{ "_id": "6aad05ed3d719c1f84074fd4", "Package": "iconic", "Title": "Causal Model Selection with Genetic Instruments and Negative\nControls", "Version": "0.99.3", "biocViews": "StatisticalMethod, Genetics, MultipleComparison, Regression,\nTranscriptomics, RNASeq, Survival", "Authors@R": "c(\nperson(\"Sean T.\", \"Bresnahan\", role = c(\"aut\", \"cre\"),\nemail = \"seantbresnahan3@gmail.com\"),\nperson(\"Charis\", \"Xiong\", role = \"aut\",\nemail = \"charis.xiong@gmail.com\"))", "Description": "Provides a model selection workflow for causal inference\nwith genetic instruments and negative controls in observational\nomics data. The package fits eight estimators of the natural\ndirect and indirect effects (NDE/NIE), diagnoses which are\nvalid for the user's data via instrument-strength checks and\nnegative-control validity screens (A1, A2, A2'), stress-tests\nthem against confounding and pleiotropy violations, and\nrecommends the estimator most likely to be unbiased. A hybrid\ngenerative texture model (a torch GAN for sample-level\nstructure and a Gaussian copula for the mediator panel) lets\nthe sensitivity analysis mirror the marginal and joint\nstructure of the user's cohort. The modular API comprises\niconic_data() to standardize data, iconic_diagnose() to assess\nestimator eligibility, iconic_estimate() to fit all eligible\nestimators, iconic_sensitivity() to sweep instrument\nexogeneity, iconic_recommend() to rank estimators by\nidentification strength and robustness, and iconic_prospect()\nto plan future studies. infer_confounding() estimates\nheld-fixed confounding parameters from the data. Helper\nfunctions construct exposure instruments (polygenic scores from\nGWAS summary statistics or PGS Catalog scoring files), mediator\ninstruments (cis-eQTL scans and elastic-net\npredicted-expression composites), and negative-control panels\n(principal components of residualized omics matrices), and data\ncan be imported directly from SummarizedExperiment objects.\nTime-to-event outcomes are supported on the Cox\nlog-hazard-ratio and restricted-mean-survival-time scales.\nBinary outcomes are supported on the log-odds-ratio (logistic\ntwo-stage predictor-substitution outcome stage) and\nrisk-difference (linear probability model) scales. The torch\npackage is required for the generative texture model\n(sensitivity and prospective analysis); all other functionality\nworks without it.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "Config/roxygen2/version": "8.1.0", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "URL": "https://seantbresnahan.com/iconic/,\nhttps://github.com/sbresnahan/iconic", "BugReports": "https://github.com/sbresnahan/iconic/issues", "NeedsCompilation": "no", "Packaged": { "Date": "2026-09-18 08:58:13 UTC", "User": "root" }, "Author": "Sean T. Bresnahan [aut, cre], Charis Xiong [aut]", "Maintainer": "Sean T. Bresnahan ", "Config/pak/sysreqs": "cmake make libicu-dev", "Repository": "https://biocstaging.r-universe.dev", "Date/Publication": "2026-08-19 18:07:21 UTC", "RemoteUrl": "https://github.com/BiocStaging/iconic", "RemoteRef": "HEAD", "RemoteSha": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "_user": "biocstaging", "_type": "src", "_file": "iconic_0.99.3.tar.gz", "_fileid": "https://r2.ropensci.org/c955fe08eb118b9d5a58e185bdf3059f893109d221f02226c7ea7c74cace7763", "_filesize": 2762571, "_sha256": "c955fe08eb118b9d5a58e185bdf3059f893109d221f02226c7ea7c74cace7763", "_expires": "2026-12-27T09:35:39.000Z", "_created": "2026-09-18T08:58:13.000Z", "_published": "2026-09-18T09:35:41.279Z", "_bioccheck": { "error": 0, "warning": 1, "note": 6 }, "_host": "GitHub-Actions", "_buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362", "_status": "success", "_upstream": "https://github.com/BiocStaging/iconic", "_commit": { "id": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "author": "sbresnahan ", "committer": "sbresnahan ", "message": "iconic 0.99.3\n\n## New features\n\n- **Binary outcome support.** `outcome_type = \"binary\"` is now\n available throughout the workflow: `iconic_data()` accepts a 0/1\n outcome vector (validated as dichotomous, stored unscaled as\n `Y_bin`), and `iconic_estimate()`, `iconic_sensitivity()`,\n `iconic_prospect()`, and `run_single_iteration()` all dispatch to\n binary-specific estimators. `generate_toy_data()` and\n `run_single_iteration()` gain a `bin_prev` argument (default 0.5)\n controlling the outcome prevalence of the simulated binary DGP.