#LOCATION OF KALLISTO COUNT DIRECTORIES: C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/ sample 1 sample2.......sample6
​
setwd("C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES")


dir <- "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES"

> dir
[1] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES"


> list.files(dir)
[1] "sample.txt"    "sample1"       "sample2"      
[4] "sample3"       "sample4"       "sample5"      
[7] "sample6"       "samples.txt"   "samples_x.txt"


#First I created a file with sample metadata [samples_x.txt] in the same directory containing kallisto out put folders

     run condition
1 sample1   control
2 sample2   control
3 sample3   control
4 sample4 treatment
5 sample5 treatment
6 sample6 treatment



samples <- read.table(file.path(dir, "samples_x.txt"), header = TRUE)

> samples
      run condition
1 sample1   control
2 sample2   control
3 sample3   control
4 sample4 treatment
5 sample5 treatment
6 sample6 treatment

files <- file.path(dir, "kallisto", samples$run, "abundance.tsv")

names(files) <- paste0("sample", 1:6)



> txdb <- makeTxDbFromGFF("C:/Users/HERIETH/Desktop/SALMON_CASSAVA/phytozome/Mesculenta/v8.1/annotation/Mesculenta_671_v8.1.gene.gff3.gz")

Import genomic features from the file as a GRanges object ... OK
Prepare the 'metadata' data frame ... OK
Make the TxDb object ... OK


> columns(txdb)
 [1] "CDSCHROM"   "CDSEND"     "CDSID"      "CDSNAME"   
 [5] "CDSPHASE"   "CDSSTART"   "CDSSTRAND"  "EXONCHROM" 
 [9] "EXONEND"    "EXONID"     "EXONNAME"   "EXONRANK"  
[13] "EXONSTART"  "EXONSTRAND" "GENEID"     "TXCHROM"   
[17] "TXEND"      "TXID"       "TXNAME"     "TXSTART"   
[21] "TXSTRAND"   "TXTYPE"

> k <- keys(txdb, keytype = "GENEID")

> tx2gene <- select(txdb, keys = k, keytype = "GENEID", columns = "TXNAME")

'select()' returned 1:many mapping between keys
and columns

> head(tx2gene)

           GENEID            TXNAME
1 Manes.01G000031 Manes.01G000031.1
2 Manes.01G000031 Manes.01G000031.2
3 Manes.01G000031 Manes.01G000031.3
4 Manes.01G000062 Manes.01G000062.1
5 Manes.01G000093 Manes.01G000093.1
6 Manes.01G000124 Manes.01G000124.1



#Link transcripts IDS and genome annotation

txdb <- makeTxDbFromGFF("C:/Users/HERIETH/Desktop/SALMON_CASSAVA/phytozome/Mesculenta/v8.1/annotation/Mesculenta_671_v8.1.gene.gff3.gz")

> columns(txdb)
 [1] "CDSCHROM"   "CDSEND"     "CDSID"      "CDSNAME"   
 [5] "CDSPHASE"   "CDSSTART"   "CDSSTRAND"  "EXONCHROM" 
 [9] "EXONEND"    "EXONID"     "EXONNAME"   "EXONRANK"  
[13] "EXONSTART"  "EXONSTRAND" "GENEID"     "TXCHROM"   
[17] "TXEND"      "TXID"       "TXNAME"     "TXSTART"   
[21] "TXSTRAND"   "TXTYPE" 


k <- keys(txdb, keytype = "GENEID")


tx2gene <- select(txdb, keys = k, keytype = "GENEID", columns = "TXNAME")

'select()' returned 1:many mapping between keys
and columns

> head(tx2gene)
           GENEID            TXNAME
1 Manes.01G000031 Manes.01G000031.1
2 Manes.01G000031 Manes.01G000031.2
3 Manes.01G000031 Manes.01G000031.3
4 Manes.01G000062 Manes.01G000062.1
5 Manes.01G000093 Manes.01G000093.1
6 Manes.01G000124 Manes.01G000124.1


txi.kallisto.tsv <- tximport(files, type = "kallisto", tx2gene = tx2gene, ignoreAfterBar = TRUE, ignoreTxVersion = TRUE)

#TRIED TO TROUBLESHOOT FOR ERRORS [FILE LOCATIONS]

> file.path(files)
[1] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample1/abundance.tsv"
[2] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample2/abundance.tsv"
[3] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample3/abundance.tsv"
[4] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample4/abundance.tsv"
[5] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample5/abundance.tsv"
[6] "C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES/kallisto/sample6/abundance.tsv"

#Recap on initial file location


C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA

> file.exists("C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES")
[1] TRUE


 list.files("C:/Users/HERIETH/Desktop/KALLISTO_CASSAVA/KALLISTO_6SAMPLES")
[1] "sample.txt"    "sample1"       "sample2"      
[4] "sample3"       "sample4"       "sample5"      
[7] "sample6"       "samples.txt"   "samples_x.txt"


# I repeated tximport command as shown below but i still get errors. What could be the problem?


> txi.kallisto.tsv <- tximport(files, type = "kallisto", tx2gene = tx2gene, ignoreAfterBar = TRUE)

Error in tximport(files, type = "kallisto", tx2gene = tx2gene, ignoreAfterBar = TRUE) : 
  all(file.exists(files)) is not TRUE