Olgica Milenković

This paper introduces a nanopore tweezers platform to subtype Abl kinase inhibitors by resolving ionic current signatures, achieving high classification accuracy without structural determination.

This study investigates cohesin's role in transcriptional loops and DNA replication using human cells, finding that cohesin loss affects long-range chromatin interactions and up-regulates early initiation zone genes.

The paper identifies intrinsic OASL expression as a determinant of IFN induction potential in influenza A virus-infected cells using scRNA-seq analysis.

This paper introduces an interpretable online dictionary learning method for analyzing long-range chromatin interactions in Drosophila using ChIA-Drop data.

The paper introduces an algorithm to infer chromatin interaction patterns from ChIA-Drop data and demonstrates its ability to reconstruct interaction networks and identify functional chromatin elements.

This paper introduces a 2D DNA-based data storage system that encodes information in both sequence and backbone structure, using machine learning for error correction and data reconstruction.

This paper introduces an extended 11-letter DNA alphabet for data storage, using nanopore readout and neural networks to improve accuracy and density.

This paper proposes a method to store quantized images in DNA using signal processing and machine learning to reduce errors and costs without redundant oligos or rewriting.

The paper introduces E2M, a deep learning framework that predicts methylation patterns from gene expression data in cancer cells, finding that this approach improves parameter estimation and modulates expression assessment.

ChIPWig compresses ChIP-seq Wig data with lossless and lossy modes, achieving high compression rates while preserving peak calling and motif discovery accuracy.

This paper presents a DNA-based data storage system that achieves error-free and random-access readouts using MinION sequencers through error correction and addressing techniques.