MsDataHub 1.6.0
The MsDataHub
package provides example mass spectrometry data,
peptide spectrum matches or quantitative data from proteomics and
metabolomics experiments. The data are served through the
ExperimentHub
infrastructure, which allows download them only ones
and cache them for further use. Currently available data are summarised
in the table below and details in the next section.
library("MsDataHub")
DT::datatable(MsDataHub())
To install the package:
if (!require("BiocManager"))
install.packages("BiocManager")
BiocManager::install("MsDataHub")
PestMix1_DDA.mzML
and PestMix1_SWATH.mzML
?TripleTOF
Load with
f <- PestMix1_DDA.mzML()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
library(Spectra)
Spectra(f)
## MSn data (Spectra) with 7602 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 1 0.231 1
## 2 1 0.351 2
## 3 1 0.471 3
## 4 1 0.591 4
## 5 1 0.711 5
## ... ... ... ...
## 7598 1 899.491 7598
## 7599 1 899.613 7599
## 7600 1 899.747 7600
## 7601 1 899.872 7601
## 7602 1 899.993 7602
## ... 33 more variables/columns.
##
## file(s):
## 1e0e954878e0b6_7861
f <- PestMix1_SWATH.mzML()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
Spectra(f)
## MSn data (Spectra) with 8999 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 2 0.203 1
## 2 2 0.300 2
## 3 2 0.397 3
## 4 2 0.494 4
## 5 2 0.591 5
## ... ... ... ...
## 8995 2 899.527 8995
## 8996 2 899.624 8996
## 8997 2 899.721 8997
## 8998 2 899.818 8998
## 8999 2 899.915 8999
## ... 33 more variables/columns.
##
## file(s):
## 1e0e955f137cc1_7862
20171016_POOL_POS_1_105-134.mzML
and 20171016_POOL_POS_3_105-134.mzML
?sciex
Load with
f <- X20171016_POOL_POS_1_105.134.mzML()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
Spectra(f)
## MSn data (Spectra) with 931 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 1 0.280 1
## 2 1 0.559 2
## 3 1 0.838 3
## 4 1 1.117 4
## 5 1 1.396 5
## ... ... ... ...
## 927 1 258.641 927
## 928 1 258.920 928
## 929 1 259.199 929
## 930 1 259.478 930
## 931 1 259.757 931
## ... 33 more variables/columns.
##
## file(s):
## 1e0e957f85077d_7859
f <- X20171016_POOL_POS_3_105.134.mzML()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
Spectra(f)
## MSn data (Spectra) with 931 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 1 0.275 1
## 2 1 0.554 2
## 3 1 0.833 3
## 4 1 1.112 4
## 5 1 1.391 5
## ... ... ... ...
## 927 1 258.636 927
## 928 1 258.915 928
## 929 1 259.194 929
## 930 1 259.473 930
## 931 1 259.752 931
## ... 33 more variables/columns.
##
## file(s):
## 1e0e9547eaa1e7_7860
TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01-20141210.mzML.gz
and
TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01-20141210.mzid
?PDX000001
Load with
f <- TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.20141210.mzML.gz()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
Spectra(f)
## MSn data (Spectra) with 7534 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 1 0.4584 1
## 2 1 0.9725 2
## 3 1 1.8524 3
## 4 1 2.7424 4
## 5 1 3.6124 5
## ... ... ... ...
## 7530 2 3600.47 7530
## 7531 2 3600.83 7531
## 7532 2 3601.18 7532
## 7533 2 3601.57 7533
## 7534 2 3601.98 7534
## ... 33 more variables/columns.
##
## file(s):
## 1e0e95128647c4_7858
f <- TMT_Erwinia_1uLSike_Top10HCD_isol2_45stepped_60min_01.20141210.mzid()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
library(PSMatch)
PSM(f)
