Johannes Linder

The paper introduces ecCLIP for high-resolution RBP binding maps and Pythia for structure-aware RNA-protein interaction modeling, improving RNA half-life prediction and variant effect assessment.

The paper introduces Cerberus, an improved regulatory sequence model using bidirectional state space blocks, achieving higher accuracy and efficiency than existing models like Borzoi.

The paper introduces Multi-ISM, a scalable framework for saturation mutagenesis that reduces computational cost while maintaining accuracy, and applies it to 5,000 genes to map regulatory elements and rare variant effects.

The paper develops COMPASS, a method to assess splicing variant effects across cell types, identifying disease-associated variants and cell type-specific splicing programs.

This paper introduces Shorkie, a DNA language model pretrained on fungal genomes that improves gene expression prediction in budding yeast by capturing regulatory motif dynamics and variant effects.

The paper trains a model on single-cell 3-seq data to predict cell type-specific coverage profiles and improves variant interpretation across diverse cell types.

The paper introduces Variant-FlowFISH to measure the effects of DNA sequence variants on gene expression, identifies regulatory mechanisms, and benchmarks predictive models.

This study evaluates parameter-efficient fine-tuning of the Borzoi model to improve gene regulation analysis across new RNA-seq datasets with high accuracy and efficiency.

This paper compares state-space models and transformers for predicting RNA-Seq read coverage, finding Mamba-based models slightly outperform transformers in accuracy but not in downstream SNP classification.

This paper introduces Borzoi, a model that predicts RNA-seq coverage from DNA sequence, enabling variant effect scoring across multiple regulatory layers and outperforming existing methods on QTLs.

The paper uses deep learning to design optimized 5'UTRs for mRNA-delivered gene editing, showing improved editing efficiency across cell types and targets.

The paper identifies sequence-specific sensitivity to JTE-607 in mRNA 3' processing by analyzing over 260,000 sequence variants and developing a predictive model.

The paper introduces CPA-Perturb-seq, a multiplexed perturbation screen dataset, and uses it to identify polyA site regulators and their functional properties.

The paper introduces APARENT2, a neural network model for predicting polyadenylation effects, and finds gain-of-function mutations linked to Autism Spectrum Disorder.

This paper introduces Scrambler networks, a method for interpreting sequence-based neural networks by learning stochastic masks to identify salient sequence positions and explain model predictions.

This paper introduces Deep Exploration Networks (DENs) to generate high-fitness DNA sequences, demonstrating improved performance in engineering RNA isoforms compared to gradient ascent methods.

This paper introduces APARENT, a deep learning model that predicts alternative polyadenylation from DNA sequence, outperforming models trained on endogenous data and identifying genetic variants impacting APA in disease contexts.