1 September 2021 in STAR Protocols
The existence of doublets is a key confounder in single-cell RNA sequencing (scRNA-seq) data analysis. Computational techniques have been developed for detecting doublets from scRNA-seq data. We developed an R package DoubletCollection to integrate the installation and execution of eight doublet detection methods. DoubletCollection provides a unified interface to perform and visualize downstream analysis after doublet detection. Here, we present a protocol of using DoubletCollection to benchmark doublet-detection methods. This protocol can accommodate new doublet-detection methods in the fast-growing scRNA-seq field.
15 April 2022 in Bioinformatics
The number of cells measured in single-cell transcriptomic data has grown fast in recent years. For such large-scale data, subsampling is a powerful and often necessary tool for exploratory data analysis. However, the easiest random subsampling is not ideal from the perspective of preserving rare cell types. Therefore, diversity-preserving subsampling is required for fast exploration of cell types in a large-scale dataset. Here, we propose scSampler, an algorithm for fast diversity-preserving subsampling of single-cell transcriptomic data. scSampler is implemented in Python and is published under the MIT source license. It can be installed by “pip install scsampler” and used with the Scanpy pipline. The code is available on GitHub: https://github.com/SONGDONGYUAN1994/scsampler. An R interface is available at: https://github.com/SONGDONGYUAN1994/rscsampler. Supplementary data are available at Bioinformatics online.
1 January 2023 in Computational and Structural Biotechnology Journal
Autoencoders are the backbones of many imputation methods that aim to relieve the sparsity issue in single-cell RNA sequencing (scRNA-seq) data. The imputation performance of an autoencoder relies on both the neural network architecture and the hyperparameter choice. So far, literature in the single-cell field lacks a formal discussion on how to design the neural network and choose the hyperparameters. Here, we conducted an empirical study to answer this question. Our study used many real and simulated scRNA-seq datasets to examine the impacts of the neural network architecture, the activation function, and the regularization strategy on imputation accuracy and downstream analyses. Our results show that (i) deeper and narrower autoencoders generally lead to better imputation performance; (ii) the sigmoid and tanh activation functions consistently outperform other commonly used functions including ReLU; (iii) regularization improves the accuracy of imputation and downstream cell clustering and DE gene analyses. Notably, our results differ from common practices in the computer vision field regarding the activation function and the regularization strategy. Overall, our study offers practical guidance on how to optimize the autoencoder design for scRNA-seq data imputation.
1 September 2023 in Quantitative Biology
Doublet is a major confounder in single‐cell RNA sequencing data analysis. Computational doublet‐detection methods aim to remove doublets from scRNA‐seq data. The performance of those methods relies on the appropriate setting of their hyperparameters. In this study, we explore the optimal hyperparameters for scDblFinder, a cutting‐edge doublet‐detection method. Our optimization utilizes a full factorial design, a response surface model, and 16 real scRNA‐seq datasets. The optimal hyperparameters achieve top doublet‐detection performance under a wide range of biological conditions. Our methodology is applicable to broader computational methods in scRNA‐seq data analysis.Background: The existence of doublets in single‐cell RNA sequencing (scRNA‐seq) data poses a great challenge in downstream data analysis. Computational doublet‐detection methods have been developed to remove doublets from scRNA‐seq data. Yet, the default hyperparameter settings of those methods may not provide optimal performance.Methods: We propose a strategy to tune hyperparameters for a cutting‐edge doublet‐detection method. We utilize a full factorial design to explore the relationship between hyperparameters and detection accuracy on 16 real scRNA‐seq datasets. The optimal hyperparameters are obtained by a response surface model and convex optimization.Results: We show that the optimal hyperparameters provide top performance across scRNA‐seq datasets under various biological conditions. Our tuning strategy can be applied to other computational doublet‐detection methods. It also offers insights into hyperparameter tuning for broader computational methods in scRNA‐seq data analysis.Conclusions: The hyperparameter configuration significantly impacts the performance of computational doublet‐detection methods. Our study is the first attempt to systematically explore the optimal hyperparameters under various biological conditions and optimization objectives. Our study provides much‐needed guidance for hyperparameter tuning in computational doublet‐detection methods.
4 May 2022 in Journal of Biopharmaceutical Statistics
Torsades de pointes (TdP) is an irregular heart rhythm characterized by faster beat rates and potentially could lead to sudden cardiac death. Much effort has been invested in understanding the drug-induced TdP in preclinical studies. However, a comprehensive statistical learning framework that can accurately predict the drug-induced TdP risk from preclinical data is still lacking. We proposed ordinal logistic regression and ordinal random forest models to predict low-, intermediate-, and high-risk drugs based on datasets generated from two experimental protocols. Leave-one-drug-out cross-validation, stratified bootstrap, and permutation predictor importance were applied to estimate and interpret the model performance under uncertainty. The potential outlier drugs identified by our models are consistent with their descriptions in the literature. Our method is accurate, interpretable, and thus useable as supplemental evidence in the drug safety assessment.