umccr / dracarys Goto Github PK

2023-04-23T21:58:50.696000+00:00 2023/04/23/[$LATEST]eefcad7e070f46039ac9deff72cb08ae Error: Aborting - duplicated file types detected in /tmp/dracarys/dracarys_gds_sync
2023-04-23T21:58:50.696000+00:00 2023/04/23/[$LATEST]eefcad7e070f46039ac9deff72cb08ae Execution halted
2023-04-23T21:58:50.696000+00:00 2023/04/23/[$LATEST]eefcad7e070f46039ac9deff72cb08ae Warning message:
2023-04-23T21:58:50.696000+00:00 2023/04/23/[$LATEST]eefcad7e070f46039ac9deff72cb08ae system call failed: Cannot allocate memory

rlang::last_trace()
<error/dplyr:::mutate_error>
Error in `dplyr::mutate()`:
ℹ In argument: `obj_parsed = list(.data$obj$read())`.
ℹ In row 1.
Caused by error:
! `%in%`(x = w, table = dragen_workflows) is not TRUE
---
Backtrace:
     ▆
  1. ├─dracarys::umccr_tidy(...)
  2. │ ├─dplyr::select(...) at dracarys/R/tidy.R:83:4
  3. │ ├─dplyr::mutate(...)
  4. │ └─dplyr:::mutate.data.frame(...)
  5. │   └─dplyr:::mutate_cols(.data, dplyr_quosures(...), by)
  6. │     ├─base::withCallingHandlers(...)
  7. │     └─dplyr:::mutate_col(dots[[i]], data, mask, new_columns)
  8. │       └─mask$eval_all_mutate(quo)
  9. │         └─dplyr (local) eval()
 10. └─.data$obj$read()
 11.   └─dracarys::multiqc_tidy_json(x) at dracarys/R/multiqc.R:26:6
 12.     └─dracarys:::.multiqc_guess_workflow(p) at dracarys/R/multiqc.R:58:2
 13.       └─assertthat::assert_that(w %in% dragen_workflows) at dracarys/R/multiqc.R:150:6
 14.         └─base::stop(assertError(attr(res, "msg")))

WARNING: No file hash info found for '/home/runner/work/dracarys/dracarys/inst/extdata/tso'. It won't be created.
WARNING: No file hash info found for '/home/runner/work/dracarys/dracarys/inst/extdata/wgs'. It won't be created.
2 files failed
ERROR: failed to pull data from the cloud - Checkout failed for following targets:
/home/runner/work/dracarys/dracarys/inst/extdata/tso
/home/runner/work/dracarys/dracarys/inst/extdata/wgs
Is your cache up to date?
<https://error.dvc.org/missing-files>
Error: Process completed with exit code 1.

> dracarys::TsoTmbTraceTsvFile$new(url1)

Error in loadNamespace(i, c(lib.loc, .libPaths()), versionCheck = vI[[i]]) : 
  namespace ‘rlang’ 1.0.6 is already loaded, but >= 1.1.0 is required

# before installing dracarys
> sessionInfo()
R version 4.2.2 Patched (2022-11-10 r83330)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 22.04.2 LTS

Matrix products: default
BLAS:   /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so

locale:
 [1] LC_CTYPE=C.UTF-8       LC_NUMERIC=C           LC_TIME=C.UTF-8       
 [4] LC_COLLATE=C.UTF-8     LC_MONETARY=C.UTF-8    LC_MESSAGES=C.UTF-8   
 [7] LC_PAPER=C.UTF-8       LC_NAME=C              LC_ADDRESS=C          
[10] LC_TELEPHONE=C         LC_MEASUREMENT=C.UTF-8 LC_IDENTIFICATION=C   

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

loaded via a namespace (and not attached):
[1] SparkR_3.4.0   compiler_4.2.2 Rserve_1.8-12 

install.packages("RJSONIO")
devtools::install_github("umccr/dracarys", upgrade_dependencies = FALSE, dependencies = FALSE)

dracarys.R tidy \
  --multi_input samples.tsv \
  --token <TOKEN> \
  --format {tsv,parquet,both}

gds_files_list <- dracarys::gds_files_list_filter_relevant(
  gds_output_directory, 
  token=Sys.getenv("ICA_ACCESS_TOKEN"), 
  include="PresignedUrl"
)

data_objects <- gds_files_list %>%
  # We only want the metrics files
  dplyr::filter(
    stringr::str_detect(.data[["type"]], "MultiqcFile|MetricsFile$")
  ) %>%
  # Work by row
  dplyr::rowwise() %>%
    # Use the func_selector to select the ingestion type
    # Based on the input data type
    dplyr::mutate(
      gen = list(dracarys:::dr_func_eval(.data$type))
    ) %>%
    # Call the dracarys function selected by mutate above
    # Using the presigned url as an input to the function
    dplyr::mutate(
      obj = list(.data$gen$new(.data$presigned_url))
    ) %>%
    # Now read the dracarys digested object
    dplyr::mutate(
      objp = list(.data$obj$read())
    ) %>%
    # Add the portal run id to the objp tbl
    dplyr::mutate(
      objp = list(
        .data$objp %>%
        dplyr::mutate(
          portal_run_id=portal_run_id
        )
      )
    ) %>%
    # # Get output table based on workflow type and data type
    dplyr::mutate(
      output_table = paste0(
        workflow_type_name, 
        "__", 
        stringr::str_replace(.data[["type"]], "MetricsFile$", "_metrics")
      )
    ) %>%
  # De row-wise tibble
  dplyr::ungroup() %>%
  # Select required outputs
  dplyr::select(
    "type",
    "output_table",
    "objp"
  )

