library(cBioPortalData)
library(AnVIL)
This document serves as a reporting tool for errors that occur when running our utility functions on the cBioPortal datasets.
cBioPortalData()
)Typically, the number of errors encountered via the API are low. There are only a handful of packages that error when we apply the utility functions to provide a MultiAssayExperiment data representation.
First, we load the error Rda
dataset.
api_errs <- system.file(
"extdata", "api", "err_api_info.rda",
package = "cBioPortalData", mustWork = TRUE
)
load(api_errs)
We can now inspect the contents of the data:
class(err_api_info)
## [1] "list"
length(err_api_info)
## [1] 6
lengths(err_api_info)
## Barcodes must start with 'TCGA'
## 2
## group length is 0 but data length > 0
## 1
## Frequency of NA values higher than the cutoff tolerance
## 2
## Inconsistent build numbers found
## 33
## `n` must be a single number, not an integer `NA`.
## 1
## Argument 1 must be a data frame or a named atomic vector.
## 1
There were about 6 unique errors during the last build run.
names(err_api_info)
## [1] "Barcodes must start with 'TCGA'"
## [2] "group length is 0 but data length > 0"
## [3] "Frequency of NA values higher than the cutoff tolerance"
## [4] "Inconsistent build numbers found"
## [5] "`n` must be a single number, not an integer `NA`."
## [6] "Argument 1 must be a data frame or a named atomic vector."
The most common error was Inconsistent build numbers found
. This is
due to annotations from different build numbers that were not able to
be resolved.
To see what datasets (cancer_study_id
s) have that error we can use:
err_api_info[['Inconsistent build numbers found']]
## [1] "msk_ch_2020" "msk_access_2021"
## [3] "mixed_msk_tcga_2021" "mixed_impact_subset_2022"
## [5] "pan_origimed_2020" "prad_msk_stopsack_2021"
## [7] "pancan_pcawg_2020" "prad_pik3r1_msk_2021"
## [9] "skcm_tcga" "stad_tcga"
## [11] "stad_tcga_pub" "skcm_tcga_pan_can_atlas_2018"
## [13] "stad_tcga_pan_can_atlas_2018" "stes_tcga_pub"
## [15] "summit_2018" "cfdna_msk_2019"
## [17] "blca_bcan_hcrn_2022" "nsclc_ctdx_msk_2022"
## [19] "thyroid_mskcc_2016" "skcm_mskcc_2014"
## [21] "tmb_mskcc_2018" "rectal_msk_2019"
## [23] "skcm_tcga_pub_2015" "msk_spectrum_tme_2022"
## [25] "ucec_ccr_cfdna_msk_2022" "paired_bladder_2022"
## [27] "mtnn_msk_2022" "pog570_bcgsc_2020"
## [29] "sarcoma_msk_2023" "bowel_colitis_msk_2022"
## [31] "luad_mskcc_2023_met_organotropism" "coad_silu_2022"
## [33] "paac_msk_jco_2023"
We can also have a look at the entirety of the dataset.
