Add ARC

README.md

-# SampleARC_RNASeq
+# ARC mininmal Example RNASeq
+
+
+## Notes
+
+- CWL not yet implemented 
+
+
+
+### isa.assay
+- split GEO SWATE templates into four sheets 
+    - 1SPL01_plants
+    - 2EXT01_RNA
+    - 3ASY01_RNASeq
+    - 4COM01_RNASeq
+
+
+### adding raw data via git lfs 
+
+```
+git lfs track "*.fastq.gz"
+```
+
+add data to assays folder
+
+```
+git add assays/Talinum_RNASeq_minimal/dataset/
+```
+
 

assays/Talinum_RNASeq_minimal/protocols/01_plant_material.md

+# Plant Material and Growth Conditions
+
+Talinum triangulare plants were grown in Miracle-Gro Potting Mix (Miracle- Gro) in “Short-One” treepots, 1.6 l (Stuewe and Sons). The experiment was initiated with 28-d-old plants in a controlled environment chamber (Environ- mental Growth Chambers) maintained under 12 h light (30°C, 37% relative humidity)/12 h dark (22°C) cycles. Photon flux density at leaf level was 425 mmol m22 s21. Irrigation was withheld on day 1 and recommenced on day 14. Leaves were harvested when plants were well-watered as well as after 4, 9, and 12 d of water deprivation and watered for two days following the drought period.
\ No newline at end of file

assays/Talinum_RNASeq_minimal/protocols/02_RNAex_libraries.md

+# RNA Extraction, Preparation, and Sequencing of Illumina Libraries
+
+The topmost mature unshaded leaves (of approximately 3–4.5 cm length) of T. triangulare were harvested in the middle of the light or the middle of the dark period and immediately frozen in liquid nitrogen. RNA was isolated from ground tissue using the GeneMatrix Universal RNA Purification Kit (EURx Ltd.). Residues of DNA were removed with DNase (New England Biolabs). RNA integrity, sequencing library, and fragment size were analyzed on a 2100 Bioanalyzer (Agilent). Libraries were prepared using the TruSeq RNA Sample Prep Kit v2 (Illumina) and quantified with a Qubit 2.0 (Invitrogen). Samples were multiplexed with 12 libraries per lane and sequenced in single-end mode (Rapid Run, 150 bp read length) on an Illumina HiSEquation 2000 platform, yielding ;14 million reads per library.

externals/README.md

+
+
+### Talinum Genome ref
+File: Talinum.gm.CDS.nt.fa
+Source: weber_fileshare/data/Eva_Maleckova-CAM/Genomics/Genome/Talinum-Flye-Polca_v201017/Talinum.gm.CDS.nt.fa
+Contributor: Eva Maleckova 
+

workflows/01_KallistoQuant.sh

+
+########################
+#### To be replaced by CWL routine
+########################
+
+ARC_root=~/Hackathon_ARCexample_rnaseq/
+cd $ARC_root'workflows/'
+
+# chmod a+x 01_KallistoQuant.sh
+# ./01_KallistoQuant.sh > $ARC_root'runs/01_kallisto.log' 2>&1 &
+
+########################
+
+
+# Map RNASeq reads via kallisto
+
+## Manual: http://pachterlab.github.io/kallisto/manual.html
+
+kallisto version
+kallisto cite
+
+### Build index 
+
+kall_ref=$ARC_root'externals/Talinum.gm.CDS.nt.fa'
+kallisto index -i $ARC_root'runs/01_kallisto_index' $kall_ref
+
+### Align reads
+
+ILLUMINASAMPLES=$(ls ${ARC_root}'assays/Talinum_RNASeq_minimal/dataset/'*fastq.gz)
+
+mkdir $ARC_root'/runs/01_kallisto_results/'
+
+for j in $ILLUMINASAMPLES; do
+
+		sampleName=$(echo $j | sed -e 's|.*/||' | cut -c -6)  # cut away path. retain only first six chars of file name
+		echo $sampleName
+		
+		kallisto quant --single -b 100 -t 30 -l 200 -s 20 -i $ARC_root'/runs/01_kallisto_index' -o $ARC_root'/runs/01_kallisto_results/'$sampleName $j
+
+	    echo 'Kallisto done'
+
+done
\ No newline at end of file