## PSM with 5802 rows and 35 columns.
## names(35): sequence spectrumID ... subReplacementResidue subLocation
cptac_a_b_c_peptides.txt
, cptac_a_b_peptides.txt
and
cptac_peptides.txt
?cptac
Load with
library(QFeatures)
f <- cptac_peptides.txt()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
ecols <- grep("Intensity\\.", names(read.delim(f)))
readSummarizedExperiment(f, ecols, sep = "\t")
## class: SummarizedExperiment
## dim: 11466 45
## metadata(0):
## assays(1): ''
## rownames(11466): 1 2 ... 11465 11466
## rowData names(143): Sequence N.term.cleavage.window ...
## Oxidation..M..site.IDs MS.MS.Count
## colnames(45): Intensity.6A_1 Intensity.6A_2 ... Intensity.6E_8
## Intensity.6E_9
## colData names(0):
cptac_a_b_c_peptides.txt()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
## EH7804
## "/home/biocbuild/.cache/R/ExperimentHub/1e0e95147925cd_7854"
cptac_a_b_peptides.txt()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
## EH7805
## "/home/biocbuild/.cache/R/ExperimentHub/1e0e9541f34035_7855"
ko15.CDF
?cdf
Load with
f <- ko15.CDF()
## see ?MsDataHub and browseVignettes('MsDataHub') for documentation
## loading from cache
Spectra(f)
## MSn data (Spectra) with 1278 spectra in a MsBackendMzR backend:
## msLevel rtime scanIndex
## <integer> <numeric> <integer>
## 1 1 2501.38 1
## 2 1 2502.94 2
## 3 1 2504.51 3
## 4 1 2506.07 4
## 5 1 2507.64 5
## ... ... ... ...
## 1274 1 4493.56 1274
## 1275 1 4495.13 1275
## 1276 1 4496.69 1276
## 1277 1 4498.26 1277
## 1278 1 4499.82 1278
## ... 33 more variables/columns.
##
## file(s):
## 1e0e951bb72970_7853
benchmarkingDIA.tsv
Report.Derks2022.plexDIA.tsv
?benchmarkingDIA.tsv
and
?Report.Derks2022.plexDIA.tsv
Load with
library(QFeatures)
lfdia <- read.delim(MsDataHub::benchmarkingDIA.tsv())
readQFeaturesFromDIANN(lfdia)
## An instance of class QFeatures containing 24 assays:
## [1] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_0_1fmol_inj1.mzML: SummarizedExperiment with 28980 rows and 1 columns
## [2] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_0_1fmol_inj2.mzML: SummarizedExperiment with 29495 rows and 1 columns
## [3] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_0_1fmol_inj3.mzML: SummarizedExperiment with 29210 rows and 1 columns
## ...
## [22] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_5fmol_inj1.mzML: SummarizedExperiment with 30941 rows and 1 columns
## [23] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_5fmol_inj2.mzML: SummarizedExperiment with 30321 rows and 1 columns
## [24] U:\712006-Proteomics\Issues\Issue 253\DIANN\raw-data\RD139_Overlap_UPS1_5fmol_inj3.mzML: SummarizedExperiment with 24168 rows and 1 columns
plexdia <- read.delim(MsDataHub::Report.Derks2022.plexDIA.tsv())
readQFeaturesFromDIANN(plexdia, multiplexing = "mTRAQ")
