Özgür Yılmaz Beker

I am a CS PhD student in the MorphoLab, located in the Department of Statistics at Columbia University, where I am extremely fortunate to be advised by Bianca Dumitrascu to work on cool problems related to computational biology.

During my undergraduate studies, I was introduced to computational biology through a joint project in the Adebali and Mustafaoglu labs, where I worked with bulk RNA-Seq data from the blood-brain barrier; this eventually gave rise to the Brendo resource. I also interned at EMBL-EBI as part of the Papatheodorou Group, where I contributed to the codebase of CATD Snakemake.

After earning my B.S. in Computer Science and Engineering from Sabancı University, I worked as a Graduate Research Assistant with the Irving Institute for Cancer Dynamics, helping start the Ladder framework for modeling single-cell data obtained from multiple experimental conditions.

Email  /  GitHub  /  Google Scholar  /  ORCID

Ladder - probabilistic modeling of single-cell omics data

Ladder is a probabilistic modeling framework developed mainly for single-cell omics data. It is under active development; check out the GitHub page for more updates soon.

Variational Learning of Disentangled Representations

Patches: A Representation Learning Framework for Decoding Shared and Condition-Specific Transcriptional Programs in Wound Healing

Biophysical modeling for morphodynamics

This section is still under construction; check in again soon.

Single-cell morphodynamics predict cell fate decisions during mucociliary epithelial differentiation

Past projects

Projects I worked on in the past.

Brendo: an open resource for uniquely transcribed genes in brain endothelial cells

CATD: a reproducible pipeline for selecting cell-type deconvolution methods across tissues

Design and source code from Jon Barron's website