Download sequences

Genbank

tmpgb <- tempfile(fileext = '.gb')
tmpfa <- tempfile(fileext = '.fa')
download_genbank(acc='AB115403', format='genbank', outfile=tmpgb)
download_genbank(acc='AB115403', format='fasta', outfile=tmpfa)
## readLines(tmpgb)[1:10]
## readLines(tmpfa)

File conversion

fasta and phylip conversion

fa_file <- system.file("extdata/HA.fas", package="seqmagick")
## use the small subset to save compilation time of the vignette
fa2 <- tempfile(fileext = '.fa')
fa_read(fa_file) %>% bs_filter('ATGAAAGTAAAA', by='sequence') %>% fa_write(fa2, type='interleaved')


alnfas <- tempfile(fileext = ".fas")
fa_read(fa2) %>% bs_aln(quiet=TRUE) %>% fa_write(alnfas)

## phylip format is only for aligned sequences
tmpphy <- tempfile(fileext = ".phy")
fas2phy(alnfas, tmpphy, type = 'sequential')

seqmagick supports both sequential and interleaved formats, users can specify the format by type parameter.

phy2fas(tmpphy, alnfas, type = 'interleaved')

interleaved and sequential format conversion

tmpfas <- tempfile(fileext='.fa')
fa_read(fa2) %>% fa_write(tmpfas, type="sequential")
tmpphy2 <- tempfile(fileext = '.phy')
phy_read(tmpphy) %>% phy_write(tmpphy2, type="interleaved")

Sequence manipulation

bs <- fa_read(fa_file)
bs_filter(bs, 'ATGAAAGTAAAA', by='sequence')

aln <- bs_filter(bs, 'ATGAAAGTAAAA', by='sequence') %>% bs_aln(quiet=TRUE)

bs_consensus(aln)

Bugs/Feature requests

If you have any, let me know. Thx!

Session info

Here is the output of sessionInfo() on the system on which this document was compiled:

## R version 4.0.2 (2020-06-22)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Arch Linux
## 
## Matrix products: default
## BLAS:   /usr/lib/libblas.so.3.9.0
## LAPACK: /usr/lib/liblapack.so.3.9.0
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=C              
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats4    parallel  stats     graphics  grDevices utils     datasets 
## [8] methods   base     
## 
## other attached packages:
## [1] seqmagick_0.1.4     Biostrings_2.56.0   XVector_0.28.0     
## [4] IRanges_2.22.2      S4Vectors_0.26.1    BiocGenerics_0.34.0
## [7] magrittr_1.5       
## 
## loaded via a namespace (and not attached):
##  [1] crayon_1.3.4    digest_0.6.25   evaluate_0.14   zlibbioc_1.34.0
##  [5] rlang_0.4.7     stringi_1.5.3   rmarkdown_2.3   tools_4.0.2    
##  [9] stringr_1.4.0   prettydoc_0.4.0 xfun_0.17       yaml_2.2.1     
## [13] compiler_4.0.2  htmltools_0.5.0 knitr_1.29

References