library(BiocStyle)
library(HPAanalyze)
library(dplyr)
What to do if you want to systematically download images from HPA?
CCNB1xml <- hpaXmlGet("ENSG00000134057")
CCNB1_ab <- hpaXmlAntibody(CCNB1xml)
CCNB1_ab
#> # A tibble: 4 x 4
#> id releaseVersion releaseDate RRID
#> <chr> <chr> <chr> <chr>
#> 1 CAB000115 1.2 2006-03-13 <NA>
#> 2 CAB003804 2.0 2006-10-30 AB_562272
#> 3 HPA030741 12.0 2013-12-05 AB_2673586
#> 4 HPA061448 16.0 2016-12-04 AB_2684522
#> # A tibble: 4 x 4
#> id releaseDate releaseVersion RRID
#> <chr> <chr> <chr> <chr>
#> 1 CAB000115 2006-03-13 1.2 <NA>
#> 2 CAB003804 2006-10-30 2 AB_562272
#> 3 HPA030741 2013-12-05 12 AB_2673586
#> 4 HPA061448 2016-12-04 16 AB_2684522
CCNB1_expr <- hpaXmlTissueExpr(CCNB1xml)
str(CCNB1_expr[[1]])
#> tibble [334 × 18] (S3: tbl_df/tbl/data.frame)
#> $ patientId : chr [1:334] "1447" "1452" "1470" "1647" ...
#> $ age : chr [1:334] "45" "44" "65" "63" ...
#> $ sex : chr [1:334] "Female" "Female" "Male" "Male" ...
#> $ staining : chr [1:334] NA NA NA NA ...
#> $ intensity : chr [1:334] NA NA NA NA ...
#> $ quantity : chr [1:334] NA NA NA NA ...
#> $ location : chr [1:334] NA NA NA NA ...
#> $ imageUrl : chr [1:334] "http://images.proteinatlas.org/115/2043_B_2_8.jpg" "http://images.proteinatlas.org/115/2043_B_1_8.jpg" "http://images.proteinatlas.org/115/2043_B_3_8.jpg" "http://images.proteinatlas.org/115/2043_B_1_7.jpg" ...
#> $ snomedCode1 : chr [1:334] "M-00100" "M-00100" "M-00100" "M-00100" ...
#> $ snomedCode2 : chr [1:334] "T-04000" "T-04000" "T-1X700" "T-64300" ...
#> $ snomedCode3 : chr [1:334] NA NA "T-28000" NA ...
#> $ snomedCode4 : chr [1:334] NA NA NA NA ...
#> $ snomedCode5 : chr [1:334] NA NA NA NA ...
#> $ tissueDescription1: chr [1:334] "Normal tissue, NOS" "Normal tissue, NOS" "Normal tissue, NOS" "Normal tissue, NOS" ...
#> $ tissueDescription2: chr [1:334] "Breast" "Breast" "Cartilage tissue" "Duodenum" ...
#> $ tissueDescription3: chr [1:334] NA NA "Lung" NA ...
#> $ tissueDescription4: chr [1:334] NA NA NA NA ...
#> $ tissueDescription5: chr [1:334] NA NA NA NA ...
#> - attr(*, "reshapeWide")=List of 5
#> ..$ v.names: NULL
#> ..$ timevar: chr "attr"
#> ..$ idvar : chr "index"
#> ..$ times : chr [1:16] "sex" "age" "patientId" "staining" ...
#> ..$ varying: chr [1, 1:16] "value.sex" "value.age" "value.patientId" "value.staining" ...
#> Classes 'tbl_df', 'tbl' and 'data.frame': 331 obs. of 18 variables:
#> $ patientId : chr "1653" "1721" "1725" "598" ...
#> $ age : chr "53" "60" "57" "7" ...
#> $ sex : chr "Male" "Female" "Male" "Male" ...
#> $ staining : chr NA NA NA NA ...
#> $ intensity : chr NA NA NA NA ...
#> $ quantity : chr NA NA NA NA ...
#> $ location : chr NA NA NA NA ...
#> $ imageUrl : chr "http://v18.proteinatlas.org/images/115/2043_B_4_5.jpg" "http://v18.proteinatlas.org/images/115/2043_B_6_5.jpg" "http://v18.proteinatlas.org/images/115/2043_B_5_5.jpg" "http://v18.proteinatlas.org/images/115/2043_A_2_2.jpg" ...
#> $ snomedCode1 : chr "M-00100" "M-00100" "M-00100" "M-00100" ...
#> $ snomedCode2 : chr "T-93000" "T-93000" "T-93000" "T-66000" ...
#> $ snomedCode3 : chr NA NA NA NA ...
#> $ snomedCode4 : chr NA NA NA NA ...
#> $ snomedCode5 : chr NA NA NA NA ...
#> $ tissueDescription1: chr "Normal tissue, NOS" "Normal tissue, NOS" "Normal tissue, NOS" "Normal tissue, NOS" ...
#> $ tissueDescription2: chr "Adrenal gland" "Adrenal gland" "Adrenal gland" "Appendix" ...
#> $ tissueDescription3: chr NA NA NA NA ...
#> $ tissueDescription4: chr NA NA NA NA ...
#> $ tissueDescription5: chr NA NA NA NA ...
dir.create("img")
for (i in 1:nrow(CCNB1_expr[[1]])) {
download.file(CCNB1_expr[[1]]$imageUrl[i],
destfile = paste0("img/", CCNB1_ab$id[1], "_",
CCNB1_expr[[1]]$patientId[i], "_",
CCNB1_expr[[1]]$tissueDescription2[i],
".jpg"),
mode = "wb")
}
Anh Tran, 2018-2021
Please cite: Tran, A.N., Dussaq, A.M., Kennell, T. et al. HPAanalyze: an R package that facilitates the retrieval and analysis of the Human Protein Atlas data. BMC Bioinformatics 20, 463 (2019) https://doi.org/10.1186/s12859-019-3059-z