Mekan Myradov

I'm currently an MSc student at Sabanci University, affiliated with the VPA Lab under the guidance of Öznur Taştan and Hilal Kazan. My research focuses on machine learning applications in biology, specifically single-cell RNA sequencing data integration.

Email  /  CV  /  GitHub  /  Google Scholar

We tested existing batch integration metrics under challenging real-world scenarios such as uneven sample compositions and overlapping cell types, identifying where each metric breaks down. Based on these findings, we developed sBEE (single-cell Batch Effect Evaluator), a unified metric that jointly evaluates cross-batch distance relationships and local neighborhood batch composition, delivering more reliable and consistent performance evaluations than existing approaches.

We introduce a novel method for batch effect correction named SCITUNA, a Single-Cell data Integration Tool Using Network Alignment. The method aligns batches iteratively, progressively integrating each batch into a unified representation to correct for batch effects. We perform evaluations on 39 individual batches from four real datasets and a simulated dataset, which include both scRNA-seq and scATAC-seq datasets, spanning multiple organisms and tissues. A thorough comparison of existing batch correction methods using 13 metrics reveals that SCITUNA outperforms current approaches and is successful at preserving biological signals present in the original data.

A comprehensive deep learning pipeline for analyzing single-cell multiome data, benchmarking multiple state-of-the-art integration methods including CCA, Joint VAE, MultiVI, MOFA+ and Seurat (Weighted Nearest Neighbors).

I implemented a comprehensive Python toolbox for statistical analysis implementing one-way ANOVA, two-way ANOVA, and multiple linear regression with various hypothesis testing and confidence interval methods.

I implemented a synthetic data generation algorithm in Python using Gaussian Mixture Models.

Website template credits to Jon Barron.