a cancer of interest. In some instances, the trained model may be configured to determine one or more subtypes of the subject's cancer. In some cases, the trained model may be configured to determine a stage of the subject's cancer, cancer prognosis, or any combination thereof. In some instances, the trained model may be configured to determine the presence or lack thereof the subject's cancer at a low-stage (stage I or stage II) tumor. In some cases, the trained model may be configured to determine an immunotherapy response of the subject when the subject is provided an immunotherapy. In some cases, the trained model may be configured to determine a category or tissue-specific location of the subject's cancer. In some cases, the trained model may be configured to determine one or more types of the subject's cancer.
In some instances the genome database may be a human genome database. In some cases step (b) of filtering may comprises computational filter of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some instances, the protein database may be the UniRef database. In some cases, step (c) of translating may be accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some cases, step (d) of mapping of the non-human proteins to the biochemical pathways may be accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank, or any combination thereof databases. In some cases, the biochemical pathways may be generated with the software package MiniPath.
In some instances, the disclosure provided herein describes a method of changing a subject's cancer treatment with a trained predictive model. In some cases, the method may comprise the steps of: (a) providing one or more sequencing reads of a subject's biological sample with cancer, cancer type, and treatment administered to treat the cancer; (b) filtering the sequencing reads with a genome database to produce a set of filtered non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) changing the subject's cancer treatment when the treatment administered differs from the treatment recommendation outputted by a trained predictive model when inputted with the set of protein database associations. In some cases, the trained predictive model is trained on a second set of one or more subjects' nucleic acid sequencing reads of a biological sample, corresponding cancer classification, corresponding treatment administered, corresponding treatment response, or any combination thereof. In some cases, the second set of one or more subjects are different than the first set of one or more subjects. In some instances, the set of protein database associations may comprise a set of functional genes, biochemical pathways, or any combination thereof, described elsewhere herein. In some instances, the method may further comprise decontaminating the filtered non-human sequencing reads prior to step (c) to remove contaminant non-human sequencing reads. In some cases, the contaminant non-human sequencing reads may be determined a prior or from a database of contaminant non-human sequencing reads determined from experimental data analysis. In some cases, the translating of step (c) may be completed in silico. In some instances, the method may in place of or in addition to step (a) comprise the step of sequencing nucleic acid compositions of the subjects. In some cases, the method may further comprise outputting with the trained model a therapy to treat the subject's cancer, where the subject will respond with positive therapeutic efficacy when administered the therapy.
In some cases, the subject may be human or non-human mammal. In some cases, the biological sample may comprise a tissue, liquid biopsy sample or any combination thereof. In some cases, the biological sample may comprise a nucleic acid composition, where the nucleic acid composition may comprise DNA, RNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some cases the non-human sequences may originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some instances, the liquid biopsy may comprise plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof.
In some instances, the subject may comprise cancer. In some cases, the cancer may comprise acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof.
In some cases, the treatment recommendation comprises a therapeutic that the subject will respond with positive efficacy. In some cases, the treatment recommendation comprises an immunotherapy response of the subject when the subject is administered an immunotherapy.
In some instances the genome database may be a human genome database. In some cases step (b) of filtering may comprises computational filter of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some instances, the protein database may be the UniRef database. In some cases, step (c) of translating may be accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some cases, step (d) of mapping of the non-human proteins to the biochemical pathways may be accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank, or any combination thereof databases. In some cases, the biochemical pathways may be generated with the software package MiniPath.
The computer system 901 may comprise a central processing unit (CPU, also “processor” and “computer processor” herein) 905, which may be a single core or multi core processor, or a plurality of processor for parallel processing. The computer system 901 may further comprise memory or memory locations 904 (e.g., random-access memory, read-only memory, flash memory), electronic storage unit 906 (e.g., hard disk), communications interface 908 (e.g., network adapter) for communicating with one or more other devices, and peripheral devices 907, such as cache, other memory, data storage and/or electronic display adapters. The memory 904, storage unit 906, interface 908, and peripheral devices 907 are in communication with the CPU 905 through a communication bus (solid lines), such as a motherboard. The storage unit 906 may be a data storage unit (or a data repository) for storing data. The computer system 901 may be operatively coupled to a computer network (“network”) 400 with the aid of the communication interface 908. The network 400 may be the Internet, an internet and/or extranet, or an intranet and/or extranet that is in communication with the Internet. The network 400 may, in some case, be a telecommunication and/or data network. The network 400 may include one or more computer servers, which may enable distributed computing, such as cloud computing. The network 400, in some cases with the aid of the computer system 901, may implement a peer-to-peer network, which may enable devices coupled to the computer system 901 to behave as a client or a server.
