Package: scLANE 1.3.0

Jack R. Leary

scLANE: Model Gene Expression Dynamics with Spline-Based NB GLMs, GEEs, & GLMMs

Our scLANE model uses truncated power basis spline models to build flexible, interpretable models of single cell gene expression over pseudotime or latent time. The modeling architectures currently supported are Negative-binomial GLMs, GEEs, & GLMMs. Downstream analysis functionalities include model comparison, dynamic gene clustering, smoothed counts generation, gene set enrichment testing, & visualization.

Authors:Jack R. Leary [aut, cre], Rhonda Bacher [ctb, fnd]

scLANE_1.3.0.tar.gz
scLANE_1.3.0.zip(r-4.7)scLANE_1.3.0.zip(r-4.6)scLANE_1.3.0.zip(r-4.5)
scLANE_1.3.0.tgz(r-4.6-x86_64)scLANE_1.3.0.tgz(r-4.6-arm64)scLANE_1.3.0.tgz(r-4.5-x86_64)scLANE_1.3.0.tgz(r-4.5-arm64)
scLANE_1.3.0.tar.gz(r-4.7-arm64)scLANE_1.3.0.tar.gz(r-4.7-x86_64)scLANE_1.3.0.tar.gz(r-4.6-arm64)scLANE_1.3.0.tar.gz(r-4.6-x86_64)
scLANE_1.3.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
scLANE/json (API)

# Install 'scLANE' in R:

install.packages('scLANE', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/jr-leary7/sclane/issues

Uses libs:

c++– GNU Standard C++ Library v3

Datasets:

scLANE_models - An object of class 'scLANE'.
sim_counts - A 'SingleCellExperiment' object containing simulated counts.
sim_pseudotime - A data.frame containing ground-truth pseudotime.

On BioConductor:scLANE-1.3.0(bioc 3.24)scLANE-1.2.0(bioc 3.23)

rnaseq software clustering timecourse sequencing regression singlecell visualization geneexpression transcriptomics genesetenrichment differentialexpression differential-expression estimating-equations genomics mixed-models pseudotime rna-velocity scrna-seq single-cell trajectory-inference cpp

6.83 score 16 stars 38 scripts 224 downloads 27 exports 103 dependencies

Last updated from:cebd511287. Checks:1 WARNING, 13 OK. Indexed: yes.

Target	Result	Time
bioc-checks	WARNING	247
linux-devel-arm64	OK	501
linux-devel-x86_64	OK	682
source / vignettes	OK	382
linux-release-arm64	OK	510
linux-release-x86_64	OK	655
macos-release-arm64	OK	379
macos-release-x86_64	OK	610
macos-oldrel-arm64	OK	339
macos-oldrel-x86_64	OK	632
windows-devel	OK	912
windows-release	OK	489
windows-oldrel	OK	1028
wasm-release	OK	376

Exports:bootstrapRandomEffects chooseCandidateGenes clusterGenes createCellOffset embedGenes enrichDynamicGenes extractBreakpoints fitGLMM geneProgramDrivers geneProgramScoring geneProgramSignificance getFittedValues getKnotDist getResultsDE marge2 nbGAM npConvolve plotClusteredGenes plotModelCoefs plotModels smoothedCountsMatrix sortGenesHeatmap sortObservations summarizeModel testDynamic testSlope theme_scLANE

Dependencies:backports bigassertr bigparallelr bigstatsr bit boot broom broom.mixed bst cli coda codetools colorspace cowplot cpp11 Deriv digest doBy doParallel doSNOW dplyr farver ff flock forcats foreach forecast fracdiff furrr future gamlss gamlss.data gamlss.dist gbm geeM generics ggplot2 glm2 glmmTMB glmnet globals glue gtable isoband iterators labeling lattice lifecycle listenv lme4 lmtest magrittr MASS Matrix mgcv microbenchmark minqa modelr mpath nlme nloptr nnet numDeriv parallelly pbkrtest pillar pkgconfig ps pscl purrr R6 rbibutils RColorBrewer Rcpp RcppArmadillo RcppEigen Rdpack reformulas RhpcBLASctl rlang rmio rpart RSpectra S7 sandwich scales shape snow stringi stringr survival tibble tidyr tidyselect timeDate TMB urca utf8 vctrs viridisLite WeightSVM withr zoo

