File S3 for Rounds et al., 2021, Genetics.

Below are custom scripts, written in either R or PRISM, generated to produce, analyze, or visualize data for the above article and associated figures, tables, supplemental material, and database accessions. Scripts are titled and bracketed by lines of hyphens. Many are well-annotated with informative in-line comments. Notably, all scripts are included as-is, and may contain unnecessary code chunks.

--------------------------------------------------------------------------------
R SCRIPTS	R SCRIPTS	R SCRIPTS	R SCRIPTS	R SCRIPTS
--------------------------------------------------------------------------------

Script Title: Combining ANOVA Output Files from PRISM

Script Type: R Script

Script Purpose: To iterate through and combine information from .txt files containing PRISM results of gene-by-gene one-way ANOVA analyses of the 5,760 genes in the RIP-Seq testable set. These ANOVAs produced two .txt files per gene, or 11,520 .txt files in total; this script combines data from all of these into a single table to enable further analysis.

Original File Name: “Combing ANOVA Output Files from PRISM - for '20-8-20, ALL12WFX Inps, ForXRIP Cnts Gr 10' - Genes 1-5760.R”

Script:
library(dplyr)
#The dplyr library contains the function bind_rows, which will append two data frames vertically regardless of
#whether the data frames match in column number (it will add NAs as needed). I believe this understanding is
#correct, check if necessary.

#library(gtools)
#The gtools library contains the function mixedsort, which allows listing files in alphanumeric order
#(i.e. "Drug 50mg" listed before "Drug 100mg") and without respect to case.

setwd("D:/Lab PC/R Scripts/Combine PRISM ANOVA Output/20-8-20, ALL12WFX Inps, ForXRIP Cnts Gr 10")
getwd()
list.files()

FileList_With_Extensions = list.files()
FileList_Without_Extensions = gsub(pattern = ".txt$", "", FileList_With_Extensions)
order(FileList_Without_Extensions)

FileList = sort(FileList_Without_Extensions)
FileList

FileListLength = length(list.files())

#########

#Proof of principle (PoP)
df_Summary_ANOVA = read.delim("_Ordinary one-way ANOVA of Ephrin.txt", header = FALSE, sep= "\t")

df_Summary_ANOVA

df_MultiComp_ANOVA = read.delim("_Ordinary one-way ANOVA of Ephrin-1.txt", header = FALSE, sep = "\t")

df_MultiComp_ANOVA

df_ANOVA_Combo = bind_rows(df_Summary_ANOVA, df_MultiComp_ANOVA)

df_ANOVA_Combo

PoP_gene_name = as.character(df_ANOVA_Combo[2,2])
PoP_ANOVA_F = as.numeric(as.character(df_ANOVA_Combo[6,2]))
PoP_ANOVA_p = as.numeric(as.character(df_ANOVA_Combo[7,2]))
PoP_total_num_values = as.numeric(as.character(df_ANOVA_Combo[31,2]))
PoP_FvsW_DunnettVal = as.numeric(as.character(df_ANOVA_Combo[42,8]))
PoP_FvsW_DunAdjp = as.numeric(as.character(df_ANOVA_Combo[38,6]))
PoP_XvsW_DunnettVal = as.numeric(as.character(df_ANOVA_Combo[43,8]))
PoP_XvsW_DunAdjp = as.numeric(as.character(df_ANOVA_Combo[39,6]))


########

#Loop testing
#psuedocode: for length of list.files, if odd num, do steps in proof of principle section. if even num, skip.

#Note: %% is the modulo division operator in R. That is, it returns the remainder leftover from the division operator / .
#Modulo division is an efficient way to determine whehter a number is even or odd.

#Generate the Tally_df, a blank data frame to which per gene ANOVA info will be appended gene-by-gene.

Tally_df = data.frame(gene_name = character(),
                      ANOVA_F = numeric(), 
                      ANOVA_p = numeric(),
                      total_num_values = numeric(),
                      FvsW_DunnettVal = numeric(),
                      FvsW_DunAdjp = numeric(),
                      XvsW_DunnettVal = numeric(),
                      XvsWDunAdjp = numeric(),
                      stringsAsFactors = FALSE)

Tally_df
str(Tally_df)
Tally_df$gene_name[1]

Tally_df_rownum = 0

#This loop expects the FileList is entirely ANOVA output tables from PRISM. The loop expects these files to be
#a list of file pairs, with each pair containing (in descending order)
#the overall and the multicomparision ANOVA output tabs from PRISM for a given gene.

#########SEE BELOW
#!!If FileList deviates in any way from the above format, this loop will not produce the expected output!!
#########SEE ABOVE


for (FilePosition in 1:FileListLength) {
  if (FilePosition %% 2 == 1) {
  #print(paste0("Loop Position = ", FilePosition, " (Odd)"))
   
  df_Summary_ANOVA = read.delim(paste0(FileList[FilePosition],".txt"), header = FALSE, sep= "\t")
  
  df_Summary_ANOVA
  
  df_MultiComp_ANOVA = read.delim(paste0(FileList[FilePosition+1],".txt"), header = FALSE, sep = "\t")
  
  df_MultiComp_ANOVA
  
  df_ANOVA_Combo = bind_rows(df_Summary_ANOVA, df_MultiComp_ANOVA)
  
  df_ANOVA_Combo
  
  gene_name = as.character(df_ANOVA_Combo[2,2])
  ANOVA_F = as.numeric(as.character(df_ANOVA_Combo[6,2]))
  ANOVA_p = as.numeric(as.character(df_ANOVA_Combo[7,2]))
  total_num_values = as.numeric(as.character(df_ANOVA_Combo[31,2]))
  FvsW_DunnettVal = as.numeric(as.character(df_ANOVA_Combo[42,8]))
  FvsW_DunAdjp = as.numeric(as.character(df_ANOVA_Combo[38,6]))
  XvsW_DunnettVal = as.numeric(as.character(df_ANOVA_Combo[43,8]))
  XvsW_DunAdjp = as.numeric(as.character(df_ANOVA_Combo[39,6]))
  
  new_info_vector = c(gene_name, ANOVA_F, ANOVA_p, total_num_values,
                      FvsW_DunnettVal, FvsW_DunAdjp,
                      XvsW_DunnettVal, XvsW_DunAdjp)
  
  Tally_df_rownum = Tally_df_rownum + 1 
  
  Tally_df[Tally_df_rownum,] = new_info_vector
  
  #print(paste0("Current row num = " , Tally_df_rownum))
  
  #print("Current row vector = ")
  #print(new_info_vector)
  
  #print("Current dataframe = ")
  #print(Tally_df)
  
  }
  else if (FilePosition %% 2 == 0) {
    #print(paste0("Loop Position = ", FilePosition, " (Even)"))
  }
  else{
    print("Unexpected error, FilePosition apparently neither odd nor even")
  }
}


#Step up in file hierarchy to set new working directory, write Tally_df to 
#a tab-delimited text output file

setwd("D:/Lab PC/R Scripts/Combine PRISM ANOVA Output")
getwd()
list.files()

write.table(Tally_df, 
            file = "ANOVA Output Stats for '20-8-20, ALL12WFX Inps, ForXRIP Cnts Gr 10' - Genes 1-5760.txt", 
            sep = "\t",
            row.names = FALSE)

#Goal = output a data frame with gene names and stats of interest (esp. p-values for overall ANOVA and multi. comps)
#to then combine manually in Excel with Norm%Inp sheets
#(plenty of ways to do this automatically, but I think I'd rather do it manually and quickly and in
#clear view than read that particular Norm%Inp Excel sheet into R, combine, and output again.)
#Note added JCR 20-8-6
--------------------------------------------------------------------------------

Script Title: Hypergeometric Test

Script Type: R Script

Script Purpose: To test for statistical significance of the overlap between lists of Nab2-associated transcripts and Atx2-associated transcripts.

