Background: Many computational methods have been developed recently to analyze single-cell RNA-seq (scRNA-seq) data. Several benchmark studies have compared these methods on their ability for dimensionality reduction, clustering, or differential analysis, often relying on default parameters. Yet, given the biological diversity of scRNA-seq datasets, parameter tuning might be essential for the optimal usage of methods, and determining how to tune parameters remains an unmet need. Results: Here, we propose a benchmark to assess the performance of five methods, systematically varying their tunable parameters, for dimension reduction of scRNA-seq data, a common first step to many downstream applications such as cell type identification or trajectory inference. We run a total of 1.5 million experiments to assess the influence of parameter changes on the performance of each method, and propose two strategies to automatically tune parameters for methods that need it. Conclusions: We find that principal component analysis (PCA)-based methods like scran and Seurat are competitive with default parameters but do not benefit much from parameter tuning, while more complex models like ZinbWave, DCA, and scVI can reach better performance but after parameter tuning.

Inferring causal effects of a treatment, intervention or policy from observational data is central to many applications. However, state-of-the-art methods for causal inference seldom consider the possibility that covariates have missing values, which is ubiquitous in many real-world analyses. Missing data greatly complicate causal inference procedures as they require an adapted unconfoundedness hypothesis which can be difficult to justify in practice. We circumvent this issue by considering latent confounders whose distribution is learned through variational autoencoders adapted to missing values. They can be used either as a pre-processing step prior to causal inference but we also suggest to embed them in a multiple imputation strategy to take into account the variability due to missing values. Numerical experiments demonstrate the effectiveness of the proposed methodology especially for non-linear models compared to competitors.

Many computational methods have been developed recently to analyze single-cell RNA-seq (scRNA-seq) data. Several benchmark studies have compared these methods on their ability for dimensionality reduction, clustering or differential analysis, often relying on default parameters. Yet given the biological diversity of scRNA-seq datasets, parameter tuning might be essential for the optimal usage of methods, and determining how to tune parameters remains an unmet need. Here, we propose a benchmark to assess the performance of five methods, systematically varying their tunable parameters, for dimension reduction (DR) of scRNA-seq data, a common first step to many downstream applications such as cell type identification or trajectory inference. We run a total of ∼1.5 million experiments to assess the influence of parameter changes on the performance of each method, and propose two strategies to automatically tune parameters for methods that need it. We find that principal component analysis (PCA)-based methods like scran and Seurat are competitive with default parameters but do not benefit much from parameter tuning, while more complex models like ZinbWave, DCA and scVI can reach better performance but after parameter tuning. We propose and evaluate two strategies to tune parameters automatically.

Single-cell omics technologies produce large quantities of data describing the genomic, transcriptomic or epigenomic profiles of many individual cells in parallel. In order to infer biological knowledge and develop predictive models from these data, machine learning (ML)-based model are increasingly used due to their flexibility, scalability, and impressive success in other fields. In recent years, we have seen a surge of new ML-based method development for low-dimensional representations of single-cell omics data, batch normalization, cell type classification, trajectory inference, gene regulatory network inference or multimodal data integration. To help readers navigate this fast-moving literature, we survey in this review recent advances in ML approaches developed to analyze single-cell omics data, focusing mainly on peer-reviewed publications published in the last two years (2019-2020).