\n\n- **Two effect scales for binary outcomes** via the `effect_scale`\n argument: `\"logor\"` (default; logistic two-stage\n predictor-substitution outcome stage, mirroring the Cox log-HR\n convention for survival) and `\"riskdiff\"` (linear probability model\n outcome stage, giving an exactly collapsible NDE/NIE decomposition).\n Inert scale requests are remapped with an informative message\n (e.g. `effect_scale = \"loghr\"` on binary data maps to `\"logor\"`).\n\n- **New binary estimators** (`R/bin_estimators.R`,\n `R/bin_mediation.R`): `fit_unadj_bin()`, `fit_direct_bin()`,\n `fit_iv2sls_bin()`, `fit_pgc_bin()`, and the mediation variants\n `fit_unadj_mediation_bin()`, `fit_direct_mediation_bin()`,\n `fit_iv2sls_mediation_bin()`, `fit_iv2sls_mediation2_bin()`,\n `fit_pgc_mediation_bin()`, `fit_pgc_mediation2_bin()`. First stages\n remain OLS; only the outcome stage changes (binomial GLM or linear\n probability model). The partial-F weak-instrument gate and the\n collinear-panel fallback behave as for continuous and survival\n outcomes.\n\n- **COCA is excluded for binary outcomes** (`fit_coca_bin()` and\n `fit_coca_mediation_bin()` return `NA` with a `reason` attribute, the\n same contract as for survival): COCA's ratio identification assumes a\n linear structural outcome model, which neither the log-OR nor the\n risk-difference binary outcome stage satisfies.\n\n## Behavioural notes\n\n- `infer_confounding()` now errors informatively for binary ou", "time": 1787162841 }, "_maintainer": { "name": "Sean T. Bresnahan", "email": "seantbresnahan3@gmail.com", "login": "sbresnahan", "bluesky": "@seantbres.bsky.social", "description": "Associate Data Scientist | PhD in Molecular, Cellular and Integrative Biosciences from Penn State", "uuid": 58915342 }, "_distro": "resolute", "_jobs": [ { "job": 105542676411, "time": 235, "config": "bioc-checks", "r": "4.6.1", "check": "WARNING", "artifact": "10539951379" }, { "job": 105542676459, "time": 638, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10539601935" }, { "job": 105542676464, "time": 866, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10539234669" }, { "job": 105542676440, "time": 594, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "10540169495" }, { "job": 105542676511, "time": 421, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "10539839688" }, { "job": 105541334706, "time": 297, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "10538349892" }, { "job": 105542676441, "time": 159, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "10539841376" }, { "job": 105542676597, "time": 807, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "10539723284" }, { "job": 105542676549, "time": 814, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "10540276452" }, { "job": 105542676518, "time": 476, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "10539627604" } ], "_registered": true, "_dependencies": [ { "package": "AER", "role": "Imports" }, { "package": "MASS", "role": "Imports" }, { "package": "parallel", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "survival", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "withr", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "patchwork", "role": "Suggests" }, { "package": "scales", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "torch", "role": "Suggests" }, { "package": "bigsnpr", "role": "Suggests" }, { "package": "bigstatsr", "role": "Suggests" }, { "package": "glmnet", "role": "Suggests" }, { "package": "irlba", "role": "Suggests" }, { "package": "SummarizedExperiment", "role": "Suggests" }, { "package": "S4Vectors", "role": "Suggests" }, { "package": "BiocStyle", "role": "Suggests" } ], "_owner": "biocstaging", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-30", "n": 11 }, { "week": "2026-31", "n": 4 }, { "week": "2026-32", "n": 7 }, { "week": "2026-33", "n": 9 }, { "week": "2026-34", "n": 3 } ], "_tags": [], "_topics": [ "statisticalmethod", "genetics", "multiplecomparison", "regression", "transcriptomics", "rnaseq", "survival" ], "_stars": 0, "_contributors": [ { "user": "sbresnahan", "count": 34, "uuid": 58915342 }, { "user": "jhuang35", "count": 1, "uuid": 6342364 } ], "_userbio": { "uuid": 278472782, "type": "organization", "name": "BiocStaging", "followers": 2 }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/iconic" }, "_devurl": "https://github.com/sbresnahan/iconic", "_pkgdown": "https://seantbresnahan.com/iconic/", "_searchresults": 0, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/iconic.html", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_cranurl": false, "_exports": [ "analyze_mediation_robust", "analyze_methods_parallel", "analyze_methods_robust", "apply_fusion_weights", "as_iconic_data", "beta_to_m", "build_mediator_instruments", "build_prs_ldpred2", "build_w_pcs", "call_cis_eqtls", "check_instrument_strength", "check_torch_setup", "composite_p_value", "fit_coca", "fit_coca_bin", "fit_coca_mediation", "fit_coca_mediation_bin", "fit_coca_mediation_surv", "fit_coca_surv", "fit_direct", "fit_direct_bin", "fit_direct_mediation", "fit_direct_mediation_bin", "fit_direct_mediation_surv", "fit_direct_surv", "fit_iv2sls", "fit_iv2sls_bin", "fit_iv2sls_mediation", "fit_iv2sls_mediation_bin", "fit_iv2sls_mediation_surv", "fit_iv2sls_mediation2", "fit_iv2sls_mediation2_bin", "fit_iv2sls_mediation2_surv", "fit_iv2sls_surv", "fit_pgc", "fit_pgc_bin", "fit_pgc_mediation", "fit_pgc_mediation_bin", "fit_pgc_mediation_surv", "fit_pgc_mediation2", "fit_pgc_mediation2_bin", "fit_pgc_mediation2_surv", "fit_pgc_scalar", "fit_pgc_scalar_mediation", "fit_pgc_surv", "fit_unadj_bin", "fit_unadj_mediation", "fit_unadj_mediation_bin", "fit_unadj_mediation_surv", "fit_unadj_surv", "gan_mediation_sensitivity", "gan_pleiotropy_sensitivity", "gan_sensitivity", "generate_toy_data", "iconic_data", "iconic_diagnose", "iconic_estimate", "iconic_method_colors", "iconic_method_order", "iconic_prospect", "iconic_recommend", "iconic_sensitivity", "infer_confounding", "list_nc_models", "load_real_input_data", "nc_completeness_capture", "nc_completeness_check", "nc_cpg", "nc_independence_check", "nc_independence_check_gm", "nc_proxy", "nc_support_check", "nc_validity_check", "nc_validity_screen", "plot_bias", "plot_bias_boxplot", "plot_bias_distribution", "plot_degradation_surface", "plot_estimate_distribution", "plot_estimated_vs_true", "plot_estimator_benchmark", "plot_feature_correlation_sweep", "plot_gan_diagnostics", "plot_instrument_strength_sweep", "plot_model_selection", "plot_nc_coverage_comparison", "plot_nc_validity_diagnostics", "plot_pleiotropy_sweep", "plot_power", "plot_prospective_analysis", "plot_sensitivity_heatmap", "plot_type1_boxplot", "plot_type1_error", "plot_type1_vs_conf", "qc_gwas_sumstats", "recommend_estimator", "residualize_matrix", "run_mediation_sim", "run_null_mediation_sim", "run_null_sim", "run_simulation", "run_single_iteration", "sample_feature_texture", "sample_texture", "scenario_manifest", "score_pgs_panel", "simulate_single_genetic_instrument", "sweep_instrument_strength", "sweep_mediation_null_by_conf", "sweep_mediation_param", "sweep_nc_validity", "sweep_null_by_conf", "sweep_param", "train_feature_texture", "train_gan_on_real_data" ], "_help": [ { "page": "analyze_mediation_robust", "title": "Run all mediation estimators on one synthetic dataset", "topics": [ "analyze_mediation_robust" ] }, { "page": "analyze_methods_parallel", "title": "Parallel version of 'analyze_methods_robust()'", "topics": [ "analyze_methods_parallel" ] }, { "page": "analyze_methods_robust", "title": "Run all five estimators (plus UNADJ) on one synthetic dataset", "topics": [ "analyze_methods_robust" ] }, { "page": "apply_fusion_weights", "title": "Apply FUSION/TWAS eQTL weights to a dosage matrix", "topics": [ "apply_fusion_weights" ] }, { "page": "as_iconic_data", "title": "Convert external data containers to iconic_data", "topics": [ "as_iconic_data", "as_iconic_data.default", "as_iconic_data.SummarizedExperiment" ] }, { "page": "beta_to_m", "title": "Convert methylation beta values to M-values", "topics": [ "beta_to_m" ] }, { "page": "build_mediator_instruments", "title": "Build mediator instruments via per-gene elastic net", "topics": [ "build_mediator_instruments" ] }, { "page": "build_prs_ldpred2", "title": "Build an exposure polygenic score with LDpred2-auto", "topics": [ "build_prs_ldpred2" ] }, { "page": "build_w_pcs", "title": "Build a negative-control panel from principal components", "topics": [ "build_w_pcs" ] }, { "page": "call_cis_eqtls", "title": "Scan for cis-eQTLs of each gene", "topics": [ "call_cis_eqtls" ] }, { "page": "check_instrument_strength", "title": "Check first-stage instrument strength (partial F)", "topics": [ "check_instrument_strength" ] }, { "page": "check_torch_setup", "title": "Check whether a working torch installation is available", "topics": [ "check_torch_setup" ] }, { "page": "composite_p_value", "title": "Composite null hypothesis test p-value", "topics": [ "composite_p_value" ] }, { "page": "fit_coca", "title": "COCA estimator: Negative-Control Outcome Correction via ratio", "topics": [ "fit_coca" ] }, { "page": "fit_coca_bin", "title": "COCA binary estimator: NOT supported (returns NA)", "topics": [ "fit_coca_bin" ] }, { "page": "fit_coca_mediation", "title": "COCA mediation estimator: negative-control calibration of both stages", "topics": [ "fit_coca_mediation" ] }, { "page": "fit_coca_mediation_bin", "title": "COCA binary mediation estimator: NOT supported (returns NA)", "topics": [ "fit_coca_mediation_bin" ] }, { "page": "fit_coca_mediation_surv", "title": "COCA survival mediation estimator: NOT supported (returns NA)", "topics": [ "fit_coca_mediation_surv" ] }, { "page": "fit_coca_surv", "title": "COCA survival estimator: NOT supported (returns NA)", "topics": [ "fit_coca_surv" ] }, { "page": "fit_direct", "title": "DIRECT estimator: OLS with instrument and negative-control as covariates", "topics": [ "fit_direct" ] }, { "page": "fit_direct_bin", "title": "DIRECT binary estimator: logistic / LPM with instrument and NC covariates", "topics": [ "fit_direct_bin" ] }, { "page": "fit_direct_mediation", "title": "DIRECT mediation estimator: OLS with instrument and NC as covariates", "topics": [ "fit_direct_mediation" ] }, { "page": "fit_direct_mediation_bin", "title": "DIRECT binary mediation estimator: logistic / LPM with G and W covariates", "topics": [ "fit_direct_mediation_bin" ] }, { "page": "fit_direct_mediation_surv", "title": "DIRECT survival mediation estimator: Cox / RMST with G and W covariates", "topics": [ "fit_direct_mediation_surv" ] }, { "page": "fit_direct_surv", "title": "DIRECT survival estimator: Cox / RMST with instrument and NC covariates", "topics": [ "fit_direct_surv" ] }, { "page": "fit_iv2sls", "title": "IV2SLS estimator: Two-Stage Least Squares with genetic instrument", "topics": [ "fit_iv2sls" ] }, { "page": "fit_iv2sls_bin", "title": "IV2SLS binary estimator: two-stage predictor substitution with logistic / LPM", "topics": [ "fit_iv2sls_bin" ] }, { "page": "fit_iv2sls_mediation", "title": "IV2SLS mediation estimator: instrumented exposure in both stages", "topics": [ "fit_iv2sls_mediation" ] }, { "page": "fit_iv2sls_mediation_bin", "title": "IV2SLS binary mediation estimator: single-instrument 2SPS with logistic / LPM", "topics": [ "fit_iv2sls_mediation_bin" ] }, { "page": "fit_iv2sls_mediation_surv", "title": "IV2SLS survival mediation estimator: single-instrument 2SPS with Cox / RMST", "topics": [ "fit_iv2sls_mediation_surv" ] }, { "page": "fit_iv2sls_mediation2", "title": "IV2SLS2 mediation estimator: 2-stage MR with instruments for both X and M", "topics": [ "fit_iv2sls_mediation2" ] }, { "page": "fit_iv2sls_mediation2_bin", "title": "IV2SLS2 binary mediation estimator: 2-stage MR with logistic / LPM outcome", "topics": [ "fit_iv2sls_mediation2_bin" ] }, { "page": "fit_iv2sls_mediation2_surv", "title": "IV2SLS2 survival mediation estimator: 2-stage MR with Cox / RMST outcome", "topics": [ "fit_iv2sls_mediation2_surv" ] }, { "page": "fit_iv2sls_surv", "title": "IV2SLS survival estimator: two-stage predictor substitution with Cox / RMST", "topics": [ "fit_iv2sls_surv" ] }, { "page": "fit_pgc", "title": "PGC estimator: Proxy G-Component Correction (matrix bridge)", "topics": [ "fit_pgc" ] }, { "page": "fit_pgc_bin", "title": "PGC binary estimator: proxy G-component correction with logistic / LPM", "topics": [ "fit_pgc_bin" ] }, { "page": "fit_pgc_mediation", "title": "PGC mediation estimator: bridge-function-adjusted natural effects (matrix bridge)", "topics": [ "fit_pgc_mediation" ] }, { "page": "fit_pgc_mediation_bin", "title": "PGC binary mediation estimator: single-panel bridge with logistic / LPM", "topics": [ "fit_pgc_mediation_bin" ] }, { "page": "fit_pgc_mediation_surv", "title": "PGC survival mediation estimator: single-panel bridge with Cox / RMST", "topics": [ "fit_pgc_mediation_surv" ] }, { "page": "fit_pgc_mediation2", "title": "PGC-2 mediation estimator: two-stage proximal mediation with path-specific bridges", "topics": [ "fit_pgc_mediation2" ] }, { "page": "fit_pgc_mediation2_bin", "title": "PGC2 / PGC2Gm binary mediation estimator: path-specific bridges with logistic / LPM", "topics": [ "fit_pgc_mediation2_bin" ] }, { "page": "fit_pgc_mediation2_surv", "title": "PGC2 / PGC2Gm survival mediation estimator: path-specific bridges with Cox / RMST", "topics": [ "fit_pgc_mediation2_surv" ] }, { "page": "fit_pgc_scalar", "title": "PGC estimator: Proxy G-Component