Last updated: 2026-08-21

Checks: 6 1

Knit directory: coderepo-local/

This reproducible R Markdown analysis was created with workflowr (version 1.7.2). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.


The R Markdown is untracked by Git. To know which version of the R Markdown file created these results, you’ll want to first commit it to the Git repo. If you’re still working on the analysis, you can ignore this warning. When you’re finished, you can run wflow_publish to commit the R Markdown file and build the HTML.

Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.

The command set.seed(20251109) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.

Great job! Recording the operating system, R version, and package versions is critical for reproducibility.

Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.

Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version c87957a. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:


Ignored files:
    Ignored:    .DS_Store
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/
    Ignored:    Rplots.pdf
    Ignored:    analysis/.DS_Store
    Ignored:    analysis/.Rhistory
    Ignored:    code/.DS_Store
    Ignored:    code/.Rhistory
    Ignored:    code/revision_simulations/.DS_Store
    Ignored:    data/appendixB/
    Ignored:    data/dynamic_eQTL_real/
    Ignored:    data/revision_simulations/
    Ignored:    data/toy_example/
    Ignored:    output/dynamic_eQTL_real/
    Ignored:    output/pdf/
    Ignored:    output/playwright/
    Ignored:    output/revision_simulations/

Untracked files:
    Untracked:  analysis/revision_internal_evaluation_grid_mc_sensitivity.rmd
    Untracked:  analysis/revision_internal_evaluation_grid_mc_sensitivity_middle_4_11.rmd
    Untracked:  analysis/revision_internal_fash_cl_manuscript_impact.rmd
    Untracked:  analysis/revision_internal_fash_discovery_variant_count.rmd
    Untracked:  analysis/revision_internal_fash_linear_real_data_ablation.rmd
    Untracked:  analysis/revision_internal_fashr_correlated_observation_model.rmd
    Untracked:  analysis/revision_internal_matched_fash_linear_real_data.rmd
    Untracked:  analysis/revision_internal_matched_fash_linear_real_data_cl.rmd
    Untracked:  analysis/revision_internal_r1_normality_assumption.rmd
    Untracked:  analysis/revision_internal_small_m_clean_working_null_sensitivity.rmd
    Untracked:  analysis/revision_internal_small_m_matched_null_eb_sensitivity.rmd
    Untracked:  analysis/revision_internal_twenty_variant_per_gene_refit.rmd
    Untracked:  apps/
    Untracked:  code/02_dyn_lfsr.R
    Untracked:  code/02_dyn_lfsr.sbatch
    Untracked:  code/revision_simulations/appendix_b/
    Untracked:  code/revision_simulations/internal/covariance_estimation/run_design_propagated_null_correlation.R
    Untracked:  code/revision_simulations/internal/covariance_estimation/run_multigene_null_beta_covariance_exploration.R
    Untracked:  code/revision_simulations/internal/early_window_sensitivity/
    Untracked:  code/revision_simulations/internal/evaluation_grid_sensitivity/
    Untracked:  code/revision_simulations/internal/fash_cl_manuscript_impact/
    Untracked:  code/revision_simulations/internal/fash_discovery_variant_count/
    Untracked:  code/revision_simulations/internal/fash_linear_real_data_ablation/
    Untracked:  code/revision_simulations/internal/matched_fash_linear_real_data/
    Untracked:  code/revision_simulations/internal/matched_fash_linear_real_data_cl/
    Untracked:  code/revision_simulations/internal/r0_linear_iwp_power_mechanism/
    Untracked:  code/revision_simulations/internal/r0_linear_summary_statistic/
    Untracked:  code/revision_simulations/internal/r1_known_truth_genotype_permutation/
    Untracked:  code/revision_simulations/internal/r1_linear_truth_composition/
    Untracked:  code/revision_simulations/internal/r1_normality_assumption/
    Untracked:  code/revision_simulations/internal/residual_correlation_fash/
    Untracked:  code/revision_simulations/internal/selected_signal_genotype_permutation/
    Untracked:  code/revision_simulations/r5_one_variant_per_gene/
    Untracked:  code/revision_simulations/shared/build_real_genotype_one_per_gene_cache.R
    Untracked:  code/revision_simulations/shared/real_genotype_one_per_gene.R
    Untracked:  code/revision_simulations/shared/test_linear_mixture_fash.R
    Untracked:  code/revision_simulations/shared/test_real_genotype_one_per_gene.R
    Untracked:  code/revision_simulations/shared/validate_r1_r2_linear_mixture_pairing.R
    Untracked:  code/revision_simulations/shared/validate_r1_r2_real_genotype_pairing.R
    Untracked:  figure/