Original File Name: “hypergeometric_test_calc_Updated w RIP-Seq, SignifEnr ANOVA Gene Lists 20-9-14.R”

Script:


library(stats)

#source = https://stats.stackexchange.com/questions/16247/calculating-the-probability-of-gene-list-overlap-between-an-rna-seq-and-a-chip-c?rq=1

#For Atx2 targets to overlap with Nab2 targets as defined by "SignifEnr, ANOVADun" Lists, as of 20-9-14

num_successes_sample = 28
sample_size = 103
num_successes_pop = 141
pop_size = 5760

num_fails_pop = pop_size - num_successes_pop

phyper(num_successes_sample-1, num_successes_pop, num_fails_pop, sample_size, lower.tail = F)

#For Nab2 targets to overlap with Atx2 targets as defined by "SignifEnr, ANOVADun" Lists, as of 20-9-14

num_successes_sample = 28
sample_size = 141
num_successes_pop = 103
pop_size = 5760

num_fails_pop = pop_size - num_successes_pop

phyper(num_successes_sample-1, num_successes_pop, num_fails_pop, sample_size, lower.tail = F)

#For Atx2 targets to overlap with dNab2 targets

num_successes_sample = 711
sample_size = 1253
num_successes_pop = 1393
pop_size = 9311

num_fails_pop = pop_size - num_successes_pop

phyper(num_successes_sample-1, num_successes_pop, num_fails_pop, sample_size, lower.tail = F)

#For dNab2 targets to overlap with Atx2 targets


num_successes_sample = 711
sample_size = 1411
num_successes_pop = 1244
pop_size = 9296

num_fails_pop = pop_size - num_successes_pop

phyper(num_successes_sample-1, num_successes_pop, num_fails_pop, sample_size, lower.tail = F)
--------------------------------------------------------------------------------

Script Title: Prep “PRISM RenameDataTables”

Script Type: R Script

Script Purpose: Due to memory constraints, PRISM 8 cannot in a single file hold and analyze via one-way ANOVA the 5,760 individual data tables represented by the RIP-Seq testable set. To overcome this limitation, the testable set was analyzed in batches, separating the single set into twelve files of 480 genes each, listed alphabetically. In each of twelve PRISM files, an original single data table of 480 genes was separated into 480 individual data tables for ANOVA analysis (see PRISM script “Loop to Split RIP-Seq Genes into Individual Data Tables” below). Once generated, each data table needed to be renamed with the gene symbol it contained, such that later ANOVA output would be associated with the appropriate gene symbol (instead of, for example, “Data Table 125”). This renaming was accomplished with a PRISM script, also included in this file, that iterated from table to table, renaming appropriately. However, PRISM scripts are limited and cannot read and use variable information within a data table for this renaming purpose. Instead, each of 12 PRISM files needed a unique script for table renaming that lists all gene names explicitly; the text of each these scripts was generated by one of twelve nearly identical R scripts. The script below is representative of those twelve R scripts. To reproduce the remaining eleven, replace references in this script to genes 1-480 (e.g. loop parameters, file names) to another gene set of interest (e.g. genes 481-960 or genes 961-1440).

Original File Name: “Prep PRISM - RenameDataTables - for 'ALL12 Genes w Detected Expression in all 12 Inps, ForXRIP Cnts Gr 10 - 20-8-17' - Genes 1-480.R”

Script:
setwd("D:/Lab PC/R Scripts/Prepare PRISM Script for many One-way ANOVAs")
getwd()
list.files()

PRISMGenes = read.delim("Norm_counts_RIP_CY+PUT_CY -(G267, p + G231, p) - Sheets and FBgns for ALL12 Genes w Detected Expression in all 12 Inps, ForXRIP Cnts Gr 10 - 20-8-17.txt", header = TRUE, sep="\t")

str(PRISMGenes)
PRISMGenes$X

PRISMGenes$Gene.Name.As.Char = as.character(PRISMGenes$X)

head(PRISMGenes)

AlphabeticalPRISMGenes = PRISMGenes[order(PRISMGenes$Gene.Name.As.Char),]

str(AlphabeticalPRISMGenes)
head(AlphabeticalPRISMGenes)
tail(AlphabeticalPRISMGenes)

numrows = length(AlphabeticalPRISMGenes$Gene.Name.As.Char)
PRISMScriptVector = as.character()
DataTableNum = 3

for (CurrentRow in 1:480) {
  DataTableNum = DataTableNum + 1
  NewLines = paste0("GoTo D ", DataTableNum, "\n",
                    "SetSheetTitle ",AlphabeticalPRISMGenes$Gene.Name.As.Char[CurrentRow], "\n")
  PRISMScriptVector  = paste0(PRISMScriptVector, NewLines)
}

print(PRISMScriptVector)
write(PRISMScriptVector, file="RenameDataTables PRISM Script for 'OneWay ANOVAs for 'ALL12 Genes w Detected Expression in all 12 Inps, ForXRIP Cnts Gr 10 - 20-8-17' - Genes 1-480.txt")
--------------------------------------------------------------------------------

Script Title: RIP-Seq Fold Enrichment Scatter Plot

Script Type: R Script

Script Purpose: To generate scatter plots visualizing the degree and statistical significance of transcript enrichment (and thus RBP-association) by Nab2 and Atx2 RIP-Seqs. All points above a statistical significance threshold are color-coded, and points corresponding to specific transcripts of interest are labeled. The x-axis displays log2(fold enrichment) (i.e. normalized IP/Input values) and the y-axis displays -log10(Dunnett Adjusted p) (i.e. the p-value resulting from our statistical significance testing pipeline). Notably, only transcripts with a positive fold enrichment value are displayed, as the x-axis minimum is set to 0. Thus, not all 5,760 transcripts included in the testable set are displayed on the plots generated by this script; this can be changed by changing the x-axis minimum.  The script below specifically generates the scatter plot included in the article as Figure 4D and displays Nab2 RIP-Seq results with five points labeled. Reproduce the scripts to generate other scatter plots in the article by making minor changes as appropriate (e.g. to axis text, point color, and point labels).

Original File Name: “Volcano Plot - W vs F, Norm PercInp from 'Norm_counts_RIP+PUT...267...231...ALL12...ForXRIP Cnts Gr 10...20824 OneWayANOVAs...' - 20-9-29-Fig5Tscrpts.R”

Script:
setwd("D:/Lab PC/R Scripts/RIP-Seq Enrichment, Volcano Plots")
getwd()
list.files()

library(ggplot2)
library(ggrepel)

#"PGenes" = RIP-Seq, IP and InPut Genes, DESeq2 Output w One-Way ANOVAs for each gene
PGenes = read.delim("Norm_counts_RIP_CY+PUT_CY -(G267, p + G231, p) - Sheets and FBgns for ALL12 Genes w Detected Expression in all 12 Inps, ForXRIP Cnts Gr 10 - 20-8-17 - 20824 OneWay ANOVAs Added_Edited,ParedDown.txt", 
                    header = TRUE,
                    sep="\t")

head(PGenes)
tail(PGenes)
str(PGenes)

#Create new variables by converting variables imported as factors in data frame into 
#either characters or numerics as needed.

PGenes$gene_nameAsChar = as.character(PGenes$Gene.Name)

PGenes$PercentInpW_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.W.AVG))
PGenes$PercentInpF_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.F.AVG))
PGenes$PercentInpX_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.X.AVG))

PGenes$Log2PercentInpW_AsNumeric = log(PGenes$PercentInpW_AsNumeric, 2)
PGenes$Log2PercentInpF_AsNumeric = log(PGenes$PercentInpF_AsNumeric, 2)
PGenes$Log2PercentInpX_AsNumeric = log(PGenes$PercentInpX_AsNumeric, 2)

PGenes$NormPercentInpW_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.W.Norm.AVG))
PGenes$NormPercentInpF_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.F.Norm.AVG))
PGenes$NormPercentInpX_AsNumeric = as.numeric(as.character(PGenes$Percent.Input.X.Norm.AVG))

str(PGenes)
PGenes[PGenes$gene_nameAsChar =="me31B",]

#Calculate the number of genes: 
#1) with Percent Input F/W >1.5, FRIP Counts > 10 ("ALLF")
#2) with Percent Input X/W >1.5, XRIP Counts > 10 ("ALLX")
#Convert these sums to characters and assign their values to variables.

NumEnrInALLF=as.character(sum(
  PGenes$NormPercentInpF_AsNumeric > 1 & 
  PGenes$FvsW.DunAdjp < 0.05, 
  na.rm=TRUE))

NumEnrInALLX=as.character(sum(
  PGenes$NormPercentInpX_AsNumeric > 1 & 
  PGenes$XvsW.DunAdjp < 0.05, 
  na.rm=TRUE))

#Create, set, and count "Enrichment Type" for:
#1) BOTH Percent Input F/W and X/W >1, FandX_vsW DunAdjp < 0.05
#2) ONLY Percent Input F/W > 1, FvsW.DunAdjp < 0.05 ; X below one or both criteria or FoldEnr=NA
#3) ONLY Percent Input X/W > 1 , XvsW.DunAdjp < 0.05 ; F below one or both criteria or FoldEnr=NA
#4) NEITHER, w Percent Input F/W and X/W < 1, and/or FandX_vsW DunAdjp < 0.05
 
#After these steps:
#A)these labels added to appropriate data frame rows and 
#B)number of each label (as a character) assigned to an appropriate variable.

