UK Biobank Data Processing and Survival Analysis Toolkit

---

Documentation for package ‘UKBAnalytica’ version 1.0.0

• DESCRIPTION file
• Package NEWS

Help Pages

A B C E F G L M P R S T U

UKBAnalytica-package

UKBAnalytica: UK Biobank Data Processing and Survival Analysis Toolkit

-- A --

assess_balance

Assess Covariate Balance

-- B --

build_survival_dataset

Build Survival Analysis Dataset

-- C --

calculate_air_pollution	Calculate air pollution exposure averages
calculate_blood_pressure	Calculate blood pressure from multiple readings
calculate_diet_score	Calculate diet score
calculate_weights	Calculate IPTW Weights
classify_metabolites	Classify UK Biobank metabolite names
coef.mediation_result	Extract Coefficients from Mediation Results
combine_disease_definitions	Combine Multiple Disease Definitions
compare_data_sources	Compare Case Counts Across Data Sources
compute_protein_ppi_metrics	Compute topological metrics for a PPI network
confint.mediation_result	Confidence Intervals for Mediation Results
create_baseline_table	Create a baseline table comparing cases and controls under different conditions.
create_disease_definition	Create Disease Definition Object
create_imputation_list	Create an imputationList Object
create_medication_definition	Create a medication definition object

-- E --

estimate_propensity_score	Estimate Propensity Score
extract_cases_by_source	Extract Cases by Specified Data Sources
extract_diabetes_subtype_baseline	Extract Baseline Diabetes Subtypes (T1DM/T2DM) with HbA1c Support
extract_disease_diagnosis	Extract participant-level disease diagnosis status
extract_disease_history	Extract Disease History (Prevalent Cases) for Covariates
extract_disease_history_sensitivity	Extract Disease History with Multiple Source Comparisons
extract_medications	Extract medication use from UKB drug fields
extract_self_report_medications	Extract self-reported medication indicators from field 20003

-- F --

fit_mi_models

Fit Regression Models on Multiple Imputed Datasets

-- G --

get_death_dates	Extract Death Dates for All Deceased Participants
get_disease_catalog	Query the built-in disease code catalog
get_field_info	Get one UK Biobank field's metadata
get_field_metadata	Get structured UK Biobank field metadata
get_medication_catalog	Query the built-in medication code catalog
get_pomegranate_diseases	Get Pomegranate-derived disease definitions
get_pomegranate_source_manifest	Get the Pomegranate source manifest
get_predefined_diseases	Get Predefined Disease Definitions
get_predefined_medications	Get predefined UK Biobank medication definitions
get_protein_ppi	Retrieve a STRING PPI network for proteomics hits
get_ukb_demo_colnames	Get column names of the synthetic UK Biobank-style demo dataset
get_variable_info	Get information about available variables
get_variable_set	Get one curated UK Biobank variable set
get_variable_sets	Curated UK Biobank variable sets for extraction

-- L --

load_pomegranate_portal_coding	Load the Pomegranate portal coding evidence table
load_ukb_medication_coding	Load UK Biobank field 20003 medication coding
load_ukb_metabolite_panel	Load the bundled UK Biobank non-ratio metabolite panel

-- M --

match_propensity	Propensity Score Matching
metabolite_to_metaboanalyst_name	Map metabolite names to MetaboAnalyst-compatible names

