library(gDRutils)
suppressPackageStartupMessages(library(MultiAssayExperiment))gDRutils is the part of gDR suite. This package provides bunch of tools for, among others:
* data manipulation, especially output of the gDRcore package (MultiAssayExperiments and SummarizedExperiment),
* data extraction,
* managing identifiers used for creating gDR experiments,
* data validation.
The basic output of gDRcore package is the MultiAssayExperiment object. Function MAEpply allows for the data manipulation of this object, and can be used in a similar way as a basic function lapply.
mae <- get_synthetic_data("finalMAE_combo_matrix_small")
MAEpply(mae, dim)
#> $combination
#> [1] 6 2
#>
#> $`single-agent`
#> [1] 5 2MAEpply(mae, rowData)
#> $combination
#> DataFrame with 6 rows and 7 columns
#> Gnumber DrugName
#> <character> <character>
#> G00004_drug_004_moa_A_G00021_drug_021_moa_D_72 G00004 drug_004
#> G00004_drug_004_moa_A_G00026_drug_026_moa_E_72 G00004 drug_004
#> G00005_drug_005_moa_A_G00021_drug_021_moa_D_72 G00005 drug_005
#> G00005_drug_005_moa_A_G00026_drug_026_moa_E_72 G00005 drug_005
#> G00006_drug_006_moa_A_G00021_drug_021_moa_D_72 G00006 drug_006
#> G00006_drug_006_moa_A_G00026_drug_026_moa_E_72 G00006 drug_006
#> drug_moa Gnumber_2
#> <character> <character>
#> G00004_drug_004_moa_A_G00021_drug_021_moa_D_72 moa_A G00021
#> G00004_drug_004_moa_A_G00026_drug_026_moa_E_72 moa_A G00026
#> G00005_drug_005_moa_A_G00021_drug_021_moa_D_72 moa_A G00021
#> G00005_drug_005_moa_A_G00026_drug_026_moa_E_72 moa_A G00026
#> G00006_drug_006_moa_A_G00021_drug_021_moa_D_72 moa_A G00021
#> G00006_drug_006_moa_A_G00026_drug_026_moa_E_72 moa_A G00026
#> DrugName_2 drug_moa_2
#> <character> <character>
#> G00004_drug_004_moa_A_G00021_drug_021_moa_D_72 drug_021 moa_D
#> G00004_drug_004_moa_A_G00026_drug_026_moa_E_72 drug_026 moa_E
#> G00005_drug_005_moa_A_G00021_drug_021_moa_D_72 drug_021 moa_D
#> G00005_drug_005_moa_A_G00026_drug_026_moa_E_72 drug_026 moa_E
#> G00006_drug_006_moa_A_G00021_drug_021_moa_D_72 drug_021 moa_D
#> G00006_drug_006_moa_A_G00026_drug_026_moa_E_72 drug_026 moa_E
#> Duration
#> <numeric>
#> G00004_drug_004_moa_A_G00021_drug_021_moa_D_72 72
#> G00004_drug_004_moa_A_G00026_drug_026_moa_E_72 72
#> G00005_drug_005_moa_A_G00021_drug_021_moa_D_72 72
#> G00005_drug_005_moa_A_G00026_drug_026_moa_E_72 72
#> G00006_drug_006_moa_A_G00021_drug_021_moa_D_72 72
#> G00006_drug_006_moa_A_G00026_drug_026_moa_E_72 72
#>
#> $`single-agent`
#> DataFrame with 5 rows and 4 columns
#> Gnumber DrugName drug_moa Duration
#> <character> <character> <character> <numeric>
#> G00004_drug_004_moa_A_72 G00004 drug_004 moa_A 72
#> G00005_drug_005_moa_A_72 G00005 drug_005 moa_A 72
#> G00006_drug_006_moa_A_72 G00006 drug_006 moa_A 72
#> G00021_drug_021_moa_D_72 G00021 drug_021 moa_D 72
#> G00026_drug_026_moa_E_72 G00026 drug_026 moa_E 72This function allows also for extraction of unified data across all the SummarizedExperiments inside MultiAssayExperiment, e.g.
MAEpply(mae, rowData, unify = TRUE)
#> Gnumber DrugName drug_moa Gnumber_2 DrugName_2 drug_moa_2 Duration
#> <char> <char> <char> <char> <char> <char> <num>
#> 1: G00004 drug_004 moa_A G00021 drug_021 moa_D 72
#> 2: G00004 drug_004 moa_A G00026 drug_026 moa_E 72
#> 3: G00005 drug_005 moa_A G00021 drug_021 moa_D 72
#> 4: G00005 drug_005 moa_A G00026 drug_026 moa_E 72
#> 5: G00006 drug_006 moa_A G00021 drug_021 moa_D 72
#> 6: G00006 drug_006 moa_A G00026 drug_026 moa_E 72
#> 7: G00004 drug_004 moa_A <NA> <NA> <NA> 72
#> 8: G00005 drug_005 moa_A <NA> <NA> <NA> 72
#> 9: G00006 drug_006 moa_A <NA> <NA> <NA> 72
#> 10: G00021 drug_021 moa_D <NA> <NA> <NA> 72
#> 11: G00026 drug_026 moa_E <NA> <NA> <NA> 72All the metrics data are stored inside assays of SummarizedExperiment. For the downstream analyses we provide tools allowing for the extraction of the data into user-friendly data.table style.
