Merge pull request #46 from igemsoftware2020/finalChanges

Fixed all text, added how to section, added link to MultiStress Explo…

public/stylesheets/style.css

@@ -282,3 +282,7 @@ td.x {
 td.y {
   color: red;
 }
+
+.redcolor a:link{
+  color: red;
+}

scripts/R/DEA/GSE147272.R

@@ -1,3 +1,17 @@
+#License
+
+# © Copyright 2020 iGEM Concordia, Maher Hassanain, Benjamin Clark, Hajar Mouddene, Grecia Orlano
+# This file is part of AstroBio.
+# AstroBio is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or any later version.
+# AstroBio is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# You should have received a copy of the GNU General Public License
+# along with AstroBio.  If not, see <https://www.gnu.org/licenses/>.
+
 library(edgeR)
 library(dplyr)
 
@@ -16,8 +30,8 @@ d0 <- calcNormFactors(d0)
 #filtering low expressed genes
 cutoff <- 1
 drop <- which(apply(cpm(d0), 1, max) < cutoff)
-d <- d0[-drop,] 
-dim(d) 
+d <- d0[-drop,]
+dim(d)
 
 #Setting up factor names
 gravity <- append(rep("MG", 4), rep("NG",4))
@@ -40,14 +54,14 @@ fit2 <- eBayes(fit2)
 tT.exp <- topTable(fit2, n = Inf, adjust.method = "fdr")
 
 
-#getting annotations 
+#getting annotations
 anno <- rtracklayer::import("ecoli_nissle_1917.gtf")
 
 anno  <-  anno %>% as.data.frame %>% filter(type == "exon") %>% select(-seqnames, -source, -score, -phase)
 vmatch <- match(rownames(tT.exp),anno$gene_id)
 
 vmatch_id <- anno$gene_name[vmatch]
-tT.exp <- tT.exp %>% mutate(Gene.Symbol = vmatch_id, Platform.ORF = rownames(tT.exp)) %>% na.omit() 
+tT.exp <- tT.exp %>% mutate(Gene.Symbol = vmatch_id, Platform.ORF = rownames(tT.exp)) %>% na.omit()
 write.csv(tT.exp, file = "datasets/GSE147272_Ecol/GSE147272_exponential.growth.csv")
 
 #now for stationary phase
@@ -59,7 +73,7 @@ tT.sta <- topTable(fit3, n = Inf, adjust.method = "fdr")
 vmatch <- match(rownames(tT.sta),anno$gene_id)
 
 vmatch_id <- anno$gene_name[vmatch]
-tT.sta <- tT.sta %>% mutate(Gene.Symbol = vmatch_id, Platform.ORF = rownames(tT.sta)) %>% na.omit() 
+tT.sta <- tT.sta %>% mutate(Gene.Symbol = vmatch_id, Platform.ORF = rownames(tT.sta)) %>% na.omit()
 write.csv(tT.sta, file = "datasets/GSE147272_Ecol/GSE147272_stationary.growth.csv")
 
 #getting metadata
@@ -73,4 +87,3 @@ strain <- "Nissle_1917"
 gselist <- list(list(GSE = mdata[,c(1,2,5,6)]), list(GSE = mdata[,c(3,4,7,8)]))
 metalabels <- c("exponential.growth", "stationary.growth")
 extractMetaData(gse_groups = gselist, filename = metaName, microgravity_type = M.TYPE$RCCS, metaLabels = metalabels, strain = strain)
-

scripts/R/DEA/GSE40648.R

@@ -1,3 +1,16 @@
+#License
+
+# © Copyright 2020 iGEM Concordia, Maher Hassanain, Benjamin Clark, Hajar Mouddene, Grecia Orlano
+# This file is part of AstroBio.
+# AstroBio is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or any later version.
+# AstroBio is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# You should have received a copy of the GNU General Public License
+# along with AstroBio.  If not, see <https://www.gnu.org/licenses/>.
 