Unstaged changes:
    Modified:   analysis/dynamic_eQTL_real.rmd
    Modified:   analysis/index.Rmd
    Modified:   analysis/nonlinear_dynamic_eQTL_real.Rmd
    Modified:   analysis/revision_balanced_variant_thinning.rmd
    Modified:   analysis/revision_combined_spiky_genotype_simulation.rmd
    Modified:   analysis/revision_enhancer_enrichment.rmd
    Modified:   analysis/revision_functional_testing_simulation.rmd
    Modified:   analysis/revision_genotype_level_simulation.rmd
    Modified:   code/revision_simulations/README.md
    Modified:   code/revision_simulations/internal/covariance_estimation/run_global_pca_factor_visualization.R
    Modified:   code/revision_simulations/internal/fash_strober_enhancer_comparison/enrichment_api.R
    Modified:   code/revision_simulations/internal/fash_strober_enhancer_comparison/reporting.R
    Modified:   code/revision_simulations/internal/fash_strober_enhancer_comparison/run_fash_strober_enhancer_comparison.R
    Modified:   code/revision_simulations/r1_random_bspline/reporting.R
    Modified:   code/revision_simulations/r1_random_bspline/run_random_bspline_mc_replication.R
    Modified:   code/revision_simulations/r2_spiky_transient/reporting.R
    Modified:   code/revision_simulations/r2_spiky_transient/run_combined_spiky_genotype_simulation.R
    Modified:   code/revision_simulations/r2_spiky_transient/run_spiky_transient_mc_replication.R
    Modified:   code/revision_simulations/r3_functional_testing/reporting.R
    Modified:   code/revision_simulations/r3_functional_testing/run_matched_functional_testing_mc_replication.R
    Modified:   code/revision_simulations/shared/simulation_functions.R

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.


There are no past versions. Publish this analysis with wflow_publish() to start tracking its development.


Internal page. This page reports the CL-PC counterpart of the matched FASH-linear real-data analysis using fashr 0.1.43. It is intentionally absent from the workflowr index, manuscript, and response letter while the PC choice remains under consideration.

Analysis definition

The CL-PC analysis uses five PCs estimated after collapsing expression to the cell-line level and repeats the same PC values across the 16 time points. The FASH-IWP1 and FASH-linear fits use the same 1,009,173 effect estimates, standard errors, exact constant null, 52-point one-day predictive-SD grid, betaprec=0, pred_step=1, penalty=10, corrected BF adjustment, and cumulative-lfdr FDR 0.05. Strober’s retained five-PC results also use cell-line-level PCs.

For FASH-linear,

\[ \beta_j(t)=a_j+b_j(t-t_{j,\min}),\qquad b_j\sim\sum_{k=1}^{51}\pi_k N\!\left(0,\left\{s_k/\mathrm{pred\_step}\right\}^2\right), \]

where \(s_k=\operatorname{SD}(b_j\,\mathrm{pred\_step})\) is sd_linear_step. The exact-null component is \(s_0=0\). Its 51 positive values are numerically identical to the CL-PC IWP1 psd grid.

The exact fitting calls are shown below and are not evaluated while rendering the page.

# Match the grid and hyperparameters to the CL-PC IWP1 reference fit.
matched_grid <- as.numeric(cl_iwp1_raw$psd_grid)
matched_pred_step <- as.numeric(cl_iwp1_raw$settings$pred_step)
matched_penalty <- as.integer(cl_iwp1_raw$settings$penalty)
matched_betaprec <- as.numeric(cl_iwp1_raw$settings$betaprec)
matched_likelihood <- as.character(cl_iwp1_raw$settings$likelihood)

# Apply the corrected BF adjustment to the CL-PC IWP reference fits.
cl_iwp1_bf <- fashr::BF_update(cl_iwp1_raw)
cl_iwp2_bf <- fashr::BF_update(cl_iwp2_raw)

