Chantriolnt-Andreas Kapourani

Rosalind, a DNA foundation model, predicts variant-gene regulatory relationships without proximity bias, identifying distal genes as more impactful in osteoporosis.

PatchDNA introduces a flexible, biologically-informed patching method for DNA sequences that outperforms tokenization in DNA benchmarks with smaller models.

scMET quantifies DNA methylation heterogeneity at single-cell resolution using a Bayesian model, identifying variable features and enabling differential analysis between cell groups.

Melissa clusters and imputes single-cell methylomes using a Bayesian method, providing accurate results on simulated and real data.

The paper uses single cell triple-omics analysis to reveal how epigenetic changes drive germ layer specification in mouse embryos, showing distinct epigenetic priming and remodeling in different lineages.

This paper introduces scNMT-seq, a method for joint profiling of chromatin accessibility, DNA methylation, and transcription in single cells, and validates it in differentiating mouse embryonic stem cells.