## An instance of class QFeatures containing 54 assays:
## [1] F:\JD\plexDIA\nPOP\wJD1146.raw: SummarizedExperiment with 2635 rows and 3 columns
## [2] F:\JD\plexDIA\nPOP\wJD1147.raw: SummarizedExperiment with 3000 rows and 3 columns
## [3] F:\JD\plexDIA\nPOP\wJD1148.raw: SummarizedExperiment with 2676 rows and 3 columns
## ...
## [52] F:\JD\plexDIA\nPOP\wJD1203.raw: SummarizedExperiment with 4441 rows and 3 columns
## [53] F:\JD\plexDIA\nPOP\wJD1204.raw: SummarizedExperiment with 4416 rows and 3 columns
## [54] F:\JD\plexDIA\nPOP\wJD1205.raw: SummarizedExperiment with 4492 rows and 3 columns
MsDataHub
MsDataHub
, start by
opening an
issue
in the package’s GitHub repository and describe the new data. In
particular, provide information about it’s provenance, its use, its
format(s) and acknowledge that the data may be shared freely with
the community without any restrictions. You may provide an open
licence specifying the terms it can be re-used, typically a
CC-BY-SA license.ExperimentHub
packages and GitHub pull requests, you may
directly send one that adds your data to the package. Make sure (1)
add appropriate references in the manual page and (2) to add
yourself as a contributor of the package in the DESCRIPTION file.## R version 4.4.1 (2024-06-14)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.1 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.20-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB 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
##
## time zone: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] MsDataHub_1.6.0 QFeatures_1.16.0
## [3] MultiAssayExperiment_1.32.0 SummarizedExperiment_1.36.0
## [5] Biobase_2.66.0 GenomicRanges_1.58.0
## [7] GenomeInfoDb_1.42.0 IRanges_2.40.0
## [9] MatrixGenerics_1.18.0 matrixStats_1.4.1
## [11] PSMatch_1.10.0 Spectra_1.16.0
## [13] BiocParallel_1.40.0 S4Vectors_0.44.0
## [15] BiocGenerics_0.52.0 BiocStyle_2.34.0
##
## loaded via a namespace (and not attached):
## [1] DBI_1.2.3 rlang_1.1.4 magrittr_2.0.3
## [4] clue_0.3-65 compiler_4.4.1 RSQLite_2.3.7
## [7] png_0.1-8 vctrs_0.6.5 reshape2_1.4.4
## [10] stringr_1.5.1 ProtGenerics_1.38.0 pkgconfig_2.0.3
## [13] MetaboCoreUtils_1.14.0 crayon_1.5.3 fastmap_1.2.0
## [16] dbplyr_2.5.0 XVector_0.46.0 utf8_1.2.4
## [19] rmarkdown_2.28 UCSC.utils_1.2.0 purrr_1.0.2
## [22] bit_4.5.0 xfun_0.48 zlibbioc_1.52.0
## [25] cachem_1.1.0 jsonlite_1.8.9 blob_1.2.4
## [28] DelayedArray_0.32.0 parallel_4.4.1 cluster_2.1.6
## [31] R6_2.5.1 bslib_0.8.0 stringi_1.8.4
## [34] jquerylib_0.1.4 Rcpp_1.0.13 bookdown_0.41
## [37] knitr_1.48 Matrix_1.7-1 igraph_2.1.1
## [40] tidyselect_1.2.1 abind_1.4-8 yaml_2.3.10
## [43] codetools_0.2-20 curl_5.2.3 lattice_0.22-6
## [46] tibble_3.2.1 plyr_1.8.9 withr_3.0.2
## [49] KEGGREST_1.46.0 evaluate_1.0.1 BiocFileCache_2.14.0
## [52] ExperimentHub_2.14.0 Biostrings_2.74.0 pillar_1.9.0
## [55] BiocManager_1.30.25 filelock_1.0.3 DT_0.33
## [58] ncdf4_1.23 generics_0.1.3 BiocVersion_3.20.0
## [61] glue_1.8.0 lazyeval_0.2.2 tools_4.4.1
## [64] AnnotationHub_3.14.0 mzR_2.40.0 fs_1.6.4
## [67] grid_4.4.1 tidyr_1.3.1 crosstalk_1.2.1
## [70] MsCoreUtils_1.18.0 AnnotationDbi_1.68.0 GenomeInfoDbData_1.2.13
## [73] cli_3.6.3 rappdirs_0.3.3 fansi_1.0.6
## [76] S4Arrays_1.6.0 dplyr_1.1.4 AnnotationFilter_1.30.0
## [79] sass_0.4.9 digest_0.6.37 SparseArray_1.6.0
## [82] htmlwidgets_1.6.4 memoise_2.0.1 htmltools_0.5.8.1
## [85] lifecycle_1.0.4 httr_1.4.7 mime_0.12
## [88] bit64_4.5.2 MASS_7.3-61