A single data.frame containing the concatenated pData from all datasets in the curatedBreastDataExprSetList list. Rownames correspond to sample IDs.
Usage
data(curatedBreastData_pData)Details
This data object was created by combining the pData slot of all ExpressionSets provided in the curatedBreastDataExprSetList.
Note
Suggestions for new datasets to add are always welcome; the maintainer does aim to only include datasets that have minimal treatment and some form of survival (and/or treatment response) to allow for richer analyses. Raw data is always preferred in order to control normalization schemes. Normalization details for each dataset can be found in the GitHub repo in the References section.
References
Planey, Butte. Database integration of 4923 publicly-available samples of breast cancer molecular and clinical data. AMIA Joint Summits Translational Science Proceedings. (2003) PMC3814460
GitHub repo with code, further documentation on datasets and baseline normalization schemes, and database quality checks: https://github.com/kplaney/curatedBreastCancer
Examples
#load up datasets that are in S4 expressionSet format.
curatedBreastDataExprSetList <- getCuratedBreastDataExprSetList(test=TRUE)
#process only the first two datasets to avoid a long-running example:
#take top 100 genes by variance from each dataset.
proc_curatedBreastDataExprSetList <- processExpressionSetList(exprSetList=
curatedBreastDataExprSetList[1:2],
outputFileDirectory = tempdir(), numTopVarGenes=100)
#>
#> Analyzing dataset 1 or dataset named study_1379_GPL1223_all
#>
#> Note: this function assumes your missing values
#> are proper NAs, not "null",etc.
#> It's best to impute NA values before running this function
#> otherwise it may set averages to NA if there is 1 NA present.
#> This function just removes any genes whose key is NA.
#>
#> You may get a notification here because key (usually gene) names are
#> duplicated so it can't use them as row names.
#> That's OK, because we are immediately collapsing them into one feature.
#>
#> Starting with 30patients.
#> found no multiple samples from the same patient(s)
#>
#> Analyzing dataset 2 or dataset named study_2034_GPL96_all
#>
#> Note: this function assumes your missing values
#> are proper NAs, not "null",etc.
#> It's best to impute NA values before running this function
#> otherwise it may set averages to NA if there is 1 NA present.
#> This function just removes any genes whose key is NA.
#>
#> You may get a notification here because key (usually gene) names are
#> duplicated so it can't use them as row names.
#> That's OK, because we are immediately collapsing them into one feature.
#>
#> Starting with 30patients.
#> found no multiple samples from the same patient(s)
#now we have processed expression matrices,
