Get Bioc package list
suppressPackageStartupMessages ({
library (BiocPkgTools)
library (dplyr)
library (DT)
})
BiocManager:: version ()
pkg <- biocPkgList (repo = "BioCsoft" )
'getOption("repos")' replaces Bioconductor standard repositories, see 'help("repositories", package = "BiocManager")'
for details.
Replacement repositories:
CRAN: https://cloud.r-project.org
adding rname 'https://bioconductor.org/packages/3.23/bioc/VIEWS'
# pkg <- biocPkgList(repo = c("BioCsoft", "BioCann", "BioCexp", "BioCworkflows"))
Get licenses
sort (table (pkg$ License, useNA = "ifany" ))
AGPL-3 | file LICENSE Apache License (== 2.0) + file LICENSE
1 1
Apache License (== 2.0) | file LICENSE Apache License (>= 2.0)
1 1
Apache License 2.0 | file LICENSE Artistic 2.0
1 1
Artistic-2.0 | GPL-2 + file LICENSE BSD_3_clause
1 1
CC BY-SA 4.0 + file LICENSE CPL
1 1
Creative Commons Attribution 4.0 International License EPL (>= 1.0)
1 1
GNU General Public License version 3 GPL (==2)
1 1
GPL (>= 2.1) GPL (>=2 )
1 1
GPL 3 GPL version 3
1 1
GPL-2 | GPL-3 | BSL-1.0 GPL-3 + file LICENCE
1 1
GPL-3 bioconductor.org GPL(>= 2)
1 1
GPL(>=3) LGPL (>= 2.1) | file LICENSE
1 1
LGPL (>= 3.0) LGPL (>= 3); File LICENSE
1 1
LGPL-2.1 MIT | file LICENSE
1 1
MIT License Mozilla Public License 2.0
1 1
Unlimited <NA>
1 1
Apache License (== 2.0) Artistic-1.0
2 2
Artistic-2.0 + file LICENSE BSD 3-clause License + file LICENSE
2 2
CC BY 4.0 CC BY-NC-ND 4.0
2 2
CC BY-NC-ND 4.0 + file LICENSE CC0
2 2
CeCILL | file LICENSE EPL
2 2
GPL (>= 3.0) GPL (>=2.0)
2 2
GPL (>=3.0) GPL (>2)
2 2
GPL (http://www.gnu.org/copyleft/gpl.html) GPL version 2
2 2
GPL Version 2 or later LGPL (>= 2.1)
2 2
LGPL (>=3) LGPL-2.1 | file LICENSE
2 2
LGPL-3 + file LICENSE AGPL-3 + file LICENSE
2 3
CeCILL GPL (>= 2.0)
3 3
GPL (>= 2) + file LICENSE GPL (>=3) + file LICENSE
3 3
Apache License (>= 2) Artistic License 2.0
4 4
GPL-2 + file LICENSE GPL-2 | file LICENSE
4 4
LGPL (>=2) MIT + file LICENCE
4 4
AGPL-3.0-only Apache License 2.0
5 5
GPL (>= 3) + file LICENSE GPL-2 | GPL-3
5 5
GPL(>=2) LGPL-2
5 5
MIT BSD_2_clause + file LICENSE
6 8
LGPL (>= 2.0) LGPL (>= 3)
8 8
GPL (>=3) Artistic-2.0 | file LICENSE
9 13
GPL-3 | file LICENSE AGPL-3
14 16
BSD_3_clause + file LICENSE LGPL (>= 2)
16 18
GPL LGPL-3
21 36
file LICENSE LGPL
39 39
GPL (>=2) GPL-3 + file LICENSE
47 61
GPL (>= 3) GPL (>= 2)
71 177
GPL-2 MIT + file LICENSE
233 345
GPL-3 Artistic-2.0
484 519
Clean up
## Get unique licenses
lic <- unique (pkg$ License)
lic <- lic[! is.na (lic)]
alres <- lapply (structure (lic, names = lic), tools::: analyze_license)
## Get information about the licenses
alres <- do.call (dplyr:: bind_rows, lapply (names (alres), function (nm) {
a <- alres[[nm]]
data.frame (License = nm,
LicenseStandardizable = a$ is_standardizable,
LicenseVerified = a$ is_verified,
LicenseStandardization = a$ standardization,
LicenseCanonical = a$ is_canonical,
LicenseFOSS = a$ is_FOSS,
LicenseRestrictsUse = a$ restricts_use)
}))
