--- title: "glmGamPoi Quickstart" author: Constantin Ahlmann-Eltze date: "`r Sys.Date()`" output: BiocStyle::html_document vignette: > %\VignetteIndexEntry{glmGamPoi Quickstart} %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- ```{r, include = FALSE} knitr::opts_chunk$set( collapse = TRUE, comment = "#>" ) set.seed(2) ``` > Fit Gamma-Poisson Generalized Linear Models Reliably. The core design aims of `gmlGamPoi` are: * Fit the Gamma-Poisson models on arbitrarily large or small datasets * Be faster than alternative methods, such as `DESeq2` or `edgeR` * Calculate exact or approximate results based on user preference * Support in memory or on-disk data * Follow established conventions around tools for RNA-seq analysis * Present a simple user-interface * Avoid unnecessary dependencies * Make integration into other tools easy # Installation You can install the release version of `r BiocStyle::Biocpkg("glmGamPoi")` from BioConductor: ``` r if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("glmGamPoi") ``` For the latest developments, see the `r BiocStyle::Githubpkg("const-ae/glmGamPoi", "GitHub")` repo. # Example To fit a single Gamma-Poisson GLM do: ```{r} # overdispersion = 1/size counts <- rnbinom(n = 10, mu = 5, size = 1/0.7) # size_factors = FALSE, because only a single GLM is fitted fit <- glmGamPoi::glm_gp(counts, design = ~ 1, size_factors = FALSE) fit # Internally fit is just a list: as.list(fit) ``` The `glm_gp()` function returns a list with the results of the fit. Most importantly, it contains the estimates for the coefficients β and the overdispersion. Fitting repeated Gamma-Poisson GLMs for each gene of a single cell dataset is just as easy: I will first load an example dataset using the `TENxPBMCData` package. The dataset has 33,000 genes and 4340 cells. It takes roughly 1.5 minutes to fit the Gamma-Poisson model on the full dataset. For demonstration purposes, I will subset the dataset to 300 genes, but keep the 4340 cells: ```{r, warning=FALSE, message = FALSE} library(SummarizedExperiment) library(DelayedMatrixStats) ``` ```{r} # The full dataset with 33,000 genes and 4340 cells # The first time this is run, it will download the data pbmcs <- TENxPBMCData::TENxPBMCData("pbmc4k") # I want genes where at least some counts are non-zero non_empty_rows <- which(rowSums2(assay(pbmcs)) > 0) pbmcs_subset <- pbmcs[sample(non_empty_rows, 300), ] pbmcs_subset ``` I call `glm_gp()` to fit one GLM model for each gene and force the calculation to happen in memory. ```{r} fit <- glmGamPoi::glm_gp(pbmcs_subset, on_disk = FALSE) summary(fit) ``` # Benchmark I compare my method (in-memory and on-disk) with `r BiocStyle::Biocpkg("DESeq2")` and `r BiocStyle::Biocpkg("edgeR")`. Both are classical methods for analyzing RNA-Seq datasets and have been around for almost 10 years. Note that both tools can do a lot more than just fitting the Gamma-Poisson model, so this benchmark only serves to give a general impression of the performance. ```{r, warning=FALSE} # Explicitly realize count matrix in memory pbmcs_subset <- as.matrix(assay(pbmcs_subset)) model_matrix <- matrix(1, nrow = ncol(pbmcs_subset)) bench::mark( glmGamPoi_in_memory = { glmGamPoi::glm_gp(pbmcs_subset, design = model_matrix, on_disk = FALSE) }, glmGamPoi_on_disk = { glmGamPoi::glm_gp(pbmcs_subset, design = model_matrix, on_disk = TRUE) }, DESeq2 = suppressMessages({ dds <- DESeq2::DESeqDataSetFromMatrix(pbmcs_subset, colData = data.frame(name = seq_len(4340)), design = ~ 1) dds <- DESeq2::estimateSizeFactors(dds, "poscounts") dds <- DESeq2::estimateDispersions(dds, quiet = TRUE) dds <- DESeq2::nbinomWaldTest(dds, minmu = 1e-6) }), edgeR = { edgeR_data <- edgeR::DGEList(pbmcs_subset) edgeR_data <- edgeR::calcNormFactors(edgeR_data) edgeR_data <- edgeR::estimateDisp(edgeR_data, model_matrix) edgeR_fit <- edgeR::glmFit(edgeR_data, design = model_matrix) }, check = FALSE ) ``` On this dataset, `glmGamPoi` is more than 6 times faster than `edgeR` and more than 20 times faster than `DESeq2`. `glmGamPoi` does **not** use approximations to achieve this performance increase. The performance comes from an optimized algorithm for inferring the overdispersion for each gene. It is tuned for datasets typically encountered in single RNA-seq with many samples and many small counts, by avoiding duplicate calculations. To demonstrate that the method is not sacrificing accuracy, I compare the parameters that each method estimates. I find that means and β coefficients are identical, but that the estimates of the overdispersion estimates from `glmGamPoi` are more reliable: ```{r message=FALSE, warning=FALSE} # Results with my method fit <- glmGamPoi::glm_gp(pbmcs_subset, design = model_matrix, on_disk = FALSE) # DESeq2 dds <- DESeq2::DESeqDataSetFromMatrix(pbmcs_subset, colData = data.frame(name = seq_len(4340)), design = ~ 1) dds <- DESeq2::estimateSizeFactors(dds, "poscounts") dds <- DESeq2::estimateDispersions(dds, quiet = TRUE) dds <- DESeq2::nbinomWaldTest(dds, minmu = 1e-6) #edgeR edgeR_data <- edgeR::DGEList(pbmcs_subset) edgeR_data <- edgeR::calcNormFactors(edgeR_data) edgeR_data <- edgeR::estimateDisp(edgeR_data, model_matrix) edgeR_fit <- edgeR::glmFit(edgeR_data, design = model_matrix) ``` ```{r coefficientComparison, fig.height=5, fig.width=10, warning=FALSE, echo = FALSE} par(mfrow = c(2, 4), cex.main = 2, cex.lab = 1.5) plot(fit$Beta[,1], coef(dds)[,1] / log2(exp(1)), pch = 16, main = "Beta Coefficients", xlab = "glmGamPoi", ylab = "DESeq2") abline(0,1) plot(fit$Beta[,1], edgeR_fit$unshrunk.coefficients[,1], pch = 16, main = "Beta Coefficients", xlab = "glmGamPoi", ylab = "edgeR") abline(0,1) plot(fit$Mu[,1], rowData(dds)$baseMean, pch = 16, log="xy", main = "Gene Mean", xlab = "glmGamPoi", ylab = "DESeq2") abline(0,1) plot(fit$Mu[,1], edgeR_fit$fitted.values[,1], pch = 16, log="xy", main = "Gene Mean", xlab = "glmGamPoi", ylab = "edgeR") abline(0,1) plot(fit$overdispersions, rowData(dds)$dispGeneEst, pch = 16, log="xy", main = "Overdispersion", xlab = "glmGamPoi", ylab = "DESeq2") abline(0,1) plot(fit$overdispersions, edgeR_fit$dispersion, pch = 16, log="xy", main = "Overdispersion", xlab = "glmGamPoi", ylab = "edgeR") abline(0,1) ``` I am comparing the gene-wise estimates of the coefficients from all three methods. Points on the diagonal line are identical. The inferred Beta coefficients and gene means agree well between the methods, however the overdispersion differs quite a bit. `DESeq2` has problems estimating most of the overdispersions and sets them to `1e-8`. `edgeR` only approximates the overdispersions which explains the variation around the overdispersions calculated with `glmGamPoi`. ## Scalability The method scales linearly, with the number of rows and columns in the dataset. For example: fitting the full `pbmc4k` dataset with subsampling on a modern MacBook Pro in-memory takes ~1 minute and on-disk a little over 4 minutes. Fitting the `pbmc68k` (17x the size) takes ~73 minutes (17x the time) on-disk. Fitting that dataset in-memory is not possible because it is just too big: the maximum in-memory matrix size is `2^31-1 ≈ 2.1e9` is elements, the `pbmc68k` dataset however has nearly 100 million elements more than that. # Session Info ```{r} sessionInfo() ```