---
title: "CKB data"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{CKB data}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)
library(ckbtools)
```

Information about the CKB cohort data is available at [www.ckbiobank.org/data-access/data-overview](https://www.ckbiobank.org/data-access/data-overview). Details of the CKB Data Sharing Policy, data release schedules and data request application procedures are available at [www.ckbiobank.org/data-access](https://www.ckbiobank.org/data-access).


This package includes the following entirely synthetic data sets, which have similar structure and variable names to real CKB data:

* ckbtools_baseline
* ckbtools_endpoints
* ckbtools_endpoint_definitions
* ckbtools_ckbtools_ascertainments
* ckbtools_raw_olink_meta_data
* ckbtools_raw_olink_protein_data
* ckbtools_raw_somascan_meta_data
* ckbtools_raw_somascan_protein_data
* ckbtools_raw_somascan_sample_data

A `ckbtools_participant_data` data set is also included in the package, which is derived from the synthetic raw data as below.

```{r, eval = FALSE}
ckbtools_baseline$sex <- factor(ckbtools_baseline$is_female,
                       levels = c(0, 1),
                       labels = c("Male", "Female"))

ckbtools_baseline$age_at_study_date <- ckbtools_baseline$age_at_study_date_x100 / 100

ckbtools_baseline$age_at_ckbtools_baseline_group <- cut(ckbtools_baseline$age_at_study_date,
                                      breaks = seq(30, 80, by = 10),
                                      right = FALSE)

ckbtools_baseline$high_school_or_higher <- ckbtools_baseline$highest_education %in% c(3, 4, 5)

ckbtools_baseline$education <- factor(ckbtools_baseline$highest_education,
                                      levels = c(0, 1, 2, 3, 4, 5),
                                      labels = c("No formal school",
                                                 "Primary School",
                                                 "Middle School",
                                                 "High School",
                                                 "Technical School / college",
                                                 "University"))

ckbtools_baseline$education_4_groups <- factor(ckbtools_baseline$highest_education,
                                      levels = c(0, 1, 2, 3, 4, 5),
                                      labels = c("No formal school",
                                                 "Primary School",
                                                 "Middle School",
                                                 "High School or higher",
                                                 "High School or higher",
                                                 "High School or higher"))

ckbtools_baseline$smoking <- factor(ckbtools_baseline$smoking_category,
                           levels = c(1, 2, 3, 4),
                           labels = c("Never smoker",
                                      "Occasional smoker",
                                      "Ex regular smoker",
                                      "Smoker"))

ckbtools_baseline$smoking_3_groups <- factor(ckbtools_baseline$smoking_category,
                                    levels = c(1, 2, 3, 4),
                                    labels = c("Never / Occasional smoker",
                                               "Never / Occasional smoker",
                                               "Ex regular smoker",
                                               "Smoker"))

ckbtools_baseline$current_regular_smoker <-  factor(ckbtools_baseline$smoking_category,
                                           levels = c(1, 2, 3, 4),
                                           labels = c("No",
                                                      "No",
                                                      "No",
                                                      "Yes"))

ckbtools_baseline$alcohol_3_groups <- factor(ckbtools_baseline$alcohol_category,
                                    levels = c(1, 2, 3, 4, 5, 6),
                                    labels = c("Never regular drinker",
                                               "Weekly / Reduced / Ex",
                                               "Occasional / Monthly",
                                               "Occasional / Monthly",
                                               "Weekly / Reduced / Ex",
                                               "Weekly / Reduced / Ex"))

ckbtools_baseline$bmi_grp <- cut(ckbtools_baseline$bmi_calc,
                        c(0, 18.5, 25, 30, Inf),
                        labels = c("<18.5", "18.5-25", "25-30", "30+"),
                        right = FALSE)

ckbtools_baseline$hours_since_last_ate <- ckbtools_baseline$hours_since_last_ate_x10 / 10

ckbtools_baseline$region <- factor(ckbtools_baseline$region_code,
                          levels = c(12, 16, 26, 36, 46, 52, 58, 68, 78, 88),
                          labels = c("Qingdao", "Harbin", "Haikou", "Suzhou", "Liuzhou",
                                     "Sichuan", "Gansu", "Henan", "Zhejiang", "Hunan"))

ckbtools_endpoints$ihd <- ckbtools_endpoints$CKB0003_ep
ckbtools_endpoints$ihd_date <- ckbtools_endpoints$CKB0003_datedeveloped

ckbtools_endpoints$respiratory_diseases <- ckbtools_endpoints$CKB0032_ep
ckbtools_endpoints$respiratory_diseases_date <- ckbtools_endpoints$CKB0032_datedeveloped

ckbtools_endpoints <- ckbtools_endpoints[, c("csid", "ihd", "ihd_date", "respiratory_diseases", "respiratory_diseases_date")]

ckbtools_baseline$all_cause_mortality_date <- ckbtools_baseline$censoring_date
ckbtools_baseline$all_cause_mortality <- as.numeric(grepl("Dead", ckbtools_baseline$censoring_reason))

ckbtools_participant_data <- merge(ckbtools_baseline, ckbtools_endpoints, by = "csid")

csid_in_subcohort <- ckbtools_ascertainments$csid[ckbtools_ascertainments$olinkexpexpan_chd_b1_subcohort == 1]
ckbtools_participant_data$proteomics_subcohort <- as.numeric(ckbtools_participant_data$csid %in% csid_in_subcohort)
```