-- P --

parse_cancer_registry	Parse Cancer Registry Records
parse_death_records	Parse Death Registry Records
parse_icd10_diagnoses	Parse ICD-10 Hospital Diagnosis Records
parse_icd9_diagnoses	Parse ICD-9 Hospital Diagnosis Records
parse_opcs4_procedures	Parse OPCS4 Hospital Procedure Records
parse_self_reported_illnesses	Parse Self-Reported Illness Records
plot.ukb_ml_flow	Plot a UKB ML Flow Object
plot.ukb_ml_flow_compare	Plot a UKB ML Flow Comparison Object
plot.ukb_rcs	Plot a restricted cubic spline exposure-response curve
plot_balance	Plot Covariate Balance (Love Plot)
plot_calibration	Plot Calibration Curve
plot_correlation	Visualize correlation matrix as a heatmap
plot_cox_loghr_correlation	Plot training-validation Cox log(HR) concordance
plot_cox_sensitivity_correlation	Plot sensitivity-analysis Cox log(HR) concordance
plot_enrichment_lollipop	Plot enrichment results as a lollipop chart via TCMDATA
plot_forest	Plot Forest Plot for Subgroup Analysis
plot_go_ora_bar	Plot GO ORA results as a bar chart via TCMDATA
plot_heatmap	Plot a publication-style heatmap
plot_km_curve	Plot Kaplan-Meier Survival Curve
plot_mediation	Plot Mediation Analysis Results
plot_mediation_forest	Plot Forest Plot for Multiple Mediator Analysis
plot_metabolite_ora_barplot	Plot metabolite ORA results as a bar plot
plot_metabolite_ora_dotplot	Plot metabolite ORA results as a dot plot
plot_mi_diagnostics	Plot Multiple Imputation Diagnostics
plot_mi_pooled	Plot Multiple Imputation Pooled Results
plot_ml_calibration	Plot Calibration Curve
plot_ml_compare	Plot Model Comparison
plot_ml_confusion	Plot Confusion Matrix
plot_ml_dca	Plot Decision Curve Analysis
plot_ml_gain	Plot Gain Curve
plot_ml_importance	Plot Variable Importance
plot_ml_ks	Plot KS Curve
plot_ml_lift	Plot Lift Curve
plot_ml_pr	Plot PR Curve
plot_ml_roc	Plot ROC Curves
plot_ml_roc_compare	Plot One or More ROC Curves from Tidy ROC Data
plot_participant_flow	Plot a participant flow table
plot_ps_distribution	Plot Propensity Score Distribution
plot_rcs	Plot a restricted cubic spline exposure-response curve
plot_rcs.ukb_rcs	Plot a restricted cubic spline exposure-response curve
plot_regression_volcano	Plot a volcano-style regression summary
plot_scatter	Plot a publication-style scatter plot
plot_shap_beeswarm	Plot SHAP Beeswarm Summary
plot_shap_dependence	Plot SHAP Dependence
plot_shap_force	Plot SHAP Force (Waterfall)
plot_shap_summary	Plot SHAP Summary
plot_stacked_bar	Plot a publication-style stacked bar chart
plot_top_hr_bars	Plot top positive and inverse Cox associations
plot_violin	Plot a publication-style violin plot
pool_custom_estimates	Pool Custom Estimates from Multiple Imputations
pool_mi_models	Pool Results from Multiple Imputation Models
preprocess_baseline	Preprocess UKB baseline variables
print.mediation_result	Print Method for Mediation Results
protein_to_gene_symbol	Convert protein identifiers to gene symbols

-- R --

rank_protein_ppi_nodes	Rank nodes in a PPI network by integrated centrality
rap_extract_pheno	Extract RAP Phenotype Data Synchronously
rap_find_dataset	Find the RAP Dataset File in the Current Project
rap_list_fields	List Approved RAP Dataset Fields
rap_plan_extract	Plan a RAP Phenotype Extraction
rap_submit_extract	Submit a RAP Table-Exporter Phenotype Extraction Job
runmulti_competing	Run Multiple Fine-Gray Competing-Risk Models
runmulti_cox	Run multiple Cox proportional hazards models
runmulti_cox_lag	Run Lagged Cox Sensitivity Analyses
runmulti_cox_zph	Run Multiple Cox Models with PH Diagnostics
runmulti_gam	Run multiple generalised additive models
runmulti_glm	Run multiple generalised linear models
runmulti_lm	Run multiple linear regression models
runmulti_logit	Run multiple logistic regression models
runmulti_negbin	Run multiple negative-binomial regression models
runmulti_trend	Run Grouped-Exposure Trend Tests
run_correlation	Calculate correlation between variables
run_imputation	Multiple imputation and merge back to full data
run_mediation	Run Causal Mediation Analysis
run_metabolite_ora	Run metabolite over-representation analysis
run_multi_mediator	Run Multiple Mediator Analysis
run_multi_subgroup	Run Multiple Subgroup Analyses
run_protein_kegg_ora	Run KEGG ORA enrichment for proteomics hits
run_protein_ora	Run GO ORA enrichment for proteomics hits
run_protein_ppi_clustering	Cluster a protein-protein interaction network
run_protein_ppi_robustness	Evaluate PPI network robustness for selected protein targets
run_rcs	Fit a restricted cubic spline exposure-response model
run_regression	Run a regression model (unified interface)
run_sensitivity_mediation	Sensitivity Analysis for Mediation
run_subgroup_analysis	Run Subgroup Analysis
run_weighted_analysis	Run Weighted Analysis

-- S --

score_protein_ppi_clusters	Score network clusters in a PPI graph
select_incident_by_years	Select Incident Cases by Time Since Enrollment
sensitivity_exclude_early_events	Exclude Early Events for Sensitivity Analysis
sensitivity_exclude_missing_covariates	Exclude Rows with Missing Covariates for Sensitivity Analysis
subset_protein_ppi	Filter a STRING PPI network via TCMDATA
summary.mediation_result	Summary Method for Mediation Results