workflows/03_KallistoCollect.R

+
+
+########################
+#### To be replaced by CWL routine
+########################
+
+ARC_root="~/Hackathon_ARCexample_rnaseq/"
+setwd(paste0(ARC_root, 'workflows/'))
+
+########################
+
+########################
+# Collect kallisto data
+########################
+
+
+# ### sleuth installation
+# 
+# if (!requireNamespace("BiocManager", quietly = TRUE))
+#   install.packages("BiocManager")
+# BiocManager::install()
+# BiocManager::install("devtools")    # only if devtools not yet installed
+# BiocManager::install("pachterlab/sleuth")
+
+library(sleuth)
+library(tidyverse)
+library(jsonlite)
+library(openxlsx)
+
+## read experimental metadata from isa.assay wb
+
+isa_assay <- paste0(ARC_root, 'assays/Talinum_RNASeq_minimal/assay.isa.xlsx')
+
+assay_data <- merge(readWorkbook(isa_assay, "1SPL01_plants", startRow = 2), 
+                    readWorkbook(isa_assay, "3ASY01_RNASeq", startRow = 2), 
+                    by = "Sample.Name"
+                    )
+
+## remove empty cols
+assay_data <- assay_data[, !apply(assay_data, 2, function(x){sum(is.na(x)) == nrow(assay_data)})]  
+
+# Pointer to kallisto results folder
+base_dir <- paste0(ARC_root, '/runs/01_kallisto_results/')
+
+# A list of paths to the kallisto results indexed by the sample IDs is collated with
+kal_dirs <- dir(base_dir, full.names = T) ## Sleuth requires full paths
+
+s2c <- assay_data[order(assay_data$Sample.Name), c('Sample.Name', "Characteristics.[Photosynthesis.mode]")]
+# For kallisto / sleuth: 's2c' (sample_to_covariates) must contain a column named 'sample'
+colnames(s2c) <- c("sample", "Photosynthesis.mode")
+
+s2c$path <- kal_dirs
+s2c <- s2c[order(s2c$sample), ]
+
+# Build a sleuth object
+so <- sleuth_prep(s2c, ~Photosynthesis.mode)
+save(so, file = paste0(ARC_root, 'runs/03_kallisto_sleuthObject.RData'))
+
+# Extract expression tables
+
+## as data.frame
+expression_data <- kallisto_table(so)
+write.csv(expression_data, paste0(ARC_root, 'runs/03_kallisto_df.csv'), row.names = F)
+
+## as tpm matrix (gene x sample)
+tpm_table <- pivot_wider(expression_data, id_cols = target_id, names_from = sample, values_from = tpm)
+write.csv(tpm_table, paste0(ARC_root, 'runs/03_kallisto_tpmMatrix.csv'), row.names = F)
+
+
+# Summarize mapping stats
+
+mapping_stats <- c()
+for(i in dir(kal_dirs, pattern = '.json', full.names = T))
+{
+  id <- unlist(strsplit(i, split = '/'))
+  
+  z <- data.frame(ID = id[length(id) - 1], read_json(i, simplifyVector = T))
+  mapping_stats <- rbind(mapping_stats, z)
+}
+
+write.csv(mapping_stats, paste0(ARC_root, 'runs/03_kallisto_mappingStats.csv'), row.names = F)
+
+
+
+
+

workflows/04_Sleuth.R

+
+
+########################
+#### To be replaced by CWL routine
+########################
+
+ARC_root="~/Hackathon_ARCexample_rnaseq/"
+setwd(paste0(ARC_root, 'workflows/'))
+
+########################
+
+########################
+# Determine diff. gene expression with sleuth
+########################
+
+library(sleuth)
+
+# Load the sleuth object
+load(file = paste0(ARC_root, 'runs/03_kallisto_sleuthObject.RData'))
+
+
+so <- sleuth_fit(so)
+so <- sleuth_fit(so, ~Group, 'full')
+so <- sleuth_fit(so, ~1, 'reduced')
+so <- sleuth_lrt(so, 'reduced', 'full')
+
+sleuth_table <- sleuth_results(so, 'reduced:full', 'lrt', show_all = FALSE)
+
+
+write.csv(sleuth_table, paste0(ARC_root, 'runs/04_sleuth_dge.csv'), row.names = F)
+
+
+
+
+

workflows/05_plot_shinyPrep.R

+
+
+########################
+#### To be replaced by CWL routine
+########################
+
+ARC_root="~/Hackathon_ARCexample_rnaseq/"
+setwd(paste0(ARC_root, 'workflows/'))
+
+########################
+
+########################
+# Prep data for shiny app
+########################
+
+library(openxlsx)
+
+expression_data <- read.csv(file = paste0(ARC_root, 'runs/03_kallisto_df.csv'))
+available_genes <- unique(expression_data$target_id)
+
+save(expression_data, available_genes, file = paste0(ARC_root, 'runs/05_shinyPrep.RData'))

workflows/05_plotshinyPrep/05_plot_shinyPrep.R

+
+########################
+# Prep data for shiny app
+########################
+
+
+install.packages("openxlsx",dependencies=TRUE, lib='./lib',repos='http://cran.rstudio.com/')
+library(openxlsx, lib.loc = "./lib")
+
+options <- commandArgs(trailingOnly = TRUE)
+wd <- getwd()
+
+expression_data <- read.csv(file = options[1])
+available_genes <- unique(expression_data$target_id)
+
+save(expression_data, available_genes, file = paste0(wd, "/05_shinyPrep.RData"))