The CPU 905 may execute a sequence of machine-readable instructions, which may be embodied in a program or software. The instructions may be directed to the CPU 905, which may subsequently program or otherwise configured the CPU 905 to implement methods of the present disclosure. Examples of operations performed by the CPU 905 may include fetch, decode, execute, and writeback.
The CPU 905 may be part of a circuit, such as an integrated circuit. One or more other components of the system 901 may be included in the circuit. In some cases, the circuit is an application specific integrated circuit (ASIC).
The storage unit 906 may store files, such as drivers, libraries and saved programs. The storage unit 906 may store one or more sequencing reads of one or more subjects' biological sample, cancer type if present, treatment administered to treat the cancer, treatment efficacy of the treatment administered, or any combination thereof. The computer system 901, in some cases may include one or more additional data storage units that are external to the computer system 901, such as located on a remote server that is in communication with the computer system 901 through an intranet or the internet.
Methods as described herein may be implemented by way of machine (e.g., computer processor) executable code stored on an electronic storage location of the computer device 901, such as, for example, on the memory 904 or electronic storage unit 906. The machine executable or machine-readable code may be provided in the form of software. During use, the code may be executed by the processor 905. In some instances, the code may be retrieved from the storage unit 906 and stored on the memory 904 for ready access by the processor 905. In some instances, the electronic storage unit 906 may be precluded, and machine-executable instructions are stored on memory 904.
The code may be pre-compiled and configured for use with a machine having a processor adapted to execute the code or may be compiled during runtime. The code may be supplied in a programming language that may be selected to enable the code to be executed in a pre-complied or as-compiled fashion.
Aspects of the systems and methods provided herein, such as the computer system 901, may be embodied in programming. Various aspects of the technology may be thought of a “product” or “articles of manufacture” typically in the form of a machine (or processor) executable code and/or associated data that is carried on or embodied in a type of machine readable medium. Machine-executable code may be stored on an electronic storage unit, such memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk. “Storage” type media may include any or all of the tangible memory of a computer, processor the like, or associated modules thereof, such as various semiconductor memories, tape drives, disk drives and the like, which may provide non-transitory storage at any time for the software programming. All or portions of the software may at times be communicated through the Internet or various other telecommunication networks. Such communications, for example, may enable loading of the software from one computer or processor into another, for example, from a management server or host computer into the computer platform of an application server. Thus, another type of media that may bear the software elements includes optical, electrical and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical landline networks and over various air-links. The physical elements that carry such waves, such as wired or wireless links, optical links or the like, also may be considered as media bearing the software. As used herein, unless restricted to non-transitory, tangible “storage’ media, term such as computer or machine “readable medium” refer to any medium that participates in providing instructions to a processor for execution.
Hence, a machine readable medium, such as computer-executable code, may take many forms, including but not limited to, a tangible storage medium, a carrier wave medium or physical transmission medium. Non-volatile storage media may include, for example, optical or magnetic disks, such as any of the storage devices in any computer(s) or the like, such as may be used to implement the databases, etc. Volatile storage media include dynamic memory, such as main memory of such a computer platform. Tangible transmission media includes coaxial cables; copper wire and fiber optics, including the wires that comprise a bus within a computer device. Carrier-wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media therefor include for example: a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD or DVD-ROM, any other optical medium, punch cards paper tape, any other physical storage medium with pattern of holes, a RAM, a ROM, a PROM and EPROM, a FLASH-EPROM, any other memory chip or cartridge, a carrier wave transporting data or instructions, cables or links transporting such a carrier wave, or any other medium from which a computer may read programming code and/or data. Many of these forms of computer readable media may be involved in carrying one or more sequences of one more instruction to a processor for execution.
The computer system may include or be in communication with an electronic display 902 that comprises a user interface (UI) 903 for viewing a therapeutic treatment outputted by a trained predictive model and/or recommendation or determination of a presence or lack thereof cancer for one or more subjects. Examples of UI's include, without limitation, a graphical user interface (GUI) and web-based user interface.
Methods and systems of the present disclosure can be implemented by way of one or more algorithms and with instructions provided with one or more processors as disclosed herein. An algorithm can be implemented by way of software upon execution by the central processing unit 905. The algorithm can be, for example, random forest, graphical models, support vector machine or other.
