dataResourceTable.Rmd

---
title: "**Data Resources Platforms**"
output: html_document
---

### **Overview**

The following table contains a list of cancer data resources that are available to researchers. These resources include genomic, epigenomic, transcriptomic, proteomic, and cancer imaging data. 


```{r,echo=FALSE,results='hide',message=FALSE, warning=FALSE}
library(DT)
library(here)
library(tidyverse)
library(magrittr)

source("scripts/format-tables.R")
```

**Table keys:** 
<div title="Table keys"> 
<img src="ITCRLogo.png" height="25"> </img> = ITCR Funded
</div>

```{r,echo=FALSE,results='hide',message=FALSE, warning=FALSE}
# Load file for Resource Table and make edits/additions
## If adding any resources/platforms/not a tool to the ITCR tables, this code block is where you'll want to do that
resource <- readr::read_csv(file = here::here("data/itcr_table_resources.csv"))

tibbleTOPAS <- tibble(
  Name = "TOPAS",
  Price = '<a href="https://www.topasmc.org/license" style="color: #be3b2a" target="_blank"<div title="Pricing Link"> </div>Paid/Free</a>'
)

resource <- dplyr::rows_update(resource, tibbleTOPAS, by="Name") #this will update the existing TOPAS entry

## Goal: Create the html version of links in resources
## Edit 1: Add a column "identifier" to the resource table to use it as a merge key variable with the Data provided column entries in other tables
## Edit 2: Make sure add new identifiers for new resources in the resource data set.
resource %<>% 
  mutate(identifier = c("PDX", "HemOnc", "ngchm", "OncoMX", "MethCon5", "CIViC", "BioMuta", "TCIA", "SCGV", "ivyGlimpse", "TCPA", "dcmqi", "Region Templates", "Cistrome", "TOPAS", "TCGA", "1000 Genomes", "TARGET", "CCLE", "dbGAP", "CPTAC", "PheKB", "NSCLC Radiomics", "ICGC"))  %>%  relocate(identifier)

## From this point forward, any additions to the resource table need to include an "identifier" in the tibble/row that will be added

## Add ISIC Archive: Submitted 06/01/2023, 13:31 (vrotemberg@gmail.com)
new_ISIC <- tibble(
  Name = "ISIC Archive",
  Funding = "Yes",
  Subcategories = "Cancer Imaging", 
  `Data Type` = "Clinical imaging",
  `Unique Factors` = "The largest public archive of dermatology photographs. It has around 20 million individual image downloads per month and is widely used for education and AI research.",
  Price = "Free",
  Link = "https://www.isic-archive.com/",
  `Summary` = "The ISIC Archive is an academic-industry collaboration that is devoted to improving dermatology artificial intelligence. It is the largest public archive of images of skin conditions, with special attention to skin cancer detection. We also host grand challenges (and live challenges) for AI models as well as conference workshops.",
  identifier = "ISIC"
  )

resource <- dplyr::rows_insert(resource, new_ISIC, conflict = "ignore") #include conflict = ignore argument because it won't re-add the resource the next time this code is run if the file is overwritten/resource is already included.


## Add The Cancer Epitope Database and Analysis Resource (CEDAR): Submitted 07/26/2023, 10:48 (nblazeska@lji.org)
new_CEDAR <- tibble(
  Name = "Cancer Epitope Database and Analysis Resource (CEDAR)",
  Funding = "Yes",
  Subcategories = "Proteomics" , #this is my assumption based on the use of epitopes; it was not submitted in the form or explicitly said on the website
  `Data Type` = "Curated literature data: experimentally-tested epitopes and their immunological, biological, and clinical contexts" ,
  `Unique Factors` = "It is a free resoure that provides the cancer community with a central repository of experimentally-tested cancer epitopes curated from peer-reviewed literature.",
  Price = "Free",
  Link = "https://cedar.iedb.org/",
  Summary = "The Cancer Epitope Database and Analysis Resource (CEDAR) is a freely available resource funded by NCI. It catalogs experimental data on antibody and T cell epitopes studied in humans, non-human primates, and other animal species in the context of cancer disease. CEDAR also hosts tools to assist in the prediction and analysis of cancer epitopes." ,
  identifier = "CEDAR"
)

## Add ARCHS4: Submitted 09/13/2023, 12:36 (avi.maayan@mssm.edu)
new_ARCHS4 <- tibble(
  Name = "ARCHS4",
  Funding = "Yes", 
  Subcategories = "Transcriptomics",
  `Data Type` = "Transcriptomics, GEO",
  `Unique Factors` = "This resource is updated frequently. It contains all GEO samples and includes metadata and data search.",
  Price = "Free for academic institutions",
  Link = "https://maayanlab.cloud/archs4/" ,
  Summary = "ARCHS4 provides gene and trasncript counts uniformly processed from all the human and mouse RNA-seq samples from GEO" ,
  identifier = "ARCHS4"
)

resource <- dplyr::rows_insert(resource, dplyr::bind_rows(new_CEDAR, new_ARCHS4), conflict = "ignore")

## Add PCDC: Submitted 01/06/2023, Issue #22 on GitHub
new_PCDC <- tibble(
  Name = "Pediatric Cancer Data Commons (PCDC)",
  Funding = "Yes",
  Subcategories = "Clinical",
  `Data Type` = "ALL Data Commons, C3P, CHIC, FA Data Commons, Global REACH, HIBiSCus, INRG, INSPiRE, INSTRuCT, INTERACT, MaGIC, NOBLE, NODAL, Reproductive HOPE",
  `Unique Factors` = "Uses consensus-based data dictionaries and maps all clinical data in the portal to standardized terms; provides a data portal and analysis tools to assess study feasibility" ,
  Price = "Free",
  Link = "https://portal.pedscommons.org/login",
  Summary = "The PCDC Data Portal offers a unified platform where researchers can use the cohort explorer and other analysis tools to explore available data and assess study feasibility; if a user wishes to perform research with data from the PCDC, the proposed project undergoes review and approval by the relevant disease consortium.",
  identifier = "PCDC"
)

resource <- dplyr::rows_insert(resource, new_PCDC, conflict="ignore")

write.csv(resource, file="data/itcr_table_resources_identifier.csv") #because this file is used as a linker for other tables/in other files, writing it out.

```

```{r, echo=FALSE, results='hide', message=FALSE, warning=FALSE}
modified_resource <- formatTheTables(resource, "NA")
```

```{r,echo=FALSE,results='hide',message=FALSE, warning=FALSE}
# Create a Resource Table

columnDefsListOfLists <- list(list(className = 'dt-center', targets = "_all"),
                                     list(width = '120px', targets = c(0)) , 
                                     list(width = '300px', targets = c(2)) , 
                                     list(width = '140px', targets = c(3)) ,
                                     list(width = '100px', targets = c(4)) 
                              )

ITCR_resource <- setup_dt_datatable(modified_resource, columnDefsListOfLists)
```

```{r,echo=FALSE,message=FALSE, warning=FALSE}
#Display the resource table
ITCR_resource
```