Interpretable Trajectory DE Testing

Rendered fromscLANE.Rmdusingknitr::rmarkdown

Last update: 2025-10-04
Started: 2023-10-19

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Backward selection function for MARGE - uses the Wald information criterion (WIC).	backward_sel_WIC
Bias-correct the GEE sandwich variance-covariance matrix.	biasCorrectGEE
Generate bootstrapped confidence intervals for random effects.	bootstrapRandomEffects
Choose candidate genes for trajectory DE analysis.	chooseCandidateGenes
Cluster the fitted values from a set of 'scLANE' models.	clusterGenes
Create an offset vector before modeling.	createCellOffset
A helper function to create a dataframe of breakpoints and associated _p_-values from a 'marge' model.	createSlopeTestData
Generate PCA & UMAP embeddings of fitted gene dynamics.	embedGenes
Perform GSEA on dynamic genes identified by 'scLANE'.	enrichDynamicGenes
Identify breakpoints in a 'marge' model.	extractBreakpoints
Build an NB GLMM using truncated power basis functions.	fitGLMM
Identify driver genes for a given gene program.	geneProgramDrivers
Add per-cell module scores for gene programs.	geneProgramScoring
Test significance of gene program enrichment across a trajectory.	geneProgramSignificance
Generate a table of fitted values and celltype metadata for genes of interest.	getFittedValues
Pull the set of knots for dynamic genes across each lineage.	getKnotDist
Tidy the results of 'testDynamic'.	getResultsDE
Fit 'MARGE' models of single cell counts.	marge2
Truncates the predictor variable value to exclude extreme values in knots selection.	max_span
A truncation function applied on the predictor variable for knot selection.	min_span
Perform a likelihood ratio test for one model against another.	modelLRT
Fit a negative-binomial GAM.	nbGAM
Convolution that matches 'np.convolve'.	npConvolve
Generate tidy results from 'clusterGenes' to use in plotting.	plotClusteredGenes
Plot gene dynamics with estimated coefficients.	plotModelCoefs
Plot results of 'marge' and other models using 'ggplot2'.	plotModels
Print method for summary.scLANE objects.	print.summary.scLANE
Generate a summary of the MARGE model.	pullMARGESummary
Generate a summary of the null model.	pullNullSummary
An object of class 'scLANE'.	scLANE_models
Given estimates from the null model fit and the design matrix for alternative model, find the score statistic (this is used for GEEs only).	score_fun_gee
Given estimates from the null model fit and the design matrix for alternative model, find the score statistic (this is used for GLMs only).	score_fun_glm
Use a Lagrange multiplier (score) test to compare nested GEE models.	scoreTestGEE
A 'SingleCellExperiment' object containing simulated counts.	sim_counts
A data.frame containing ground-truth pseudotime.	sim_pseudotime
Generate a smoothed matrix of gene expression using 'scLANE' models.	smoothedCountsMatrix
Sort genes by where their peak expression occurs across pseudotime.	sortGenesHeatmap
Sort observations by sample ID and pseudotime.	sortObservations
Fits a linear regression model and calculates RSS/GCV measures (used for MARS linear models).	stat_out
Calculate part of the score statistic for a GEE.	stat_out_score_gee_null
Calculate part of the score statistic for a GLM.	stat_out_score_glm_null
Make GLM objects much smaller.	stripGLM
Represent a 'marge' model as a series of piecewise equations.	summarizeModel
Summary method for scLANE objects.	summary.scLANE
Test whether a gene is dynamic over pseudotime.	testDynamic
Test whether a gene is dynamic over a pseudotime interval.	testSlope
A 'ggplot2' theme for 'scLANE'.	theme_scLANE
Truncated p-th power function (positive part).	tp1
Truncated p-th power function (negative part).	tp2
Use a Wald test to compare nested GEE models.	waldTestGEE