Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/579839

A Methylation Density Binary Classifier for Predicting and Optimizing the Performance of Methylation Biomarkers in Clinical Samples

Miller, B. F.·Pisanic, T. R.·Margolin, G.·Petrykowska, H. M.·Athamanolap, P.·Osei-Tutu, A.·Annunziata, C. M.·Wang, T.-H.·Elnitski, L.
View original source ↗Export metadata ↓

Abstract

BackgroundVariation in intercellular methylation patterns can complicate the use of methylation biomarkers for clinical diagnostic applications such as blood-based cancer testing. Here, we describe development and validation of a methylation density binary classification method called EpiClass (available for download at https://github.com/Elnitskilab/EpiClass), that can be used to predict and optimize the performance of methylation biomarkers, particularly in challenging, heterogeneous samples such as liquid biopsies. This approach is based upon leveraging statistical differences in single-molecule sample methylation density distributions to identify ideal thresholds for sample classification. ResultsWe developed and tested the classifier using reduced representation bisulfite sequencing (RRBS) data derived from ovarian carcinoma tissue DNA and controls. We used these data to perform in silico simulations using methylation density profiles from individual epiallelic copies of ZNF154, a genomic locus known to be recurrently methylated in numerous cancer types. From these profiles, we predicted the performance of the classifier in liquid biopsies for the detection of epithelial ovarian carcinomas (EOC). In silico analysis indicated that EpiClass could be leveraged to better identify cancer-positive liquid biopsy samples by implementing precise thresholds with respect to methylation density profiles derived from circulating cell-free DNA (cfDNA) analysis. These predictions were confirmed experimentally using DREAMing to perform digital methylation density analysis on a cohort of low volume (1-mL) plasma samples obtained from 26 EOC-positive and 41 cancer-free women. EpiClass performance was then validated in an independent cohort of 24 plasma specimens, derived from a longitudinal study of 8 EOC-positive women, and 12 plasma specimens derived from 12 healthy women, respectively, attaining a sensitivity/specificity of 91.7%/100.0%. Direct comparison of CA-125 measurements with EpiClass demonstrated that EpiClass was able to better identify EOC-positive women than standard CA-125 assessment. Finally, we used independent whole genome bisulfite sequencing (WGBS) datasets to demonstrate that EpiClass can also identify other cancer types as well or better than alternative methylation-based classifiers. ConclusionsOur results indicate that assessment of intramolecular methylation density distributions calculated from cfDNA facilitate the use of methylation biomarkers for diagnostic applications. Furthermore, we demonstrated that EpiClass analysis of ZNF154 methylation was able to outperform CA-125 in the detection of etiologically-diverse ovarian carcinomas, indicating the broad utility of ZNF154 for use as a biomarker of ovarian cancer.

Source connections

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Miller, B. F., Pisanic, T. R., Margolin, G., Petrykowska, H. M., Athamanolap, P., Osei-Tutu, A., Annunziata, C. M., Wang, T.-H., Elnitski, L.. 2019-03-18. A Methylation Density Binary Classifier for Predicting and Optimizing the Performance of Methylation Biomarkers in Clinical Samples. https://doi.org/10.1101/579839

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

RoDPAA: A Robust Dissimilarity-Based Principal Angle Analysis Framework for Multi-View Microbiome Data Integration

Multiview microbiome studies profile the same participants across body sites or molecular layers, but integration is hampered by sparse, compositional data, modest sample sizes and methods that recognize only exact sharing. We present RoDPAA (Robust Dissimilarity-based Principal Angle Analysis), a framework that represents each view through any data-appropriate dissimilarity, such as Bray--Curtis, without log-ratio transformation or likelihood assumptions. RoDPAA aligns view-specific signal subspaces through principal angles, captures complete and partial sharing, and tests by permutation how many components are shared, using only eigendecomposition and little tuning. In Gaussian simulations, RoDPAA matched JIVE and MOFA given true ranks, ran faster and alone recovered the shared dimension in every replicate. In two inflammatory bowel disease (IBD) cohorts with sparse, zero-inflated data, Bray--Curtis-based RoDPAA recovered shared structure that was stable to prevalence filtering, whereas log-ratio-based alternatives were not. Its leading microbiome--metabolome factors, learned without disease labels, were the only ones associated with IBD.

bioinformatics↗
bioRxiv2026

Deducing splicing events from transcript sets with splicelogic

Long-read RNA sequencing captures a greater proportion of full-length transcripts, enabling more accurate isoform identification, discovery of novel isoforms, and more precise differential transcript usage analysis. However, comparing transcripts, whether between conditions or between sets such as novel and annotated isoforms, yields complex isoform changes that are hard to manipulate, summarize, and visualize. This is compounded by vertical integration of some tools, where downstream analysis depends on the specific output of a particular upstream tool. To address this gap, we have developed splicelogic, an R/Bioconductor package that makes transcript-set comparisons biologically interpretable by turning them into discrete splicing events, such as exon skipping, alternative splice sites, intron retention, and alternative transcription start and end sites. We designed splicelogic to integrate easily with existing RNA-seq workflows and tools. The splicelogic functions are modular, readable, and extensible, making it easy for users to adapt core logic to their own custom scientific questions or novel splicing definitions. By obtaining interpretable splicing events from transcript changes, splicelogic enables downstream analyses, including annotation of RNA-binding protein recognition sites, alongside summary statistics and visualization. The splicelogic package is publicly available and distributed through Bioconductor.

bioinformatics↗
bioRxiv2026

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.

bioinformatics↗