2

I have a data frame called input that looks like the following:

structure(list(sequence = c("LdBPK_010012800.1", "MAQNDKIAPQDQDSF", 
"AQNDKIAPQDQDSFL", "QNDKIAPQDQDSFLD", "NDKIAPQDQDSFLDD", "DKIAPQDQDSFLDDQ", 
"KIAPQDQDSFLDDQP", "IAPQDQDSFLDDQPG", "APQDQDSFLDDQPGV", "PQDQDSFLDDQPGVR", 
"LdBPK_020009000.1", "MAQNDKIAPQDQDSF", "AQNDKIAPQDQDSFL", "QNDKIAPQDQDSFLD", 
"NDKIAPQDQDSFLDD", "DKIAPQDQDSFLDDQ", "KIAPQDQDSFLDDQP", "IAPQDQDSFLDDQPG", 
"APQDQDSFLDDQPGV", "PQDQDSFLDDQPGVR"), score = c(1, 17007, 12388, 
15984, 23405, 31897, 26826, 35239, 35361, 36486, 1, 17007, 12388, 
15984, 23405, 31897, 26826, 35239, 35361, 36486), epitope = structure(c(1L, 
2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 
3L, 3L, 3L), .Label = c("", "Epitope", "Non-Epitope"), class = "factor"), 
    positioning = c(TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, 
    FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, 
    FALSE, FALSE, FALSE, FALSE, FALSE), accessions = c("LdBPK_010012800.1", 
    NA, NA, NA, NA, NA, NA, NA, NA, NA, "LdBPK_020009000.1", 
    NA, NA, NA, NA, NA, NA, NA, NA, NA)), row.names = c(NA, -20L
), .Names = c("sequence", "score", "epitope", "positioning", 
"accessions"), class = "data.frame")

(actually my original data frame has over 1 million rows, so this is just a small portion of it)

I want to recycle the non-NA values under input$accessions (starting with LdBPK_010012800.1) until I found the next non-NA value (considering the present example, LdBPK_020009000.1). Then I would recycle the NA values below LdBPK_020009000.1 until I encounter the next non-NA value, and so on.

After this operation, my new data frame should look like this: 

structure(list(sequence = c("LdBPK_010012800.1", "MAQNDKIAPQDQDSF", 
"AQNDKIAPQDQDSFL", "QNDKIAPQDQDSFLD", "NDKIAPQDQDSFLDD", "DKIAPQDQDSFLDDQ", 
"KIAPQDQDSFLDDQP", "IAPQDQDSFLDDQPG", "APQDQDSFLDDQPGV", "PQDQDSFLDDQPGVR", 
"LdBPK_020009000.1", "MAQNDKIAPQDQDSF", "AQNDKIAPQDQDSFL", "QNDKIAPQDQDSFLD", 
"NDKIAPQDQDSFLDD", "DKIAPQDQDSFLDDQ", "KIAPQDQDSFLDDQP", "IAPQDQDSFLDDQPG", 
"APQDQDSFLDDQPGV", "PQDQDSFLDDQPGVR"), score = c(1, 17007, 12388, 
15984, 23405, 31897, 26826, 35239, 35361, 36486, 1, 17007, 12388, 
15984, 23405, 31897, 26826, 35239, 35361, 36486), epitope = structure(c(1L, 
2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 2L, 2L, 2L, 3L, 3L, 3L, 
3L, 3L, 3L), .Label = c("", "Epitope", "Non-Epitope"), class = "factor"), 
    positioning = c(TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, 
    FALSE, FALSE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, 
    FALSE, FALSE, FALSE, FALSE, FALSE), accessions = c("LdBPK_010012800.1", 
    "LdBPK_010012800.1", "LdBPK_010012800.1", "LdBPK_010012800.1", 
    "LdBPK_010012800.1", "LdBPK_010012800.1", "LdBPK_010012800.1", 
    "LdBPK_010012800.1", "LdBPK_010012800.1", "LdBPK_010012800.1", 
    "LdBPK_020009000.1", "LdBPK_020009000.1", "LdBPK_020009000.1", 
    "LdBPK_020009000.1", "LdBPK_020009000.1", "LdBPK_020009000.1", 
    "LdBPK_020009000.1", "LdBPK_020009000.1", "LdBPK_020009000.1", 
    "LdBPK_020009000.1")), row.names = c(NA, -20L), .Names = c("sequence", 
"score", "epitope", "positioning", "accessions"), class = "data.frame")

I am doing this because my ultimate goal is to use dplyr to group by accessions and get the sum of each group under score

BCArg
  • 2,094
  • 2
  • 19
  • 37

1 Answers1

0

We can use fill

library(tidyverse)
df1 %>% 
    fill(accessions)
akrun
  • 874,273
  • 37
  • 540
  • 662