#each with the top 100 genes by variance
data(curatedBreastData_pData)
dim(curatedBreastData_pData)
#> [1] 2719 153
head(curatedBreastData_pData)
#> datasetName dbUniquePatientID
#> study_1379_GPL1223_all.22449 study_1379_GPL1223_all 925
#> study_1379_GPL1223_all.22450 study_1379_GPL1223_all 926
#> study_1379_GPL1223_all.22451 study_1379_GPL1223_all 927
#> study_1379_GPL1223_all.22452 study_1379_GPL1223_all 928
#> study_1379_GPL1223_all.22453 study_1379_GPL1223_all 929
#> study_1379_GPL1223_all.22454 study_1379_GPL1223_all 930
#> study_ID.x patient_ID GEO_GSMID platform_ID
#> study_1379_GPL1223_all.22449 1379 22449 22449 1223
#> study_1379_GPL1223_all.22450 1379 22450 22450 1223
#> study_1379_GPL1223_all.22451 1379 22451 22451 1223
#> study_1379_GPL1223_all.22452 1379 22452 22452 1223
#> study_1379_GPL1223_all.22453 1379 22453 22453 1223
#> study_1379_GPL1223_all.22454 1379 22454 22454 1223
#> GEO_platform_ID AE_platform_ID
#> study_1379_GPL1223_all.22449 GPL1223 <NA>
#> study_1379_GPL1223_all.22450 GPL1223 <NA>
#> study_1379_GPL1223_all.22451 GPL1223 <NA>
#> study_1379_GPL1223_all.22452 GPL1223 <NA>
#> study_1379_GPL1223_all.22453 GPL1223 <NA>
#> study_1379_GPL1223_all.22454 GPL1223 <NA>
#> coordinating_GSE_series_GSMID original_study_ID
#> study_1379_GPL1223_all.22449 22365 25
#> study_1379_GPL1223_all.22450 22366 59
#> study_1379_GPL1223_all.22451 22367 68
#> study_1379_GPL1223_all.22452 22368 140
#> study_1379_GPL1223_all.22453 22369 180
#> study_1379_GPL1223_all.22454 22370 260
#> site_ID site_ID_preprocessed microarray_outlier
#> study_1379_GPL1223_all.22449 <NA> <NA> 0
#> study_1379_GPL1223_all.22450 <NA> <NA> 0
#> study_1379_GPL1223_all.22451 <NA> <NA> 0
#> study_1379_GPL1223_all.22452 <NA> <NA> 0
#> study_1379_GPL1223_all.22453 <NA> <NA> 0
#> study_1379_GPL1223_all.22454 <NA> <NA> 0
#> biopsy_preTreat biopsy_postTrt_days
#> study_1379_GPL1223_all.22449 1 0
#> study_1379_GPL1223_all.22450 1 0
#> study_1379_GPL1223_all.22451 1 0
#> study_1379_GPL1223_all.22452 1 0
#> study_1379_GPL1223_all.22453 1 0
#> study_1379_GPL1223_all.22454 1 0
#> pCR_postTrt_days tumor_size_cm_preTrt_preSurgery
#> study_1379_GPL1223_all.22449 NA 3.5
#> study_1379_GPL1223_all.22450 NA 3.0
#> study_1379_GPL1223_all.22451 NA 3.0
#> study_1379_GPL1223_all.22452 NA 2.0
#> study_1379_GPL1223_all.22453 NA 1.6
#> study_1379_GPL1223_all.22454 NA 0.9
#> tumor_size_cm_secondAxis_preTrt_preSurgery
#> study_1379_GPL1223_all.22449 NA
#> study_1379_GPL1223_all.22450 NA
#> study_1379_GPL1223_all.22451 NA
#> study_1379_GPL1223_all.22452 NA
#> study_1379_GPL1223_all.22453 NA
#> study_1379_GPL1223_all.22454 NA
#> tumor_size_cm_preTrt_preSurgeryMin
#> study_1379_GPL1223_all.22449 NA
#> study_1379_GPL1223_all.22450 NA
#> study_1379_GPL1223_all.22451 NA
#> study_1379_GPL1223_all.22452 NA