Correction (scalar bridge)", "topics": [ "fit_pgc_scalar" ] }, { "page": "fit_pgc_scalar_mediation", "title": "PGC mediation estimator: bridge-function-adjusted natural effects (scalar bridge)", "topics": [ "fit_pgc_scalar_mediation" ] }, { "page": "fit_pgc_surv", "title": "PGC survival estimator: proxy G-component correction with Cox / RMST", "topics": [ "fit_pgc_surv" ] }, { "page": "fit_unadj_bin", "title": "UNADJ binary estimator: unadjusted logistic / linear-probability regression", "topics": [ "fit_unadj_bin" ] }, { "page": "fit_unadj_mediation", "title": "UNADJ mediation estimator: naive Baron-Kenny style", "topics": [ "fit_unadj_mediation" ] }, { "page": "fit_unadj_mediation_bin", "title": "UNADJ binary mediation estimator: naive Baron-Kenny with logistic / LPM", "topics": [ "fit_unadj_mediation_bin" ] }, { "page": "fit_unadj_mediation_surv", "title": "UNADJ survival mediation estimator: naive Baron-Kenny with Cox / RMST", "topics": [ "fit_unadj_mediation_surv" ] }, { "page": "fit_unadj_surv", "title": "UNADJ survival estimator: unadjusted Cox / RMST regression", "topics": [ "fit_unadj_surv" ] }, { "page": "gan_mediation_sensitivity", "title": "Benchmark mediation estimators across confounding scenarios", "topics": [ "gan_mediation_sensitivity" ] }, { "page": "gan_pleiotropy_sensitivity", "title": "Benchmark estimators across pleiotropy and confounding scenarios", "topics": [ "gan_pleiotropy_sensitivity" ] }, { "page": "gan_sensitivity", "title": "Benchmark estimators across confounding scenarios on synthetic data", "topics": [ "gan_sensitivity" ] }, { "page": "generate_toy_data", "title": "Generate one synthetic dataset (internal)", "topics": [ "generate_toy_data" ] }, { "page": "iconic_data", "title": "Construct a standardized data object for ICONIC model selection", "topics": [ "iconic_data" ] }, { "page": "iconic_diagnose", "title": "Diagnose data and determine estimator eligibility", "topics": [ "iconic_diagnose" ] }, { "page": "iconic_estimate", "title": "Fit all eligible estimators on real data", "topics": [ "iconic_estimate" ] }, { "page": "iconic_method_colors", "title": "Colour palette for iconic methods", "topics": [ "iconic_method_colors" ] }, { "page": "iconic_method_order", "title": "Default method display order", "topics": [ "iconic_method_order" ] }, { "page": "iconic_prospect", "title": "Prospective bias-reduction analysis for data without instruments or negative controls", "topics": [ "bias_reduction_prospective", "iconic_prospect" ] }, { "page": "iconic_recommend", "title": "Recommend the best causal estimator for the user's data", "topics": [ "iconic_recommend" ] }, { "page": "iconic_sensitivity", "title": "Sensitivity (degradation) surface and effect-decomposition bias sweep", "topics": [ "effect_decomposition_bias_sweep", "iconic_sensitivity" ] }, { "page": "infer_confounding", "title": "Infer confounding parameters from the user's data", "topics": [ "infer_confounding" ] }, { "page": "list_nc_models", "title": "List the built-in negative-control models", "topics": [ "list_nc_models" ] }, { "page": "load_real_input_data", "title": "Load and standardise a real multi-omic dataset for GAN training", "topics": [ "load_real_input_data" ] }, { "page": "nc_completeness_capture", "title": "Covariance-capture completeness test", "topics": [ "nc_completeness_capture" ] }, { "page": "nc_completeness_check", "title": "Check negative-control completeness (dimensional + covariance-capture)", "topics": [ "nc_completeness_check" ] }, { "page": "nc_cpg", "title": "CpG-predicted-expression negative-control model (SCENIC case)", "topics": [ "nc_cpg" ] }, { "page": "nc_independence_check", "title": "Test instrument-independence of negative controls (W _|_ G | C)", "topics": [ "nc_independence_check" ] }, { "page": "nc_independence_check_gm", "title": "Test mediator-instrument independence of negative controls (W _|_ Gm | C)", "topics": [ "nc_independence_check_gm" ] }, { "page": "nc_proxy", "title": "Direct-proxy negative-control model", "topics": [ "nc_proxy" ] }, { "page": "nc_support_check", "title": "Negative-control support/range check", "topics": [ "nc_support_check" ] }, { "page": "nc_validity_check", "title": "Check negative-control validity across confounding scenarios", "topics": [ "nc_validity_check" ] }, { "page": "nc_validity_screen", "title": "Screen negative controls for exposure dependence (W _|_ X | C)", "topics": [ "nc_validity_screen" ] }, { "page": "plot_bias", "title": "Plot absolute bias vs a