PGenes$EnrType = as.character("NA")

#BOTH - Set and count Enrichment Type - BOTH
PGenes$EnrType[
              PGenes$NormPercentInpF_AsNumeric > 1 & PGenes$FvsW.DunAdjp < 0.05 &
              PGenes$NormPercentInpX_AsNumeric > 1 & PGenes$XvsW.DunAdjp < 0.05] = "BOTH"

NumEnrInBOTHFandX = as.character(nrow(PGenes[PGenes$EnrType=="BOTH",]))

#ONLYF - Set and count Enrichment Type - ONLYF
PGenes$EnrType[
             ((PGenes$NormPercentInpF_AsNumeric > 1 & PGenes$FvsW.DunAdjp < 0.05) 
              &
             (PGenes$NormPercentInpX_AsNumeric < 1 | is.na(PGenes$XvsW.DunAdjp) | 
              PGenes$XvsW.DunAdjp >= 0.05))] = "ONLYF"

NumEnrInONLYF = as.character(nrow(PGenes[PGenes$EnrType=="ONLYF",]))

#ONLYX - Set and count Enrichment Type - ONLYX
PGenes$EnrType[
            ((PGenes$NormPercentInpX_AsNumeric > 1 & PGenes$XvsW.DunAdjp < 0.05) 
             &
            (PGenes$NormPercentInpF_AsNumeric < 1 | is.na(PGenes$FvsW.DunAdjp) | 
             PGenes$FvsW.DunAdjp >= 0.05))] = "ONLYX"
NumEnrInONLYX = as.character(nrow(PGenes[PGenes$EnrType=="ONLYX",]))

#NEITHER - Set and count Enrichment Type - NEITHER
PGenes$EnrType[
           ((PGenes$NormPercentInpF_AsNumeric < 1 | is.na(PGenes$FvsW.DunAdjp) |
               PGenes$FvsW.DunAdjp >= 0.05) 
            & 
            (PGenes$NormPercentInpX_AsNumeric < 1 |is.na(PGenes$XvsW.DunAdjp) |
               PGenes$XvsW.DunAdjp >= 0.05))] = "NEITHER"

NumEnrInNEITHER = as.character(nrow(PGenes[PGenes$EnrType=="NEITHER",]))

#Test EnrType contents
PGenes[PGenes$EnrType=="ONLYF",1]
str(PGenes$EnrType)
write.table(PGenes[PGenes$EnrType=="BOTH",], file = "PGenes EnrinBOTH 20-8-24", sep = "\t")
write.table(PGenes[PGenes$EnrType=="ONLYF",], file = "PGenes EnrinONLYF 20-8-24", sep = "\t")

#Refer to previous Volcano Plot scripts for examples of choosing genes by name to be labelled on final plot.

#Generate Point Color (PtColor) variable. Set color for each gene based on EnrType value (can add others, e.g. gene name)

ColorDEFAULT = "gray"
ColorBOTH = "lightseagreen"
ColorONLYF = "lightseagreen"
ColorONLYX = "gray"
#ColorBOTH = "midnightblue"
#ColorONLYX = "maroon"
#ColorBOTH = "tan4"
#ColorONLYF = "forestgreen"
#ColorONLYX = "darkorange1"
#other color options: "lightsea green, 
#                       violetred series, slateblue series, darkslateblue, darkslategrey/gray, 
#                       darkorchid series, navy, midnight blue

PGenes$PtColor = ColorDEFAULT
PGenes$GraphOrder = 1

PGenes$PtColor[PGenes$EnrType=="BOTH" ] = ColorBOTH
PGenes$GraphOrder[PGenes$EnrType=="BOTH" ] = 4

PGenes$PtColor[PGenes$EnrType=="ONLYF" ] = ColorONLYF
PGenes$GraphOrder[PGenes$EnrType=="ONLYF" ] = 3

PGenes$PtColor[PGenes$EnrType=="ONLYX" ] = ColorONLYX
PGenes$GraphOrder[PGenes$EnrType=="ONLYX" ] = 2

str(PGenes)
PGenes[PGenes$PtColor==ColorBOTH,]
nrow(PGenes[PGenes$PtColor==ColorBOTH,])

#Give unique color to a single point

#SGenesClean[SGenes$gene_nameAsChar =="Nab2",]
#SGenes$PtColor[SGenes$gene_nameAsChar=="Nab2"] = "green4"

#Generate PlotLabel, to be called while graphing in order to label only points of interest
#Setting PlotLabel to an empty character vector rather than NA will confer an unseen label to every point by
#default. This way, geom_text_repel will pad around every point when requested, rather than only points with
#visible labels. See ?help for geom_text_repel for more info.

PGenes$PlotLabel = ""
PGenes$PlotLabel[PGenes$gene_nameAsChar =="Arpc2"] = "Arpc2"
PGenes$PlotLabel[PGenes$gene_nameAsChar =="side-II"] = "side-II"
PGenes$PlotLabel[PGenes$gene_nameAsChar =="Cpsf160"] = "Cpsf160"
PGenes$PlotLabel[PGenes$gene_nameAsChar =="drk"] = "drk"
PGenes$PlotLabel[PGenes$gene_nameAsChar =="me31B"] = "me31B"

#SGenes$PlotLabel[SGenes$PtColor == "forestgreen"] = SGenes$gene_nameAsChar[SGenes$PtColor=="forestgreen"]
#SGenes$PlotLabel[SGenes$PtColor == "green4"] = SGenes$gene_nameAsChar[SGenes$PtColor=="green4"]

#Create "clean" data frames, which include only genes which were assigned a normalized Percent Input W (versus a #DIV/0! or NA).
#In many cases, these genes were not detected at least one W.INP, meaning a DIV/0 was assigned to the corresponding %Input calculation.
#These genes are excluded from the analysis, such that only genes with detectable expression in all 4 controls inputs are considered.
#This should increase confidence in results, eliminate genes which are just expressed in F or X and not W, and shift focus to more reliably expressed, less noisy genes.
#Importantly, if this step is skipped,
#any points with an NA for x or y will not be graphed by ggplot2.
#Thus, this step isn't necessary in this version of the script (5-1-20), but these genes should not be considered
#enriched or non-enriched, at least without new parameters/manual inspection,
#so removing them is safer for future graph functions/calculations that may not automatically remove them.

PGenesClean=subset(PGenes, !is.na(NormPercentInpW_AsNumeric),select = Gene.Name:PlotLabel)
str(PGenesClean)
head(PGenesClean, 20)
tail(PGenesClean)

str(PGenesClean$PlotLabel)
length(PGenesClean$PlotLabel)

#Create new data frames, ordering the GenesClean data frames by GraphOrder followed by Gene.Name
#My understanding is that ggplot2 draws points on a graph in descending order through a data frame.
#Therefore, in order to bring colored points and associated labels to the front, they should be drawn last
#Using a data frame ordered in this way accomplishes this drawing order.