# Fit the exact-null plus 51-component linear-slope mixture.
linear_raw <- fit_linear_mixture_fash_from_stats(
  statistics = statistics,
  grid = matched_grid,
  pred_step = matched_pred_step,
  penalty = matched_penalty,
  statistic_time_span = 15,
  n_time = 16
)
linear_raw$settings$betaprec <- matched_betaprec
linear_raw$settings$likelihood <- matched_likelihood
linear_bf <- BF_update_linear_mixture_fash(linear_raw)
settings_to_report <- matched_settings_table[, c(
  "setting", "fash_iwp1", "fash_linear", "alignment"
)]
names(settings_to_report) <- c(
  "Setting", "FASH-IWP1", "FASH-linear", "Alignment"
)
render_scrollable_table_matched_cl(
  settings_to_report,
  caption = "Table 1. Matched CL-PC data, prior-scale, fitting, and discovery settings.",
  minimum_width = "1040px"
)
Table 1. Matched CL-PC data, prior-scale, fitting, and discovery settings.
Setting FASH-IWP1 FASH-linear Alignment
Tested units 1,009,173 1,009,173 Identical
PC covariates Five cell-line-collapsed PCs Five cell-line-collapsed PCs Identical
Time grid 0:15 0:15 Identical
Likelihood Gaussian Gaussian Identical
Null trajectory Unrestricted constant Unrestricted constant Identical
Alternative family IWP1 Gaussian process mixture Zero-centered Gaussian slope mixture Matched scale; different covariance geometry
Scale parameter psd SD(beta * pred_step) Equivalent one-step SD
Grid components 52 52 Identical
Positive grid range 0.006738 to 1.0 0.006738 to 1.0 Identical
pred_step 1 1 Identical
betaprec 0 0 Matched; not used by linear kernel
penalty 10 10 Identical
IWP basis functions 20 Not used: exact rank-one linear kernel Not applicable
FDR rule Cumulative lfdr at 0.05 Cumulative lfdr at 0.05 Identical

The scientific selection rules used below are:

alpha <- 0.05

iwp1_bf_indices <- select_cumulative_lfdr_calls_linear(
  cl_iwp1_bf$lfdr,
  alpha
)
iwp2_bf_indices <- select_cumulative_lfdr_calls_linear(
  cl_iwp2_bf$lfdr,
  alpha
)
linear_bf_indices <- select_cumulative_lfdr_calls_linear(
  linear_bf$lfdr,
  alpha
)
strober_quadratic_discoveries <- subset(strober_quadratic, eFDR <= alpha)
strober_linear_discoveries <- subset(strober_linear, eFDR <= alpha)

Discovery counts

After BF adjustment, CL-PC FASH-IWP1 identifies 5,395 pairs, 686 genes, and 5,363 unique variants. CL-PC FASH-linear identifies 9,059 pairs, 1,012 genes, and 8,989 unique variants.

render_scrollable_table_matched_cl(
  discovery_counts_display,
  caption = "Table 2. CL-PC raw and BF-adjusted cumulative-lfdr FDR-0.05 discovery counts.",
  digits = 6L,
  minimum_width = "820px"
)
Table 2. CL-PC raw and BF-adjusted cumulative-lfdr FDR-0.05 discovery counts.
Method Adjustment Pairs Genes Unique variants Estimated pi0
FASH-IWP1 Raw 30,344 2,403 29,771 0.472166
FASH-IWP1 BF-adjusted 5,395 686 5,363 0.95077
FASH-linear Raw 38,634 2,809 37,741 0.538551
FASH-linear BF-adjusted 9,059 1,012 8,989 0.93652

The directional coverage is the fraction of each CL-PC IWP discovery set also found by CL-PC FASH-linear.

render_scrollable_table_matched_cl(
  iwp1_linear_proportion_display,
  caption = "Table 3. BF-adjusted CL-PC FASH-IWP1 discoveries covered by BF-adjusted CL-PC FASH-linear at the three reporting levels.",
  minimum_width = "860px"
)
Table 3. BF-adjusted CL-PC FASH-IWP1 discoveries covered by BF-adjusted CL-PC FASH-linear at the three reporting levels.
Level FASH-linear FASH-IWP1 Intersection FASH-IWP1 covered by linear
Pairs 9,059 5,395 4,793 88.8%
Genes 1,012 686 628 91.5%
Variants 8,989 5,363 4,761 88.8%
render_scrollable_table_matched_cl(
  iwp2_linear_proportion_display,
  caption = "Table 4. BF-adjusted CL-PC FASH-IWP2 discoveries covered by BF-adjusted CL-PC FASH-linear at the three reporting levels.",
  minimum_width = "860px"
)
Table 4. BF-adjusted CL-PC FASH-IWP2 discoveries covered by BF-adjusted CL-PC FASH-linear at the three reporting levels.
Level FASH-linear FASH-IWP2 Intersection FASH-IWP2 covered by linear
Pairs 9,059 60 6 10.0%
Genes 1,012 6 3 50.0%
Variants 8,989 60 6 10.0%

CL-PC FASH-linear covers 88.8% of the CL-PC FASH-IWP1 pair discoveries and 10.0% of the CL-PC FASH-IWP2 pair discoveries.

