Package: SpiecEasi 2.1.1

Zachary Kurtz

SpiecEasi: Sparse Inverse Covariance for Ecological Statistical Inference

Estimate networks from the precision matrix of compositional microbial abundance data.

Authors:Zachary Kurtz [aut, cre], Christian Mueller [aut], Emily Miraldi [aut], Richard Bonneau [aut], Laura Tipton [ctb]

SpiecEasi_2.1.1.tar.gz
SpiecEasi_2.1.1.zip(r-4.7)SpiecEasi_2.1.1.zip(r-4.6)SpiecEasi_2.1.1.zip(r-4.5)
SpiecEasi_2.1.1.tgz(r-4.6-x86_64)SpiecEasi_2.1.1.tgz(r-4.6-arm64)SpiecEasi_2.1.1.tgz(r-4.5-x86_64)SpiecEasi_2.1.1.tgz(r-4.5-arm64)
SpiecEasi_2.1.1.tar.gz(r-4.7-arm64)SpiecEasi_2.1.1.tar.gz(r-4.7-x86_64)SpiecEasi_2.1.1.tar.gz(r-4.6-arm64)SpiecEasi_2.1.1.tar.gz(r-4.6-x86_64)
SpiecEasi_2.1.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
SpiecEasi/json (API)

# Install 'SpiecEasi' in R:
install.packages('SpiecEasi', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/zdk123/spieceasi/issues

Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
Datasets:

On BioConductor:SpiecEasi-2.1.1(bioc 3.24)SpiecEasi-2.0.0(bioc 3.23)

softwaremicrobiomemetagenomicsgraphandnetworknetworkinferenceopenblascpp

9.58 score 230 stars 792 scripts 50 exports 63 dependencies

Last updated from:3c747724ed. Checks:1 WARNING, 10 OK, 3 NOTE. Indexed: yes.

TargetResultTimeFilesSyslog
bioc-checksWARNING207
linux-devel-arm64OK337
linux-devel-x86_64OK332
source / vignettesOK383
linux-release-arm64OK352
linux-release-x86_64OK500
macos-release-arm64OK311
macos-release-x86_64OK471
macos-oldrel-arm64NOTE374
macos-oldrel-x86_64NOTE534
windows-develOK369
windows-releaseOK331
windows-oldrelNOTE411
wasm-releaseOK153

Exports:adj2igraphalrclrcoatcor2covcov2precebicedge.dissfitdistrget_comm_paramsgetOptBetagetOptCovgetOptiCovgetOptIndgetOptLambdagetOptMergegetOptNetgetRefitgetStabilitygraph2precmake_graphmulti.spiec.easineffneighborhood.netnorm_pseudonorm_rdiricnorm_to_totalprec2covpval.sparccbootqqdplot_commrmvnegbinrmvnormrmvpoisrmvzinegbinrmvzipoisrobustPCArzipoisshannonsparccsparccbootsparseiCovsparseLowRankiCovspiec.easistars.prstars.rocsymBetasynth_comm_from_countstriltriutriu2diag

Dependencies:ade4apeBiobaseBiocGenericsbiomformatBiostringscliclustercodetoolscpp11crayondata.tabledigestfarverforeachgenericsggplot2glmnetgluegtablehugeigraphIRangesisobanditeratorsjsonlitelabelinglatticelifecyclemagrittrMASSMatrixmgcvmulttestnlmepermutephyloseqpixmappkgconfigplyrpulsarR6RColorBrewerRcppRcppArmadilloRcppEigenreshape2rlangS4VectorsS7scalesSeqinfoshapespstringistringrsurvivalvctrsveganVGAMviridisLitewithrXVector

Cross Domain SPIEC-EASI
Key features of cross-domain analysis | Example with custom data | Interpretation
Rendered fromcross-domain-interactions.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

Introduction to SpiecEasi
Installation | Available vignettes | Basic Usage | Analysis of American Gut data | Next steps
Rendered fromSpiecEasi.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

