Package: qch 2.1.3

Tristan Mary-Huard

qch: Query Composite Hypotheses

Provides functions for the joint analysis of Q sets of p-values obtained for the same list of items. This joint analysis is performed by querying a composite hypothesis, i.e. an arbitrary complex combination of simple hypotheses, as described in Mary-Huard et al. (2021) <doi:10.1093/bioinformatics/btab592> and De Walsche et al.(2025) <doi:10.1093/nargab/lqaf118>. In this approach, the Q-uplet of p-values associated with each item is distributed as a multivariate mixture, where each of the 2^Q components corresponds to a specific combination of simple hypotheses. The dependence between the p-value series is considered using a Gaussian copula function. A p-value for the composite hypothesis test is derived from the posterior probabilities.

Authors:Tristan Mary-Huard [aut, cre], Annaig De Walsche [aut], Franck Gauthier [ctb]

qch_2.1.3.tar.gz
qch_2.1.3.tar.gz(r-4.7-arm64)qch_2.1.3.tar.gz(r-4.7-x86_64)qch_2.1.3.tar.gz(r-4.6-arm64)qch_2.1.3.tar.gz(r-4.6-x86_64)
qch_2.1.3.tgz(r-4.6-emscripten)
manual.pdf |manual.html
card.svg |card.png
qch/json (API)

# Install 'qch' in R:
install.packages('qch', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))
Uses libs:
  • openblas– Optimized BLAS
  • c++– GNU Standard C++ Library v3
  • openmp– GCC OpenMP (GOMP) support library
Datasets:
  • PvalSets - Synthetic example to illustrate the main qch functions
  • PvalSets_cor - Synthetic example to illustrate the main qch functions using Gaussian copula

On CRAN:

Conda:

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

openblascppopenmp

1.48 score 6 scripts 228 downloads 5 exports 41 dependencies

Last updated from:a83f980907. Checks:6 OK. Indexed: no.

TargetResultTimeFilesSyslog
linux-devel-arm64OK144
linux-devel-x86_64OK154
source / vignettesOK171
linux-release-arm64OK145
linux-release-x86_64OK159
wasm-releaseOK128

Exports:GetH1AtLeastGetH1EqualGetHconfigqch.fitqch.test

Dependencies:ADGofTestcliclustercolorspacecopuladplyrFNNgenericsgluegslkernlabKernSmoothkslatticelifecyclemagrittrMatrixmclustmgcvmulticoolmvtnormnlmenumDerivpcaPPpillarpkgconfigpracmapsplinepurrrR6RcppRcppArmadillorlangstablediststringistringrtibbletidyselectutf8vctrswithr

Readme and manuals

Help Manual

Help pageTopics
Gaussian copula density for each H-configuration.Copula.Hconfig_gaussian_density
EM calibration in the case of the Gaussian copula (unsigned)EM_calibration_gaussian
EM calibration in the case of the Gaussian copula (unsigned) with memory managementEM_calibration_gaussian_memory
EM calibration in the case of conditional independenceEM_calibration_indep
EM calibration in the case of conditional independence with memory management (unsigned)EM_calibration_indep_memory
Signed case function: Separate f1 into f+ and f-f1_separation_signed
FastKerFdr signedFastKerFdr_signed
FastKerFdr unsignedFastKerFdr_unsigned
Computation of the sum sum_c(w_c*psi_c) using Gaussian copula parallelized versionfHconfig_sum_update_gaussian_copula_ptr_parallel
Computation of the sum sum_c(w_c*psi_c) parallelized versionfHconfig_sum_update_ptr_parallel
Gaussian copula densitygaussian_copula_density
Specify the configurations corresponding to the composite H_1 test "AtLeast".GetH1AtLeast
Specify the configurations corresponding to the composite H_1 test "Equal".GetH1Equal
Generate the H_0/H_1 configurations.GetHconfig
This function is a re-implementation of the initial R loop computing last incomplete trapezoid. See R function integral.kde_adapted().last_incomplete_trapezoid_arma
Update of the prior estimate in EM algo parallelized versionprior_update_arma_ptr_parallel
Update of the prior estimate in EM algo using Gaussian copula, parallelized versionprior_update_gaussian_copula_ptr_parallel
Synthetic example to illustrate the main qch functionsPvalSets
Synthetic example to illustrate the main qch functions using Gaussian copulaPvalSets_cor
Infer posterior probabilities of H_0/H_1 configurations.qch.fit
Perform composite hypothesis testing.qch.test
Update the estimate of R correlation matrix of the gaussian copula, parallelized versionR_MLE_update_gaussian_copula_ptr_parallel
Gaussian copula correlation matrix Maximum Likelihood estimator.R.MLE
Check the Gaussian copula correlation matrix Maximum Likelihood estimatorR.MLE.check
Gaussian copula correlation matrix Maximum Likelihood estimator (memory handling)R.MLE.memory
Same as function above but does not handle the index ordering of the vector q. Therefore, the 2nd argument order_q has to be an index ordered version of the vector q. Indeed, the R base function: order() is twice as fast as the arma::sort_index(q) This is therefore the recommended function to use.remove_decreasing_values_cpp
This function is a re-implementation of the initial R side while loop. See the end of R function integral.kde_adapted(). As shown in the commentary below, it is twice as slow to handle the index ordering of the vector q (2nd argument) here with the function arma::sort_index(). Consequently, it is recommended to use the function remove_decreasing_values_cpp() instead.remove_decreasing_values_cpp_slow_ordering