In some cases, the disclosure provided herein describes a computer-implemented method for utilizing a trained predictive model to provide a therapeutic treatment prediction for one or more subjects. In some instances, the method may comprise the steps of: (a) receiving a first set of one or more subjects' nucleic acid sequencing reads of a biological sample and corresponding cancer classification; (b) filtering the nucleic acid sequencing reads with a build of a genome database to generate non-human sequencing reads; (c) translating the non-human sequencing reads to non-human proteins; (d) mapping the non-human proteins to a protein database, thereby producing a set of protein database associations; and (e) utilizing a trained predictive model to provide a treatment prediction for the first set of one or more subjects when the set of protein database associates are provided as an input to the trained predictive model. In some cases, the method may further comprise the step of decontaminating the filtered non-human sequencing reads prior to (c) to remove contaminant non-human sequencing reads. In some instances, translating of step (c) may be completed in silico.
In some cases, the trained predictive model may be trained on a second set of one or more subjects' nucleic acid sequencing reads of a biological sample, corresponding cancer classification, corresponding treatment administered, corresponding treatment response, or any combination thereof. In some instances, the second set of one or more subjects may be different than the first set of one or more subjects. In some cases, set of protein database associations may comprises a set of functional genes, biochemical pathways, or any combination thereof. In some cases, the biological sample may comprise a tissue, liquid biopsy sample or any combination thereof. In some instances the liquid biopsy may comprises: plasma, serum, whole blood, urine, cerebral spinal fluid, saliva, sweat, tears, exhaled breath condensate, or any combination thereof. In some cases, the first set of one or more subjects may be human or a non-human mammal. In some instances, the biological sample nucleic acid composition may comprise DNA, RNA, cell-free DNA, cell-free RNA, exosomal DNA, exosomal RNA, or any combination thereof. In some instances, the genome database may be a human genome database. In some cases, the non-human sequences may originate from bacterial, archaeal, fungal, viral, or any combination thereof origins of life. In some instances, the treatment prediction may comprise an immunotherapy response of the first set of one or more subjects when the first set of one or more subjects are administered an immunotherapy. In some instances, the treatment prediction may comprise a therapeutic efficacy that the first set of one or more subjects will respond with positive efficacy. In some cases, the cancer classification may comprise comprises: acute myeloid leukemia, adrenocortical carcinoma, bladder urothelial carcinoma, brain lower grade glioma, breast invasive carcinoma, cervical squamous cell carcinoma and endocervical adenocarcinoma, cholangiocarcinoma, colon adenocarcinoma, esophageal carcinoma, glioblastoma multiforme, head and neck squamous cell carcinoma, kidney chromophobe, kidney renal clear cell carcinoma, kidney renal papillary cell carcinoma, liver hepatocellular carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, lymphoid neoplasm diffuse large B-cell lymphoma, mesothelioma, ovarian serous cystadenocarcinoma, pancreatic adenocarcinoma, pheochromocytoma and paraganglioma, prostate adenocarcinoma, rectum adenocarcinoma, sarcoma, skin cutaneous melanoma, stomach adenocarcinoma, testicular germ cell tumors, thymoma, thyroid carcinoma, uterine carcinosarcoma, uterine corpus endometrial carcinoma, uveal melanoma, or any combination thereof.
In some cases, filtering of step (b) may comprise computationally filtering of the sequencing reads by bowtie2, Kraken, or any combination thereof programs. In some cases, the protein database may be the UniRef database. In some instances, translating of step (c) may be accomplished by BLASTP, USEARCH, LAST, MMSeqs2, DIAMOND, or any combination thereof software packages. In some cases, mapping of the non-human proteins to the biochemical pathways of step (d) may be accomplished by mapping non-human proteins to KEGG, MetaCyc, PANTHER Pathway, PathBank or any combination thereof databases. In some cases, the biochemical pathways may be generated with the software package MinPath.
Although the above steps show a method of a system in accordance with an example, a person of ordinary skill in the art will recognize many variations based on the teaching described herein. The steps may be completed in a different order. Steps may be added or deleted. Some of the steps may comprise sub-steps. Many of the steps may be repeated as often as if beneficial to the platform.
Unless defined otherwise, all terms of art, notations and other technical and scientific terms or terminology used herein are intended to have the same meaning as is commonly understood by one of ordinary skill in the art to which the claimed subject matter pertains. In some cases, terms with commonly understood meanings are defined herein for clarity and/or for ready reference, and the inclusion of such definitions herein should not necessarily be construed to represent a substantial difference over what is generally understood in the art.
Throughout this application, various embodiments may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the disclosure. Accordingly, the description of a range should be considered to have specifically disclosed all the possible subranges as well as individual numerical values within that range. For example, description of a range such as from 1 to 6 should be considered to have specifically disclosed subranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6 etc., as well as individual numbers within that range, for example, 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.