 #GSE40648 Ecoli MICROARRAY
 #R script by BENJAMIN CLARK
@@ -8,7 +21,7 @@ library(Biobase)
 library(limma)
 library(org.EcK12.eg.db)
 source("microarray_functions.R")
-#This pulls the all the samples from the microarry dataset. This returns a list containing a single expressionSet object. 
+#This pulls the all the samples from the microarry dataset. This returns a list containing a single expressionSet object.
 list.gse <- getGEO("GSE40648", GSEMatrix =TRUE, AnnotGPL=TRUE)
 
 gse <- list.gse[[1]]
@@ -31,7 +44,7 @@ treatment <- c(4,5,6)
 
 ecoli <- de.analysis(gse = gse.rm, microgravity_group = treatment, ground_group = control)
 
-#print out the toptable 
+#print out the toptable
 ecoliname <- "datasets/GSE40648_Ecoli/GSE40648_Ecoli.csv"
 write.table(ecoli$TopTable, ecoliname, row.names = FALSE, sep = ",")
 remove.controls(ecoli$TopTable)
@@ -64,44 +77,44 @@ anno.go.genome <- function(go.ids){
     terms <- sapply(names(line.go.items[[1]]),FUN = Term)
     names(terms) <- NULL
     terms <- unlist(terms)
-    
+
     ontologies <- sapply(names(line.go.items[[1]]), FUN = Ontology)
     names(ontologies) <- NULL
     ontologies <- unlist(ontologies)
-    
+
     inner_out <- data.frame(id = names(line.go.items[[1]]), term = terms, ontology = ontologies)
     out[names(go.ids)[i]]<- list(inner_out)
-    
-    
-    
+
+
+
   }
   return(out)
 }
 go.genome <- anno.go.genome(mapped_gos)
 valid_ids <- c()
 for(i in 1:length(entrez_ids)){
-  if(length(go.genome[[entrez_ids[i]]]$ontology) > 0){  
+  if(length(go.genome[[entrez_ids[i]]]$ontology) > 0){
     GO.Function <- paste(dplyr::filter(go.genome[[entrez_ids[i]]], ontology == "MF")$term , collapse = "///")
     GO.Process <- paste(dplyr::filter(go.genome[[entrez_ids[i]]], ontology == "BP")$term , collapse = "///")
     GO.Component <- paste(dplyr::filter(go.genome[[entrez_ids[i]]], ontology == "CC")$term , collapse = "///")
   }
   else{
     next
   }
-  
+
   ided.rows <- grep(filtered.tT$TopTable$Gene.symbol, pattern = names(entrez_ids[i]))
   correct.probe <-  which.min(filtered.tT$TopTable[ided.rows,]$P.Value)
-  
+
   filtered.tT$TopTable$GO.Function[ided.rows[correct.probe]] <- GO.Function
-  
+
   filtered.tT$TopTable$GO.Component[ided.rows[correct.probe]] <- GO.Component
-  
+
   filtered.tT$TopTable$GO.Process[ided.rows[correct.probe]] <- GO.Process
-  
-  
+
+
   valid_ids <- append(valid_ids, ided.rows[correct.probe])
-  
-  
+
+
 }
 valid_ids <- valid_ids[-which(duplicated(valid_ids))]
 filtered.tT$TopTable <- filtered.tT$TopTable[valid_ids,]
@@ -118,4 +131,3 @@ strain <- "K12 MG1655"
 gse_list <- list(ecoli)
 labels <- c("ecoli")
 extractMetaData(filename = metaName, gse_groups = gse_list, microgravity_type = M.TYPE$RPM, metaLabels = labels, strain = strain)
-

scripts/R/DEA/GSE4136.R

@@ -1,3 +1,16 @@
+#License
+
+# © Copyright 2020 iGEM Concordia, Maher Hassanain, Benjamin Clark, Hajar Mouddene, Grecia Orlano
+# This file is part of AstroBio.
+# AstroBio is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or any later version.
+# AstroBio is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# You should have received a copy of the GNU General Public License
+# along with AstroBio.  If not, see <https://www.gnu.org/licenses/>.
 
