CODEWITHSUNDEEP
r
user2300940
user2300940

Reputation: 2385

Modify multiple input files

For all my files in the folder miraligner I would like to combine the columns as shown in my example. I would like to combine the columns c("mir","seq","mism","add","t5","t3") as well as adding "freq" as column 2 in the output. I am not sure how to do this for multiple input files

> setwd("~/miraligner/")
> file_list <- list.files(pattern = "*.mirna")
> head(file_list)

[1] "1_JH_F12_S41.mirna"   "107_MAE_E7_S11.mirna" "108_IME_A8_S23.mirna" "109_GW_B11_S27.mirna" "111_PH_H1_S77.mirna" 
[6] "116_TH_E6_S10.mirna" 

> head(1_JH_F12_S41.mirna)
                       seq          name freq             mir start end mism   add t5  t3       s5       s3    DB
1    TGGAGTGTGATAATGGTGTTT seq_100003_x4    4  hsa-miR-122-5p    15  35 11TC     0  0   g GCTGTGGA TTTGTGTC miRNA
2 TGTAAACATCCCCGACCGGAAGCT seq_100045_x4    4  hsa-miR-30d-5p     6  29 17CT     0  0  CT TTGTTGTA GAAGCTGT miRNA
3   CTAGACTGAAGCTCCTTGAAAA seq_100048_x4    4 hsa-miR-151a-3p    47  65    0 I-AAA  0  gg CCTACTAG GAGGACAG miRNA
4   AGGCGGAGACTTGGGCAATTGC seq_100059_x4    4   hsa-miR-25-5p    14  35    0     0  0   C TGAGAGGC ATTGCTGG miRNA
5    AAACCGTTACCATTACTGAAT seq_100067_x4    4    hsa-miR-451a    17  35    0  I-AT  0 gtt AAGGAAAC AGTTTAGT miRNA
6   TGAGGTAGTAGCTTGTGCTGTT seq_10007_x24   24   hsa-let-7i-5p     6  27 12CT     0  0   0 TGGCTGAG TGTTGGTC miRNA
     precursor ambiguity
1  hsa-mir-122         1
2  hsa-mir-30d         1
3 hsa-mir-151a         1
4   hsa-mir-25         1
5 hsa-mir-451a         1
6   hsa-let-7i         1

output

ID                                                  freq
hsa-miR-122-5p_TGGAGTGTGATAATGGTGTTT_11TC_0_0_g     4
hsa-miR-30d-5p_TGTAAACATCCCCGACCGGAAGCT_17CT_0_0_CT     4

Upvotes: 0

Views: 53

Answers (1)

vdep
vdep

Reputation: 3590

file_list <- list.files(pattern = "*.mirna")
df = data.frame()  
for (i in file_list) {
  df <- rbind(df,read.csv(paste(i)))  #combines all files into a single dataframe
}

df$merged <- paste(df$seq,df$mism,df$add,df$t5,df$t3,sep = "_")
df <- data.frame(ID = df$merged,freq = df$freq)

Upvotes: 1

Related Questions