As used in the specification and claims, the singular forms “a”, “an” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “a sample” includes a plurality of samples, including mixtures thereof.
The terms “determining,” “measuring,” “evaluating,” “assessing,” “assaying,” and “analyzing” are often used interchangeably herein to refer to forms of measurement. The terms include determining if an element is present or not (for example, detection). These terms can include quantitative, qualitative or quantitative and qualitative determinations. Assessing can be relative or absolute. “Detecting the presence of” can include determining the amount of something present in addition to determining whether it is present or absent depending on the context.
The terms “subject,” “individual,” or “patient” are often used interchangeably herein. A “subject” can be a biological entity containing expressed genetic materials. The biological entity can be a plant, animal, or microorganism, including, for example, bacteria, viruses, fungi, and protozoa. The subject can be tissues, cells and their progeny of a biological entity obtained in vivo or cultured in vitro. The subject can be a mammal. The mammal can be a human. The subject may be diagnosed or suspected of being at high risk for a disease. In some cases, the subject is not necessarily diagnosed or suspected of being at high risk for the disease.
The term “in vivo” is used to describe an event that takes place in a subject's body.
The term “ex vivo” is used to describe an event that takes place outside of a subject's body. An ex vivo assay is not performed on a subject. Rather, it is performed upon a sample separate from a subject. An example of an ex vivo assay performed on a sample is an “in vitro” assay.
The term “in vitro” is used to describe an event that takes places contained in a container for holding laboratory reagent such that it is separated from the biological source from which the material is obtained. In vitro assays can encompass cell-based assays in which living or dead cells are employed. In vitro assays can also encompass a cell-free assay in which no intact cells are employed.
As used herein, the term “about” a number refers to that number plus or minus 10% of that number. The term “about” a range refers to that range minus 10% of its lowest value and plus 10% of its greatest value.
Use of absolute or sequential terms, for example, “will,” “will not,” “shall,” “shall not,” “must,” “must not,” “first,” “initially,” “next,” “subsequently,” “before,” “after,” “lastly,” and “finally,” are not meant to limit scope of the present embodiments disclosed herein but as exemplary.
Any systems, methods, software, compositions, and platforms described herein are modular and not limited to sequential steps. Accordingly, terms such as “first” and “second” do not necessarily imply priority, order of importance, or order of acts.
As used herein, the terms “treatment” or “treating” are used in reference to a pharmaceutical or other intervention regimen for obtaining beneficial or desired results in the recipient. Beneficial or desired results include but are not limited to a therapeutic benefit and/or a prophylactic benefit. A therapeutic benefit may refer to eradication or amelioration of symptoms or of an underlying disorder being treated. Also, a therapeutic benefit can be achieved with the eradication or amelioration of one or more of the physiological symptoms associated with the underlying disorder such that an improvement is observed in the subject, notwithstanding that the subject may still be afflicted with the underlying disorder. A prophylactic effect includes delaying, preventing, or eliminating the appearance of a disease or condition, delaying or eliminating the onset of symptoms of a disease or condition, slowing, halting, or reversing the progression of a disease or condition, or any combination thereof. For prophylactic benefit, a subject at risk of developing a particular disease, or to a subject reporting one or more of the physiological symptoms of a disease may undergo treatment, even though a diagnosis of this disease may not have been made.
The section headings used herein are for organizational purposes only and are not to be construed as limiting the subject matter described.
Diagnostic models configured to classify subjects categorically based on their non-mammalian pathway abundance as healthy, having lung cancer, or having lung disease were generated and tested. Cell-free DNA (cfDNA) sequencing libraries of 166 healthy, 288 lung cancer, and 109 lung disease subjects was obtained and further processed. Further breakdown of the sub cancer categories is referenced in
Diagnostic models configured to classify subjects' cancer stage based on non-mammalian pathway abundance in a background of a pathway abundance of lung disease were generated and tested. Cell-free DNA (cfDNA) sequencing data of subjects with cancer at varying stages in addition to subjects with lung disease were obtained. The sequencing data was comprised of 288 subjects with cancer at varying known stages and 109 subjects with lung disease, as shown in
This application claims benefit of U.S. Provisional Patent Application No. 63/114,447, filed Nov. 16, 2020, which is entirely incorporated herein by reference
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/US2021/059559 | 11/16/2021 | WO |
| Number | Date | Country | |
|---|---|---|---|
| 63114447 | Nov 2020 | US |