#> study_1379_GPL1223_all.22453 NA
#> study_1379_GPL1223_all.22454 NA
#> tumor_size_cm_postTrt treatment_protocol_number
#> study_1379_GPL1223_all.22449 NA 1
#> study_1379_GPL1223_all.22450 NA 1
#> study_1379_GPL1223_all.22451 NA 1
#> study_1379_GPL1223_all.22452 NA 1
#> study_1379_GPL1223_all.22453 NA 1
#> study_1379_GPL1223_all.22454 NA 1
#> clinical_AJCC_stage clinical_AJCC_stageRangeMin
#> study_1379_GPL1223_all.22449 <NA> <NA>
#> study_1379_GPL1223_all.22450 <NA> <NA>
#> study_1379_GPL1223_all.22451 <NA> <NA>
#> study_1379_GPL1223_all.22452 <NA> <NA>
#> study_1379_GPL1223_all.22453 <NA> <NA>
#> study_1379_GPL1223_all.22454 <NA> <NA>
#> clinical_AJCC_stageRangeMax
#> study_1379_GPL1223_all.22449 <NA>
#> study_1379_GPL1223_all.22450 <NA>
#> study_1379_GPL1223_all.22451 <NA>
#> study_1379_GPL1223_all.22452 <NA>
#> study_1379_GPL1223_all.22453 <NA>
#> study_1379_GPL1223_all.22454 <NA>
#> preTrt_lymph_node_status postTrt_lymph_node_status
#> study_1379_GPL1223_all.22449 N0 <NA>
#> study_1379_GPL1223_all.22450 positive <NA>
#> study_1379_GPL1223_all.22451 N0 <NA>
#> study_1379_GPL1223_all.22452 positive <NA>
#> study_1379_GPL1223_all.22453 positive <NA>
#> study_1379_GPL1223_all.22454 positive <NA>
#> preTrt_totalLymphNodes preTrt_numPosLymphNodes
#> study_1379_GPL1223_all.22449 9 0
#> study_1379_GPL1223_all.22450 38 33
#> study_1379_GPL1223_all.22451 17 0
#> study_1379_GPL1223_all.22452 28 8
#> study_1379_GPL1223_all.22453 19 2
#> study_1379_GPL1223_all.22454 13 1
#> preTrt_numPosLymphNodesRemoved
#> study_1379_GPL1223_all.22449 NA
#> study_1379_GPL1223_all.22450 NA
#> study_1379_GPL1223_all.22451 NA
#> study_1379_GPL1223_all.22452 NA
#> study_1379_GPL1223_all.22453 NA
#> study_1379_GPL1223_all.22454 NA
#> postTrt_totalLymphNodes postTrt_numPosLymphNodes
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> preTrt_posDichLymphNodes
#> study_1379_GPL1223_all.22449 NA
#> study_1379_GPL1223_all.22450 NA
#> study_1379_GPL1223_all.22451 NA
#> study_1379_GPL1223_all.22452 NA
#> study_1379_GPL1223_all.22453 NA
#> study_1379_GPL1223_all.22454 NA
#> notthingham_prognostic_index tumor_stage_preTrt
#> study_1379_GPL1223_all.22449 NA <NA>
#> study_1379_GPL1223_all.22450 NA <NA>
#> study_1379_GPL1223_all.22451 NA <NA>
#> study_1379_GPL1223_all.22452 NA <NA>
#> study_1379_GPL1223_all.22453 NA <NA>
#> study_1379_GPL1223_all.22454 NA <NA>
#> tumor_stage_preTrtMin tumor_stage_preTrtMax
#> study_1379_GPL1223_all.22449 <NA> <NA>
#> study_1379_GPL1223_all.22450 <NA> <NA>
#> study_1379_GPL1223_all.22451 <NA> <NA>
#> study_1379_GPL1223_all.22452 <NA> <NA>
#> study_1379_GPL1223_all.22453 <NA> <NA>
#> study_1379_GPL1223_all.22454 <NA> <NA>
#> tumor_stage_postTrt
#> study_1379_GPL1223_all.22449 <NA>
#> study_1379_GPL1223_all.22450 <NA>
#> study_1379_GPL1223_all.22451 <NA>