OrderedPGenesClean = PGenesClean[order(PGenesClean$GraphOrder,PGenesClean$Gene.Name),]
str(OrderedPGenesClean)
head(OrderedPGenesClean)
tail(OrderedPGenesClean)
OrderedPGenesClean[OrderedPGenesClean$Gene.Name =="me31B",]

#OrdPGenesClnFCntsGr10 = subset(OrderedPGenesClean, 
                                      #OrderedPGenesClean$F.CY.RIP.1.4..Avg.Count. > 10,
                                      #select = Gene.Name:PlotLabel)

#Generate character variables describing the size of the final data frame and the actual number of points to be plotted 
#(i.e. the whole data frame is defined by the number of genes with a Norm.PercentInpW value able to be calculated and with FandXRIP Cnts Gr 10,
#while the number of points to be graphed are also required to have values for both the x- and y-axis (a handful in the final df won't necessarily meet this, almost all will))
#NUMBER OF ROWS REMOVED BY GGPLOT2 FOR GEOM_POINT SHOULD EQUAL DIFFERENCE BETWEEN NumGenesInFinalDataFrame AND NumGenesMetGraphingCriteria
#NumGenesInFinalDataFrame = prettyNum(nrow(OrdPGenesClnFCntsGr10),big.mark = ",")

#NumGenesMetGraphingCriteria = prettyNum(
  #(nrow(OrdPGenesClnFCntsGr10[
    #!is.na(OrdPGenesClnFCntsGr10$PercentInpW_AsNumeric) &
    #!is.na(OrdPGenesClnFCntsGr10$PercentInpF_AsNumeric),])), big.mark = ",")

NumGenesInFinalDataFrame = prettyNum(nrow(OrderedPGenesClean),big.mark = ",")

NumGenesMetGraphingCriteria = prettyNum(
  (nrow(OrderedPGenesClean[
      !is.na(OrderedPGenesClean$PercentInpW_AsNumeric) &
      !is.na(OrderedPGenesClean$PercentInpF_AsNumeric),])), 
  big.mark = ",")

###CLEAN THIS UP!! 3 DIFFERENT WAYS OF TESTING LINEAR REGRESSION MODELING ARE USED BELOW, CLEAN UP TO JUST ONE
#TESTING WAS REQUIRED B/C OF TEMP. DISAGREEMENT BETWEEN geom_smooth's lm line and the line predicted by the
#lm function outside of ggplot2. The source of the discrepancy looks simple - I wasn't calculating the right line from the output of the outside lm function
#NAs are removed from both internal and external lm function, so this didn't need to be done to bring into agreement.
#Consider keeping step (w/ shorter variable names) anyway, as it makes adding predicted vals from linear reg to plotted data frame possible if
#both same length (i.e. have had the 5 NA's removed)
#Additionally, this means the R-squared value calc'ed outside ggplot2 can be accurately reported on graph associated with the lm drawn by geom_smooth, if desired.
#This may not be necessary though, as perfing lm outside ggplot and then adding appropriate vals to df/line to plot may prove best, as gives easy access to other lm output (e.g. R-squared values)
#JCR 20-5-1

#Linear Regression Calcs
cor(OrderedPGenesClean$PercentInpW_AsNumeric,
    OrderedPGenesClean$PercentInpF_AsNumeric, use = "pairwise.complete.obs")

    #lm formula format = y~x
LinearRegModel = lm(PercentInpF_AsNumeric ~ PercentInpW_AsNumeric, OrderedPGenesClean)
print(LinearRegModel)
summary(LinearRegModel)
summary(LinearRegModel)$r.squared
R_Squared_Char = as.character(round(summary(LinearRegModel)$r.squared, digits=2))
predict(LinearRegModel)

OrderedPGenesClean$LinearRegPredictedVals[
  !is.na(OrderedPGenesClean$PercentInpW_AsNumeric) &
  !is.na(OrderedPGenesClean$PercentInpF_AsNumeric)] = predict(LinearRegModel)

str(OrderedPGenesClean)

OrderedPGenesClean$Log2NormPercentInpF = log(OrderedPGenesClean$NormPercentInpF_AsNumeric, 2)
OrderedPGenesClean$Log2NormPercentInpX = log(OrderedPGenesClean$NormPercentInpX_AsNumeric, 2)
OrderedPGenesClean$NegLog10.FvsW.DunAdjp = -log(OrderedPGenesClean$FvsW.DunAdjp, 10)
OrderedPGenesClean$NegLog10.XvsW.DunAdjp = -log(OrderedPGenesClean$XvsW.DunAdjp, 10)

str(OrderedPGenesClean)

#Plotting Variables
xmaxVar = 3  
ymaxVar = 4

#ENSURE CITATION of the authors of ggplot2 AND ggrepel. ggrepel is not included in the base ggplot2, and is
#responsible for data labels not overlapping & being called out with lines if placed far away from associated point.
library(ggplot2)
ggplot(OrderedPGenesClean, aes(x=Log2NormPercentInpF, y=NegLog10.FvsW.DunAdjp)) + 
  geom_point(col=OrderedPGenesClean$PtColor, size=4, shape=19)+
  #geom_point(col = "gray", size=4, shape=19)+
  geom_text_repel(aes(label=OrderedPGenesClean$PlotLabel),
                  fontface = "bold", size = 5,
                  box.padding = 0.75,
                  point.padding = 0.3,
                  min.segment.length = 0, nudge_x = 0.1, nudge_y = 0.1,
                  seed = 0) +
  #geom_smooth(method = "lm", formula = y~x, se = FALSE, col="black", linetype = "longdash", size = 1.5)+
  labs(x=bquote(bold("Log2(Nab2 Fold Enrichment (Norm. IP/Input))")), 
       y=bquote(bold("-log10(DunAdjp)")), 
       title="RIP-Seq IP/Input", 
       subtitle = "Heads, Pan-neuronal Control vs. Nab2-FLAG vs. Atx2-3xFLAG") +
  #geom_segment(x=0,y=0,xend=xmaxVar*2,yend=ymaxVar*2, col="black",linetype = "longdash", size =1.5)+
  #geom_hline(size = 0.5, yintercept = 1.30102999566398 ) +
  #geom_segment(size = 0.5, x=1.5, xend = 1.5, y=0.25, yend=1.5 )+
  #geom_segment(size = 0.5, x=1.5, xend = 4, y=1.5, yend=1.5 )+
  #geom_segment(size = 0.5, x=0.25, xend = 1.5, y=1.5, yend=1.5 ) +
  #geom_segment(size = 0.5, x=1.5, xend = 1.5, y=1.5, yend=4 ) +
  #geom_segment(size=1.5, x=-3, xend=30, y=-3, yend=30)+
  #geom_segment(size=1.5, x=0, y =0.3966, xend=5, yend=3.4941, col="green")+
  #geom_line(aes(y=OrdPGenesClnFXCntsGr10$LinearRegPredictedVals), col="blue", size = 1.5)+
  #geom_point(col="gray", size=4, shape=19)+
  theme(text = element_text(family = "sans"),
        panel.background = element_rect(fill = "white" ), 
        axis.line = element_line(size=2),
        axis.ticks = element_line(size=2),
        axis.ticks.length = unit(15,"points"),
        axis.text = element_text(face = "bold", size=40, color = "black"),
        axis.text.x = element_text(margin = margin(10,0,0,0)),
        axis.text.y = element_text(margin = margin(0,5,0,0)),
        axis.title = element_text(face = "bold", size=40),
        plot.title = element_text(size=16)) +
  #annotate("text", x=0.65*xmaxVar, y=0.1*ymaxVar, fontface="bold", size=7, col=ColorONLYF, label = paste("Enriched in F ONLY", NumEnrInONLYF, sep="\n")) +
  #annotate("text", x=0.15*xmaxVar, y=0.65*ymaxVar,fontface="bold", size=7, col=ColorONLYX, label = paste("Enriched in X ONLY", NumEnrInONLYX, sep="\n")) +
  #annotate("text", x=0.65*xmaxVar, y=0.65*ymaxVar, fontface="bold", size=7, col=ColorBOTH, label = paste("Enriched in BOTH", NumEnrInBOTHFandX, sep="\n")) +
  #annotate("text", x=0.94*xmaxVar, y=0.6*ymaxVar, fontface="bold", size=7, col="black", label = bquote(bold(atop("R"^2*"=",.(R_Squared_Char)))))+
  annotate("text", x=0.8*xmaxVar, y=0.9*ymaxVar, fontface="bold", size=7, col=ColorONLYF, label = paste("Enriched in F", NumEnrInALLF, sep="\n")) +
  annotate("text", x=0.8*xmaxVar, y=0.8*ymaxVar, fontface="bold", size=7, col=ColorDEFAULT, label = paste("Total Genes Tested for Enrichment", NumGenesMetGraphingCriteria, sep="\n")) +
  #annotate("text", x=0.90*xmaxVar, y=0.9*ymaxVar, fontface="bold", size=7, col="black",label = paste("Nab2-FLAG=","Control",sep="\n"), angle = 35)+
  #scale_x_continuous(breaks=c((1-xmaxVar),(1-(0.5*xmaxVar)),1,(1+(0.5*xmaxVar)),(1+xmaxVar)), expand = c(0,0))+
  #scale_y_continuous(breaks=c(0,0.25*ymaxVar,0.5*ymaxVar,0.75*ymaxVar,ymaxVar), expand = c(0,0))+
  #coord_cartesian(xlim = c((-1.05*xmaxVar),(1.05*xmaxVar)), ylim = c(0,ymaxVar+(ymaxVar*0.05)))
  #annotate("text", x=8, y=120, fontface="bold", size=4.5, label = paste("DEGs Up in Females:", NumUpDEGs, sep="\n")) +
  #annotate("text", x=-8, y=120,fontface="bold", size=4.5, label = paste("DEGs Down in Females:", NumDownDEGs, sep="\n"))+
  scale_x_continuous(breaks=c(-3,-2,-1,0,1,2,3))+
  scale_y_continuous(breaks=c(0,0.25*ymaxVar,0.5*ymaxVar,0.75*ymaxVar,ymaxVar), expand = c(0,0))+
  coord_cartesian(xlim = c(0,1.05*xmaxVar), ylim = c(0,ymaxVar+(ymaxVar*0.05)), expand = FALSE)