## Add additional column removing the "+/| file LICENSE" part (if we want to
## assume that this is compatible with the main license indication)
alres$ LicenseStandardizationShort <- gsub ("[ ]* \\ +* \\ |*[ ]*file LICEN[SC]E" ,
"" , alres$ LicenseStandardization)
dim (alres)
length (unique (alres$ LicenseStandardizationShort))
DT:: datatable (alres,
extensions = "FixedColumns" ,
rownames = FALSE ,
options = list (scrollX = TRUE ,
fixedColumns = list (leftColumns = 1 ),
search = list (regex = FALSE , caseInsensitive = TRUE ),
pageLength = 20 ))
## Add license columns to pkg list
pkg <- pkg %>%
dplyr:: select (Package, Maintainer, License, hasLICENSE) %>%
dplyr:: left_join (alres, by = "License" )
dim (pkg)
DT:: datatable (pkg,
extensions = "FixedColumns" ,
rownames = FALSE ,
options = list (scrollX = TRUE ,
fixedColumns = list (leftColumns = 1 ),
search = list (regex = FALSE , caseInsensitive = TRUE ),
pageLength = 20 ))
Tabulate licenses
sort (table (pkg$ LicenseStandardizationShort, useNA = "ifany" ))
Apache License (>= 2.0) Artistic-2.0 | GPL-2
1 1
CC BY-SA 4.0 CPL
1 1
Creative Commons Attribution 4.0 International License EPL (>= 1.0)
1 1
GNU General Public License version 3 GPL (== 2)
1 1
GPL (>= 2.1) GPL-2 | GPL-3 | BSL-1.0
1 1
LGPL (>= 3.0) MIT License
1 1
Mozilla Public License 2.0 Unlimited
1 1
Artistic-1.0 BSD 3-clause License
2 2
CC BY 4.0 CC0
2 2
EPL GPL (> 2)
2 2
LGPL (>= 2.1) LGPL-2.1
3 3
Apache License (== 2.0) Apache License (>= 2)
4 4
Artistic License 2.0 CC BY-NC-ND 4.0
4 4
GPL (>= 3.0) CeCILL
4 5
GPL (>= 2.0) GPL-2 | GPL-3
5 5
LGPL-2 Apache License 2.0
5 6
BSD_2_clause LGPL (>= 2.0)
8 8
LGPL (>= 3) <NA>
10 10
BSD_3_clause AGPL-3
17 20
GPL LGPL (>= 2)
21 22
LGPL-3
38 39
LGPL GPL (>= 3)
39 89
GPL (>= 2) GPL-2
236 243
MIT Artistic-2.0
356 535
GPL-3
562
Some cases that may need attention
We attempt to estimate the fraction of packages that are provided under an OSI approved license. It should be noted that, automatically performed, this will necessary be a rough estimate, e.g. since there are several packages that do not mention the license explicitly in the DESCRIPTION file but only provide the license text in a separate LICENSE file.
totalNbrPkg <- nrow (pkg)
ccLicensed <- pkg$ Package[grep ("CC|Creative Commons" , pkg$ LicenseStandardizationShort)]
fileLicense <- pkg$ Package[which (pkg$ LicenseStandardizationShort == "" )]
licUnlimited <- pkg$ Package[which (pkg$ LicenseStandardizationShort == "Unlimited" )]
licNotStandardizable <- pkg$ Package[is.na (pkg$ LicenseStandardizationShort)]
fractionOSIApproved <- 1 - length (unique (c (ccLicensed, fileLicense,
licUnlimited, licNotStandardizable)))/ totalNbrPkg
print (paste0 ("Rough estimate of fraction packages with OSI approved license: " ,
signif (100 * fractionOSIApproved, digits = 4 ), "%" ))
[1] "Rough estimate of fraction packages with OSI approved license: 97.43%"
Packages that have just a ‘file LICENSE’
These need to be checked manually.