# Write to table
data_objects %>%
  dplyr::rowwise() %>%
  dplyr::mutate(
    wrote_output = write_tbl_to_uc_table(sc, .data$objp, .data$output_table)
  ) %>%
  dplyr::ungroup()

dracarys.R tidy -i /mnt/dracarys_sync/ -o /mnt/tidied_files/

$ grep "date" multiqc_data.json
    "config_creation_date": "2022-12-14, 05:52",

Warning message:
In normalizePath(path) :
[<url>]
 No such file or directory

> url_jsongz
[1] "https://stratus-gds-aps2.s3.ap-southeast-2.amazonaws.com/11143240-789c-4320-b4e2-08d89d4636a9/analysis_data/SBJ00006/tso_ctdna_tumor_only/20230506af3bd7d9/L2300565/Results/NTC_ctTSO230501_L2300565/NTC_ctTSO230501_L2300565.AlignCollapseFusionCaller_metrics.json.gz?X-Amz-Expires=604800&response-content-disposition=filename%3D%22NTC_ctTSO230501_L2300565.AlignCollapseFusionCaller_metrics.json.gz%22&response-content-type=binary%2Foctet-stream[...]

> RJSONIO::fromJSON(url_jsongz)
Error in nchar(content) : invalid multibyte string, element 1

# how about something non-ICA related
> RJSONIO::fromJSON("https://wiki.mozilla.org/images/f/ff/Example.json.gz")
Error in nchar(content) : invalid multibyte string, element 1

> "https://wiki.mozilla.org/images/f/ff/Example.json.gz" |>
+     base::url() |> 
+     base::gzcon() |> 
+     readr::read_lines() |>
+     RJSONIO::fromJSON() |> str()
List of 26                                                                                                                                                                            
 $ InstallTime          : chr "1295768962"
 $ Comments             : chr "Will test without extension."
 $ Theme                : chr "classic/1.0"
 $ Version              : chr "4.0b10pre"
 $ id                   : chr "ec8030f7-c20a-464f-9b0e-13a3a9e97384"
 $ Vendor               : chr "Mozilla"
 $ EMCheckCompatibility : chr "false"
 $ Throttleable         : chr "1"
[...]

Error in `dplyr::mutate()`:
ℹ In argument: `plot = ifelse(...)`.
ℹ In row 2.
Caused by error in `loadNamespace()`:
! there is no package called ‘ggrepel’

# A tibble: 13 × 4
   ID    Number Type    Description                                                                               
   <chr> <chr>  <chr>   <chr>                                                                                     
 1 GT    1      String  Genotype                                                                                  
 2 GQ    1      Integer Genotype Quality                                                                          
 3 AD    .      Integer Allele Depth                                                                              
 4 DP    1      Integer Total Depth Used For Variant Calling                                                      
 5 VF    .      Float   Variant Frequency                                                                         
 6 NL    1      Integer Applied BaseCall Noise Level                                                              
 7 SB    1      Float   StrandBias Score                                                                          
 8 NC    1      Float   Fraction of bases which were uncalled or with basecall quality below the minimum threshold
 9 US    .      Integer Supporting read type counts                                                               
10 AQ    1      Float   Variant artifact adjusted quality score                                                   
11 LQ    1      Float   Likelihood ratio quality score                                                            
12 LQUS  6      Float   Likelihood ratio quality score by supporting read types                                   
13 BFQ   1      Float   Variant support Bias Filter Quality score

rlang::last_trace()
<error/dplyr:::mutate_error>
Error in `dplyr::mutate()`:
ℹ In argument: `obj_parsed = list(.data$obj$read())`.
ℹ In row 1.
Caused by error in `dplyr::bind_rows()`:
! Can't combine `PRJ230202$(Chr X SNPs)/(chr Y SNPs) ratio over genome` <character> and `PRJ230203$(Chr X SNPs)/(chr Y SNPs) ratio over genome` <double>.
---
Backtrace:
     ▆
  1. ├─dracarys::umccr_tidy(...)
  2. │ ├─dplyr::select(...) at dracarys/R/tidy.R:83:4
  3. │ ├─dplyr::mutate(...)
  4. │ └─dplyr:::mutate.data.frame(...)
  5. │   └─dplyr:::mutate_cols(.data, dplyr_quosures(...), by)
  6. │     ├─base::withCallingHandlers(...)
  7. │     └─dplyr:::mutate_col(dots[[i]], data, mask, new_columns)
  8. │       └─mask$eval_all_mutate(quo)
  9. │         └─dplyr (local) eval()
 10. └─.data$obj$read()
 11.   └─dracarys::multiqc_tidy_json(x) at dracarys/R/multiqc.R:26:6
 12.     ├─dplyr::select(...) at dracarys/R/multiqc.R:66:2
 13.     ├─dplyr::mutate(...)
 14.     └─dplyr::bind_rows(d, .id = "umccr_id")