EVscope_report.Rmd

---
title: "EVscope output report"
author:
  - Rambo (Yiyong) Zhao^[yiyong.zhao@yale.edu]
  - Xianjun Dong^[xianjun.dong@yale.edu]
  - Himanshu Chintalapudi^[himanshu.chintalapudi@yale.edu]
date: "`r format(Sys.time(), '%d %B, %Y')`"
output:
  bookdown::html_document2:
    collapsed: true
    fig_width: 8
    highlight: haddock
    number_sections: false
    keep_md: false
    theme: cerulean
    toc: true
    toc_depth: 4
    toc_float:
      collapsed: yes
    css: !expr file.path(here::here(), "EVscope.css")
editor_options: 
  chunk_output_type: console
---

```{r, echo=FALSE, message = FALSE}
knitr::opts_chunk$set(echo = F, fig.height=8, fig.width=8, message=F, warning=F, cache=F, fig.align = 'center')

library(DT)
library(kableExtra)
library(here)

# some required helper functions:
downloadableDT<- function(atable, rownames = NULL, pageLength = 50){
  require(DT)
  datatable(atable,
            rownames = rownames,
            extensions = 'Buttons',
            options = list(
              autoWidth = TRUE,
              scrollX=TRUE,
              dom = 'Blfrtip',  # 'B' adds buttons, 'frtip' keeps other controls
              pageLength = pageLength,  # Number of rows per page
              buttons = c('copy', 'csv', 'excel', 'pdf'),
              lengthMenu = list( c(10, 20, -1), # declare values
                                 c(10, 20, "All") # declare titles
              )
              ),
            class = "compact stripe hover")
  }
```

**This report contains a comprehensive breakdown of all relevant QC reports, log files and plots for all steps after running EVscope.  **

```{r, echo=FALSE, results='asis'}
knitr::asis_output("\n\n&nbsp;\n\n")
```

```{r, out.width="75%", out.height="75%"}
knitr::include_graphics("figures/EVscope_pipeline.png")
```

```{r, echo=FALSE, results='asis'}
fp = file.path

here::i_am(knitr::current_input()) 
proj_dir<- here()

dirs <- list.dirs(proj_dir, recursive = FALSE, full.names = TRUE)
output_dir<- dirs[grep("processed", dirs, ignore.case = TRUE)][1]

# Only proceed if the output_dir is found, else stop knitting
if (is.na(output_dir) || output_dir == "") {
    stop("Error: The output directory was not found, required module outputs have not been generated by the pipeline!")
}
```

# 01_raw_fastqc {.tabset}

This section contains the QC reports generated by <a href="https://www.bioinformatics.babraham.ac.uk/projects/fastqc">FastQC</a>.

```{r, echo=FALSE, results='asis'}
raw_fastc_01<- list.files(fp(output_dir, "01_raw_fastqc"), pattern = ".html", full.names = T)

html_links <- paste0("[", basename(raw_fastc_01), "](", raw_fastc_01, ")")

for (file in raw_fastc_01) {
  cat(basename(file), "\n\n")  # Display the filename
  cat(sprintf('<iframe src="%s" width="100%%" height="1000px"></iframe>\n\n', file))  # Embed the file in an iframe
}

cat('<br>')
cat('<br>')
```

# 02_UMI_motif

This section contains the results of UMI motif extraction (14-bp motifs) from Read2

```{r}
umi_motif_02_files<- list.files(fp(output_dir, "02_UMI_motif"), full.names = T)
umi_motif_02_png<- umi_motif_02_files[grepl("png", umi_motif_02_files)]
knitr::include_graphics(umi_motif_02_png)

umi_motif_02_csv_name<- umi_motif_02_files[grepl(".csv", umi_motif_02_files)]
```

`r basename(umi_motif_02_csv_name)`

```{r, class.output="scroll-100"}
umi_motif_02_csv<- read.csv(umi_motif_02_csv_name)

#downloadableDT(umi_motif_02_csv, pageLength=10)
datatable(umi_motif_02_csv, rownames = NULL, options = list(scrollX=F))
```


```{r, results='asis'}
cat("<br><br><br>") 
```