Four-method overlap

The following Venn diagrams add BF-adjusted CL-PC FASH-linear to Strober quadratic, Strober linear, and BF-adjusted CL-PC FASH-IWP1. Strober discoveries use eFDR at most 0.05.

pair_sets <- list(
  `Strober quad.` =
    venn_sets$`Gene-variant pairs`$`Strober quadratic`,
  `Strober linear` =
    venn_sets$`Gene-variant pairs`$`Strober linear`,
  `FASH-linear` =
    venn_sets$`Gene-variant pairs`$`FASH-linear BF`,
  `FASH-IWP1` =
    venn_sets$`Gene-variant pairs`$`FASH-IWP1 BF`
)

ggVennDiagram::ggVennDiagram(
  pair_sets,
  label = "count",
  label_alpha = 0,
  label_size = 3.7,
  set_size = 3.8,
  edge_size = 0.8
) +
  ggplot2::scale_fill_gradient(low = "#f7fbff", high = "#2171b5") +
  ggplot2::theme(
    legend.position = "right",
    plot.margin = ggplot2::margin(20, 40, 20, 40)
  )
Figure 1. Gene-variant-pair overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. FASH sets use cumulative-lfdr FDR 0.05; Strober sets use eFDR 0.05.

Figure 1. Gene-variant-pair overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. FASH sets use cumulative-lfdr FDR 0.05; Strober sets use eFDR 0.05.

gene_sets <- list(
  `Strober quad.` = venn_sets$Genes$`Strober quadratic`,
  `Strober linear` = venn_sets$Genes$`Strober linear`,
  `FASH-linear` = venn_sets$Genes$`FASH-linear BF`,
  `FASH-IWP1` = venn_sets$Genes$`FASH-IWP1 BF`
)

ggVennDiagram::ggVennDiagram(
  gene_sets,
  label = "count",
  label_alpha = 0,
  label_size = 3.7,
  set_size = 3.8,
  edge_size = 0.8
) +
  ggplot2::scale_fill_gradient(low = "#f7fbff", high = "#2171b5") +
  ggplot2::theme(
    legend.position = "right",
    plot.margin = ggplot2::margin(20, 40, 20, 40)
  )
Figure 2. Gene-level overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. A gene enters a set when at least one of its tested variants is discovered by that method.

Figure 2. Gene-level overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. A gene enters a set when at least one of its tested variants is discovered by that method.

variant_sets <- list(
  `Strober quad.` = venn_sets$Variants$`Strober quadratic`,
  `Strober linear` = venn_sets$Variants$`Strober linear`,
  `FASH-linear` = venn_sets$Variants$`FASH-linear BF`,
  `FASH-IWP1` = venn_sets$Variants$`FASH-IWP1 BF`
)

ggVennDiagram::ggVennDiagram(
  variant_sets,
  label = "count",
  label_alpha = 0,
  label_size = 3.7,
  set_size = 3.8,
  edge_size = 0.8
) +
  ggplot2::scale_fill_gradient(low = "#f7fbff", high = "#2171b5") +
  ggplot2::theme(
    legend.position = "right",
    plot.margin = ggplot2::margin(20, 40, 20, 40)
  )
Figure 3. Unique-variant overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. Each rsID is counted once per method, regardless of the number of associated genes.

Figure 3. Unique-variant overlap among Strober quadratic, Strober linear, BF-adjusted CL-PC FASH-IWP1, and BF-adjusted CL-PC FASH-linear. Each rsID is counted once per method, regardless of the number of associated genes.

The BF-adjusted CL-PC IWP1–linear intersections are 4,793 pairs, 628 genes, and 4,761 unique variants. These are real-data set comparisons, not known-truth power comparisons.

Reproducibility and validation

The page reads the versioned CL-PC cache and does not refit the million-pair models.

