Dominik Klein

Generative inverse design steers human hematopoietic cell fate in vitro

This paper introduces LabCompass, a generative inverse-modeling framework that optimizes culture conditions to steer human hematopoietic cell fate in vitro, demonstrating its effectiveness through iterative experimental validation.

Benchmarking gene expression reconstruction from single-cell latent representations

The paper benchmarks gene expression reconstruction from single-cell latent representations, finding autoencoders perform best at low dimensionality and foundation models depend on decoder architecture.

Mapping cells through time and space with moscot

moscot unifies optimal transport for temporal, spatial and spatiotemporal single-cell mapping, using multimodal cost spaces and low-rank solvers to scale to 1.7 million mouse embryo cells.

Mapping lineage-traced cells across time points with moslin

The paper introduces moslin, a method that combines lineage and gene expression data across time points to predict cell fate and decision driver genes.

Learning sequence-based regulatory dynamics in single-cell genomics

The paper introduces muBind, a deep learning model that predicts genomic counts from DNA sequences and cell relationships, enhancing understanding of regulatory dynamics during cell transitions.

Deep generative modeling of transcriptional dynamics for RNA velocity analysis in single cells

This paper introduces veloVI, a deep generative model for RNA velocity analysis, showing improved data fit, consistency, and uncertainty quantification compared to existing methods.

Modeling Single-Cell Dynamics Using Unbalanced Parameterized Monge Maps

This paper introduces UPMM to model single-cell dynamics, showing it outperforms existing methods on real developmental data.

Protein-Ligand Interaction Graphs: Learning from Ligand-Shaped 3D Interaction Graphs to Improve Binding Affinity Prediction

The paper introduces Protein-Ligand Interaction Graphs (PLIGs) to improve binding affinity prediction by encoding 3D protein-ligand interactions into GNN node features, achieving high performance on the CASF-2016 benchmark.