swept parameter", "topics": [ "plot_bias" ] }, { "page": "plot_bias_boxplot", "title": "Grouped boxplots of per-seed bias across a parameter sweep", "topics": [ "plot_bias_boxplot" ] }, { "page": "plot_bias_distribution", "title": "Baseline bias distribution (single-setting hero plot)", "topics": [ "plot_bias_distribution" ] }, { "page": "plot_degradation_surface", "title": "Degradation surface figure", "topics": [ "plot_degradation_surface" ] }, { "page": "plot_estimate_distribution", "title": "Boxplot of estimate distributions from run_simulation()", "topics": [ "plot_estimate_distribution" ] }, { "page": "plot_estimated_vs_true", "title": "Plot estimated effect vs true effect", "topics": [ "plot_estimated_vs_true" ] }, { "page": "plot_estimator_benchmark", "title": "Estimator benchmark figure", "topics": [ "plot_estimator_benchmark" ] }, { "page": "plot_feature_correlation_sweep", "title": "Feature correlation sweep figure", "topics": [ "plot_feature_correlation_sweep" ] }, { "page": "plot_gan_diagnostics", "title": "Compare real vs synthetic marginals from a trained generator", "topics": [ "plot_gan_diagnostics" ] }, { "page": "plot_instrument_strength_sweep", "title": "Instrument strength sweep figure", "topics": [ "plot_instrument_strength_sweep" ] }, { "page": "plot_model_selection", "title": "Model selection workflow figure", "topics": [ "plot_model_selection" ] }, { "page": "plot_nc_coverage_comparison", "title": "NC coverage comparison figure", "topics": [ "plot_nc_coverage_comparison" ] }, { "page": "plot_nc_validity_diagnostics", "title": "NC validity diagnostics figure (5 panels)", "topics": [ "plot_nc_validity_diagnostics" ] }, { "page": "plot_pleiotropy_sweep", "title": "Pleiotropy sweep figure", "topics": [ "plot_pleiotropy_sweep" ] }, { "page": "plot_power", "title": "Plot detection rate (power) vs a swept parameter", "topics": [ "plot_power" ] }, { "page": "plot_prospective_analysis", "title": "Prospective analysis figure", "topics": [ "plot_prospective_analysis" ] }, { "page": "plot_sensitivity_heatmap", "title": "Heatmap of a sensitivity metric across the scenario grid", "topics": [ "plot_sensitivity_heatmap" ] }, { "page": "plot_type1_boxplot", "title": "Type I error boxplot per method", "topics": [ "plot_type1_boxplot" ] }, { "page": "plot_type1_error", "title": "Bar chart of Type I error rates", "topics": [ "plot_type1_error" ] }, { "page": "plot_type1_vs_conf", "title": "Type I error rate vs confounding strength", "topics": [ "plot_type1_vs_conf" ] }, { "page": "print.iconic_confounding", "title": "Print method for iconic_confounding objects", "topics": [ "print.iconic_confounding" ] }, { "page": "print.iconic_data", "title": "Print method for iconic_data objects", "topics": [ "print.iconic_data" ] }, { "page": "print.iconic_diagnosis", "title": "Print method for iconic_diagnosis objects", "topics": [ "print.iconic_diagnosis" ] }, { "page": "print.iconic_feature_texture", "title": "Print method for iconic_feature_texture objects", "topics": [ "print.iconic_feature_texture" ] }, { "page": "print.iconic_gan", "title": "Print method for iconic_gan objects", "topics": [ "print.iconic_gan" ] }, { "page": "print.iconic_prospect", "title": "Print method for iconic_prospect objects", "topics": [ "print.iconic_prospect" ] }, { "page": "print.iconic_recommendation", "title": "Print method for iconic_recommendation objects", "topics": [ "print.iconic_recommendation" ] }, { "page": "print.iconic_sensitivity", "title": "Print method for iconic_sensitivity objects", "topics": [ "print.iconic_sensitivity" ] }, { "page": "qc_gwas_sumstats", "title": "Standardize and QC GWAS summary statistics", "topics": [ "qc_gwas_sumstats" ] }, { "page": "recommend_estimator", "title": "Recommend the preferred estimator from a sensitivity sweep", "topics": [ "recommend_estimator" ] }, { "page": "residualize_matrix", "title": "Residualize a feature matrix on covariates", "topics": [ "residualize_matrix" ] }, { "page": "run_mediation_sim", "title": "Run repeated mediation simulations for a single parameter configuration", "topics": [ "run_mediation_sim" ] }, { "page": "run_null_mediation_sim", "title": "Run null mediation simulations to estimate Type I error rates", "topics": [ "run_null_mediation_sim" ] }, { "page": "run_null_sim", "title": "Run null simulations to estimate Type I error rates", "topics": [ "run_null_sim" ] }, { "page": "run_simulation", "title": "Run repeated simulations for a single parameter configuration", "topics": [ "run_simulation" ] }, { "page": "run_single_iteration", "title": "Generate one synthetic dataset under the generalised SCM", "topics": [ "run_single_iteration" ] }, { "page": "sample_feature_texture", "title": "Draw synthetic feature vectors from a trained feature texture model", "topics": [ "sample_feature_texture" ] }, { "page": "sample_texture", "title": "Draw synthetic base rows from a trained texture model", "topics": [ "sample_texture" ] }, { "page": "scenario_manifest", "title": "Scenario manifest: truth and parameter ranges for a simulation", "topics": [ "scenario_manifest" ] }, { "page": "score_pgs_panel", "title": "Score a published polygenic-score panel on a dosage matrix", "topics": [ "score_pgs_panel" ] }, { "page": "simulate_single_genetic_instrument", "title": "Simulate a single genetic instrument", "topics": [ "simulate_single_genetic_instrument" ] }, { "page": "summary.iconic_diagnosis", "title": "Summary method for iconic_diagnosis objects", "topics": [ "summary.iconic_diagnosis" ] }, { "page": "summary.iconic_prospect", "title": "Summary method for iconic_prospect objects", "topics": [ "summary.iconic_prospect" ] }, { "page": "summary.iconic_recommendation", "title": "Summary method for iconic_recommendation objects", "topics": [ "summary.iconic_recommendation" ] }, { "page": "summary.iconic_sensitivity", "title": "Summary method for iconic_sensitivity objects", "topics": [ "summary.iconic_sensitivity" ] }, { "page": "sweep_instrument_strength", "title": "Sweep instrument strength", "topics": [ "sweep_instrument_strength" ] }, { "page": "sweep_mediation_null_by_conf", "title": "Sweep mediation Type I error across confounding strength levels", "topics": [ "sweep_mediation_null_by_conf" ] }, { "page": "sweep_mediation_param", "title": "Sweep a single mediation simulation parameter across a grid", "topics": [ "sweep_mediation_param" ] }, { "page": "sweep_nc_validity", "title": "Sweep negative-control validity diagnostics", "topics": [ "sweep_nc_validity" ] }, { "page": "sweep_null_by_conf", "title": "Sweep Type I error rate across confounding strength levels", "topics": [ "sweep_null_by_conf" ] }, { "page": "sweep_param", "title": "Sweep a single simulation parameter across a grid", "topics": [ "sweep_param" ] }, { "page": "train_feature_texture", "title": "Train a feature-level texture model for the mediator panel", "topics": [ "train_feature_texture" ] }, { "page": "train_gan_on_real_data", "title": "Train a generative texture model on real data", "topics": [ "train_gan_on_real_data" ] } ], "_pkglogo": "https://github.com/BiocStaging/iconic/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/BiocStaging/iconic/raw/HEAD/README.md", "_rundeps": [ "abind", "AER", "backports", "boot", "broom", "car", "carData", "cli", "colorspace", "cowplot", "cpp11", "Deriv", "doBy", "dplyr", "farver", "forecast", "Formula", "fracdiff", "generics", "ggplot2", "glue", "gtable", "isoband", "labeling", "lattice", "lifecycle", "lme4", "lmtest", "magrittr", "MASS", "Matrix", "MatrixModels", "mgcv", "minqa", "modelr", "nlme", "nloptr", "nnet", "numDeriv", "pbkrtest", "pillar", "pkgconfig", "purrr", "quantreg", "R6", "rbibutils", "RColorBrewer", "Rcpp", "RcppArmadillo", "RcppEigen", "Rdpack", "reformulas", "rlang", "S7", "sandwich", "scales", "SparseM", "stringi", "stringr", "survival", "tibble", "tidyr", "tidyselect", "timeDate", "urca", "utf8", "vctrs", "viridisLite", "withr", "zoo" ], "_vignettes": [ { "source": "iconic-diagnose.Rmd", "filename": "iconic-diagnose.html", "title": "Diagnosing Estimator Eligibility", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "What diagnosis checks", "A minimal example", "Instrument strength", "Negative-control validity", "Proceeding without instruments or controls", "Further reading", "Session information" ], "created": "2026-07-26 15:26:11", "modified": "2026-08-12 15:28:48", "commits": 3 }, { "source": "iconic-instruments.Rmd", "filename": "iconic-instruments.html", "title": "Genetic Instruments and Negative Controls from External Data", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "Exposure instruments from GWAS summary statistics", "Quality-control the summary statistics", "Build a polygenic score with LDpred2", "Score a panel of pre-computed weights", "Verify instrument strength", "Mediator instruments", "Scan for cis-eQTLs", "Build a genetically predicted mediator (GReX-style)", "Negative controls from high-dimensional panels", "Methylation beta to M-values", "Residualise