#For values used in tiffs labeled "Longer Axes" (on 6-5-18), use xlim = c(-7.5,7.5), ylim = c(0,300)
#For values used in tiffs without referecne to axis size, use xlim = c(-10,10), ylim = c(0,120) (Note added 9-4-19 based on values in "ALL DEGs Counted" version of this code)
#For values used in tiffs labeled "Small Axes", use xlim = c(-3,3), ylim = c(-2,20) (Note added 9-4-19 based on values in 5-16-19's version of this code)


#Methods of printing specific row(s) of a data frame. The variable defined here is a logical vector (of TRUEs and FALSEs)
#Only the rows corresponding to the poisition of TRUE in this array are printed in the second line.
#The third line is a more concise way of accomplishing a specific row call
Atx2Print = SGenes$test_idAsChar=="Atx2"
SGenes[Atx2Print,]
SGenes[SGenes$test_idAsChar=="Atx2",]
SGenes$PlotLabel
SGenes$gene_nameAsChar
SGenes$GoIAsChar=="Of interest"
?options

#Testing the is.na function. is.na returns (a matrix of?) 
#TRUE for NAs (the value; not "NA" as a string), FALSE for any other value.

#Therefore, !is.na returns (a matrix of?) 
#FALSE for NAs, (the value, not "NA" as a string) and TRUE for any other value.

AdjPValIsNA = is.na(SGenes$Adj..p.value..FDR.controlled.signif.)
AdjPValIsNA
tail(AdjPValIsNA, 200)

AdjPValIsNotNA = !is.na(SGenes$Adj..p.value..FDR.controlled.signif.)
AdjPValIsNotNA
tail(AdjPValIsNotNA, 200)

#Method for writing data frames to a tab-delimited text file. Especially useful for debugging
write.table(SGenesClean, file = "SGenes Clean Output DEBUG 6-4-18", sep = "\t")

x= count.fields("FE_P4 v FE_X3 - gene_exp_diff - 2-23-18.txt", sep="\t")
str(x)
--------------------------------------------------------------------------------
PRISM SCRIPTS	PRISM SCRIPTS	PRISM SCRIPTS	PRISM SCRIPTS	PRISM SCRIPTS
--------------------------------------------------------------------------------

Script Title: Loop to Split RIP-Seq Genes into Individual Data Tables 

Script Type: PRISM Script

Script Purpose: Following RIP-Seq, normalized IP/Input (i.e. Fold Enrichment) values were calculated for all 5,760 genes in the testable set and stored in a single table. However, PRISM 8 cannot perform one-way ANOVAs line-by-line in a single data table. Instead, an individual data table was required for each gene; each table would include a gene symbol and its associated normalized IP/Input values. This script generates these individual data tables one-by-one, at each iteration copying a new row from a single source data table containing values for 480 genes in the testable set. The testable set was subsetted in this way because, due to memory constraints, PRISM 8 cannot in a single file hold and analyze via one-way ANOVA the 5,760 individual data tables represented by the RIP-Seq testable set. To overcome this memory limitation, the testable set was analyzed in batches, separating the single testable set into twelve files of 480 genes each, listed alphabetically.

Original File Name: “Loop - Duplicate Template Table, Copy One Row Into It.pzc”

Script:
ForEach 480
GoTo D 2
Copy 1 10 %N 0
GoTo D 3
DuplicateDataTable
Paste 1 0
Next
--------------------------------------------------------------------------------

Script Title: Change All One-Way ANOVA Analysis Tabs, Summary Tab

Script Type: PRISM Script

Script Purpose: To set all PRISM ANOVA results tables to the Summary tab. PRISM 8 outputs results of one-way ANOVAs with multiple comparisons as two separate tabs, the Summary tab and the Multiple Comparisons tab. For further analysis of our ANOVA results, output data from both tabs for all genes needed to be collected, searched through, and combined (see “Combining ANOVA Output Files from PRISM” R script above). PRISM readily exports analysis results to .txt files in bulk, enabling this process of collection and combination. However, PRISM only exports in bulk tabs currently set as primary/viewed. Thus, we required short scripts to change the primary/viewed analysis tab for all 480 ANOVA results tables in each PRISM file. The script to change each results table to Summary tab view is shown below.

Original File Name: “Change All One-Way ANOVA Analysis Tabs to ANOVA Summary Tab.pzc”

Script:
GoTo R, 1
ForEach 480
GoTo V1
GoTo +
Next
--------------------------------------------------------------------------------
Script Title: Change All One-Way ANOVA Analysis Tabs, Multiple Comparisons Tab

Script Type: PRISM Script

Script Purpose: To set all PRISM ANOVA results tables to the Multiple Comparisons tab. PRISM 8 outputs results of one-way ANOVAs with multiple comparisons as two separate tabs, the Summary tab and the Multiple Comparisons tab. For further analysis of our ANOVA results, output data from both tabs for all genes needed to be collected, searched through, and combined (see “Combining ANOVA Output Files from PRISM” R script above). PRISM readily exports analysis results to .txt files in bulk, enabling this process of collection and combination. However, PRISM only exports in bulk tabs currently set as primary/viewed. Thus, we required short scripts to change the primary/viewed analysis tab for all 480 ANOVA results tables in each PRISM file. The script to change each results table to Multiple Comparisons tab view is shown below.

Original File Name: “Change All One-Way ANOVA Analysis Tabs to MultiComp Tab.pzc”

Script:
GoTo R, 1
ForEach 480
GoTo V2
GoTo +
Next
--------------------------------------------------------------------------------

Script Title: PRISM RenameDataTables

Script Type: PRISM Script

Script Purpose: Due to memory constraints, PRISM 8 cannot in a single file hold and analyze via one-way ANOVA the 5,760 individual data tables represented by the RIP-Seq testable set. To overcome this limitation, the testable set was analyzed in batches, separating the single set into twelve files of 480 genes each, listed alphabetically. In each of twelve PRISM files, an original single data table of 480 genes was separated into 480 individual data tables for ANOVA analysis (see PRISM script “Loop to Split RIP-Seq Genes into Individual Data Tables” above). Once generated, each data table needed to be renamed with the gene symbol it contained, such that later ANOVA output would be associated with the appropriate gene symbol (instead of, for example, “Data Table 125”). This renaming was accomplished with this PRISM script, which iterates from table to table, renaming appropriately. Notably, PRISM scripts are limited and cannot read and use variable information within a data table for this renaming purpose. Hence, each of 12 PRISM files needed a unique script for table renaming that lists all gene names explicitly. The script below is one of those twelve PRISM scripts and is representative of the rest. To reproduce the remaining eleven, replace gene symbols for testable set genes 1-480 in this script with symbols for genes in another batch of the testable set (e.g. genes 481-960 or genes 961-1440). Importantly, the text of each these twelve PRISM scripts was generated by one of twelve nearly identical R scripts (see “Prep “PRISM RenameDataTables”” above). 

