---
title: "Introduction to snifter"
author:
  - name: Alan O'Callaghan
    email: alan.ocallaghan@outlook.com
package: snifter
output:
  BiocStyle::html_document:
    toc_float: yes
    fig_width: 10
    fig_height: 8
vignette: >
  %\VignetteIndexEntry{Introduction to snifter}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

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

# Introduction

snifter provides an R wrapper for the [openTSNE](https://opentsne.readthedocs.io/en/latest/)
implementation of fast interpolated t-SNE (FI-tSNE).
It is based on `r Biocpkg("basilisk")` and `r CRANpkg("reticulate")`.
This vignette aims to provide a brief overview of typical use 
when applied to scRNAseq data, but it does not provide a comprehensive
guide to the available options in the package.

It is highly advisable to review the documentation in snifter and the 
[openTSNE documentation](https://opentsne.readthedocs.io/en/latest/)
to gain a full understanding of the available options.

# Setting up the data

We will illustrate the use of snifter by generating some toy data.
First, we'll load the needed libraries, and set a random seed to
ensure the simulated data are reproducible
(note: it is good practice to ensure that a t-SNE embedding is robust
by running the algorithm multiple times).

```{r setup}
library("snifter")
library("ggplot2")
theme_set(theme_bw())
set.seed(42)

n_obs <- 500
n_feats <- 200
means_1 <- rnorm(n_feats)
means_2 <- rnorm(n_feats)
counts_a <- replicate(n_obs, rnorm(n_feats, means_1))
counts_b <- replicate(n_obs, rnorm(n_feats, means_2))
counts <- t(cbind(counts_a, counts_b))
label <- rep(c("A", "B"), each = n_obs)
```

# Running t-SNE

The main functionality of the package lies in the `fitsne`
function. This function returns a matrix of t-SNE co-ordinates. In this case,
we pass in the 20 principal components computed based on the 
log-normalised counts. We colour points based on the discrete 
cell types identified by the authors.

```{r run}
fit <- fitsne(counts, random_state = 42L)
ggplot() +
    aes(fit[, 1], fit[, 2], colour = label) +
    geom_point(pch = 19) +
    scale_colour_discrete(name = "Cluster") +
    labs(x = "t-SNE 1", y = "t-SNE 2")
```

# Projecting new data into an existing embedding

The openTNSE package, and by extension snifter,
also allows the embedding of new data into
an existing t-SNE embedding.
Here, we will split the data into "training"
and "test" sets. Following this, we generate a t-SNE embedding
using the training data, and project the test data into this embedding.

```{r split}
test_ind <- sample(nrow(counts), nrow(counts) / 2)
train_ind <- setdiff(seq_len(nrow(counts)), test_ind)
train_mat <- counts[train_ind, ]
test_mat <- counts[test_ind, ]

train_label <- label[train_ind]
test_label <- label[test_ind]

embedding <- fitsne(train_mat, random_state = 42L)
```

Once we have generated the embedding, we can now `project` the unseen test
data into this t-SNE embedding.

```{r plot-embed}
new_coords <- project(embedding, new = test_mat, old = train_mat)
ggplot() +
    geom_point(
        aes(embedding[, 1], embedding[, 2],
            colour = train_label,
            shape = "Train"
        )
    ) +
    geom_point(
        aes(new_coords[, 1], new_coords[, 2], 
            colour = test_label,
            shape = "Test"
        )
    ) +
    scale_colour_discrete(name = "Cluster") +
    scale_shape_discrete(name = NULL) +
    labs(x = "t-SNE 1", y = "t-SNE 2")
```


# Session information {.unnumbered}

```{r}
sessionInfo()
```