#> study_1379_GPL1223_all.22452 <NA>
#> study_1379_GPL1223_all.22453 <NA>
#> study_1379_GPL1223_all.22454 <NA>
#> molecular_subtype_outdatedUsePam50 pam50
#> study_1379_GPL1223_all.22449 <NA> <NA>
#> study_1379_GPL1223_all.22450 <NA> <NA>
#> study_1379_GPL1223_all.22451 <NA> <NA>
#> study_1379_GPL1223_all.22452 <NA> <NA>
#> study_1379_GPL1223_all.22453 <NA> <NA>
#> study_1379_GPL1223_all.22454 <NA> <NA>
#> hist_grade hist_gradeMax hist_gradeMin
#> study_1379_GPL1223_all.22449 2 <NA> <NA>
#> study_1379_GPL1223_all.22450 2 <NA> <NA>
#> study_1379_GPL1223_all.22451 2 <NA> <NA>
#> study_1379_GPL1223_all.22452 2 <NA> <NA>
#> study_1379_GPL1223_all.22453 2 <NA> <NA>
#> study_1379_GPL1223_all.22454 2 <NA> <NA>
#> nuclear_grade_preTrt path_diagnosis path
#> study_1379_GPL1223_all.22449 <NA> <NA> IDC
#> study_1379_GPL1223_all.22450 <NA> <NA> ILC
#> study_1379_GPL1223_all.22451 <NA> <NA> IDC
#> study_1379_GPL1223_all.22452 <NA> <NA> ILC
#> study_1379_GPL1223_all.22453 <NA> <NA> IDC
#> study_1379_GPL1223_all.22454 <NA> <NA> IDC and ILC
#> chemosensitivity_prediction SET_class ggi_class
#> study_1379_GPL1223_all.22449 <NA> <NA> <NA>
#> study_1379_GPL1223_all.22450 <NA> <NA> <NA>
#> study_1379_GPL1223_all.22451 <NA> <NA> <NA>
#> study_1379_GPL1223_all.22452 <NA> <NA> <NA>
#> study_1379_GPL1223_all.22453 <NA> <NA> <NA>
#> study_1379_GPL1223_all.22454 <NA> <NA> <NA>
#> pCR near_pCR pCR_spectrum RCB
#> study_1379_GPL1223_all.22449 NA NA <NA> <NA>
#> study_1379_GPL1223_all.22450 NA NA <NA> <NA>
#> study_1379_GPL1223_all.22451 NA NA <NA> <NA>
#> study_1379_GPL1223_all.22452 NA NA <NA> <NA>
#> study_1379_GPL1223_all.22453 NA NA <NA> <NA>
#> study_1379_GPL1223_all.22454 NA NA <NA> <NA>
#> months_from_surgery_measured_RCB
#> study_1379_GPL1223_all.22449 NA
#> study_1379_GPL1223_all.22450 NA
#> study_1379_GPL1223_all.22451 NA
#> study_1379_GPL1223_all.22452 NA
#> study_1379_GPL1223_all.22453 NA
#> study_1379_GPL1223_all.22454 NA
#> months_until_first_event_or_last_checkup RFS
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> RFS_months_or_MIN_months_of_RFS DFS
#> study_1379_GPL1223_all.22449 NA 0
#> study_1379_GPL1223_all.22450 NA 0
#> study_1379_GPL1223_all.22451 NA 0
#> study_1379_GPL1223_all.22452 NA 0
#> study_1379_GPL1223_all.22453 NA 1
#> study_1379_GPL1223_all.22454 NA 0
#> DFS_months_or_MIN_months_of_DFS OS
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> OS_months_or_MIN_months_of_OS OS_up_until_death
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> metastasis metastasis_months
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> relapseOneYearVsFivePlus metastasis_stage_preTrt
#> study_1379_GPL1223_all.22449 NA <NA>
#> study_1379_GPL1223_all.22450 NA <NA>
#> study_1379_GPL1223_all.22451 NA <NA>
#> study_1379_GPL1223_all.22452 NA <NA>