 #GSE4136 YEAST MICROARRAY
 #BENJAMIN CLARK
@@ -9,7 +22,7 @@ library(stats)
 library(dendextend)
 library(gplots)
 source("microarray_functions.R")
-#This pulls the all the samples from the microarry dataset. This returns a list containing a single expressionSet object. 
+#This pulls the all the samples from the microarry dataset. This returns a list containing a single expressionSet object.
 list.gse <- getGEO("GSE4136", GSEMatrix =TRUE, AnnotGPL=TRUE)
 
 gse <- list.gse[[1]]
@@ -28,7 +41,7 @@ control <- c(1,2,3)
 treatment <- c(7,8,9)
 gen5 <- de.analysis(gse = gse, microgravity_group = treatment, ground_group = control)
 
-#print out the toptable 
+#print out the toptable
 gen5name <- "datasets/GSE4136_Scer/GSE4136_5thGen.csv"
 write.table(gen5$TopTable, gen5name, row.names = FALSE, sep = ",")
 
@@ -74,7 +87,7 @@ ex_genes_f <- readxl::read_xlsx("essential/TableS3_excludedStrains-hom.xlsx", sh
 
 ex_genes <- union(ex_genes_f, ex_genes_g)
 
-#Adding to Gen5 Study 
+#Adding to Gen5 Study
 essential_bool5 <- c()
 
 essential_bool5[match(full_names, gen5$TopTable$Gene.symbol)] <- TRUE
@@ -121,7 +134,7 @@ gen25.orfs <- gen25$TopTable$ID[gen25.sig.df.genes]
 
 grouped.orfs <- union(gen5.orfs,gen25.orfs)
 
-#pulling relevent expression data 
+#pulling relevent expression data
 ex <- exprs(gse)
 filtered.ex <- ex[rownames(ex) %in% grouped.orfs,]
 
@@ -147,8 +160,8 @@ hc <- as.dendrogram(hclust(as.dist(1-cor(t(filtered.ex), method="pearson")), met
 
 #c.index <- which(labels(hc) %in% both)
 
-hc %>% set("labels_col", "white") %>% 
-  set("by_labels_branches_col", value = both) %>% 
+hc %>% set("labels_col", "white") %>%
+  set("by_labels_branches_col", value = both) %>%
   plot(main = "Highlighted Union Genes Across Timescales")
 
 #PLOTTING INTERSECTING Genes

scripts/R/DEA/GSE50881.R

@@ -1,5 +1,19 @@
+#License
+
+# © Copyright 2020 iGEM Concordia, Maher Hassanain, Benjamin Clark, Hajar Mouddene, Grecia Orlano
+# This file is part of AstroBio.
+# AstroBio is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or any later version.
+# AstroBio is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# You should have received a copy of the GNU General Public License
+# along with AstroBio.  If not, see <https://www.gnu.org/licenses/>.
+
 ###GSE50881 YEAST MICROARRAY TWO CHANNEL
-#BENJAMIN CLARK 
+#BENJAMIN CLARK
 
 library(GEOquery)
 library(Biobase)
@@ -28,17 +42,17 @@ fvarLabels(gse) <- make.names(fvarLabels(gse))
 
 # design <- cbind(DyeEffect = 1,SpaceVsGround = c(1,-1,1,-1,1,-1,1,-1))
 # #block <- fData(gse[,1])$Block
-# 
-# 
+#
+#
 # fit <- lmFit(gse,design)
 # fit <- eBayes(fit, 0.01)
-# 
+#
 # #topTable.dyes <- topTable(fit, coef = "DyeEffect")
-# 
+#
 # anno.data <- fData(gse)
-# 
+#
 # f.tT <- remove.candida.controls(topTable.SvsG)
-# 
+#
 # f.tT <- subset(f.tT, select = c("CGD_Systematic_Name", "Description", "SpaceVsGround", "AveExpr", "F", "P.Value", "adj.P.Val"))
 
 topTable.SvsG <- topTable(fit, adjust.method = "fdr", sort.by = "B", number = length(fit[[1]]))
@@ -48,10 +62,10 @@ f.tT <- subset(f.tT, select = c("CGD_Systematic_Name", "Description", "SpaceVsGr
 
 
 
