Ahmet Doǧan

This study uses spatial transcriptomics and single-cell analysis to reveal how MDS bone marrow microenvironments are altered, showing TGFβ dysregulation in malignant cells and immune escape mechanisms.

This study analyzes whole-genome sequencing data from multiple myeloma patients to show that the timing of genetic events, not just their presence, affects clinical outcomes.

The paper develops Mosaic, a machine learning system that classifies tumors into detailed subtypes and identifies molecular phenotypes using histopathologic and genomic data from a large patient cohort.

DeepHeme is a convolutional neural network trained on bone marrow single-cell images that achieves high accuracy in classifying hematologic cell types, outperforming human experts.

This study presents a paired tumor:normal sequencing dataset for hematologic malignancies, showing improved identification of somatic variants and their clinical relevance.

This study shows copy number signatures predict chromothripsis in multiple myeloma and link to poor clinical outcomes using whole genome and exome sequencing data.

This study identifies 100 SV hotspots and 31 new candidate driver genes in multiple myeloma, revealing that 63% of SVs remain unexplained and are associated with outlier gene expression.