Original File Name: “Genes 1-480 - RenameDataTables PRISM Script for 'OneWay ANOVAs for ALL12, ForXRIP Cnts Gr 10 - 20-8-17'.pzc”

Script:
GoTo D 4
SetSheetTitle 128up
GoTo D 5
SetSheetTitle 14-3-3epsilon
GoTo D 6
SetSheetTitle 14-3-3zeta
GoTo D 7
SetSheetTitle 18SrRNA-Psi:CR41602
GoTo D 8
SetSheetTitle 18w
GoTo D 9
SetSheetTitle 26-29-p
GoTo D 10
SetSheetTitle 28SrRNA-Psi:CR40596
GoTo D 11
SetSheetTitle 28SrRNA-Psi:CR40741
GoTo D 12
SetSheetTitle 28SrRNA-Psi:CR41609
GoTo D 13
SetSheetTitle 28SrRNA-Psi:CR45848
GoTo D 14
SetSheetTitle 28SrRNA-Psi:CR45851
GoTo D 15
SetSheetTitle 28SrRNA-Psi:CR45855
GoTo D 16
SetSheetTitle 28SrRNA-Psi:CR45859
GoTo D 17
SetSheetTitle 28SrRNA-Psi:CR45860
GoTo D 18
SetSheetTitle 2mit
GoTo D 19
SetSheetTitle 43709
GoTo D 20
SetSheetTitle 43710
GoTo D 21
SetSheetTitle 43712
GoTo D 22
SetSheetTitle 4E-T
GoTo D 23
SetSheetTitle 5-HT1A
GoTo D 24
SetSheetTitle 5-HT1B
GoTo D 25
SetSheetTitle 5-HT2A
GoTo D 26
SetSheetTitle 5-HT2B
GoTo D 27
SetSheetTitle 5-HT7
GoTo D 28
SetSheetTitle 5PtaseI
GoTo D 29
SetSheetTitle 7B2
GoTo D 30
SetSheetTitle 7SLRNA:CR32864
GoTo D 31
SetSheetTitle 7SLRNA:CR42652
GoTo D 32
SetSheetTitle a
GoTo D 33
SetSheetTitle A16
GoTo D 34
SetSheetTitle a6
GoTo D 35
SetSheetTitle Aac11
GoTo D 36
SetSheetTitle AANAT1
GoTo D 37
SetSheetTitle AANATL2
GoTo D 38
SetSheetTitle Aatf
GoTo D 39
SetSheetTitle aay
GoTo D 40
SetSheetTitle ab
GoTo D 41
SetSheetTitle ABCA
GoTo D 42
SetSheetTitle ABCB7
GoTo D 43
SetSheetTitle Abi
GoTo D 44
SetSheetTitle Abl
GoTo D 45
SetSheetTitle Abp1
GoTo D 46
SetSheetTitle Ac13E
GoTo D 47
SetSheetTitle Ac3
GoTo D 48
SetSheetTitle Ac76E
GoTo D 49
SetSheetTitle Ac78C
GoTo D 50
SetSheetTitle ACC
GoTo D 51
SetSheetTitle AcCoAS
GoTo D 52
SetSheetTitle Ace
GoTo D 53
SetSheetTitle Acer
GoTo D 54
SetSheetTitle Acf
GoTo D 55
SetSheetTitle Achl
GoTo D 56
SetSheetTitle Ack
GoTo D 57
SetSheetTitle Ack-like
GoTo D 58
SetSheetTitle Acn
GoTo D 59
SetSheetTitle Acon
GoTo D 60
SetSheetTitle Acox57D-d
GoTo D 61
SetSheetTitle Acox57D-p
GoTo D 62
SetSheetTitle Acp1
GoTo D 63
SetSheetTitle Acph-1
GoTo D 64
SetSheetTitle Acsl
GoTo D 65
SetSheetTitle Act42A
GoTo D 66
SetSheetTitle Act57B
GoTo D 67
SetSheetTitle Act5C
GoTo D 68
SetSheetTitle Act79B
GoTo D 69
SetSheetTitle Act87E
GoTo D 70
SetSheetTitle Actbeta
GoTo D 71
SetSheetTitle Actn
GoTo D 72
SetSheetTitle Ada2b
GoTo D 73
SetSheetTitle Ada3
GoTo D 74
SetSheetTitle AdamTS-A
GoTo D 75
SetSheetTitle Adar
GoTo D 76
SetSheetTitle ADD1
GoTo D 77
SetSheetTitle AdenoK
GoTo D 78
SetSheetTitle Adf1
GoTo D 79
SetSheetTitle Adgf-A
GoTo D 80
SetSheetTitle Adgf-D
GoTo D 81
SetSheetTitle Adi1
GoTo D 82
SetSheetTitle AdipoR
GoTo D 83
SetSheetTitle Adk1
GoTo D 84
SetSheetTitle Adk2
GoTo D 85
SetSheetTitle adp
GoTo D 86
SetSheetTitle AdSL
GoTo D 87
SetSheetTitle AdSS
GoTo D 88
SetSheetTitle Aduk
GoTo D 89
SetSheetTitle Ady43A
GoTo D 90
SetSheetTitle Aef1
GoTo D 91
SetSheetTitle aft
GoTo D 92
SetSheetTitle Afti
GoTo D 93
SetSheetTitle AGBE
GoTo D 94
SetSheetTitle ago
GoTo D 95
SetSheetTitle AGO1
GoTo D 96
SetSheetTitle AGO2
GoTo D 97
SetSheetTitle Ahcy
GoTo D 98
SetSheetTitle AhcyL1
GoTo D 99
SetSheetTitle AhcyL2
GoTo D 100
SetSheetTitle AIF
GoTo D 101
SetSheetTitle AIMP2
GoTo D 102
SetSheetTitle AIMP3
GoTo D 103
SetSheetTitle Akap200
GoTo D 104
SetSheetTitle AkhR
GoTo D 105
SetSheetTitle akirin
GoTo D 106
SetSheetTitle Akt1
GoTo D 107
SetSheetTitle AlaRS
GoTo D 108
SetSheetTitle AlaRS-m
GoTo D 109
SetSheetTitle Alas
GoTo D 110
SetSheetTitle alc
GoTo D 111
SetSheetTitle Ald
GoTo D 112
SetSheetTitle Aldh
GoTo D 113
SetSheetTitle Aldh-III
GoTo D 114
SetSheetTitle Alg1
GoTo D 115
SetSheetTitle Alg11
GoTo D 116
SetSheetTitle Alg2
GoTo D 117
SetSheetTitle Alh
GoTo D 118
SetSheetTitle alien
GoTo D 119
SetSheetTitle ALiX
GoTo D 120
SetSheetTitle Alk
GoTo D 121
SetSheetTitle Alp4
GoTo D 122
SetSheetTitle alph
GoTo D 123
SetSheetTitle alpha-Cat
GoTo D 124
SetSheetTitle alpha-Catr
GoTo D 125
SetSheetTitle alpha-Est1
GoTo D 126
SetSheetTitle alpha-Est10
GoTo D 127
SetSheetTitle alpha-Est2
GoTo D 128
SetSheetTitle alpha-Est3
GoTo D 129
SetSheetTitle alpha-Est7
GoTo D 130
SetSheetTitle alpha-Est8
GoTo D 131
SetSheetTitle alpha-Est9
GoTo D 132
SetSheetTitle alpha-Man-Ia
GoTo D 133
SetSheetTitle alpha-Man-Ib
GoTo D 134
SetSheetTitle alpha-Man-IIa
GoTo D 135
SetSheetTitle alpha-Man-IIb
GoTo D 136
SetSheetTitle alpha-PheRS
GoTo D 137
SetSheetTitle alpha-Spec
GoTo D 138
SetSheetTitle alpha4GT1
GoTo D 139
SetSheetTitle alphaCOP
GoTo D 140
SetSheetTitle alphaSnap
GoTo D 141
SetSheetTitle alphaTub84B
GoTo D 142
SetSheetTitle alphaTub84D
GoTo D 143
SetSheetTitle alrm
GoTo D 144
SetSheetTitle Als2
GoTo D 145
SetSheetTitle alt
GoTo D 146
SetSheetTitle amon
GoTo D 147
SetSheetTitle AMPdeam
GoTo D 148
SetSheetTitle Amph
GoTo D 149
SetSheetTitle AMPKalpha
GoTo D 150
SetSheetTitle Amun
GoTo D 151
SetSheetTitle Amy-d
GoTo D 152
SetSheetTitle ana
GoTo D 153
SetSheetTitle ana1
GoTo D 154
SetSheetTitle Ance
GoTo D 155
SetSheetTitle Ance-3
GoTo D 156
SetSheetTitle Ance-4
GoTo D 157
SetSheetTitle Ance-5
GoTo D 158
SetSheetTitle Ank
