GLMsim: a GLM-based single cell RNA-seq simulator incorporating batch and biological effects
Wang, J.; Chen, L.; Thijssen, R.; Phipson, B.; Speed, T. P.
Show abstract
With development of the single cell RNA-seq technologies, large numbers of cells can now be routinely sequenced by different platforms. This requires us to choose an efficient integration tool to merge those cells, and computational simulators to help benchmark and assess the performance of these tools. Although existing single cell RNA-seq simulators can simulate library size, biological and batch effects separately, they currently do not capture associations among these three factors. Here we present GLMsim, the first single cell RNA-seq simulator to simultaneously capture the library size, biology and unwanted variation and their associations via a generalized linear model, and to simulate data resembling the original experimental data in these respects. GLMsim is capable of quantitatively benchmarking different single cell integration methods, and assessing their abilities to retain biology and remove library size and batch effects.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- scDesign2: a transparent simulator that generates high-fidelity single-cell gene expression count data with gene correlations captured 97%
- Heterogeneous pseudobulk simulation enables realistic benchmarking of cell-type deconvolution methods 97%
- simATAC: A single-cell ATAC-seq simulation framework 97%
Similar papers in this journal
Similar papers in this journal
- SMNN: Batch Effect Correction for Single-cell RNA-seq data via Supervised Mutual Nearest Neighbor Detection 97%
- scDeepInsight: a supervised cell-type identification method for scRNA-seq data with deep learning 96%
- A Robust and Scalable Graph Neural Network for Accurate Single Cell Classification 96%
Similar papers in this journal
- G2S3: a gene graph-based imputation method for single-cell RNA sequencing data 97%
- Mcadet: a feature selection method for fine-resolution single-cell RNA-seq data based on multiple correspondence analysis and community detection 97%
- Reconstruction Set Test (RESET): a computationally efficient method for single sample gene set testing based on randomized reduced rank reconstruction error 96%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.