on covariates", "Extract negative-control factors with PCA", "Apply FUSION-style TWAS weights", "Importing a SummarizedExperiment", "Session information" ], "created": "2026-08-12 15:28:48", "modified": "2026-08-12 15:28:48", "commits": 1 }, { "source": "iconic-walkthrough.Rmd", "filename": "iconic-walkthrough.html", "title": "ICONIC: Causal Model Selection with Genetic Instruments and Negative Controls", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "What this package is for", "Quick start", "Step 1: Diagnose", "Step 2: Estimate", "Step 3: Train a texture model once", "Step 4: Sensitivity analysis", "Step 5: Recommend", "Step 6: Prospective analysis", "Survival outcomes", "Putting it together", "Further reading", "Session information" ], "created": "2026-07-22 16:36:08", "modified": "2026-08-12 15:28:48", "commits": 8 }, { "source": "iconic-sensitivity.Rmd", "filename": "iconic-sensitivity.html", "title": "Sensitivity Analysis and Confounding Inference", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "What sensitivity analysis does", "A minimal example", "Inferring confounding from the data", "Inferred vs. default confounding", "Further reading", "Session information" ], "created": "2026-07-26 15:26:11", "modified": "2026-08-12 15:28:48", "commits": 5 }, { "source": "iconic-survival.Rmd", "filename": "iconic-survival.html", "title": "Survival Outcomes", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "Time-to-event outcomes in ICONIC", "Two effect scales", "COCA incompatibility", "A minimal example", "Cox log-HR scale", "RMST scale", "Diagnosis and eligibility", "Further reading", "Session information" ], "created": "2026-07-26 15:26:11", "modified": "2026-08-12 15:28:48", "commits": 4 }, { "source": "iconic-texture-model.Rmd", "filename": "iconic-texture-model.html", "title": "The Generative Texture Model", "author": "Sean T. Bresnahan and Charis Xiong", "engine": "knitr::rmarkdown", "headings": [ "Introduction", "Installation", "Two simulation modes", "The hybrid GAN + copula architecture", "Training the texture model", "Attaching the texture model", "When to use each mode", "Further reading", "Session information" ], "created": "2026-07-26 15:26:11", "modified": "2026-08-12 15:28:48", "commits": 4 } ], "_score": 4.176091259055681, "_indexed": true, "_nocasepkg": "iconic", "_universes": [ "biocstaging", "sbresnahan" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.99.3", "date": "2026-09-18T09:01:17.000Z", "distro": "resolute", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/6b991125e2e9de1bb4133113fe1a6dd7c68042260dab6b63c4cd696b0f1933a9", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.6.1", "os": "linux", "version": "0.99.3", "date": "2026-09-18T09:01:16.000Z", "distro": "resolute", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/dc1d1e71efe802d33e4cde661910d59e3ebc9dd979de45883374dccfdeb0df6a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.5.3", "os": "mac", "version": "0.99.3", "date": "2026-09-18T09:15:58.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/b6558ebb26f283ee6235e8b766b20bf237ca752864dbf0f75780e8bbbfbe5f3e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.6.1", "os": "mac", "version": "0.99.3", "date": "2026-09-18T09:29:37.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/d2b704f945abcb8375873979d2b03a31b84642e1c8d28f1864322960a6aae221", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.6.0", "os": "wasm", "version": "0.99.3", "date": "2026-09-18T09:01:24.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/e1074afa801ec8567a9a5f83a82f0464e39e02a1cc0e332633aaffe83907b82a", "status": "success", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.7.0", "os": "win", "version": "0.99.3", "date": "2026-09-18T09:00:05.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/2a2d86a5e0181f848a72cb932d7d0600616202a03f52a7cb80550ff071ab300a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.5.3", "os": "win", "version": "0.99.3", "date": "2026-09-18T09:00:09.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/87b638649acf6b921069acc81fa27175769b923df626642a5cde34dcd64a845e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" }, { "r": "4.6.1", "os": "win", "version": "0.99.3", "date": "2026-09-18T08:59:52.000Z", "commit": "e89f4936c01c4624c802e5b601a97f3a7a13384e", "fileid": "https://r2.ropensci.org/39c647d14777c184fe0e23a07411179f8a9e54aecf2cbb2f3cb7ba2c2ac4a7e3", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/biocstaging/actions/runs/35326678362" } ] }