From e502d2638f988a569aa01524cc3044636a494d49 Mon Sep 17 00:00:00 2001
From: "Adri K. Grow" <42044618+adriannagrow@users.noreply.github.com>
Date: Fri, 1 Sep 2023 14:35:08 -0400
Subject: [PATCH] Add files via upload

---
 Utilities/for_fastas/PlotComps.r | 47 ++++++++++++++++++--------------
 1 file changed, 26 insertions(+), 21 deletions(-)

diff --git a/Utilities/for_fastas/PlotComps.r b/Utilities/for_fastas/PlotComps.r
index 2a1107d..b3c443a 100644
--- a/Utilities/for_fastas/PlotComps.r
+++ b/Utilities/for_fastas/PlotComps.r
@@ -1,30 +1,35 @@
 #The purpose of this script is to make a simple jellyfish plot from a dataset like the one
-#produced by the CUB.py script, also in the Github Utilities folder. This script was written
-#by Auden Cote-L'Heureux and last updated in May 2023
+#produced by the CUB_v2.1.py script, also in the Github Utilities folder. This script was written
+#by Auden Cote-L'Heureux and last updated in September 2023 by Adri
 
+#load necessary packages
 library(tidyverse)
 
-#Change this path
-setwd('/Your/Working/Directory')
+#Change to the path of the directory you're working from
+#Use "getwd()" in console below to get path
+setwd("/Users/agrow/Desktop/NewCUB_meta/CUBOutput/SpreadSheets")
 
-#You will need to change name of data frame below
-#if you used the CUB.py script, it should be in the spreadsheets folder
-#in the output and end in CompTrans.ENc.Raw.tsv
-gc3 <- data.frame(read_tsv('CompTrans.ENc.Raw.tsv'))
+#You may need to change name of data frame below
+#if you used the CUB_v2.1.py script from Github, it should be in the 
+#CUBOutput folder and then inside the SpreadSheets folder
+#you are looking for the CompTrans.ENc.Raw.tsv
+gc3 <- data.frame(read_tsv('CompTrans.ENc.Raw.tsv'))%>%
+  mutate(taxon = paste(substr(SequenceID, 1, 4), substr(SequenceID,6,10), sep = '')) #this line reads in your 10-digit codes to a column in the data frame called taxon
 
-gc3$GC3.Degen <- as.numeric(gc3$GC3.Degen)
-gc3$ObsWrightENc_6Fold <- as.numeric(gc3$ObsWrightENc_6Fold)
-
-#The data for the null expectation curve will be in the same folder as above
+#This .tsv is generated by the CUB script and will be in the same folder as the .tsv above
+#This generates the null expectation line
 enc_null <- data.frame(read_tsv('ENc.Null.tsv'))
 
-gc3_plot <- ggplot(data = gc3, mapping = aes(as.numeric(GC3.Degen), as.numeric(ObsWrightENc_6Fold))) +
-   geom_point() +
-   geom_line(data = enc_null, aes(GC3, ENc)) +
-   theme_classic() +
-   labs(x = '%GC at 3rd-pos 4-fold sites', y = 'Observed Wright ENc (6Fold)') +
-   theme(
-      legend.position = 'none'
-   )
-
+#change data in first line here to what you want plotted
+#you need as.numeric to ensure R is reading the variable correctly
+gc3_plot <- ggplot(gc3, aes(as.numeric(GC3.Degen), as.numeric(ObsWrightENc_No6Fold)))+
+  geom_point(size = 0.1)+
+  geom_line(data = enc_null, aes(GC3, ENc))+
+  theme_classic()+
+  labs(x = 'GC3 Degen', y = 'ObsWrightENc_No6fold')+
+  theme(legend.position = 'none')+
+  ggtitle("Metatranscriptomics R2G NTD files")+
+  theme(axis.text.x=element_text(colour="black"))+
+  theme(axis.text.y=element_text(colour="black"))+
+  facet_wrap(vars(taxon), scales = 'free_x')
 gc3_plot