OMP_NUM_THREADS=1 \
OPENBLAS_NUM_THREADS=1 \
MKL_NUM_THREADS=1 \
VECLIB_MAXIMUM_THREADS=1 \
BLIS_NUM_THREADS=1 \
Rscript --vanilla \
  code/revision_simulations/internal/matched_fash_linear_real_data_cl/\
run_matched_fash_linear_real_data_cl.R

Rscript --vanilla \
  code/revision_simulations/internal/matched_fash_linear_real_data_cl/\
test_matched_fash_linear_real_data_cl.R

Rscript --vanilla -e \
  'workflowr::wflow_build("analysis/revision_internal_matched_fash_linear_real_data_cl.rmd", local = TRUE)'
render_scrollable_table_matched_cl(
  package_display,
  caption = "Table 5. Software provenance for the matched CL-PC rerun.",
  minimum_width = "1120px"
)
Table 5. Software provenance for the matched CL-PC rerun.
Package Version Git ref Git SHA Built
fashr 0.1.43 fashr-0.1.43-testing bf223df75da6e41ae48607a56b4cd12d7c3b24e7 R 4.5.1; aarch64-apple-darwin20; 2026-08-21 05:39:43 UTC; unix
render_scrollable_table_matched_cl(
  validation,
  caption = "Table 6. Numerical, provenance, set-construction, and resource validations for the CL-PC analysis.",
  minimum_width = "760px"
)
Table 6. Numerical, provenance, set-construction, and resource validations for the CL-PC analysis.
check passed
approved_fashr_version_and_sha TRUE
cl_pc_iwp1_settings_match_requested_hyperparameters TRUE
grid_values_and_size_identical TRUE
pair_count_and_order_identical TRUE
retained_statistics_match_cl_pc_iwp_data TRUE
direct_and_accelerated_likelihoods_match TRUE
raw_linear_fit_valid TRUE
bf_linear_fit_valid TRUE
linear_bf_preserves_conditional_alternative_weights TRUE
iwp1_bf_preserves_conditional_alternative_weights TRUE
iwp2_bf_preserves_conditional_alternative_weights TRUE
authoritative_inputs_immutable TRUE
four_method_venn_sets_complete TRUE
exclusive_venn_regions_partition_each_union TRUE
single_process_single_thread_configuration TRUE
render_scrollable_table_matched_cl(
  runtime_summary,
  caption = "Table 7. Single-process runtime for the matched CL-PC analysis.",
  digits = 2L,
  minimum_width = "620px"
)
Table 7. Single-process runtime for the matched CL-PC analysis.
stage elapsed_seconds
CL-PC IWP1 BF update 11
Full CL-PC linear fit plus BF update 64
CL-PC IWP2 BF update 21
Complete runner 125

sessionInfo()
R version 4.5.1 (2025-06-13)
Platform: aarch64-apple-darwin20
Running under: macOS Sequoia 15.6.1

Matrix products: default
BLAS:   /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib 
LAPACK: /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.1

locale:
[1] C.UTF-8/C.UTF-8/C.UTF-8/C/C.UTF-8/C.UTF-8

time zone: America/Chicago
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

loaded via a namespace (and not attached):
 [1] gtable_0.3.6        jsonlite_2.0.0      dplyr_1.1.4        
 [4] compiler_4.5.1      promises_1.5.0      tidyselect_1.2.1   
 [7] Rcpp_1.1.1-1.1      stringr_1.6.0       git2r_0.36.2       
[10] dichromat_2.0-0.1   later_1.4.4         jquerylib_0.1.4    
[13] scales_1.4.0        yaml_2.3.12         fastmap_1.2.0      
[16] ggVennDiagram_1.5.4 ggplot2_4.0.3       R6_2.6.1           
[19] labeling_0.4.3      generics_0.1.4      workflowr_1.7.2    
[22] knitr_1.50          tibble_3.3.0        rprojroot_2.1.1    
[25] bslib_0.9.0         pillar_1.11.1       RColorBrewer_1.1-3 
[28] rlang_1.2.0         cachem_1.1.0        stringi_1.8.9      
[31] httpuv_1.6.16       xfun_0.55           S7_0.2.2           
[34] fs_1.6.6            sass_0.4.10         otel_0.2.0         
[37] cli_3.6.6           withr_3.0.3         magrittr_2.0.5     
[40] digest_0.6.39       grid_4.5.1          rstudioapi_0.17.1  
[43] lifecycle_1.0.5     vctrs_0.7.3         evaluate_1.0.5     
[46] glue_1.8.1          farver_2.1.2        rmarkdown_2.30     
[49] tools_4.5.1         pkgconfig_2.0.3     htmltools_0.5.9