---
title: "NeuroDataSets: A Comprehensive Collection of Neuroscience and Brain-Related Datasets"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{NeuroDataSets: A Comprehensive Collection of Neuroscience and Brain-Related Datasets}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

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

# Introduction

The `NeuroDataSets` package offers a rich and diverse collection of datasets focused on the brain, the nervous system, and neurological and psychiatric disorders. It includes comprehensive data on conditions such as **Parkinson's disease, Alzheimer's disease, dementia, epilepsy, schizophrenia, autism spectrum disorder, attention deficit hyperactivity disorder (ADHD), Tourette's syndrome, traumatic brain injury, gliomas, migraines, headaches, sleep disorders, concussions, encephalitis, subarachnoid hemorrhage, and mental health conditions**.

The package contains a wide variety of data types, including clinical, experimental, neuroimaging, behavioral, cognitive, and simulated datasets. These datasets encompass **structural and functional brain data, cross-sectional and longitudinal MRI imaging studies, neurotransmission metrics, gene expression profiles, cognitive performance assessments, intelligence metrics, sleep deprivation effects, treatment outcomes, brain-body relationships across species, neurological injury patterns, and acupuncture interventions**.

**Designed for researchers, neuroscientists, clinicians, psychologists, data scientists, and students**, this package facilitates exploratory data analysis, statistical modeling, machine learning applications, and hypothesis testing in neuroscience and neuroepidemiology.

## All datasets within NeuroDataSets

```{r NeuroDataSets-datasets,echo = TRUE,message = FALSE,warning = FALSE,results = 'markup'}


view_datasets_NeuroDataSets()


```


## Dataset Suffixes

Each dataset in the `NeuroDataSets` package uses a `suffix` to denote the type of R object:

- `_df`: A data frame

- `_list`: A list

- `_tbl_df`: A tibble

- `_matrix`: A matrix

## Example Datasets

Below are selected example datasets included in the `NeuroDataSets` package:

- `subcortical_patterns_tbl_df`: Patterns of Subcortical Structures.

- `WMpatterns_tbl_df`: Expected Patterns of White Matter.

- `hippocampus_lesions_df`: Memory and the Hippocampus.


## Data Visualization with NeuroDataSets Data

###  Patterns of Subcortical Structures

```{r patterns-subcortical-plot, fig.width=6, fig.height=4, out.width="100%"}

# Convert the dataset to long format using only base R + dplyr

long_data <- subcortical_patterns_tbl_df %>%
  select(Subcortical, everything()) %>%
  as.data.frame() %>%
  reshape(
    varying = names(.)[-1],
    v.names = "Value",
    timevar = "Condition",
    times = names(.)[-1],
    direction = "long"
  ) %>%
  select(Subcortical, Condition, Value)

# Create a heatmap
ggplot(long_data, aes(x = Condition, y = Subcortical, fill = Value)) +
  geom_tile(color = "white") +
  scale_fill_gradient(low = "lightblue", high = "darkred") +
  labs(
    title = "Subcortical Patterns by Condition",
    x = "Condition",
    y = "Subcortical Region",
    fill = "Value"
  ) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

```


### Expected Patterns of White Matter

```{r white-matter-plot, fig.width=6, fig.height=4.5, out.width="90%"}

# Compute mean values using updated anonymous function syntax
summary_data <- WMpatterns_tbl_df %>%
  select(-WM) %>%
  summarise(across(everything(), \(x) mean(x, na.rm = TRUE))) %>%
  as.data.frame()

# Reshape from wide to long format using base R
summary_data <- data.frame(
  Condition = names(summary_data),
  MeanValue = as.numeric(summary_data[1, ])
)

# Plot
ggplot(summary_data, aes(x = Condition, y = MeanValue, fill = Condition)) +
  geom_bar(stat = "identity") +
  labs(
    title = "Average Value per Condition across White Matter Regions",
    x = "Condition",
    y = "Mean Value"
  ) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  guides(fill = "none")  # Optional

```


### Memory and the Hippocampus

```{r memory-hippocampus-plot, fig.width=6, fig.height=4.5, out.width="90%"}

# Lesion Size and Memory Score

ggplot(hippocampus_lesions_df, aes(x = lesion, y = memory)) +
  geom_point(color = "blue", size = 2) +
  labs(
    title = "Relationship Between Lesion Size and Memory Score",
    x = "Lesion Size",
    y = "Memory Score"
  ) +
  theme_minimal()


```

## Conclusion

The `NeuroDataSets` package offers a comprehensive and curated collection of datasets spanning a wide spectrum of neurological, psychiatric, and cognitive conditions. By integrating data from clinical trials, peer-reviewed research, military health records, sports injury databases, and international comparative studies, this package provides researchers with robust resources for cutting-edge neuroscience research.

Whether you are conducting exploratory data analysis, building predictive models, testing statistical hypotheses, or teaching neuroepidemiology and data science, `NeuroDataSets` delivers well-structured, documented, and diverse datasets that reflect the complexity of brain function, neurological disorders, and their treatments.

For detailed information and full documentation of each dataset, including variable descriptions, data sources, and usage examples, please refer to the reference manual and help files included within the package.

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