A Machine Learning Tool Integrating Circulating Cell-Free DNA Methylation with Clinical Variables for Non-Invasive Diagnosis of Liver Graft Pathology
|Study ID||Alternative Stable ID||Type|
Liver Transplant Recipients (LTRs) with elevated liver enzymes can develop graft injury due to various etiologies, such as T-cell mediated rejection (TCMR) and NASH (NASH-LT). While liver biopsy is the gold standard method for diagnosis of graft pathology, it is invasive and is associated with risks. The goal of our study was to develop a Machine Learning (ML) tool integrating clinical variables with methylation patterns on circulating DNA in plasma as a non-invasive diagnostic tool of graft injury. We generated methylation profiles of circulating DNA in a pilot study of 43 LTRs (11 NASH-LT, 19 TCMR, and 13 Control-LT), and developed an L2 multinomial logistic regression ML approach across 101 bootstrapped models to distinguish between the graft conditions. NASH was associated with distinctive methylation patterns on genes involved in fatty acid metabolism, while methylation of platelet-derived growth factors was identified in patients with TCMR. Our ML model achieved a mean multi-classification accuracy of 0.91, with mean specificity and sensitivity of 0.94 and 0.91, respectively. ... (Show More)
Study Datasets 1 dataset.
Click on a Dataset ID in the table below to learn more, and to find out who to contact about access to these data
Bam and indexed bam files after removal of duplicates and trimming of the unique molecular identifiers. Sequencing was performed on NovaSeq 6000 platform.