02_cDNA_indexing.Rmd

---
title: "cDNA_Indexing"
author: "Natalia Andrade"
date: "2022-12-10"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
library(ggplot2)
library(tidyr)
library(dplyr)
library(stringr)
```
# Get NOVA_all from "Data/NOVA_lab"

```{r}
meta_lab<- read.csv("data/meta_NOVA_lab.csv") %>% 
  
                dplyr::select("Sample_ID","RNA_Ext_Coordinate","qPCR_Coordinate",
                       "RNA_Original_concentration","RNA_Dilution_concentration","Cq",                         "Plate_Number","Extraction_CD")
```
#Creating columns with number of cycles

```{r}
NOVA_lab_cycles<- meta_lab %>% 
  
                  mutate(cycles_15 = if_else( grepl("13|14|15", Cq), TRUE, FALSE)) %>% 
    
                  mutate(cycles_18 = if_else( grepl("16|17|18", Cq), TRUE, FALSE)) %>% 
    
                  mutate(cycles_21 = if_else( grepl("19|20|21", Cq), TRUE, FALSE)) %>% 
    
                  mutate(cycles_24 = if_else( grepl("22|23|24", Cq), TRUE, FALSE)) %>%
    
                  mutate(cycles_27 = if_else( grepl("25|26|27", Cq), TRUE, FALSE)) %>%
  
                  mutate(cycles_28 = if_else( grepl("28", Cq), TRUE, FALSE)) 
  
```

Adding indexes IDs
```{r}
Indexes_A1_A3<- read.csv("raw_data/Index_A1_A3.csv")
dim(Indexes_A1_A3)
#Only 270 samples in NOVA experiment so cut number of rows/indexes
Indexes_NOVA<- Indexes_A1_A3[1:270,1:8]

#Arrange data by Cq

NOVA_lab_cycles<- NOVA_lab_cycles %>% 
          
                  arrange(Cq)
#Bind columns from indexes to our database

NOVA_indexes<- bind_cols(NOVA_lab_cycles, Indexes_NOVA) %>% 
  
              mutate(Lane_seq = 1)



```


#Creating plate maps by Grouping samples per cycles
```{r}
NOVA_indexes_platemaps<- NOVA_indexes %>% 
  
                        dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set","cycles_15",
                                      "cycles_18","cycles_21",
                                      "cycles_24","cycles_27","cycles_28") %>% 
  
                        arrange("UDI_ID") %>% 
  
                        mutate(order = 1:270) %>% 
  
                        mutate(Index_cord = paste(Row,Col, sep = "_"))

cycles_15<- NOVA_indexes_platemaps %>% 
  
                filter(cycles_15 ==TRUE) %>% 
                
                dplyr::select("Sample_ID","Plate_Number","Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set","cycles_15") #8

cycles_18<- NOVA_indexes_platemaps %>% 
  
                filter(grepl("16|17|18", Cq)) %>% 
                
                dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set",
                                      "cycles_18")#83

cycles_21<- NOVA_indexes_platemaps %>% 
  
                filter(grepl("19|20|21", Cq)) %>% 

                dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set","cycles_21")#79

cycles_24<- NOVA_indexes_platemaps %>% 
  
                filter(grepl("22|23|24", Cq)) %>% 

                dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set",
                                      "cycles_24")#4

cycles_27<- NOVA_indexes_platemaps %>% 
  
                filter(grepl("25|26|27", Cq)) %>% 
  
                 dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set","cycles_27")# 65

cycles_28<- NOVA_indexes_platemaps %>% 
  
                filter(grepl("28", Cq)) %>% 

                dplyr::select("Sample_ID","Plate_Number",
                                      "Cq","qPCR_Coordinate",
                                      "Row", "Col", "UDI_ID","Set","cycles_28")#4

#write.csv(cycles_15,"data/cycles_15_plate_NOVA.csv")
#write.csv(cycles_18,"data/cycles_18_plate_NOVA.csv")
#write.csv(cycles_21,"data/cycles_21_plate_NOVA.csv")
#write.csv(cycles_24,"data/cycles_24_plate_NOVA.csv")
#write.csv(cycles_27,"data/cycles_27_plate_NOVA.csv")
#write.csv(cycles_28,"data/cycles_28_plate_NOVA.csv")

```
#Get samples per indexing plate
```{r}
NOVA_cDNA_SetA1<- NOVA_indexes_platemaps %>% 
  
                  filter(Set == "UDI_Set_A1")

NOVA_cDNA_SetA2<- NOVA_indexes_platemaps %>% 
  
                  filter(Set == "UDI_Set_A2")

NOVA_cDNA_SetA3<- NOVA_indexes_platemaps %>% 
  
                  filter(Set == "UDI_Set_A3")