GoTo D 159
SetSheetTitle Ank2
GoTo D 160
SetSheetTitle Ankle2
GoTo D 161
SetSheetTitle anne
GoTo D 162
SetSheetTitle antdh
GoTo D 163
SetSheetTitle AnxB10
GoTo D 164
SetSheetTitle AnxB11
GoTo D 165
SetSheetTitle AnxB9
GoTo D 166
SetSheetTitle aop
GoTo D 167
SetSheetTitle aos
GoTo D 168
SetSheetTitle AOX1
GoTo D 169
SetSheetTitle AOX3
GoTo D 170
SetSheetTitle ap
GoTo D 171
SetSheetTitle AP-1-2beta
GoTo D 172
SetSheetTitle AP-1gamma
GoTo D 173
SetSheetTitle AP-1mu
GoTo D 174
SetSheetTitle AP-1sigma
GoTo D 175
SetSheetTitle AP-2alpha
GoTo D 176
SetSheetTitle AP-2mu
GoTo D 177
SetSheetTitle Apc
GoTo D 178
SetSheetTitle aPKC
GoTo D 179
SetSheetTitle Aplip1
GoTo D 180
SetSheetTitle apolpp
GoTo D 181
SetSheetTitle Apoltp
GoTo D 182
SetSheetTitle app
GoTo D 183
SetSheetTitle APP-BP1
GoTo D 184
SetSheetTitle Appl
GoTo D 185
SetSheetTitle Aps
GoTo D 186
SetSheetTitle apt
GoTo D 187
SetSheetTitle aralar1
GoTo D 188
SetSheetTitle Arc1
GoTo D 189
SetSheetTitle Arc42
GoTo D 190
SetSheetTitle Arf51F
GoTo D 191
SetSheetTitle Arf79F
GoTo D 192
SetSheetTitle ArfGAP1
GoTo D 193
SetSheetTitle ArfGAP3
GoTo D 194
SetSheetTitle Arfip
GoTo D 195
SetSheetTitle Argk
GoTo D 196
SetSheetTitle ari-1
GoTo D 197
SetSheetTitle ari-2
GoTo D 198
SetSheetTitle Arl4
GoTo D 199
SetSheetTitle Arl5
GoTo D 200
SetSheetTitle Arl6IP1
GoTo D 201
SetSheetTitle arm
GoTo D 202
SetSheetTitle Arp1
GoTo D 203
SetSheetTitle Arp10
GoTo D 204
SetSheetTitle Arp2
GoTo D 205
SetSheetTitle Arp3
GoTo D 206
SetSheetTitle Arpc1
GoTo D 207
SetSheetTitle Arpc2
GoTo D 208
SetSheetTitle arr
GoTo D 209
SetSheetTitle Arr1
GoTo D 210
SetSheetTitle Arr2
GoTo D 211
SetSheetTitle Ars2
GoTo D 212
SetSheetTitle Art1
GoTo D 213
SetSheetTitle Art4
GoTo D 214
SetSheetTitle aru
GoTo D 215
SetSheetTitle Asap
GoTo D 216
SetSheetTitle Asator
GoTo D 217
SetSheetTitle ash1
GoTo D 218
SetSheetTitle ash2
GoTo D 219
SetSheetTitle Ask1
GoTo D 220
SetSheetTitle AsnRS
GoTo D 221
SetSheetTitle AsnS
GoTo D 222
SetSheetTitle Asph
GoTo D 223
SetSheetTitle ASPP
GoTo D 224
SetSheetTitle AspRS
GoTo D 225
SetSheetTitle AspRS-m
GoTo D 226
SetSheetTitle asrij
GoTo D 227
SetSheetTitle asRNA:CR43480
GoTo D 228
SetSheetTitle asRNA:CR45601
GoTo D 229
SetSheetTitle Asx
GoTo D 230
SetSheetTitle Ate1
GoTo D 231
SetSheetTitle Atet
GoTo D 232
SetSheetTitle Atf3
GoTo D 233
SetSheetTitle Atf6
GoTo D 234
SetSheetTitle Atg1
GoTo D 235
SetSheetTitle Atg101
GoTo D 236
SetSheetTitle Atg13
GoTo D 237
SetSheetTitle Atg14
GoTo D 238
SetSheetTitle Atg17
GoTo D 239
SetSheetTitle Atg18a
GoTo D 240
SetSheetTitle Atg18b
GoTo D 241
SetSheetTitle Atg2
GoTo D 242
SetSheetTitle Atg3
GoTo D 243
SetSheetTitle Atg4a
GoTo D 244
SetSheetTitle Atg4b
GoTo D 245
SetSheetTitle Atg8a
GoTo D 246
SetSheetTitle Atg9
GoTo D 247
SetSheetTitle atilla
GoTo D 248
SetSheetTitle atk
GoTo D 249
SetSheetTitle atl
GoTo D 250
SetSheetTitle atms
GoTo D 251
SetSheetTitle Atox1
GoTo D 252
SetSheetTitle ATP6AP2
GoTo D 253
SetSheetTitle ATP7
GoTo D 254
SetSheetTitle ATP8B
GoTo D 255
SetSheetTitle Atpalpha
GoTo D 256
SetSheetTitle ATPCL
GoTo D 257
SetSheetTitle ATPsynB
GoTo D 258
SetSheetTitle ATPsynbeta
GoTo D 259
SetSheetTitle ATPsynC
GoTo D 260
SetSheetTitle ATPsynCF6
GoTo D 261
SetSheetTitle ATPsynD
GoTo D 262
SetSheetTitle ATPsyndelta
GoTo D 263
SetSheetTitle ATPsynE
GoTo D 264
SetSheetTitle ATPsynF
GoTo D 265
SetSheetTitle ATPsynG
GoTo D 266
SetSheetTitle ATPsyngamma
GoTo D 267
SetSheetTitle ATPsynO
GoTo D 268
SetSheetTitle AttA
GoTo D 269
SetSheetTitle AttB
GoTo D 270
SetSheetTitle AttC
GoTo D 271
SetSheetTitle Atu
GoTo D 272
SetSheetTitle Atx2
GoTo D 273
SetSheetTitle Atxn7
GoTo D 274
SetSheetTitle aux
GoTo D 275
SetSheetTitle awd
GoTo D 276
SetSheetTitle axed
GoTo D 277
SetSheetTitle Axn
GoTo D 278
SetSheetTitle axo
GoTo D 279
SetSheetTitle Axs
GoTo D 280
SetSheetTitle Axud1
GoTo D 281
SetSheetTitle b
GoTo D 282
SetSheetTitle B4
GoTo D 283
SetSheetTitle B52
GoTo D 284
SetSheetTitle bab2
GoTo D 285
SetSheetTitle babo
GoTo D 286
SetSheetTitle babos
GoTo D 287
SetSheetTitle Bacc
GoTo D 288
SetSheetTitle bai
GoTo D 289
SetSheetTitle Baldspot
GoTo D 290
SetSheetTitle Bap111
GoTo D 291
SetSheetTitle Bap170
GoTo D 292
SetSheetTitle Bap60
GoTo D 293
SetSheetTitle barc
GoTo D 294
SetSheetTitle bark
GoTo D 295
SetSheetTitle baz
GoTo D 296
SetSheetTitle bbc
GoTo D 297
SetSheetTitle bbg
GoTo D 298
SetSheetTitle bc10
GoTo D 299
SetSheetTitle bchs
GoTo D 300
SetSheetTitle bdg
GoTo D 301
SetSheetTitle bdl
GoTo D 302
SetSheetTitle Bdp1
GoTo D 303
SetSheetTitle be
GoTo D 304
SetSheetTitle BEAF-32
GoTo D 305
SetSheetTitle beat-Ic
GoTo D 306
SetSheetTitle beat-IIa
GoTo D 307
SetSheetTitle beat-IIb
GoTo D 308
SetSheetTitle beat-IIIc
GoTo D 309
SetSheetTitle beat-IV
GoTo D 310
SetSheetTitle beat-Va
GoTo D 311
SetSheetTitle beat-VI
GoTo D 312
SetSheetTitle beat-VII
GoTo D 313
SetSheetTitle bel
GoTo D 314
SetSheetTitle Bem46
GoTo D 315
SetSheetTitle ben
GoTo D 316
SetSheetTitle Best1
GoTo D 317
SetSheetTitle Best2
GoTo D 318
SetSheetTitle beta'COP
GoTo D 319
SetSheetTitle beta-Man
GoTo D 320
SetSheetTitle beta-PheRS
