Welcome to ctMethTracer

ctMethTracer (tissue-of-origin prediction using methylation profiles of cell-free DNA) is a web server that infers the proportions and the tissue-of-origin of tumor-derived cell-free DNA in a blood sample using DNA methylation data. To date, DNA methylation has been realized to be an ideal target for cancer diagnosis in clinical practice. The non-invasive hallmark of ctDNA methylation makes it a promising strategy for general cancer screen. Here, ctMethTracer attempts to provide a platform for the tissue-of-origin prediction by integrating published epigenomic data and algorithms. Currently, four probabilistic methods are provided in ctMethTracer (CancerLocator, random forest, logistic regression and support vector machine).

Step 1: select a file

Example

Choose an example.

Download the example data you chose.

OR

Upload your data

Upload your tumor-derived cell-free DNA methylation data (Hg19).

File uploaded.

Your data is supposed to have the same format with this example data. This tool can help you convert the result file of BSMAP (ends with _methratio.txt) to the required format. This tool can help you convert the result file of bismark (dens with bismark.cov.gz) to the required format.

Input files can be created from the output of Bismark or BSMAP using the programs provided on the right.

Step 2: select model

pic CancerLocator

CancerLocator uses a probabilistic method which simultaneously infers the proportions and the tissue-of-origin of tumor-derived cell-free DNA in a blood sample using genome-wide DNA methylation data.

more

pic Random Forest

Random forest is an ensemble learning method for classification that operate by constructing a multitude of decision trees at training time and outputting the class that is the mode of the classes of the individual trees.

more

pic Logistic regression

Multinomial logistic regression is a model used to predict the probabilities of the different possible outcomes of a categorically distributed dependent variable, given a set of independent variables.

more

pic Support vector machine

Support vector machines (SVMs) are supervised learning models with associated learning algorithms that analyze data used for classification.

more

Step 3: run