#write.csv(NOVA_cDNA_SetA1, "data/NOVA_cDNA_SetA1.csv")
#write.csv(NOVA_cDNA_SetA2, "data/NOVA_cDNA_SetA2.csv")
#write.csv(NOVA_cDNA_SetA3, "data/NOVA_cDNA_SetA3.csv")

```
#List of RNA coordinates of sample to redo
```{r}
NOVA_cDNA_SetA3_cDNA_redo_12<- NOVA_indexes %>% 
  
                  filter(Set == "UDI_Set_A3") %>% 
  
                  filter(!grepl("\\d", Cq)) %>% 

                dplyr::select("Sample_ID","Plate_Number",
                              "RNA_Ext_Coordinate","qPCR_Coordinate",
                              "RNA_Original_concentration",
                              "Row", "Col", "UDI_ID","Set")#27

#write.csv(NOVA_cDNA_SetA3_cDNA_redo_12, "data/list_forcDNA_12_Redos_NOVA.csv")
```


# Adding informtion of redos and 12 left

```{r}
qPCR_Plate_8<- read.csv("raw_data/Plate8_qPCR_platemap.csv")  %>% 
  
                      filter(Project == 'NOVA') %>% 
  
                      dplyr::select("Sample_ID","Well_Position", "Cq","qPCR_plate"  )
```


#Find Cq distribution plate 8 
```{r}
#meta_lab$Cq<- as.integer(meta_lab$Cq)

Cq_8<- qPCR_Plate_8 %>% 
          
          filter(grepl("\\d", Cq)) %>% 
  
          arrange(desc(Cq))

Cq_8$Cq<- as.integer(Cq_8$Cq)
         
Cq_8_max<- max(Cq_8$Cq)#27

Cq_8_min<- min(Cq_8$Cq) #12
#here plot to see categories
```
PLOT

```{r}
data_plot_Cq_8 <- Cq_8

plot_Cq_8 <- ggplot(data_plot_Cq_8, aes(Cq)) + 
  geom_bar(aes(), position = "dodge") +
  scale_x_continuous(breaks = 0 : 40, guide = guide_axis(check.overlap = TRUE))

print(plot_Cq_8)
```

#Creating cycles column

```{r}


cycles_21<- qPCR_Plate_8 %>% 
  
                filter(grepl("19|20|21", Cq)) %>% 
  
                 mutate(cycles = 21) #18


cycles_23<- qPCR_Plate_8 %>% 
  
                filter(grepl("22|23", Cq)) %>% 
  
                mutate(cycles = 23 )#10

          
  
 
```


```{r}
qPCR_Plate_8_cycles<- bind_rows(cycles_21,
                                cycles_23) 
```

Adding information to data base with indexes
```{r}
names(NOVA_indexes_platemaps)

No_cycles_samples<- NOVA_indexes_platemaps %>% 
  
  
                    filter(!grepl("\\d", Cq)) %>% 
  
                    dplyr::select(-"Cq")

Samples_new_cycles<- left_join(qPCR_Plate_8_cycles, No_cycles_samples, by="Sample_ID")

```

NEW INDEX order for plate_Set_A3
```{r}
Samples_plate_NOVA_Set_A3<- Samples_new_cycles %>% 
  
                          filter(Set == "UDI_Set_A3")

Indexes_NOVA_Set_A3<- Samples_plate_NOVA_Set_A3 %>% 
  
                      dplyr:: select("UDI_ID", "Set", "Index_cord") %>% 
  
                      arrange(UDI_ID)

Samples_plate_NOVA_Set_A3_cycle<- Samples_plate_NOVA_Set_A3 %>% 
  
                               dplyr:: select("Sample_ID","qPCR_plate","Well_Position",
                                                "cycles") %>% 
                               arrange(cycles) %>% 
         
                               dplyr::rename('qPCR_Coordinate' =  'Well_Position', 
                               "Plate_Number" = "qPCR_plate" )
  

Samples_new_cycles_NOVA_Set_A3<- cbind(Samples_plate_NOVA_Set_A3_cycle, Indexes_NOVA_Set_A3) 

Samples_new_cycles_NOVA_Set_A3<- Samples_new_cycles_NOVA_Set_A3 %>% 
     
                             dplyr:: select("Sample_ID", "Plate_Number", "qPCR_Coordinate", 
                                     "Index_cord", "UDI_ID","Set","cycles" )

write.csv(Samples_new_cycles_NOVA_Set_A3, "data/FOR_Plating_NOVA_Set_A3_new.csv")


####################################### New plate NOVA_cDNA_SetA3 ##################################

#First cut the section of the old table with cycles = 0
dim(NOVA_cDNA_SetA3)
names(NOVA_cDNA_SetA3)
names(Samples_new_cycles_NOVA_Set_A3)
#matching_column names
NOVA_cDNA_SetA3_new<- NOVA_cDNA_SetA3 %>% 
  
  dplyr::rename("cycles"= 'Cq') %>% 
  
  dplyr::select("Sample_ID","Plate_Number","qPCR_Coordinate","Index_cord","UDI_ID", "Set","cycles")       


NOVA_cDNA_SetA3_cut<- NOVA_cDNA_SetA3_new[1:51,]

#Bind samples with new assinged indexes

NOVA_cDNA_SetA3_new<- rbind(Samples_new_cycles_NOVA_Set_A3, NOVA_cDNA_SetA3_cut)

#### !!!! !!! IMPORTANT !! ### Fix cycle column!!
```