err_api_info
## $`Barcodes must start with 'TCGA'`
## [1] "blca_msk_tcga_2020" "nsclc_tcga_broad_2016"
##
## $`group length is 0 but data length > 0`
## [1] "glioma_msk_2018"
##
## $`Frequency of NA values higher than the cutoff tolerance`
## [1] "mixed_selpercatinib_2020" "ucec_ccr_msk_2022"
##
## $`Inconsistent build numbers found`
## [1] "msk_ch_2020" "msk_access_2021"
## [3] "mixed_msk_tcga_2021" "mixed_impact_subset_2022"
## [5] "pan_origimed_2020" "prad_msk_stopsack_2021"
## [7] "pancan_pcawg_2020" "prad_pik3r1_msk_2021"
## [9] "skcm_tcga" "stad_tcga"
## [11] "stad_tcga_pub" "skcm_tcga_pan_can_atlas_2018"
## [13] "stad_tcga_pan_can_atlas_2018" "stes_tcga_pub"
## [15] "summit_2018" "cfdna_msk_2019"
## [17] "blca_bcan_hcrn_2022" "nsclc_ctdx_msk_2022"
## [19] "thyroid_mskcc_2016" "skcm_mskcc_2014"
## [21] "tmb_mskcc_2018" "rectal_msk_2019"
## [23] "skcm_tcga_pub_2015" "msk_spectrum_tme_2022"
## [25] "ucec_ccr_cfdna_msk_2022" "paired_bladder_2022"
## [27] "mtnn_msk_2022" "pog570_bcgsc_2020"
## [29] "sarcoma_msk_2023" "bowel_colitis_msk_2022"
## [31] "luad_mskcc_2023_met_organotropism" "coad_silu_2022"
## [33] "paac_msk_jco_2023"
##
## $``n` must be a single number, not an integer `NA`.`
## [1] "msk_met_2021"
##
## $`Argument 1 must be a data frame or a named atomic vector.`
## [1] "makeanimpact_ccr_2023"
cBioDataPack()
Now let’s look at the errors in the packaged datasets that are used for
cBioDataPack
:
pack_errs <- system.file(
"extdata", "pack", "err_pack_info.rda",
package = "cBioPortalData", mustWork = TRUE
)
load(pack_errs)
We can do the same for this data:
length(err_pack_info)
## [1] 5
lengths(err_pack_info)
## more columns than column names
## 9
## Frequency of NA values higher than the cutoff tolerance
## 5
## non-character argument
## 2
## invalid class "ExperimentList" object: \n Non-unique names provided
## 2
## 'wget' call had nonzero exit status
## 11
We can get a list of all the errors present:
names(err_pack_info)
## [1] "more columns than column names"
## [2] "Frequency of NA values higher than the cutoff tolerance"
## [3] "non-character argument"
## [4] "invalid class \"ExperimentList\" object: \n Non-unique names provided"
## [5] "'wget' call had nonzero exit status"
And finally the full list of errors:
err_pack_info
## $`more columns than column names`
## [1] "ccrcc_utokyo_2013" "coadread_tcga_pan_can_atlas_2018"
## [3] "gbm_cptac_2021" "ov_tcga_pan_can_atlas_2018"
## [5] "pan_origimed_2020" "sarc_tcga_pan_can_atlas_2018"
## [7] "luad_mskimpact_2021" "mbl_dkfz_2017"
## [9] "brca_tcga_pan_can_atlas_2018"
##
## $`Frequency of NA values higher than the cutoff tolerance`
## [1] "ihch_mskcc_2020" "ihch_msk_2021"
## [3] "mixed_selpercatinib_2020" "mixed_msk_tcga_2021"
## [5] "ucec_ccr_msk_2022"
##
## $`non-character argument`
## [1] "mbn_mdacc_2013" "pcpg_tcga_pub"
##
## $`invalid class "ExperimentList" object: \n Non-unique names provided`
## [1] "stad_tcga_pub" "mpnst_mskcc"
##
## $`'wget' call had nonzero exit status`
## [1] "makeanimpact_ccr_2023" "prad_organoids_msk_2022"
## [3] "mtnn_msk_2022" "sarcoma_msk_2023"
## [5] "bowel_colitis_msk_2022" "bladder_mskcc_2022"
## [7] "paac_msk_jco_2023" "nbl_msk_2023"
## [9] "rms_msk_2023" "gist_msk_2023"
## [11] "egc_trap_ccr_msk_2023"
sessionInfo()