-- T --

tidy.mi_pooled_result

Tidy Method for mi_pooled_result

-- U --

UKBAnalytica	UKBAnalytica: UK Biobank Data Processing and Survival Analysis Toolkit
ukb_check_rap_env	Check the UK Biobank RAP execution environment
ukb_clean_missing	Clean UK Biobank Missing and Non-response Values
ukb_compare_cox_results	Compare Cox results between training and validation sets
ukb_compare_sensitivity_cox	Compare sensitivity Cox results against a main analysis
ukb_cox_diagnostics	Diagnose Proportional Hazards Assumptions for a Cox Model
ukb_create_extraction_manifest	Create a RAP extraction manifest
ukb_decode	Decode UK Biobank RAP exports
ukb_decode_column_names	Decode UK Biobank column names
ukb_decode_values	Decode UK Biobank coded values
ukb_demo	Generate a small synthetic UK Biobank-style demo dataset
ukb_dictionary_zh	Chinese UK Biobank field-path dictionary
ukb_download_rap_dictionary	Download the official RAP data dictionary
ukb_extract_fields	Extract UK Biobank fields from a search result or field list
ukb_field_info	Inspect one UK Biobank field
ukb_metadata_setup	Set up UK Biobank metadata for search, extraction, and decoding
ukb_ml_as_split	Standardize Manual ML Train/Test Splits
ukb_ml_calibration	Calibration Curve Analysis
ukb_ml_compare	Compare Multiple ML Models
ukb_ml_compare_feature_sets	Compare Multiple Feature Sets with a Frozen-Test ML Workflow
ukb_ml_compare_flows	Compare Multiple Feature Sets and/or Models
ukb_ml_confusion	Confusion Matrix
ukb_ml_cv	Cross-Validation for ML Models
ukb_ml_dca	Decision Curve Analysis
ukb_ml_evaluate_test	Evaluate the Final Model Once on the Frozen Test Set
ukb_ml_feature_select	Select Features for UKB ML Workflows
ukb_ml_fit_final	Refit the Final ML Model on Training Development Data
ukb_ml_flow	Run a Complete Single-Model UKB ML Flow
ukb_ml_gain_lift	Gain and Lift Curve Analysis
ukb_ml_importance	Get Variable Importance
ukb_ml_ks	KS Curve Analysis
ukb_ml_metrics	Calculate Model Performance Metrics
ukb_ml_model	Train a Machine Learning Model
ukb_ml_pr	Precision-Recall Curve Analysis
ukb_ml_predict	Predict from ML Model
ukb_ml_roc	ROC Curve Analysis
ukb_ml_roc_data	Create ROC Curve Data for Binary ML Predictions
ukb_ml_split_data	Split Data into Frozen ML Train/Test Sets
ukb_ml_supported_models	List Supported Machine Learning Models
ukb_ml_survival	Train Survival Machine Learning Model
ukb_ml_survival_as_split	Standardize Manual Survival ML Train/Test Splits
ukb_ml_survival_evaluate_test	Evaluate Survival ML Once on the Frozen Test Set
ukb_ml_survival_feature_select	Select Features for Survival ML Workflows
ukb_ml_survival_fit_final	Refit Final Survival ML Model
ukb_ml_survival_importance	Get Variable Importance for Survival Model
ukb_ml_survival_predict	Predict from Survival ML Model
ukb_ml_survival_shap	SHAP Values for Survival Models
ukb_ml_survival_split_data	Split Data into Frozen Survival ML Train/Test Sets
ukb_ml_survival_tune	Tune Survival ML Hyperparameters Without Touching the Test Set
ukb_ml_survival_workflow	Run a Frozen-Test Survival ML Workflow
ukb_ml_threshold	Learn a Binary Classification Threshold
ukb_ml_tune	Tune ML Hyperparameters Without Touching the Test Set
ukb_ml_workflow	Run a Frozen-Test UKB ML Workflow
ukb_participant_flow	Build a participant flow table
ukb_protein_annotation	Annotate Olink-style protein variables
ukb_query_dictionary	Query UK Biobank dictionary metadata
ukb_scale_with_parameters	Standardize variables using existing scaling parameters
ukb_search_fields	Search UK Biobank fields
ukb_sensitivity_suite	Run a Cox sensitivity-analysis suite
ukb_shap	Compute SHAP Values
ukb_shap_dependence	SHAP Dependence Values
ukb_shap_force	SHAP Force Plot Data
ukb_shap_summary	SHAP Summary Statistics
ukb_snapshot	Record or Retrieve UKB Cohort Snapshots
ukb_standardize_by_train	Standardize variables using training-set parameters
ukb_time_skeleton	Build a UK Biobank follow-up time skeleton
ukb_top_hr_results	Select top Cox associations by hazard ratio
ukb_train_validation_cox	Run Cox models in training and validation sets
ukb_validate_columns	Validate requested columns against a data object
ukb_write_extraction_manifest	Write a RAP extraction manifest