Package: IHWpaper 1.41.0

Nikos Ignatiadis

IHWpaper: Reproduce figures in IHW paper

This package conveniently wraps all functions needed to reproduce the figures in the IHW paper (https://www.nature.com/articles/nmeth.3885) and the data analysis in https://rss.onlinelibrary.wiley.com/doi/10.1111/rssb.12411, cf. the arXiv preprint (http://arxiv.org/abs/1701.05179). Thus it is a companion package to the Bioconductor IHW package.

Authors:Nikos Ignatiadis [aut, cre]

IHWpaper_1.41.0.tar.gz
IHWpaper_1.41.0.tar.gz(r-4.7-arm64)IHWpaper_1.41.0.tar.gz(r-4.7-x86_64)IHWpaper_1.41.0.tar.gz(r-4.6-arm64)IHWpaper_1.41.0.tar.gz(r-4.6-x86_64)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
IHWpaper/json (API)

# Install 'IHWpaper' in R:
install.packages('IHWpaper', repos = c('https://bioc.r-universe.dev', 'https://cloud.r-project.org'))
Uses libs:
  • c++– GNU Standard C++ Library v3

On BioConductor:IHWpaper-1.41.0(data/experiment 3.24)IHWpaper-1.40.0(data/experiment 3.23)

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

reproducibleresearchexperimentdatarnaseqdataexpressiondatadatapkgcpp

5.04 score 2 scripts 29 exports 89 dependencies

Last updated from:4458da47a1. Checks:1 ERROR, 4 NOTE, 1 OK. Indexed: yes.

TargetResultTimeFilesSyslog
bioc-checksERROR184
linux-devel-arm64NOTE348
linux-devel-x86_64NOTE401
source / vignettesOK412
linux-release-arm64NOTE350
linux-release-x86_64NOTE469

Exports:analyze_datasetbhbonfclfdrcontinuous_wrapddhfdu_ttest_simdu_ttest_sim_fungbhihw_5foldihw_5fold_regihw_bonf_5fold_regihw_ecdf_5foldihw_naiveihw_storey_5foldlsl_gbhlsl_pi0_estnull_simnull_sim_funpretty_legendrun_evalsstorey_qvaluestratified_bhtst_gbhtst_pi0_estwasserman_normal_prds_simwasserman_normal_prds_sim_funwasserman_normal_simwasserman_normal_sim_fun

Dependencies:abindannotateAnnotationDbiaskpassBHBiobaseBiocBaseUtilsBiocGenericsBiocParallelBiostringsbitbit64blobcachemclicodetoolscowplotcpp11crayoncurlDBIDelayedArrayDESeq2dplyrfarverfastmapfdrtoolformatRfutile.loggerfutile.optionsgenefiltergenericsGenomicRangesggplot2gluegtablehttrIHWIRangesisobandjsonliteKEGGRESTlabelinglambda.rlatticelifecyclelocfitlpsymphonymagrittrMatrixMatrixGenericsmatrixStatsmemoisemimeopensslpillarpkgconfigplyrpngqvalueR6RColorBrewerRcppRcppArmadilloreshape2rlangRSQLiteS4ArraysS4VectorsS7scalesSeqinfoslamsnowSparseArraystringistringrSummarizedExperimentsurvivalsystibbletidyselectutf8vctrsviridisLitewithrXMLxtableXVector

Explaining tdr
Introduction | Size investing and tdr

Last update: 2021-10-25
Started: 2016-04-21

Real data examples
Panel a) | Panel b) | Proteomics Example | panel c) | Panel d) | hQTL Example | Load in data | Panel e) | Panel f) | Put all panels together for main fig! | Put all panels together for suppl fig.

Last update: 2021-10-25
Started: 2016-04-21

hQTL analysis with IHW-Benjamini-Yekutieli
Histogram plots | Apply IHW-BY and BY | Hypotheses shown in table | Set out to do the weight/threshold/lfdr plots | Start the plotting | Weights chromosome 1

Last update: 2021-10-25
Started: 2018-07-11

Simulation Results
Panels a,b | Data for panels a,b | Panel a) | Panel b) | Panels a, b) | Panels c, d) | Data for panels c,d) | Panel c) | Panel d) | Put panels c), d) together: | Panels e),f) | Load data for panels e),f) | Panel e) | Panel f) | Combine main panels for size investing | Combine everything into main text simulation figure | New main fig sim. figures without borders: | Supplementary panel b) | Combine supplementary effect size simulations | Supplementary Size Investing | Supplementary Panel c), FDR in size investing simulations | Supplementary Panel d), Power in size investing simulations | Combine supplemental size investing panels | Full supplementary simulations figure | New supplementary simulations figure

Last update: 2020-06-23
Started: 2016-04-21

Grenander Estimator as applied to IHW (vs ECDF)

Last update: 2020-06-23
Started: 2016-04-21

IHW-Bonferroni simulations
Null simulation | FWER control | Effect size simulation (t-test) | Power | Size investing simulation | Composite panel:

Last update: 2018-06-09
Started: 2016-04-21

Stratified Histograms
Old example | Examples for Figure 1 of paper | Figure 1 of paper

Last update: 2018-06-09
Started: 2016-04-21

BH explanation / visualization
B.Sc. thesis plot (low $\pi_0$) | Bioc presentation plot (higher $\pi_0$)

Last update: 2018-06-09
Started: 2016-04-21

Real data examples: 1-fold weight function
DESeq2 Bottomly | hQTL example

Last update: 2018-06-09
Started: 2016-04-21

tdr and pvalue rejection regions

Last update: 2018-06-09
Started: 2016-04-21

Weights vs Independent Filtering

Last update: 2018-06-09
Started: 2016-04-21

Readme and manuals

Help Manual

Help pageTopics
analyze_dataset: Basically performs preprocessing and then returns analyzed RNASeq dataset (diff. expression) , i.e. the DESeq2 result whose p-values and baseMean statistics can then be used with IHWanalyze_dataset
bh: Wrapper for Benjamini Hochbergbh
bonf: Wrapper for Bonferronibonf
clfdr: Cai's local fdr based methodclfdr
Benchmarking wrapper: Given a multiple testing method, convert it so that it takes a simulation object (see simulation function) and a nominal level alpha as inputscontinuous_wrap
ddhf: Greedy independent filteringddhf
t-test simulation: Simulate rowwise t-testsdu_ttest_sim du_ttest_sim_fun
gbh: Grouped Benjamini Hochberggbh lsl_gbh tst_gbh
IHW wrappersihw_5fold ihw_5fold_reg ihw_bonf_5fold_reg ihw_ecdf_5fold ihw_naive ihw_storey_5fold
LSL (Least-Slope) pi0 estimatorlsl_pi0_est
Null simulation: Generate uniformly distributed p-values and covariatesnull_sim null_sim_fun
helper function to create nice legendspretty_legend
run_evals: Main function to benchmark FDR methods on given simulations.run_evals
scott_fdrreg: Wrapper for FDR regression (https://github.com/jgscott/FDRreg)scott_fdrreg
storey_qvalue: Wrapper for Storey's qvalue packagestorey_qvalue
stratified_bh: Stratified Benjamini Hochbergstratified_bh
TST (Two-Step) pi0 estimatortst_pi0_est
Normal PRDS simulation: Covariate is effect size under alternative, there are latent factors driving PRDS correlations among hypotheseswasserman_normal_prds_sim wasserman_normal_prds_sim_fun
Normal simulation: Covariate is effect size under alternativewasserman_normal_sim wasserman_normal_sim_fun