---
title: "OncoDataSets: A Comprehensive Collection of Cancer Datasets"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{OncoDataSets: A Comprehensive Collection of Cancer Datasets}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.width = 10,
  fig.height = 6
)
```

```{r setup}
library(OncoDataSets)
library(ggplot2)
library(dplyr)

```


# Introduction

The `OncoDataSets` package offers a comprehensive collection of datasets focused on cancer research, covering aspects like survival rates, genetic studies, biomarkers, and epidemiological insights. The datasets include data on various **cancer types such as melanoma, leukemia, breast, ovarian, and lung cancer**. This package is designed to support researchers, analysts, and bioinformaticians interested in understanding cancer epidemiology, treatment outcomes, and genetic factors.

## Dataset Suffixes

Each dataset in the `OncoDataSets` package comes with a suffix to identify the type of R object it represents:

- `df`: A data frame
- `tbl_df`: A tibble (modern version of a data frame)
- `array`: An array
- `list`: A list


## Example Datasets

Below are some example datasets included in the `OncoDataSets` package:

- CA19PancreaticCancer_df: A data frame focused on the diagnosis of pancreatic cancer with the CA19-9 biomarker.

- ColorectalMiRNAs_tbl_df: A tibble containing PubMed data of miRNAs in colorectal cancer.

- CancerSmokeCity_array: An array with lung cancer data categorized by smoking status and city.

- VALungCancer_list: A list containing VA lung cancer study data.


## Data Visualization with OncoDataSets Data

Here are examples of how to visualize data from the `OncoDataSets` package:

### 1. Visualization of Pancreatic Cancer Diagnosis by Biomarker

```{r ggplot_001}

# Visualizing True Positives (TP) in Pancreatic Cancer Diagnosis
CA19PancreaticCancer_df %>%
  ggplot(aes(x = TP)) +
  geom_histogram(bins = 30, alpha = 0.7, fill = "steelblue") +
  labs(title = "Pancreatic Cancer Diagnosis - True Positives (TP)",
       x = "True Positives (TP)",
       y = "Frequency") +
  theme_minimal()

```

### 2. Visualization of ColorectalMiRNAs_tbl_df

```{r ggplot2_002}


ggplot(ColorectalMiRNAs_tbl_df, aes(x = Year, fill = miRNA)) +
  geom_bar(position = "dodge") +
  labs(title = "Distribution miRNA Types Over the Years",
       x = "Year",
       y = "Number of Publications") +
  theme_minimal()

```



## Conclusion

The `OncoDataSets` package provides essential datasets for cancer research, offering diverse data structures that are easily accessible for analysis. The dataset suffixes help users identify the format of the data quickly, making the analysis process more efficient.

For more detailed information and examples on each dataset, please refer to the full package documentation.

<div class="tocify-extend-page" data-unique="tocify-extend-page" style="height: 0;"></div>