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 4.3.2 (2023-10-31 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 11 x64 (build 22621)
## 
## Matrix products: default
## 
## 
## locale:
## [1] LC_COLLATE=C                               
## [2] LC_CTYPE=Chinese (Simplified)_China.utf8   
## [3] LC_MONETARY=Chinese (Simplified)_China.utf8
## [4] LC_NUMERIC=C                               
## [5] LC_TIME=Chinese (Simplified)_China.utf8    
## 
## time zone: Asia/Shanghai
## tzcode source: internal
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
## [1] seqmagick_0.1.7     Biostrings_2.70.1   GenomeInfoDb_1.38.1
## [4] XVector_0.42.0      IRanges_2.36.0      S4Vectors_0.40.2   
## [7] BiocGenerics_0.48.1 magrittr_2.0.3     
## 
## loaded via a namespace (and not attached):
##  [1] crayon_1.5.2            cli_3.6.1               knitr_1.45             
##  [4] rlang_1.1.2             xfun_0.41               jsonlite_1.8.7         
##  [7] RCurl_1.98-1.13         htmltools_0.5.7         sass_0.4.7             
## [10] rmarkdown_2.25          evaluate_0.23           jquerylib_0.1.4        
## [13] prettydoc_0.4.1         bitops_1.0-7            fastmap_1.1.1          
## [16] yaml_2.3.7              lifecycle_1.0.4         memoise_2.0.1          
## [19] compiler_4.3.2          fs_1.6.3                digest_0.6.33          
## [22] R6_2.5.1                GenomeInfoDbData_1.2.11 bslib_0.6.0            
## [25] tools_4.3.2             zlibbioc_1.48.0         yulab.utils_0.1.3      
## [28] cachem_1.0.8

References