Nikolaus Fortelny

The paper identifies epigenetic regulators of fibrotic transformation in cardiac fibroblasts using bulk and single-cell CRISPR screens and shows KAT5 inhibition reduces fibrotic responses in human fibroblasts.

The paper compares perturbation outcomes in in vivo and ex vivo hematopoietic stem cell models, finding systematic biases and challenges in predicting in vivo effects from ex vivo data.

This study shows that HH/GLI and Hippo/YAP pathway interactions suppress T cell chemotaxis and promote immunosuppression in BCC by downregulating chemokine signaling.

This study evaluates interpretability in biology-inspired deep learning models, identifying biases and proposing methods to improve robustness in P-NET trained on patient mutation data.

The paper maps DNA methylation in 580 animal species, revealing conserved and evolving patterns across vertebrates and invertebrates.

This study uses CRISPR screens and Perturb-Seq to analyze 550 chromatin factors in haematopoiesis and AML, revealing lineage-specific roles and therapeutic implications.

This paper introduces knowledge-primed neural networks (KPNNs) for interpretable deep learning on single-cell RNA-seq data, demonstrating their ability to predict T cell receptor stimulation and infer cell types.

This study maps DNA methylation changes in glioblastoma tumors over time and space, revealing heterogeneity and links to tumor microenvironment and patient survival.