#> study_1379_GPL1223_all.22453 NA <NA>
#> study_1379_GPL1223_all.22454 NA <NA>
#> metastasis_stage_endPoint dead
#> study_1379_GPL1223_all.22449 <NA> NA
#> study_1379_GPL1223_all.22450 <NA> NA
#> study_1379_GPL1223_all.22451 <NA> NA
#> study_1379_GPL1223_all.22452 <NA> NA
#> study_1379_GPL1223_all.22453 <NA> NA
#> study_1379_GPL1223_all.22454 <NA> NA
#> died_from_cancer_if_dead age age_bin_description
#> study_1379_GPL1223_all.22449 NA 62 <NA>
#> study_1379_GPL1223_all.22450 NA 70 <NA>
#> study_1379_GPL1223_all.22451 NA 53 <NA>
#> study_1379_GPL1223_all.22452 NA 63 <NA>
#> study_1379_GPL1223_all.22453 NA 69 <NA>
#> study_1379_GPL1223_all.22454 NA 73 <NA>
#> age_bin race nationality menopausal_status
#> study_1379_GPL1223_all.22449 NA <NA> <NA> <NA>
#> study_1379_GPL1223_all.22450 NA <NA> <NA> <NA>
#> study_1379_GPL1223_all.22451 NA <NA> <NA> <NA>
#> study_1379_GPL1223_all.22452 NA <NA> <NA> <NA>
#> study_1379_GPL1223_all.22453 NA <NA> <NA> <NA>
#> study_1379_GPL1223_all.22454 NA <NA> <NA> <NA>
#> ER_preTrt ER_percentage_preTrt ER_expr_preTrt
#> study_1379_GPL1223_all.22449 0 NA NA
#> study_1379_GPL1223_all.22450 1 NA NA
#> study_1379_GPL1223_all.22451 1 NA NA
#> study_1379_GPL1223_all.22452 1 NA NA
#> study_1379_GPL1223_all.22453 1 NA NA
#> study_1379_GPL1223_all.22454 1 NA NA
#> ER_fmolmg_preTrt ESR1_preTrt ERbb2_preTrt
#> study_1379_GPL1223_all.22449 NA NA NA
#> study_1379_GPL1223_all.22450 NA NA NA
#> study_1379_GPL1223_all.22451 NA NA NA
#> study_1379_GPL1223_all.22452 NA NA NA
#> study_1379_GPL1223_all.22453 NA NA NA
#> study_1379_GPL1223_all.22454 NA NA NA
#> Erbeta_preTrt ERBB2_CPN_amplified PR_preTrt
#> study_1379_GPL1223_all.22449 NA NA 1
#> study_1379_GPL1223_all.22450 NA NA 1
#> study_1379_GPL1223_all.22451 NA NA 1
#> study_1379_GPL1223_all.22452 NA NA 1
#> study_1379_GPL1223_all.22453 NA NA 1
#> study_1379_GPL1223_all.22454 NA NA 1
#> PR_percentage_preTrt PR_expr_preTrt
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> PR_fmolmg_preTrt HER2_preTrt HER2_IHC_score_preTrt
#> study_1379_GPL1223_all.22449 NA 1 <NA>
#> study_1379_GPL1223_all.22450 NA 0 <NA>
#> study_1379_GPL1223_all.22451 NA 0 <NA>
#> study_1379_GPL1223_all.22452 NA 0 <NA>
#> study_1379_GPL1223_all.22453 NA 0 <NA>
#> study_1379_GPL1223_all.22454 NA 0 <NA>
#> HER2_expr_preTrt HER2_fish_cont_score_preTrt
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> HER2_SNP6_state p53_mutation p53_mutation_type p53
#> study_1379_GPL1223_all.22449 <NA> NA <NA> NA
#> study_1379_GPL1223_all.22450 <NA> NA <NA> NA
#> study_1379_GPL1223_all.22451 <NA> NA <NA> NA
#> study_1379_GPL1223_all.22452 <NA> NA <NA> NA
#> study_1379_GPL1223_all.22453 <NA> NA <NA> NA
#> study_1379_GPL1223_all.22454 <NA> NA <NA> NA
#> cellularity PIK3CA_mutation PTEN_pos PTEN_mutation
#> study_1379_GPL1223_all.22449 <NA> NA NA NA
