---
title: "Quantifying velocity from noisy data with cellmig"
author: "Simo Kitanovski (simo.kitanovski@uni-due.de)"
output:
  BiocStyle::html_document
vignette: >
  %\VignetteEncoding{UTF-8}
  %\VignetteIndexEntry{User Manual: cellmig}
  %\VignetteEngine{knitr::rmarkdown}
editor_options: 
  markdown: 
    wrap: 72
---

```{r setup, include = FALSE, warning = FALSE}
knitr::opts_chunk$set(comment = FALSE, 
                      warning = FALSE, 
                      message = FALSE)
```

```{r}
library(cellmig)
library(ggplot2)
library(ggforce)
ggplot2::theme_set(new = theme_bw(base_size = 10))
```

```{r load-data}
data("d", package = "cellmig")
str(d)
head(d)
```


```{r, fig.width=7, fig.height=6}
ggplot(data = d)+
  facet_wrap(facets = ~paste0("compound=", compound), 
             scales = "free_y", ncol = 2)+
  geom_sina(aes(x = as.factor(dose), col = plate, y = v, group = well), 
            size = 0.5)+
  theme_bw()+
  theme(legend.position = "top",
        strip.text.x = element_text(margin = margin(0.03,0,0.03,0, "cm")))+
  ylab(label = "migration velocity")+
  xlab(label = '')+
  scale_color_grey()+
  guides(color = guide_legend(override.aes = list(size = 3)))+
  guides(shape = guide_legend(override.aes = list(size = 3)))+
  scale_y_log10()+
  annotation_logticks(base = 10, sides = "l")
```

# Create experimental ``artifact'' -> merge C2 and C6 to create a bimodal velocity distribution

```{r}
c6 <- d[d$compound == "C6",]
c2 <- d[d$compound == "C2",]
c6$well <- c2$well
c6$v <- c6$v+20
c6$compound <- "C2"


q <- d[d$compound != "C6",]
q <- rbind(q, c6)
d <- q
```

```{r, fig.width=7, fig.height=6}
ggplot(data = d)+
  facet_wrap(facets = ~paste0("compound=", compound), 
             scales = "free_y", ncol = 2)+
  geom_sina(aes(x = as.factor(dose), col = plate, y = v, group = well), 
            size = 0.5)+
  theme_bw()+
  theme(legend.position = "top",
        strip.text.x = element_text(margin = margin(0.03,0,0.03,0, "cm")))+
  ylab(label = "migration velocity")+
  xlab(label = '')+
  scale_color_grey()+
  guides(color = guide_legend(override.aes = list(size = 3)))+
  guides(shape = guide_legend(override.aes = list(size = 3)))+
  scale_y_log10()+
  annotation_logticks(base = 10, sides = "l")
```





```{r fit-model, fig.width=7, fig.height=3.5}
o <- cellmig(x = d,
             control = list(mcmc_warmup = 300,  # Warmup iterations
                            mcmc_steps = 1000,  # Sampling iterations
                            mcmc_chains = 2,    # Number of chains
                            mcmc_cores = 2))    # Parallel cores
```

```{r plot-delta, fig.width=6, fig.height=4}
ggplot(data = o$posteriors$delta_t) +
  geom_line(aes(x = dose, y = mean, col = compound, group = compound)) +
  geom_point(aes(x = dose, y = mean, col = compound)) +
  geom_errorbar(aes(x = dose, y = mean, ymin = X2.5., ymax = X97.5., 
                    col = compound), width = 0.1) +
  ylab(label = expression("Log-Fold Change ("*delta*")")) +
  xlab("Dose") +
  theme(legend.position = "top")
```


```{r ppc-cell, fig.width=8, fig.height=10}
g <- get_ppc_violins(x = o, wrap = TRUE, ncol = 3)
g + scale_y_log10()
```

```{r ppc-well, fig.width=5, fig.height=5}
g <- get_ppc_means(x = o)
g
```

```{r plot-variance, fig.height=3, fig.width=7}
# Plate-specific baseline effects
g_alpha_p <- ggplot(data = o$posteriors$alpha_p) +
  geom_errorbarh(aes(y = plate, x = mean, xmin = X2.5., xmax = X97.5.),
                 height = 0.2) +
  geom_point(aes(y = plate, x = mean)) +
  xlab("Plate Effect (log-scale)")

# Variance parameters (Biological vs Technical)
g_sigma <- ggplot() +
  geom_errorbarh(data = o$posteriors$sigma_bio,
                 aes(y = "Biological (Plate)",
                     x = mean, xmin = X2.5., xmax = X97.5.), height = 0.2) +
  geom_errorbarh(data = o$posteriors$sigma_tech,
                 aes(y = "Technical (Well)",
                     x = mean, xmin = X2.5., xmax = X97.5.), height = 0.2) +
  geom_errorbarh(data = o$posteriors$sigma_delta,
                 aes(y = "Treatment Variation",
                     x = mean, xmin = X2.5., xmax = X97.5.), height = 0.2) +
  geom_point(data = o$posteriors$sigma_bio,
             aes(y = "Biological (Plate)", x = mean)) +
  geom_point(data = o$posteriors$sigma_tech,
             aes(y = "Technical (Well)", x = mean)) +
  geom_point(data = o$posteriors$sigma_delta,
             aes(y = "Treatment Variation", x = mean)) +
  xlab("Standard Deviation")

g_alpha_p | g_sigma
```

# Session Info

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