Gökçen Eraslan

GEMS associates GWAS variants with cell types using sequence-to-function predictions, revealing cell-type-specific mechanisms for disease risk variants.

gRely provides reliability scores for sequence-to-expression models, improving prediction filtering beyond magnitude thresholds in low-magnitude regimes.

The paper designs Müller glia-specific cis-regulatory elements using deep learning and validates their function in vivo.

The paper introduces Decima, a model that predicts cell type- and condition-specific gene expression from DNA sequence using single-cell RNA sequencing data.

This paper introduces CompBioBench, a benchmark for evaluating agentic systems in computational biology, showing strong performance across diverse tasks.

Nona is a multimodal masking framework that unifies sequence-to-function models, language models, and generative models for functional genomics, improving predictions and revealing privacy vulnerabilities in ATAC-seq data.

Polygraph assesses synthetic regulatory DNA elements using features like diversity and motif composition to improve gene therapy design.

This work benchmarks DNA sequence models for predicting causal regulatory variants in human genetics using a curated dataset of 113 Mendelian and 83 complex traits.

gReLU provides a framework for DNA sequence modeling and design, including tools for training, evaluating, and applying pre-trained models to predict and create regulatory elements.

This paper introduces regLM, a framework using autoregressive language models to design synthetic regulatory DNA elements with desired properties, showing they match biological features of validated CREs.

ChromDMM clusters heterogeneous epigenetic data by improving profile shifting, strand orientation, and smoothness, outperforming existing methods on simulated and ENCODE data.

ECLIPSER identifies causal cell types and genes for complex traits by integrating GWAS loci with single-cell RNA-seq data through e/sQTL mapping and enrichment analysis.

The paper introduces PHAGE-ATAC, a method for simultaneous single-cell measurement of surface proteins, chromatin accessibility, and mtDNA-based clonal tracing, and demonstrates its application in human immune cells.

Across 1,176,683 airway and lung cells from 22 datasets, ACE2 rises with age, in males and in smokers' multiciliated cells, and is lowest in young children.

DeepWAS integrates regulatory effect predictions of variants into GWAS to identify regulatory SNPs associated with diseases and traits.

This paper introduces HDST, a high-resolution spatial transcriptomics method, and demonstrates its application in mouse brain tissue to resolve spatial expression patterns and cell types.

The paper examines how genetic and environmental factors influence DNA methylation at variably methylated regions in neonatal blood, finding that combined effects best explain methylation variability.

This paper introduces a deep count autoencoder (DCA) for denoising scRNA-seq data, showing it improves analysis quality and speed compared to existing methods.