storeylab / biobroom Goto Github PK

fix_data_frame <- function(x, newnames = NULL, newcol = "term") {
  if (!is.null(newnames) && length(newnames) != ncol(x)) {
    stop("newnames must be NULL or have length equal to number of columns")
  }

  if (all(rownames(x) == seq_len(nrow(x)))) {
    # don't need to move rownames into a new column
    ret <- data.frame(x, stringsAsFactors = FALSE)
    if (!is.null(newnames)) {
      colnames(ret) <- newnames
    }
  }
  else {
    ret <- data.frame(
      ...new.col... = rownames(x),
      unrowname(x),
      stringsAsFactors = FALSE
    )
    colnames(ret)[1] <- newcol
    if (!is.null(newnames)) {
      colnames(ret)[-1] <- newnames
    }
  }
  as_tibble(ret)
}

Warning message:
`tbl_df()` is deprecated as of dplyr 1.0.0.
Please use `tibble::as_tibble()` instead.

> data(hammer)
> pData(hammer)
                  sample.id num.tech.reps protocol         strain     Time
SRX020102         SRX020102             1  control Sprague Dawley 2 months
SRX020103         SRX020103             2  control Sprague Dawley 2 months
SRX020104         SRX020104             1   L5 SNL Sprague Dawley 2 months
SRX020105         SRX020105             2   L5 SNL Sprague Dawley  2months
SRX020091-3     SRX020091-3             1  control Sprague Dawley  2 weeks
SRX020088-90   SRX020088-90             2  control Sprague Dawley  2 weeks
SRX020094-7     SRX020094-7             1   L5 SNL Sprague Dawley  2 weeks
SRX020098-101 SRX020098-101             2   L5 SNL Sprague Dawley  2 weeks

> tidy(hammer)
# A tibble: 236,128 x 3
                 gene    sample value
                <chr>     <chr> <int>
1  ENSRNOG00000000001 SRX020102     2
2  ENSRNOG00000000007 SRX020102     4
3  ENSRNOG00000000008 SRX020102     0
4  ENSRNOG00000000009 SRX020102     0
5  ENSRNOG00000000010 SRX020102    19
6  ENSRNOG00000000012 SRX020102     7
7  ENSRNOG00000000014 SRX020102     0
8  ENSRNOG00000000017 SRX020102     4
9  ENSRNOG00000000021 SRX020102     7
10 ENSRNOG00000000024 SRX020102    86
# ... with 236,118 more rows
> pData(hammer) %>% dplyr::filter(grepl('SRX020091',sample.id))
    sample.id num.tech.reps protocol         strain    Time
1 SRX020091-3             1  control Sprague Dawley 2 weeks

> tidy(hammer) %>% dplyr::filter(grepl('SRX020091',sample))
# A tibble: 29,516 x 3
                 gene      sample value
                <chr>       <chr> <int>
1  ENSRNOG00000000001 SRX020091.3     7
2  ENSRNOG00000000007 SRX020091.3     5
3  ENSRNOG00000000008 SRX020091.3     0
4  ENSRNOG00000000009 SRX020091.3     0
5  ENSRNOG00000000010 SRX020091.3    50
6  ENSRNOG00000000012 SRX020091.3    31
7  ENSRNOG00000000014 SRX020091.3     0
8  ENSRNOG00000000017 SRX020091.3    21
9  ENSRNOG00000000021 SRX020091.3    30
10 ENSRNOG00000000024 SRX020091.3   257
# ... with 29,506 more rows

read_fasta <- function(fasta_filename, annot = FALSE){
    fasta <- seqinr::read.fasta(fasta_filename, as.string = TRUE)

    # Convert seqinr SeqFastadna object to data.frame
    fasta_df <- fasta %>%
                   sapply(function(x){x[1:length(x)]}) %>%
                   as.data.frame %>%
                   broom::fix_data_frame(newcol = "ID", newnames = "Sequence")

    if(annot == TRUE){
        annot_df <- getAnnot(fasta) %>%
                         sapply(function(x){x[1:length(x)]}) %>%
                         as.data.frame() %>%
                         broom::fix_data_frame(newnames = "Annot")

        fasta_df <- cbind(fasta_df, annot_df)
    }
    return(fasta_df)
}
read_fasta('https://www.uniprot.org/uniprot/?query=PGH1&format=fasta&limit=10')