There are two functions working on MultiAssayExperiment object (convert_mae_assay_to_dt) and for SummarizedExperiment (convert_se_assay_to_dt).
mdt <- convert_mae_assay_to_dt(mae, "Metrics")
#> Loading required package: BumpyMatrix
head(mdt, 3)
#> rId
#> <char>
#> 1: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> 2: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> 3: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> cId x_mean x_AOC x_AOC_range xc50 x_max
#> <char> <num> <num> <num> <num> <num>
#> 1: CL00016_cellline_GB_tissue_y_46 -0.7046 1.7046 1.7046 -Inf -0.7046
#> 2: CL00016_cellline_GB_tissue_y_46 -0.7039 1.7039 1.7039 -Inf -0.7039
#> 3: CL00016_cellline_GB_tissue_y_46 -0.6920 1.6920 1.6920 -Inf -0.6920
#> ec50 x_inf x_0 h r2 x_sd_avg fit_type
#> <num> <num> <num> <num> <num> <num> <char>
#> 1: 0 -0.7046 -0.7046 1e-04 0 0 DRCConstantFitResult
#> 2: 0 -0.7039 -0.7039 1e-04 0 0 DRCConstantFitResult
#> 3: 0 -0.6920 -0.6920 1e-04 0 0 DRCConstantFitResult
#> maxlog10Concentration N_conc normalization_type fit_source cotrt_value ratio
#> <num> <int> <char> <char> <num> <num>
#> 1: 0.4996871 8 GR gDR 3.160 NA
#> 2: 0.4996871 8 GR gDR 1.000 NA
#> 3: 0.4996871 8 GR gDR 0.316 NA
#> source Gnumber DrugName drug_moa Gnumber_2 DrugName_2 drug_moa_2
#> <char> <char> <char> <char> <char> <char> <char>
#> 1: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> 2: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> 3: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> Duration clid CellLineName Tissue ReferenceDivisionTime
#> <num> <char> <char> <char> <num>
#> 1: 72 CL00016 cellline_GB tissue_y 46
#> 2: 72 CL00016 cellline_GB tissue_y 46
#> 3: 72 CL00016 cellline_GB tissue_y 46or alternatively for SummarizedExperiment object:
se <- mae[[1]]
sdt <- convert_se_assay_to_dt(se, "Metrics")
head(sdt, 3)
#> rId
#> <char>
#> 1: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> 2: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> 3: G00004_drug_004_moa_A_G00021_drug_021_moa_D_72
#> cId x_mean x_AOC x_AOC_range xc50 x_max
#> <char> <num> <num> <num> <num> <num>
#> 1: CL00016_cellline_GB_tissue_y_46 -0.7046 1.7046 1.7046 -Inf -0.7046
#> 2: CL00016_cellline_GB_tissue_y_46 -0.7039 1.7039 1.7039 -Inf -0.7039
#> 3: CL00016_cellline_GB_tissue_y_46 -0.6920 1.6920 1.6920 -Inf -0.6920
#> ec50 x_inf x_0 h r2 x_sd_avg fit_type
#> <num> <num> <num> <num> <num> <num> <char>
#> 1: 0 -0.7046 -0.7046 1e-04 0 0 DRCConstantFitResult
#> 2: 0 -0.7039 -0.7039 1e-04 0 0 DRCConstantFitResult
#> 3: 0 -0.6920 -0.6920 1e-04 0 0 DRCConstantFitResult
#> maxlog10Concentration N_conc normalization_type fit_source cotrt_value ratio
#> <num> <int> <char> <char> <num> <num>
#> 1: 0.4996871 8 GR gDR 3.160 NA
#> 2: 0.4996871 8 GR gDR 1.000 NA
#> 3: 0.4996871 8 GR gDR 0.316 NA
#> source Gnumber DrugName drug_moa Gnumber_2 DrugName_2 drug_moa_2
#> <char> <char> <char> <char> <char> <char> <char>
#> 1: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> 2: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> 3: row_fittings G00004 drug_004 moa_A G00021 drug_021 moa_D
#> Duration clid CellLineName Tissue ReferenceDivisionTime
#> <num> <char> <char> <char> <num>
#> 1: 72 CL00016 cellline_GB tissue_y 46
#> 2: 72 CL00016 cellline_GB tissue_y 46
#> 3: 72 CL00016 cellline_GB tissue_y 46In gDR we require standard identifiers that should be visible in the input data, such as e.g. Gnumber, CLID, Concentration. However, user can define their own custom identifiers.