#> study_1379_GPL1223_all.22450 <NA> NA NA NA
#> study_1379_GPL1223_all.22451 <NA> NA NA NA
#> study_1379_GPL1223_all.22452 <NA> NA NA NA
#> study_1379_GPL1223_all.22453 <NA> NA NA NA
#> study_1379_GPL1223_all.22454 <NA> NA NA NA
#> cytokeratin5_pos ki67_score ploidy ggi_preTrt
#> study_1379_GPL1223_all.22449 NA NA <NA> NA
#> study_1379_GPL1223_all.22450 NA NA <NA> NA
#> study_1379_GPL1223_all.22451 NA NA <NA> NA
#> study_1379_GPL1223_all.22452 NA NA <NA> NA
#> study_1379_GPL1223_all.22453 NA NA <NA> NA
#> study_1379_GPL1223_all.22454 NA NA <NA> NA
#> top2atri_preTrt topoihc_preTrt S_phase DNA_index
#> study_1379_GPL1223_all.22449 NA NA NA NA
#> study_1379_GPL1223_all.22450 NA NA NA NA
#> study_1379_GPL1223_all.22451 NA NA NA NA
#> study_1379_GPL1223_all.22452 NA NA NA NA
#> study_1379_GPL1223_all.22453 NA NA NA NA
#> study_1379_GPL1223_all.22454 NA NA NA NA
#> BRCA1_mutation BRCA2_mutation
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> overall_BRCA_mutation family_history surgery_type
#> study_1379_GPL1223_all.22449 NA NA <NA>
#> study_1379_GPL1223_all.22450 NA NA <NA>
#> study_1379_GPL1223_all.22451 NA NA <NA>
#> study_1379_GPL1223_all.22452 NA NA <NA>
#> study_1379_GPL1223_all.22453 NA NA <NA>
#> study_1379_GPL1223_all.22454 NA NA <NA>
#> relapse_beforeYR1 relapseOneYearVsThreePlus
#> study_1379_GPL1223_all.22449 NA NA
#> study_1379_GPL1223_all.22450 NA NA
#> study_1379_GPL1223_all.22451 NA NA
#> study_1379_GPL1223_all.22452 NA NA
#> study_1379_GPL1223_all.22453 NA NA
#> study_1379_GPL1223_all.22454 NA NA
#> intarvenous intramuscular oral radiotherapyClass
#> study_1379_GPL1223_all.22449 1 0 1 0
#> study_1379_GPL1223_all.22450 1 0 1 0
#> study_1379_GPL1223_all.22451 1 0 1 0
#> study_1379_GPL1223_all.22452 1 0 1 0
#> study_1379_GPL1223_all.22453 1 0 1 0
#> study_1379_GPL1223_all.22454 1 0 1 0
#> chemotherapyClass hormone_therapyClass
#> study_1379_GPL1223_all.22449 0 1
#> study_1379_GPL1223_all.22450 0 1
#> study_1379_GPL1223_all.22451 0 1
#> study_1379_GPL1223_all.22452 0 1
#> study_1379_GPL1223_all.22453 0 1
#> study_1379_GPL1223_all.22454 0 1
#> postmenopausal_only immediate_biol_target
#> study_1379_GPL1223_all.22449 0 0
#> study_1379_GPL1223_all.22450 0 0
#> study_1379_GPL1223_all.22451 0 0
#> study_1379_GPL1223_all.22452 0 0
#> study_1379_GPL1223_all.22453 0 0
#> study_1379_GPL1223_all.22454 0 0
#> anthracycline taxane anti_estrogen
#> study_1379_GPL1223_all.22449 0 0 1
#> study_1379_GPL1223_all.22450 0 0 1
#> study_1379_GPL1223_all.22451 0 0 1
#> study_1379_GPL1223_all.22452 0 0 1
#> study_1379_GPL1223_all.22453 0 0 1
#> study_1379_GPL1223_all.22454 0 0 1
#> aromatase_inhibitor estrogen_receptor_blocker
#> study_1379_GPL1223_all.22449 0 1
#> study_1379_GPL1223_all.22450 0 1
#> study_1379_GPL1223_all.22451 0 1