# 03_trim_galore

```{r, echo=FALSE, results='asis',  class.output="scroll-100"}
trim_galore_03_files<- list.files(fp(output_dir, "03_trim_galore"), full.names = T)

trim_galore_03_reports<- trim_galore_03_files[grepl("report", trim_galore_03_files)]

for (file in trim_galore_03_reports) {
  cat(basename(file), "\n\n")  # Display the filename
  cat(sprintf('<iframe src="%s" width="100%%" height="600px"></iframe>\n\n', file))  # Embed the file in an iframe
}

cat('<br>')
cat('<br>')
```

# 04_trim_galore_fastqc 

```{r, echo=FALSE, results='asis'}
trim_galore_fastqc_files<- list.files(fp(output_dir, "04_trim_galore_fastqc"), full.names = T, pattern = ".html")

for (file in trim_galore_fastqc_files) {
  cat(basename(file), "\n\n")  # Display the filename
  cat(sprintf('<iframe src="%s" width="100%%" height="1000px"></iframe>\n\n', file))  # Embed the file in an iframe
}

cat('<br>')
cat('<br>')
```

# 07_second_STAR

```{r}
second_STAR_07_files<- list.files(fp(output_dir, "07_second_STAR"), full.names = T)

second_STAR_07_log<- second_STAR_07_files[grepl("\\_dedup_Log.final.out$", second_STAR_07_files)]
#second_STAR_07_log<- read.delim(second_STAR_07_log, header = F)
```

[`r basename(second_STAR_07_log)`](`r second_STAR_07_log`)

```{r, results='asis'}
cat("<br><br><br>") 
```

# 08_CIRCexplorer2

```{r,  class.output="scroll-100"}
CIRCexplorer2_08_files<- list.files(fp(output_dir, "08_CIRCexplorer2"), full.names = T)

CIRCexplorer2_08_cpm_tsv<- CIRCexplorer2_08_files[grepl("\\_CPM.tsv$", CIRCexplorer2_08_files)]
```

`r basename(CIRCexplorer2_08_cpm_tsv)`

```{r,  class.output="scroll-100"}
CIRCexplorer2_08_cpm_tsv<- read.table(CIRCexplorer2_08_cpm_tsv, header = T)

downloadableDT(CIRCexplorer2_08_cpm_tsv)

CIRCexplorer2_08_circularRNA<- CIRCexplorer2_08_files[grepl("circularRNA", CIRCexplorer2_08_files)]
```

`r basename(CIRCexplorer2_08_circularRNA)`

```{r}
CIRCexplorer2_08_circularRNA<- read.table(CIRCexplorer2_08_circularRNA)

downloadableDT(CIRCexplorer2_08_circularRNA)
```

```{r, results='asis'}
cat("<br><br><br>") 
```

# 09_BWA_CIRI2

```{r}
BWA_CIRI2_09_files<- list.files(fp(output_dir, "09_BWA_CIRI2"), full.names = T)

BWA_CIRI2_09_readcounts_CPM <- BWA_CIRI2_09_files[grepl("\\_readcounts_CPM.tsv$", BWA_CIRI2_09_files)]

```

`r basename(BWA_CIRI2_09_readcounts_CPM)`

```{r}
BWA_CIRI2_09_readcounts_CPM<- read.table(BWA_CIRI2_09_readcounts_CPM, header = T)

downloadableDT(BWA_CIRI2_09_readcounts_CPM)

BWA_CIRI2_09_CIRI2_out<- BWA_CIRI2_09_files[grepl("\\_CIRI2_out.tsv$", BWA_CIRI2_09_files)]
```

`r basename(BWA_CIRI2_09_CIRI2_out)`

```{r}
BWA_CIRI2_09_CIRI2_out<- read.delim(BWA_CIRI2_09_CIRI2_out)

downloadableDT(BWA_CIRI2_09_CIRI2_out)
```

```{r, results='asis'}
cat("<br><br><br>") 
```

# 10_merge_CIRI2_CIRCexplorer2

```{r}
merge_CIRI2_CIRCexplorer2_files<- list.files(fp(output_dir, "10_merge_CIRI2_CIRCexplorer2"), full.names = T)

merge_CIRI2_CIRCexplorer2_CIRI2_tsv<- merge_CIRI2_CIRCexplorer2_files[grepl("\\CIRI2.tsv$", merge_CIRI2_CIRCexplorer2_files)]