## 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] survminer_0.4.9 ggpubr_0.6.0
## [3] ggplot2_3.5.1 survival_3.7-0
## [5] cBioPortalData_2.18.0 MultiAssayExperiment_1.32.0
## [7] SummarizedExperiment_1.36.0 Biobase_2.66.0
## [9] GenomicRanges_1.58.0 GenomeInfoDb_1.42.0
## [11] IRanges_2.40.0 S4Vectors_0.44.0
## [13] BiocGenerics_0.52.0 MatrixGenerics_1.18.0
## [15] matrixStats_1.4.1 AnVIL_1.18.0
## [17] AnVILBase_1.0.0 dplyr_1.1.4
## [19] BiocStyle_2.34.0
##
## loaded via a namespace (and not attached):
## [1] jsonlite_1.8.9 magrittr_2.0.3
## [3] magick_2.8.5 GenomicFeatures_1.58.0
## [5] farver_2.1.2 rmarkdown_2.28
## [7] BiocIO_1.16.0 zlibbioc_1.52.0
## [9] vctrs_0.6.5 memoise_2.0.1
## [11] Rsamtools_2.22.0 RCurl_1.98-1.16
## [13] tinytex_0.53 rstatix_0.7.2
## [15] htmltools_0.5.8.1 S4Arrays_1.6.0
## [17] BiocBaseUtils_1.8.0 lambda.r_1.2.4
## [19] curl_5.2.3 broom_1.0.7
## [21] Formula_1.2-5 SparseArray_1.6.0
## [23] sass_0.4.9 bslib_0.8.0
## [25] htmlwidgets_1.6.4 httr2_1.0.5
## [27] zoo_1.8-12 futile.options_1.0.1
## [29] cachem_1.1.0 commonmark_1.9.2
## [31] GenomicAlignments_1.42.0 mime_0.12
## [33] lifecycle_1.0.4 pkgconfig_2.0.3
## [35] Matrix_1.7-1 R6_2.5.1
## [37] fastmap_1.2.0 GenomeInfoDbData_1.2.13
## [39] shiny_1.9.1 digest_0.6.37
## [41] colorspace_2.1-1 RaggedExperiment_1.30.0
## [43] AnnotationDbi_1.68.0 ps_1.8.1
## [45] RSQLite_2.3.7 labeling_0.4.3
## [47] filelock_1.0.3 RTCGAToolbox_2.36.0
## [49] km.ci_0.5-6 fansi_1.0.6
## [51] RJSONIO_1.3-1.9 httr_1.4.7
## [53] abind_1.4-8 compiler_4.4.1
## [55] bit64_4.5.2 withr_3.0.2
## [57] backports_1.5.0 BiocParallel_1.40.0
## [59] carData_3.0-5 DBI_1.2.3
## [61] highr_0.11 ggsignif_0.6.4
## [63] rappdirs_0.3.3 DelayedArray_0.32.0
## [65] rjson_0.2.23 tools_4.4.1
## [67] chromote_0.3.1 httpuv_1.6.15
## [69] glue_1.8.0 restfulr_0.0.15
## [71] promises_1.3.0 gridtext_0.1.5
## [73] grid_4.4.1 generics_0.1.3
## [75] gtable_0.3.6 KMsurv_0.1-5
## [77] tzdb_0.4.0 tidyr_1.3.1
## [79] websocket_1.4.2 data.table_1.16.2
## [81] hms_1.1.3 car_3.1-3
## [83] xml2_1.3.6 utf8_1.2.4
## [85] XVector_0.46.0 markdown_1.13
## [87] pillar_1.9.0 stringr_1.5.1
## [89] later_1.3.2 splines_4.4.1
## [91] ggtext_0.1.2 BiocFileCache_2.14.0
## [93] lattice_0.22-6 rtracklayer_1.66.0
## [95] bit_4.5.0 tidyselect_1.2.1
## [97] Biostrings_2.74.0 miniUI_0.1.1.1
## [99] knitr_1.48 gridExtra_2.3
## [101] bookdown_0.41 futile.logger_1.4.3
## [103] xfun_0.48 DT_0.33
## [105] stringi_1.8.4 UCSC.utils_1.2.0
## [107] yaml_2.3.10 evaluate_1.0.1
## [109] codetools_0.2-20 tibble_3.2.1
## [111] BiocManager_1.30.25 cli_3.6.3
## [113] xtable_1.8-4 munsell_0.5.1
## [115] processx_3.8.4 jquerylib_0.1.4
## [117] survMisc_0.5.6 Rcpp_1.0.13
## [119] GenomicDataCommons_1.30.0 dbplyr_2.5.0
## [121] png_0.1-8 XML_3.99-0.17
## [123] rapiclient_0.1.8 parallel_4.4.1
## [125] TCGAutils_1.26.0 readr_2.1.5
## [127] blob_1.2.4 bitops_1.0-9
## [129] scales_1.3.0 purrr_1.0.2
## [131] crayon_1.5.3 rlang_1.1.4
## [133] KEGGREST_1.46.0 rvest_1.0.4
## [135] formatR_1.14