-rowid <- c() 
+rowid <- c()
 for(i in 1:length(f.tT$ID)){
   rowid <- append(rowid,((f.tT %>% filter(SPOT_ID == f.tT$SPOT_ID[i]) %>% arrange(P.Value))[1,])$ID)
-  
+
 }
 
 best.rows.ids <- rowid[-which(duplicated(rowid))]
@@ -81,9 +95,9 @@ go_ids <- read.csv("Candida_albicans_GO.csv")
 ordered.gos <- list()
 for(annos in 1:length(rm.ftT$CGD_Systematic_Name)){
   indexes <- which(rm.ftT$CGD_Systematic_Name[annos] == go_ids$systemic_id)
-  ids <- go_ids$go_id[indexes]  
+  ids <- go_ids$go_id[indexes]
   ordered.gos[annos] <- list(ids)
-  
+
 }
 
 anno.terms <- list()
@@ -96,24 +110,24 @@ for(i in 1:length(ordered.gos)){
   GO.COMPONENT <- c()
   if(length(ordered.gos[[i]]) == 0){
    full.MF <- append(full.MF, NA)
-   full.CC <-  append(full.CC, NA) 
+   full.CC <-  append(full.CC, NA)
    full.BP <- append(full.BP, NA)
    next
   }
   for(j in 1:length(ordered.gos[[i]])){
-    
+
     if(Ontology(ordered.gos[[i]][[j]]) == "MF"){
       GO.FUNCTION <- append(GO.FUNCTION, Term(ordered.gos[[i]][[j]]))
-      
+
     }else if(Ontology(ordered.gos[[i]][[j]]) == "CC"){
       GO.COMPONENT <- append(GO.COMPONENT, Term(ordered.gos[[i]][[j]]))
-      
+
     }
     else if(Ontology(ordered.gos[[i]][[j]]) == "BP"){
       GO.PROCESS <- append(GO.PROCESS, Term(ordered.gos[[i]][[j]]))
-      
+
     }
-    
+
   }
   if(length(GO.FUNCTION) != 0){
     full.MF <- append(full.MF, paste(GO.FUNCTION, collapse = "///"))}
@@ -145,15 +159,15 @@ names <- unlist(names)
 Chromosome_Location <- stringr::str_extract_all(rm.ftT$Description, pattern = "(Contig\\d+:\\D+\\d+..\\d+\\)|Contig\\d+:\\d+..\\d+)")
 Chromosome_Location <- sapply(Chromosome_Location, FUN = paste, collapse = "///", USE.NAMES = FALSE)
 
-final.tT <- rm.ftT %>% mutate( GO.Function = full.MF, GO.Component = full.CC, 
-                               GO.Process = full.BP, Gene.Name = names, 
-                               Chromosome.Location = Chromosome_Location, 
-                               ID = NULL, SPOT_ID = NULL, Description = NULL) %>% 
+final.tT <- rm.ftT %>% mutate( GO.Function = full.MF, GO.Component = full.CC,
+                               GO.Process = full.BP, Gene.Name = names,
+                               Chromosome.Location = Chromosome_Location,
+                               ID = NULL, SPOT_ID = NULL, Description = NULL) %>%
           rename(LogFC = SpaceVsGround, Platform_ORF = CGD_Systematic_Name)
 
 
 write.csv(final.tT, file = "datasets/GSE50881_Calb/GSE50881.csv")
 
 
-extractMetaData(gse_groups = list(list(GSE = gse[,c(1,3,5,7)]), list(GSE = gse[,c(2,4,6,8)])), microgravity_type = M.TYPE$SPACEFLOWN, 
+extractMetaData(gse_groups = list(list(GSE = gse[,c(1,3,5,7)]), list(GSE = gse[,c(2,4,6,8)])), microgravity_type = M.TYPE$SPACEFLOWN,
                 filename = "datasets/GSE50881_Calb/GSE50881_meta", metaLabels = c("dye_swap1", "dye_swap2"), strain = "SC5413")

scripts/R/DEA/GSE64468.R

@@ -1,5 +1,19 @@
+#License
+
+# © Copyright 2020 iGEM Concordia, Maher Hassanain, Benjamin Clark, Hajar Mouddene, Grecia Orlano
+# This file is part of AstroBio.
+# AstroBio is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or any later version.
+# AstroBio is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+# You should have received a copy of the GNU General Public License
+# along with AstroBio.  If not, see <https://www.gnu.org/licenses/>.
+
 ###GSE64468 YEAST MICROARRAY
-#BENJAMIN CLARK 
+#BENJAMIN CLARK
 
 library(GEOquery)
 library(Biobase)