```

`r basename(merge_CIRI2_CIRCexplorer2_CIRI2_tsv)`

```{r}
merge_CIRI2_CIRCexplorer2_CIRI2_tsv<- read.delim(merge_CIRI2_CIRCexplorer2_CIRI2_tsv)

downloadableDT(merge_CIRI2_CIRCexplorer2_CIRI2_tsv)
```


```{r,echo=FALSE, results='asis'}
merge_CIRI2_CIRCexplorer2_pdfs<- merge_CIRI2_CIRCexplorer2_files[grepl("\\.pdf$", merge_CIRI2_CIRCexplorer2_files)]

for (pdf in merge_CIRI2_CIRCexplorer2_pdfs) {
  cat(basename(pdf), "<br>\n")
  cat(sprintf('<iframe src="%s" width="100%%" height="600px"></iframe><br><br>\n\n', pdf))  # Add iframe and extra breaks
}

cat('<br>')
cat('<br>')
```

# 11_picard_metrics

```{r, fig.height=12}
picard_metrics_files<- list.files(fp(output_dir, "11_picard_metrics"), full.names = T)

picard_metrics_pdf<- picard_metrics_files[grepl("pdf", picard_metrics_files)]
#knitr::include_graphics(picard_metrics_pdf)
```

<iframe src="`r picard_metrics_pdf`" width="100%" height="600px"></iframe>

```{r, results='asis'}
cat("<br><br><br>") 
```

# 12_featureCounts

```{r}
featureCounts_12_files<- list.files(fp(output_dir, "12_featureCounts"), full.names = T,
                                    pattern = "fragment_level_featureCounts\\.tsv$")

# featureCounts_12_tsv<- read.table(featureCounts_12_files, header = T)
# 
# featureCounts_12_tsv%>%
#   DT::datatable(
#     extensions = 'Buttons', 
#     options = list(dom = 'Bfrtip', 
#                    pageLength = 10,
#                    buttons = c('excel', "csv")))

links <- paste0("<a href='", featureCounts_12_files, "' download>", basename(featureCounts_12_files), "</a>")
knitr::kable(data.frame(Files = links), escape = FALSE)
```

```{r, results='asis'}
cat("<br><br><br>") 
```

# 13_plot_RNA_distribution

```{r}
plot_RNA_distribution_files<- list.files(fp(output_dir, "13_plot_RNA_distribution"), full.names = T)

plot_RNA_distribution_tsv<- plot_RNA_distribution_files[grepl("CPM.tsv", plot_RNA_distribution_files)]

```

`r basename(plot_RNA_distribution_tsv)`

```{r, echo=FALSE, results='asis'}
plot_RNA_distribution_tsv<- read.table(plot_RNA_distribution_tsv, header = T)

downloadableDT(plot_RNA_distribution_tsv)

plot_RNA_distribution_pdfs<- plot_RNA_distribution_files[grepl("pdf", plot_RNA_distribution_files)]


for (pdf in plot_RNA_distribution_pdfs) {
  cat(basename(pdf), "<br>\n")
  cat(sprintf('<iframe src="%s" width="100%%" height="600px"></iframe><br><br>\n\n', pdf))  # Add iframe and extra breaks
}

cat('<br>')
cat('<br>')
```

# 15_Kraken

```{r}
kraken_15_files<- list.files(fp(output_dir, "15_Kraken"), full.names = T, pattern = ".html")
```

`r basename(kraken_15_files)`

<iframe src=`r kraken_15_files` width="100%" height="600px"></iframe>


```{r, results='asis'}
cat("<br><br><br>") 
```

# 17_QC_matrix

```{r}
QC_matrix_files<- list.files(fp(output_dir, "17_QC_matrix"), full.names = T, pattern = "\\.tsv$")

QC_matrix_tsv<- read.delim(QC_matrix_files)
```

`r basename(QC_matrix_files)`

```{r}
downloadableDT(QC_matrix_tsv)
```

```{r, results='asis'}
cat("<br><br><br>") 
```

# R session info
This section includes technical details about the R packages used to produce this report. Most readers can safely ignore it.

<button class="btn btn-rcode" data-toggle="collapse" data-target="#BlockName"> Show/Hide R Session Details </button>
<div id="BlockName" class="collapse">

```{r session info}
sess <- devtools::session_info()
sess$platform
knitr::kable(as.data.frame(sess$packages), caption="Package versions")
```

</div>

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