To display gDR default identifier they can use get_env_identifiers function:
get_env_identifiers()
#> $duration
#> [1] "Duration"
#>
#> $cellline
#> [1] "clid"
#>
#> $cellline_name
#> [1] "CellLineName"
#>
#> $cellline_tissue
#> [1] "Tissue"
#>
#> $cellline_ref_div_time
#> [1] "ReferenceDivisionTime"
#>
#> $cellline_parental_identifier
#> [1] "parental_identifier"
#>
#> $cellline_subtype
#> [1] "subtype"
#>
#> $drug
#> [1] "Gnumber"
#>
#> $drug_name
#> [1] "DrugName"
#>
#> $drug_moa
#> [1] "drug_moa"
#>
#> $untreated_tag
#> [1] "vehicle" "untreated"
#>
#> $masked_tag
#> [1] "masked"
#>
#> $well_position
#> [1] "WellRow" "WellColumn"
#>
#> $concentration
#> [1] "Concentration"
#>
#> $template
#> [1] "Template" "Treatment"
#>
#> $barcode
#> [1] "Barcode" "Plate"
#>
#> $drug2
#> [1] "Gnumber_2"
#>
#> $drug_name2
#> [1] "DrugName_2"
#>
#> $drug_moa2
#> [1] "drug_moa_2"
#>
#> $concentration2
#> [1] "Concentration_2"
#>
#> $drug3
#> [1] "Gnumber_3"
#>
#> $drug_name3
#> [1] "DrugName_3"
#>
#> $drug_moa3
#> [1] "drug_moa_3"
#>
#> $concentration3
#> [1] "Concentration_3"
#>
#> $data_source
#> [1] "data_source"
#>
#> $replicate
#> [1] "Replicate"To change any of these identifiers user can use set_env_identifier, e.g.
set_env_identifier("concentration", "Dose")and confirm, by displaying:
get_env_identifiers("concentration")
#> [1] "Dose"To restore default identifiers user can use reset_env_identifiers.
reset_env_identifiers()get_env_identifiers("concentration")
#> [1] "Concentration"Applied custom changes in the gDR output can upset internal functions operation. Custom changes can be validated using validate_MAE
validate_MAE(mae)or validate_SE.
validate_SE(se)assay(se, "Normalized") <- NULL
validate_SE(se)
#> Error in validate_SE(se): Assertion on 'exp_assay_names' failed: Must be a subset of {'RawTreated','Controls','Averaged','excess','all_iso_points','isobolograms','scores','Metrics'}, but has additional elements {'Normalized'}.sessionInfo()
#> R version 4.4.0 beta (2024-04-15 r86425)
#> Platform: x86_64-pc-linux-gnu
#> Running under: Ubuntu 22.04.4 LTS
#>
#> Matrix products: default
#> BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
#>
#> locale:
#> [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
#> [3] 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
#> [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] BumpyMatrix_1.12.0 MultiAssayExperiment_1.30.0
#> [3] SummarizedExperiment_1.34.0 Biobase_2.64.0
#> [5] GenomicRanges_1.56.0 GenomeInfoDb_1.40.0
#> [7] IRanges_2.38.0 S4Vectors_0.42.0
#> [9] BiocGenerics_0.50.0 MatrixGenerics_1.16.0
#> [11] matrixStats_1.3.0 gDRutils_1.2.0
#> [13] BiocStyle_2.32.0
#>
#> loaded via a namespace (and not attached):
#> [1] Matrix_1.7-0 jsonlite_1.8.8 compiler_4.4.0
#> [4] BiocManager_1.30.22 crayon_1.5.2 Rcpp_1.0.12
#> [7] jquerylib_0.1.4 yaml_2.3.8 fastmap_1.1.1
#> [10] lattice_0.22-6 R6_2.5.1 XVector_0.44.0
#> [13] S4Arrays_1.4.0 knitr_1.46 backports_1.4.1
#> [16] checkmate_2.3.1 DelayedArray_0.30.0 bookdown_0.39
#> [19] stringfish_0.16.0 GenomeInfoDbData_1.2.12 bslib_0.7.0
#> [22] rlang_1.1.3 cachem_1.0.8 xfun_0.43
#> [25] sass_0.4.9 RcppParallel_5.1.7 SparseArray_1.4.0
#> [28] cli_3.6.2 zlibbioc_1.50.0 digest_0.6.35
#> [31] grid_4.4.0 lifecycle_1.0.4 data.table_1.15.4
#> [34] evaluate_0.23 abind_1.4-5 RApiSerialize_0.1.2
#> [37] rmarkdown_2.26 httr_1.4.7 qs_0.26.1
#> [40] tools_4.4.0 htmltools_0.5.8.1 UCSC.utils_1.0.0