Muhammed Hasan Çelik

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

This paper improves the computational efficiency of protein language models, achieving faster inference, reduced memory usage, and efficient fine-tuning for better accessibility.

This paper introduces EpiOut, a tool to detect chromatin accessibility outliers in ALS, showing they correlate with gene expression and protein level aberrations.

Benchmarking six long-read RNA-seq protocol-platform combinations and 14 tools across human, mouse, and manatee shows read length and accuracy drive isoform detection, depth drives quantification.

Long-read sequencing of 81 human and mouse samples yields 200,000 full-length transcripts plus a triplet framework that separates promoter choice, splicing and 3' end use across tissues.

LAPA analyzes alternative polyadenylation from long-read and short-read RNA-seq data, showing improved detection and revealing gene expression links to polyadenylation changes.

The paper predicts tissue-specific aberrant splicing by improving DNA-based models with RNA-seq data and benchmarking over 8.8 million variants across 49 human tissues.

MTSplice predicts the effects of genetic variants on tissue-specific splicing in 56 tissues and identifies enrichment of autism-associated de novo mutations in brain splicing.

FRASER detects aberrant splicing events in RNA-seq data, identifying pathogenic intron retention and improving sensitivity over z-score methods.

The paper introduces MMSplice, a modular framework for predicting genetic variant effects on splicing, achieving performance comparable to state-of-the-art methods.