GoTo D 321
SetSheetTitle beta-Spec
GoTo D 322
SetSheetTitle beta4GalNAcTA
GoTo D 323
SetSheetTitle betaCOP
GoTo D 324
SetSheetTitle betaggt-I
GoTo D 325
SetSheetTitle betaggt-II
GoTo D 326
SetSheetTitle betaTub56D
GoTo D 327
SetSheetTitle betaTub60D
GoTo D 328
SetSheetTitle betaTub97EF
GoTo D 329
SetSheetTitle bgm
GoTo D 330
SetSheetTitle bi
GoTo D 331
SetSheetTitle BI-1
GoTo D 332
SetSheetTitle bic
GoTo D 333
SetSheetTitle BicD
GoTo D 334
SetSheetTitle bif
GoTo D 335
SetSheetTitle bigmax
GoTo D 336
SetSheetTitle Bili
GoTo D 337
SetSheetTitle bin3
GoTo D 338
SetSheetTitle bip1
GoTo D 339
SetSheetTitle bip2
GoTo D 340
SetSheetTitle Blimp-1
GoTo D 341
SetSheetTitle blot
GoTo D 342
SetSheetTitle blow
GoTo D 343
SetSheetTitle blw
GoTo D 344
SetSheetTitle bma
GoTo D 345
SetSheetTitle Bmcp
GoTo D 346
SetSheetTitle bmm
GoTo D 347
SetSheetTitle bnb
GoTo D 348
SetSheetTitle bnl
GoTo D 349
SetSheetTitle boca
GoTo D 350
SetSheetTitle bocks
GoTo D 351
SetSheetTitle BOD1
GoTo D 352
SetSheetTitle bol
GoTo D 353
SetSheetTitle bon
GoTo D 354
SetSheetTitle bond
GoTo D 355
SetSheetTitle bor
GoTo D 356
SetSheetTitle boss
GoTo D 357
SetSheetTitle botv
GoTo D 358
SetSheetTitle bowl
GoTo D 359
SetSheetTitle br
GoTo D 360
SetSheetTitle Br140
GoTo D 361
SetSheetTitle brat
GoTo D 362
SetSheetTitle Brca2
GoTo D 363
SetSheetTitle Bre1
GoTo D 364
SetSheetTitle Brf
GoTo D 365
SetSheetTitle brm
GoTo D 366
SetSheetTitle Brms1
GoTo D 367
SetSheetTitle brp
GoTo D 368
SetSheetTitle bru1
GoTo D 369
SetSheetTitle bru2
GoTo D 370
SetSheetTitle bru3
GoTo D 371
SetSheetTitle Bruce
GoTo D 372
SetSheetTitle brun
GoTo D 373
SetSheetTitle BRWD3
GoTo D 374
SetSheetTitle bs
GoTo D 375
SetSheetTitle bsf
GoTo D 376
SetSheetTitle Bsg
GoTo D 377
SetSheetTitle Bsg25D
GoTo D 378
SetSheetTitle bsk
GoTo D 379
SetSheetTitle bt
GoTo D 380
SetSheetTitle BTBD9
GoTo D 381
SetSheetTitle BtbVII
GoTo D 382
SetSheetTitle Btk29A
GoTo D 383
SetSheetTitle btsz
GoTo D 384
SetSheetTitle btz
GoTo D 385
SetSheetTitle Bub1
GoTo D 386
SetSheetTitle Buffy
GoTo D 387
SetSheetTitle BuGZ
GoTo D 388
SetSheetTitle bun
GoTo D 389
SetSheetTitle bur
GoTo D 390
SetSheetTitle bves
GoTo D 391
SetSheetTitle bw
GoTo D 392
SetSheetTitle bwa
GoTo D 393
SetSheetTitle Bx
GoTo D 394
SetSheetTitle Bx42
GoTo D 395
SetSheetTitle by
GoTo D 396
SetSheetTitle c11.1
GoTo D 397
SetSheetTitle c12.2
GoTo D 398
SetSheetTitle C1GalTA
GoTo D 399
SetSheetTitle C3G
GoTo D 400
SetSheetTitle ca
GoTo D 401
SetSheetTitle Ca-alpha1D
GoTo D 402
SetSheetTitle Ca-alpha1T
GoTo D 403
SetSheetTitle Ca-beta
GoTo D 404
SetSheetTitle CaBP1
GoTo D 405
SetSheetTitle cac
GoTo D 406
SetSheetTitle cact
GoTo D 407
SetSheetTitle Cad74A
GoTo D 408
SetSheetTitle Cad86C
GoTo D 409
SetSheetTitle Cad87A
GoTo D 410
SetSheetTitle Cad96Ca
GoTo D 411
SetSheetTitle Cad99C
GoTo D 412
SetSheetTitle CadN
GoTo D 413
SetSheetTitle CadN2
GoTo D 414
SetSheetTitle Cadps
GoTo D 415
SetSheetTitle Caf1-55
GoTo D 416
SetSheetTitle CAH1
GoTo D 417
SetSheetTitle CAH2
GoTo D 418
SetSheetTitle cal1
GoTo D 419
SetSheetTitle CalpA
GoTo D 420
SetSheetTitle CalpB
GoTo D 421
SetSheetTitle CalpC
GoTo D 422
SetSheetTitle Calr
GoTo D 423
SetSheetTitle Cals
GoTo D 424
SetSheetTitle Calx
GoTo D 425
SetSheetTitle Cam
GoTo D 426
SetSheetTitle CaMKI
GoTo D 427
SetSheetTitle CaMKII
GoTo D 428
SetSheetTitle Camta
GoTo D 429
SetSheetTitle cana
GoTo D 430
SetSheetTitle CanA-14F
GoTo D 431
SetSheetTitle CanB
GoTo D 432
SetSheetTitle CanB2
GoTo D 433
SetSheetTitle Cand1
GoTo D 434
SetSheetTitle CAP
GoTo D 435
SetSheetTitle Cap-G
GoTo D 436
SetSheetTitle Cap-H2
GoTo D 437
SetSheetTitle Caper
GoTo D 438
SetSheetTitle Capr
GoTo D 439
SetSheetTitle caps
GoTo D 440
SetSheetTitle capt
GoTo D 441
SetSheetTitle capu
GoTo D 442
SetSheetTitle car
GoTo D 443
SetSheetTitle CarT
GoTo D 444
SetSheetTitle CASK
GoTo D 445
SetSheetTitle casp
GoTo D 446
SetSheetTitle Cat
GoTo D 447
SetSheetTitle cathD
GoTo D 448
SetSheetTitle Catsup
GoTo D 449
SetSheetTitle Cbl
GoTo D 450
SetSheetTitle Cbp53E
GoTo D 451
SetSheetTitle Cbp80
GoTo D 452
SetSheetTitle cbs
GoTo D 453
SetSheetTitle Cbs
GoTo D 454
SetSheetTitle cbt
GoTo D 455
SetSheetTitle CCHa2
GoTo D 456
SetSheetTitle Cchl
GoTo D 457
SetSheetTitle Ccm3
GoTo D 458
SetSheetTitle Ccn
GoTo D 459
SetSheetTitle CCT1
GoTo D 460
SetSheetTitle CCT2
GoTo D 461
SetSheetTitle CCT3
GoTo D 462
SetSheetTitle CCT4
GoTo D 463
SetSheetTitle CCT5
GoTo D 464
SetSheetTitle CCT6
GoTo D 465
SetSheetTitle CCT7
GoTo D 466
SetSheetTitle CCT8
GoTo D 467
SetSheetTitle Ccz1
GoTo D 468
SetSheetTitle CD98hc
GoTo D 469
SetSheetTitle Cda5
GoTo D 470
SetSheetTitle CDase
GoTo D 471
SetSheetTitle cdc14
GoTo D 472
SetSheetTitle Cdc27
GoTo D 473
SetSheetTitle Cdc42
GoTo D 474
SetSheetTitle Cdc5
GoTo D 475
SetSheetTitle Cdc7
GoTo D 476
SetSheetTitle Cdep
GoTo D 477
SetSheetTitle CdGAPr
GoTo D 478
SetSheetTitle cdi
GoTo D 479
SetSheetTitle cDIP
GoTo D 480
SetSheetTitle Cdk12
GoTo D 481
SetSheetTitle Cdk4
GoTo D 482
SetSheetTitle Cdk5
GoTo D 483
SetSheetTitle Cdk5alpha
--------------------------------------------------------------------------------