Source of origin deconvolution based on methylation fragments in cell-free DNA samples
A method and system for determining one or more sources of a cell free deoxyribonucleic acid (cfDNA) test sample from a test subject. The cfDNA test sample contains a plurality of deoxyribonucleic acid (DNA) molecules with numerous CpG sites that may be methylated or unmethylated. A trained deconvolution model comprises a plurality of methylation parameters, including a methylation level at each CpG site for each source, and a function relating a sample vector as input and a source of origin prediction as output. The method generates a test sample vector comprising a site methylation metric relating to DNA molecules from the test sample that are methylated at that CpG site. The method inputs the test sample vector into the trained deconvolution model to generate a source of origin prediction indicating a predicted DNA molecule contribution of each source.
1. A method for determining a cancer type from a test sample comprising a set of deoxyribonucleic acid (DNA) fragments from a test subject, the method comprising:
accessing a data set derived from the test sample, the data set comprising the set of DNA fragments, each DNA fragment including one or more CpG sites, wherein a methylation state at each of the one or more CpG sites has been determined to be methylated or unmethylated;
generating a test sample vector comprising, for each of a plurality of CpG sites, a site methylation metric for the DNA fragments from the test sample that are methylated at that CpG site;
inputting the test sample vector into a trained deconvolution model to generate a source of origin prediction comprising a plurality of values, each value indicating a fraction of the DNA fragments predicted to have originated from one of a plurality of sources including tissue types and cell types, wherein the trained deconvolution model is trained on a training data set comprising training samples that are obtained from healthy subjects;
inputting the source of origin prediction for the test sample into a trained cancer classifier to generate a cancer prediction comprising a plurality of cancer prediction values, each cancer prediction value describing a likelihood the test subject has a particular cancer type of a plurality of cancer types, wherein the trained cancer classifier is trained by:
accessing an additional training data set comprising training samples obtained from healthy subjects and training samples obtained from subjects diagnosed with cancer, wherein each training sample in the additional training data set includes a methylation state at each of one or more CpG sites on each of a set of DNA fragments,
generating, for each training sample in the additional training data set, a training sample vector comprising, for each of the plurality of CpG sites, a site methylation metric for the DNA fragments from the training sample that are methylated at that CpG site,
inputting each training sample vector into the trained deconvolution model to generate a corresponding source of origin prediction for the training sample, and
training the cancer classifier with the source of origin predictions and the cancer types of the training samples from the additional training data set; and
determining whether the test subject has a first cancer type from the plurality of cancer types based on the cancer prediction.
2. The method of claim 1 ,
wherein the cancer classifier comprises a second function representing a relation between the source of origin prediction received as input and the cancer prediction provided as output based on classification parameters and the second function.
3. The method of claim 2 , wherein the plurality of cancer types include a breast cancer type, a colorectal cancer type, an esophageal cancer type, a head/neck cancer type, a hepatobiliary cancer type, a lung cancer type, a lymphoma cancer type, an ovarian cancer type, a pancreas cancer type, an anorectal cancer type, a cervical cancer type, a gastric cancer type, a leukemia cancer type, a multiple myeloma cancer type, a prostate cancer type, a renal cancer type, a thyroid cancer type, a uterine cancer type, a brain cancer type, a sarcoma cancer type, a neuroendocrine cancer type.
4. The method of claim 2 , wherein the trained cancer classifier is a logistic regression classifier or a multinomial logistic regression classifier.
5. The method of claim 1 , wherein the trained deconvolution model comprises:
a plurality of methylation parameters, wherein the methylation parameters comprise a methylation level at each of the plurality of CpG sites for each of the plurality of sources, and
a function representing a relation between the test sample vector received as input and the source of origin prediction generated as output based on the test sample vector and the plurality of methylation parameters.
6. The method of claim 5 , wherein the plurality of methylation parameters is generated from a first set of training samples from the plurality of sources.
7. The method of claim 6 , wherein the first set of training samples is obtained from healthy individuals.
8. The method of claim 6 , wherein the methylation parameters are trained on information comprising:
the first set of training samples from the plurality of sources, each of the training samples from a source of the plurality of sources comprising:
a training sample vector comprising a plurality of methylation metrics for each of the plurality of CpG sites, and
an identification of the source the training sample originates from.
9. The method of claim 8 , wherein the trained deconvolution model is trained by applying a minimization function to reduce a least squares difference between each training sample and a matrix product of the methylation parameters and a vector of values representing the source of the training sample.
10. The method of claim 1 , wherein the CpG sites used in the trained deconvolution model are identified according to:
for each CpG site of an initial set of CpG sites, computing information gain for deriving one or more sources of the plurality of sources; and
identifying a plurality of informative CpG sites to be used in the trained model from the initial set of CpG sites based on the computed information gain of each CpG site.
11. The method of claim 10 , further comprising:
ranking the initial set of CpG sites based on the computed information gain, and
wherein identifying the informative CpG sites to be used in the trained model is based on the ranking of the initial set of CpG sites.
12. The method of claim 1 , wherein the plurality of sources comprises any combination of a large intestine tissue type, a breast tissue type, a thyroid tissue type, a lung tissue type, a bladder tissue type, a cervix tissue type, and a colorectal tissue type.
13. The method of claim 12 , wherein the plurality of sources further comprises any combination of an esophagus tissue type, a gastric tissue type, a tonsil tissue type, a liver tissue type, a white blood cell tissue type, an ovary tissue type, a pancreas tissue type, a prostate tissue type, a kidney tissue type, a thyroid tissue type, and a uterus tissue type.
14. The method of claim 1 wherein the plurality of sources comprises any combination of a B cell type, a dendritic cell type, an endothelial cell type, an eosinophil cell type, an erythroblast cell type, a macrophage cell type, a megakaryocyte cell type, a monocyte cell type, a natural killer cell type, a neutrophil cell type, a precursor B cell type, a T cell type, a thymocyte cell type, an adipocyte cell type, a hepatocyte cell type, an islet cell type, and a preadipocyte cell type.
15. The method of claim 1 , wherein the plurality of sources comprises any combination of a large intestine tissue type, a breast tissue type, a thyroid tissue type, a lung tissue type, a bladder tissue type, a cervix tissue type, a colorectal tissue type, an esophagus tissue type, a gastric tissue type, a tonsil tissue type, a liver tissue type, a white blood cell tissue type, an ovary tissue type, a pancreas tissue type, a prostate tissue type, a kidney tissue type, a thyroid tissue type, a uterus tissue type, a B cell type, a dendritic cell type, an endothelial cell type, an eosinophil cell type, an erythroblast cell type, a macrophage cell type, a megakaryocyte cell type, a monocyte cell type, a natural killer cell type, a neutrophil cell type, a precursor B cell type, a T cell type, a thymocyte cell type, an adipocyte cell type, a hepatocyte cell type, an islet cell type, and a preadipocyte cell type.
16. The method of claim 1 , wherein each DNA fragment of a plurality of the set of fragments is an anomalous fragment, the method further comprising:
filtering an initial set of fragments with p-value filtering to generate the set of anomalous fragments, the filtering comprising removing fragments from the initial set having below a threshold p-value with respect to others to produce the set of anomalous fragments.
17. The method of claim 16 , wherein each fragment of the plurality of the set of fragments is also hypomethylated or hypermethylated such that the fragment includes at least a threshold number of CpG sites with more than a threshold percentage of the CpG sites being unmethylated or with more than the threshold percentage of the CpG sites being methylated, respectively.