Learning latent variable graphical models
Key differences from standard SPIEC-EASI
Rendered fromlatent-variable-models.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

pulsar: parallel utilities for model selection
Windows-specific considerations | Option 1: Use batch mode with snow | Option 2: Use serial processing | Option 3: Use batch mode | Batch Mode | Performance comparison | Key parameters | Platform-specific recommendations | Unix-like systems (Linux, macOS): | Windows systems:
Rendered frompulsar-parallel.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

Troubleshooting
Common issues and solutions | 1. Empty networks | 2. Very dense networks | 3. Computational issues | 4. Windows parallel processing issues | 5. Convergence issues | 6. Memory issues | Platform-specific considerations | Windows users: | Unix-like systems (Linux, macOS): | Diagnostic functions | Parameter tuning guidelines | For small datasets (< 100 samples, < 50 taxa): | For medium datasets (100-1000 samples, 50-200 taxa): | For large datasets (> 1000 samples, > 200 taxa): | Windows-specific recommendations:
Rendered fromtroubleshooting.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

Working with phyloseq
Rendered fromphyloseq-integration.Rmdusingknitr::rmarkdown

Last update: 2026-04-29
Started: 2025-09-24

Readme and manuals

Help Manual

Help pageTopics
Adjacency to igraphadj2igraph
American Gut ProjectAGP amgut1.filt amgut2.filt.phy
Additive log-ratio functionsalr alr.data.frame alr.default alr.matrix
s3 method for graph to other data typesas.data.frame.graph
s3 method for graph to other data typesas.matrix.graph
Centered log-ratio functionsclr clr.data.frame clr.default clr.matrix
COATcoat
Convert a symmetric correlation matrix to a covariance matrix given the standard deviationcor2cov
Covariance matrix to its matrix inverse (Precision matrix)cov2prec
Extended BICebic
Edge set dissimilarityedge.diss
Fit parameters of a marginal distribution to some data vectorfitdistr
Get the parameters for the OTUs (along mar) of each communityget_comm_params
get StARS-optimal networkgetOptBeta getOptCov getOptiCov getOptInd getOptLambda getOptMerge getOptNet getRefit getStability
Convert a symmetric graph (extension of R matrix class)graph2prec
Human Microbiome Project 2hmp2 hmp216S hmp2prot
Procedure to generate graph topologies for Gaussian Graphical Modelsmake_graph
multi domain SPIEC-EASImulti.spiec.easi spiec.easi.list
N_effective: Compute the exponential of the shannon entropy. linearizes shannon entropy, for a better diveristy metric (effective number of species)neff
Neighborhood net estimatesneighborhood.net
Normalize w/ Pseudocountnorm_pseudo
Normalize via dirichlet samplingnorm_rdiric
Total Sum Normalizenorm_to_total
Precision matrix (inverse covariance) to a covariance matrixprec2cov
pulsar paramspulsar.params
SparCC p-valspval.sparccboot
qq-plot for theoretical vs observed communitiesqqdplot_comm
Generate multivariate, Zero-inflated negative binomial data, with counts approximately correlated according to Sigmarmvnegbin
Draw samples from multivariate, correlated normal distribution with counts correlated according to Sigmarmvnorm
Generate multivariate poisson data, with counts approximately correlated according to Sigmarmvpois
Generate multivariate, negative binomial data, with counts approximately correlated according to Sigmarmvzinegbin
Generate multivariate, Zero-inflated poisson data, with counts approximately correlated according to Sigmarmvzipois
robust PCArobustPCA
Draw samples from a zero-inflated poisson distributionrzipois
compute the shannon entropy from a vector (normalized internally)shannon
sparcc wrappersparcc
Bootstrap SparCCsparccboot
Sparse/penalized estimators of covariance matricessparseiCov
Sparse plus Low Rank inverse covariancesparseLowRankiCov
SPIEC-EASI pipelinespiec.easi spiec.easi.default spiec.easi.otu_table spiec.easi.phyloseq
stars.roc, stars.prstars.pr stars.roc
sym betasymBeta
synth_comm_from_countssynth_comm_from_counts