Melanie Weilert

AlphaGenome Atlas: in silico mutagenesis of the entire human genome improves prioritization and interpretation of non-coding variants

AlphaGenome Atlas predicts regulatory effects of non-coding variants across the human genome, improving their prioritization and interpretation.

Widespread low-affinity motifs enhance chromatin accessibility and regulatory potential in mESCs

The paper maps and interprets low-affinity transcription factor motifs in mESCs, showing they enhance chromatin accessibility and regulatory potential through cooperative interactions.

Positional Interpretation of Cis-Regulatory Code and Nucleosome Organization with Deep Learning Models

This paper introduces PISA, a tool for interpreting sequence-to-function neural networks, enabling the discovery of nucleosome-positioning motifs and understanding cis-regulatory code through MNase-seq data.

High-resolution binding data of TFIID and cofactors show promoter-specific differences in vivo

The paper uses ChIP-nexus to analyze TFIID subunit binding in Drosophila, revealing promoter-specific differences in TBP and TAF interactions.

Interpretable deep learning reveals the sequence rules of Hippo signaling

The paper uses interpretable deep learning to identify sequence rules governing Hippo signaling in mouse trophoblast stem cells, revealing how transcription factors influence enhancer activity.

Chromatin accessibility is a two-tier process regulated by transcription factor pioneering and enhancer activation

The paper uses deep learning to analyze chromatin accessibility in Drosophila embryos, revealing a two-phase process driven by pioneer TFs and enhancer-activating TFs.

De novo distillation of thermodynamic affinity from deep learning regulatory sequence models of in vivo protein-DNA binding

The paper introduces Affinity Distillation (AD), a method to extract thermodynamic affinities from deep learning models of in vivo TF binding, showing it outperforms motif-based methods in predicting sequence variation impacts.

Base-resolution models of transcription factor binding reveal soft motif syntax

The paper introduces BPNet, a deep learning model that predicts base-resolution ChIP-nexus binding profiles of TFs and identifies soft syntax rules for cooperative TF binding.