.makeLinkToLicense <- function (pkg, text) {
sprintf ('<a href="%s" target="_blank"> %s</a>' ,
paste0 ("https://bioconductor.org/packages/devel/bioc/licenses/" ,
pkg, "/LICENSE" ),
text)
}
DT:: datatable (subset (pkg, LicenseStandardizationShort == "" ) %>%
dplyr:: mutate (License = vapply (seq_along (License), function (i) {
.makeLinkToLicense (Package[i], License[i])
}, "NA" )),
extensions = "FixedColumns" ,
rownames = FALSE ,
escape = FALSE ,
options = list (scrollX = TRUE ,
fixedColumns = list (leftColumns = 1 ),
search = list (regex = FALSE , caseInsensitive = TRUE ),
pageLength = 20 ))
Packages that have license “Unlimited”
DT:: datatable (subset (pkg, LicenseStandardizationShort == "Unlimited" ),
extensions = "FixedColumns" ,
rownames = FALSE ,
options = list (scrollX = TRUE ,
fixedColumns = list (leftColumns = 1 ),
search = list (regex = FALSE , caseInsensitive = TRUE ),
pageLength = 20 ))
Packages that have licenses that can not be standardized
Some of these may be false positives.
DT:: datatable (subset (pkg, is.na (LicenseStandardizationShort)),
extensions = "FixedColumns" ,
rownames = FALSE ,
options = list (scrollX = TRUE ,
fixedColumns = list (leftColumns = 1 ),
search = list (regex = FALSE , caseInsensitive = TRUE ),
pageLength = 20 ))
The rest of the licenses appear to be approved open source licenses (https://opensource.org/licenses/alphabetical ).
Session info
R Under development (unstable) (2025-12-07 r89119)
Platform: x86_64-pc-linux-gnu
Running under: Ubuntu 24.04.3 LTS
Matrix products: default
BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so; LAPACK version 3.12.0
locale:
[1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
[5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8 LC_PAPER=en_US.UTF-8 LC_NAME=C
[9] LC_ADDRESS=C LC_TELEPHONE=C LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
time zone: Etc/UTC
tzcode source: system (glibc)
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] DT_0.34.0 dplyr_1.1.4 BiocPkgTools_1.29.2 htmlwidgets_1.6.4
loaded via a namespace (and not attached):
[1] xfun_0.54 bslib_0.9.0 httr2_1.2.1 gh_1.5.0 Biobase_2.71.0
[6] tzdb_0.5.0 vctrs_0.6.5 tools_4.6.0 crosstalk_1.2.2 bitops_1.0-9
[11] generics_0.1.4 stats4_4.6.0 curl_7.0.0 RUnit_0.4.33.1 tibble_3.3.0
[16] RSQLite_2.4.5 blob_1.2.4 pkgconfig_2.0.3 dbplyr_2.5.1 graph_1.89.1
[21] lifecycle_1.0.4 compiler_4.6.0 stringr_1.6.0 biocViews_1.79.0 htmltools_0.5.9
[26] sass_0.4.10 RCurl_1.98-1.17 yaml_2.3.11 jquerylib_0.1.4 pillar_1.11.1
[31] tidyr_1.3.1 cachem_1.1.0 tidyselect_1.2.1 rvest_1.0.5 digest_0.6.39
[36] stringi_1.8.7 purrr_1.2.0 fastmap_1.2.0 cli_3.6.5 magrittr_2.0.4
[41] RBGL_1.87.0 XML_3.99-0.20 readr_2.1.6 withr_3.0.2 filelock_1.0.3
[46] rappdirs_0.3.3 bit64_4.6.0-1 lubridate_1.9.4 timechange_0.3.0 rmarkdown_2.30
[51] httr_1.4.7 igraph_2.2.1 bit_4.6.0 hms_1.1.4 memoise_2.0.1
[56] evaluate_1.0.5 knitr_1.50 BiocFileCache_3.1.0 rlang_1.1.6 glue_1.8.0
[61] DBI_1.2.3 BiocManager_1.30.27 xml2_1.5.1 BiocGenerics_0.57.0 jsonlite_2.0.0
[66] R6_2.6.1