Large-scale single-cell gene expression data analysis
Wolf et al. (Genome Biology, 2018), Lücken et al. (Molecular Systems Biology, 2019)
Scanpy is a scalable toolkit for analyzing single-cell gene expression data. It includes preprocessing, visualization, clustering, pseudotime and trajectory inference, differential expression testing, and simulation of gene regulatory networks. It allows researchers to tackle the recently exploding dataset sizes without subsampling, scaling to more than one million cells.
Generalizing RNA velocity to transient cell states through dynamical modeling
Bergen et al. (Nature Biotechnology, 2020)
scVelo is a method that generalizes RNA velocity to systems with transient cell states by solving the full transcriptional dynamics of splicing kinetics using a likelihood-based dynamical model. scVelo identifies regimes of regulatory changes, such as stages of cell fate commitment and, therein, systematically detects putative driver genes.
Probabilistic fate mapping using RNA velocity
Lange et al. (Nature Methods, 2022)
CellRank is a toolkit to uncover cellular dynamics based on scRNA-seq data with RNA velocity annotations. CellRank models cellular dynamics as a Markov chain, where transition probabilities are computed based on RNA velocity and transcriptomic similarity, taking into account uncertainty in the velocities and the stochastic nature of cell fate decisions.
Mapping single-cell data to reference atlases by transfer learning
Lotfollahi et al. (Nature Biotechnology, 2021)
scArches is a deep learning strategy called single-cell architectural surgery to map query single-cell datasets onto an integrated reference. It uses transfer learning and parameter optimization to enable efficient, decentralized, iterative reference building, and the contextualization of new datasets with existing references without sharing raw data.
Automatic gene selection using multi-objective optimization for RNA-seq deconvolution
Aliee et al. (Cell Systems, 2021)
AutoGeneS is a cell-type deconvolution tool for bulk RNA-seq data. It uses single-cell RNA-seq reference data and an automatic gene selection technique that optimizes multiple criteria such as minimizing correlation and maximizing distance between cell types.
Prediction of single-cell perturbation responses
Lotfollahi et al. (Nature Methods, 2019)
scGen is a generative model to predict single-cell perturbation responses across cell types, studies and species. scGen is implemented using the scvi-tools framework.
Data and model repository for single-cell data
Fischer et al. (Genome Biology, 2021)
Sfaira facilitates data sharing in analysis and collaborations by allowing users to access single-cell datasets and pre-trained models via streamlined data loaders.
Mapping out the coarse-grained connectivity structures of complex manifolds
Wolf et al. (Genome Biology, 2019)
PAGA provides an interpretable graph-like map of single-cell data manifolds, based on connectivity estimations of manifold partitions. PAGA maps preserve the global topology of data, allow researchers to analyze data at different resolutions, and increase the computational efficiency of the typical exploratory data analysis workflow.
Single-cell differential composition analysis
Büttner et al. (Nature Communications, 2021)
scCODA allows for the identification of compositional changes in high-throughput sequencing count data, enabling cell composition estimation from scRNA-seq data. It also provides a framework for the integration of cell type annotated data directly from Scanpy and other sources.
Mechanistic insights into transcription factor cooperativity and its impact on protein-phenotype interactions
Ibarra et al. (Nature Communications, 2020)
coop-TF-binding is a statistical learning framework that provides structural insight into TF cooperativity and its functional consequences based on next generation sequencing data.