F. Alexander Wolf

The paper introduces anndata, a Python package for handling annotated data matrices, providing features like sparse data support and a PyTorch interface.

The compositional perturbation autoencoder separates drug, dose and cell-type effects in single-cell transcriptomes, predicts unseen combinations, and generates 5,329 unmeasured genetic combinations in silico.

The paper introduces an interpretable autoencoder framework for single-cell RNA-seq data using annotated feature sets, showing improved scalability over factor models.

scVelo fits a likelihood-based model of full splicing kinetics, extending RNA velocity to transient cell states and adding gene-specific kinetic rates, a latent time and putative driver genes.

This paper introduces PAGA, a method that reconciles clustering with trajectory inference by creating a topology-preserving graph map of single-cell data, demonstrating its effectiveness across multiple datasets.

This paper introduces kBET, a new metric to assess batch effects in scRNA-seq data and evaluates its effectiveness compared to existing methods.

Python toolkit Scanpy, built on HDF5-backed AnnData, achieves speedups of 5 to 16 times over Cell Ranger's R kit and clusters 1.3 million cells without subsampling.

This paper uses deep learning to reconstruct cell cycle stages and disease progression from image data, achieving lower error rates and faster analysis.