David van Dijk

CpG Atlas integrates over 1.2 million CpG sites across multiple methylation arrays with 18 annotation layers and provides a query interface for epigenetic research.

The paper uses patient tumor samples to identify lineage- and context-specific mechanisms of innate immune resistance through perturbational single-cell RNA sequencing.

The paper uses a transformer model to analyze cholinergic and calcium signaling in mice during learning, finding spatiotemporal plasticity in frontal cortical subnetworks.

This paper scales large language models for single-cell analysis, improving predictive and generative capabilities and enabling biological discovery through virtual screening.

AAnet identifies archetypal cell states in single-cell data to reveal tumor heterogeneity and spatial organization.

This study uses longitudinal single-nucleus RNA sequencing to analyze transcriptional dynamics in SCA1 cerebellum, identifying early cellular changes and applying deep learning to predict disease state.

CINEMA-OT identifies causal effects of single-cell perturbations by separating confounding variation, outperforming existing methods on simulated and real datasets.

A masked-prediction model pretrained on 6,700 hours of fMRI that fine-tunes to predict clinical variables, forecasts future brain states, and recovers functional networks without supervision.

Cell2Sentence converts single-cell gene expression profiles into text-like cell sentences so standard large language models like GPT-2 can be fine-tuned for cell generation and cell-type annotation.

The paper introduces FMGAN, a conditional GAN that predicts hard-to-obtain biological information from easy-to-obtain data, demonstrating applications in drug discovery and clinical outcomes.

This study uses single-cell RNA sequencing to identify molecular markers of forelimb and hindlimb projecting corticospinal neurons, revealing subtype-specific gene expression patterns.

This paper introduces a method to quantify perturbation effects at single-cell resolution using manifold-based likelihood estimation and vertex frequency clustering, achieving higher accuracy than existing methods.

The paper presents a drug-target-mechanism graph to identify synergistic drug combinations for SARS-CoV-2 treatment, validated through experimental testing.

A genome-wide CRISPR screen with SARS-CoV-2 recovers ACE2 and Cathepsin L and nominates SWI/SNF, TGF-beta signalling and HMGB1 as pro-viral; pathway inhibitors blocked virus-induced death.

Time-course single-cell RNA sequencing of infected human bronchial epithelial cultures reports ciliated cells as a major target, with tropism later widening to basal and club cells.

This paper introduces PhEMD, a method to embed drug perturbation effects in single-cell experiments, revealing low-dimensional manifold structures and enabling efficient drug effect inference.

The paper introduces PHATE, a visualization method that captures nonlinear structure in biological data, showing it preserves patterns better than existing tools and reveals novel insights in scRNA-seq data.

SAUCIE is a deep neural network that processes large single-cell datasets, performs batch correction, and identifies cluster-based signatures in dengue patient T cells.

MAGIC improves single-cell RNA-seq data by imputing missing values and revealing gene-gene interactions through a diffusion-based method.