#> study_1379_GPL1223_all.22452 0 1
#> study_1379_GPL1223_all.22453 0 1
#> study_1379_GPL1223_all.22454 0 1
#> estrogen_receptor_blocker_and_stops_production
#> study_1379_GPL1223_all.22449 0
#> study_1379_GPL1223_all.22450 0
#> study_1379_GPL1223_all.22451 0
#> study_1379_GPL1223_all.22452 0
#> study_1379_GPL1223_all.22453 0
#> study_1379_GPL1223_all.22454 0
#> estrogen_receptor_blocker_and_eliminator anti_HER2
#> study_1379_GPL1223_all.22449 0 0
#> study_1379_GPL1223_all.22450 0 0
#> study_1379_GPL1223_all.22451 0 0
#> study_1379_GPL1223_all.22452 0 0
#> study_1379_GPL1223_all.22453 0 0
#> study_1379_GPL1223_all.22454 0 0
#> tamoxifen doxorubicin epirubicin docetaxel
#> study_1379_GPL1223_all.22449 1 0 0 0
#> study_1379_GPL1223_all.22450 1 0 0 0
#> study_1379_GPL1223_all.22451 1 0 0 0
#> study_1379_GPL1223_all.22452 1 0 0 0
#> study_1379_GPL1223_all.22453 1 0 0 0
#> study_1379_GPL1223_all.22454 1 0 0 0
#> capecitabine fluorouracil paclitaxel
#> study_1379_GPL1223_all.22449 0 0 0
#> study_1379_GPL1223_all.22450 0 0 0
#> study_1379_GPL1223_all.22451 0 0 0
#> study_1379_GPL1223_all.22452 0 0 0
#> study_1379_GPL1223_all.22453 0 0 0
#> study_1379_GPL1223_all.22454 0 0 0
#> cyclophosphamide anastrozole fulvestrant gefitinib
#> study_1379_GPL1223_all.22449 0 0 0 0
#> study_1379_GPL1223_all.22450 0 0 0 0
#> study_1379_GPL1223_all.22451 0 0 0 0
#> study_1379_GPL1223_all.22452 0 0 0 0
#> study_1379_GPL1223_all.22453 0 0 0 0
#> study_1379_GPL1223_all.22454 0 0 0 0
#> trastuzumab letrozole radiotherapy chemotherapy
#> study_1379_GPL1223_all.22449 0 0 0 0
#> study_1379_GPL1223_all.22450 0 0 0 0
#> study_1379_GPL1223_all.22451 0 0 0 0
#> study_1379_GPL1223_all.22452 0 0 0 0
#> study_1379_GPL1223_all.22453 0 0 0 0
#> study_1379_GPL1223_all.22454 0 0 0 0
#> hormone_therapy no_treatment methotrexate
#> study_1379_GPL1223_all.22449 0 0 0
#> study_1379_GPL1223_all.22450 0 0 0
#> study_1379_GPL1223_all.22451 0 0 0
#> study_1379_GPL1223_all.22452 0 0 0
#> study_1379_GPL1223_all.22453 0 0 0
#> study_1379_GPL1223_all.22454 0 0 0
#> cetuximab carboplatin other taxaneGeneral
#> study_1379_GPL1223_all.22449 0 0 0 0
#> study_1379_GPL1223_all.22450 0 0 0 0
#> study_1379_GPL1223_all.22451 0 0 0 0
#> study_1379_GPL1223_all.22452 0 0 0 0
#> study_1379_GPL1223_all.22453 0 0 0 0
#> study_1379_GPL1223_all.22454 0 0 0 0
#> neoadjuvant_or_adjuvant
#> study_1379_GPL1223_all.22449 adj
#> study_1379_GPL1223_all.22450 adj
#> study_1379_GPL1223_all.22451 adj
#> study_1379_GPL1223_all.22452 adj
#> study_1379_GPL1223_all.22453 adj
#> study_1379_GPL1223_all.22454 adj
#> study_specific_protocol_number
#> study_1379_GPL1223_all.22449 1
#> study_1379_GPL1223_all.22450 1
#> study_1379_GPL1223_all.22451 1
#> study_1379_GPL1223_all.22452 1
#> study_1379_GPL1223_all.22453 1
#> study_1379_GPL1223_all.22454 1