example in vignette error
Closed this issue · 4 comments
if I follow the example in the vignette I encounter this error:
Add IDs
targets$IDFILE <- list.files(paste0(tempdir(), "/GSE70970/Data"))
library(NACHO)Attaching package: 'NACHO'
The following object is masked from 'package:BiocGenerics':
normalize
GSE70970_sum <- summarise(
- data_directory = paste0(tempdir(), "/GSE70970/Data"), # Where the data is
- ssheet_csv = targets, # The samplesheet
- id_colname = "IDFILE", # Name of the column that contains the identfiers
- housekeeping_genes = NULL, # Custom list of housekeeping genes
- housekeeping_predict = TRUE, # Predict the housekeeping genes based on the data?
- normalisation_method = "GEO", # Geometric mean or GLM
- n_comp = 5 # Number indicating the number of principal components to compute.
- )
[NACHO] Importing RCC files.
Error: Columncolsmust be length 1 (the number of rows), not 3
Hi,
I can't replicate your error.
And the vignette successfully compiled as you can see on the website
Below is a full reproducible example of the code you mentionned, as you can see I don't have your error. Please check the session information in the end.
library(GEOquery)
#> Loading required package: Biobase
#> Loading required package: BiocGenerics
#> Loading required package: parallel
#>
#> Attaching package: 'BiocGenerics'
#> The following objects are masked from 'package:parallel':
#>
#> clusterApply, clusterApplyLB, clusterCall, clusterEvalQ,
#> clusterExport, clusterMap, parApply, parCapply, parLapply,
#> parLapplyLB, parRapply, parSapply, parSapplyLB
#> The following objects are masked from 'package:stats':
#>
#> IQR, mad, sd, var, xtabs
#> The following objects are masked from 'package:base':
#>
#> anyDuplicated, append, as.data.frame, basename, cbind,
#> colnames, dirname, do.call, duplicated, eval, evalq, Filter,
#> Find, get, grep, grepl, intersect, is.unsorted, lapply, Map,
#> mapply, match, mget, order, paste, pmax, pmax.int, pmin,
#> pmin.int, Position, rank, rbind, Reduce, rownames, sapply,
#> setdiff, sort, table, tapply, union, unique, unsplit, which,
#> which.max, which.min
#> Welcome to Bioconductor
#>
#> Vignettes contain introductory material; view with
#> 'browseVignettes()'. To cite Bioconductor, see
#> 'citation("Biobase")', and for packages 'citation("pkgname")'.
#> Setting options('download.file.method.GEOquery'='auto')
#> Setting options('GEOquery.inmemory.gpl'=FALSE)
# Download data
gse <- getGEO("GSE70970")
#> Found 1 file(s)
#> GSE70970_series_matrix.txt.gz
#> Parsed with column specification:
#> cols(
#> .default = col_double(),
#> ID_REF = col_character()
#> )
#> See spec(...) for full column specifications.
#> File stored at:
#> /tmp/RtmpKA2y6S/GPL20699.soft
# Get phenotypes
targets <- pData(phenoData(gse[[1]]))
getGEOSuppFiles(GEO = "GSE70970", baseDir = tempdir())
#> size
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar 1986560
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz 672
#> isdir mode
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar FALSE 644
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz FALSE 644
#> mtime
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar 2019-11-15 11:25:23
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz 2019-11-15 11:25:24
#> ctime
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar 2019-11-15 11:25:23
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz 2019-11-15 11:25:24
#> atime
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar 2019-11-15 11:25:21
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz 2019-11-15 11:25:23
#> uid gid
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar 1738 50
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz 1738 50
#> uname
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar mcanouil
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz mcanouil
#> grname
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_RAW.tar staff
#> /tmp/RtmpKA2y6S/GSE70970/GSE70970_characteristics_readme.txt.gz staff
# Unzip data
untar(
tarfile = paste0(tempdir(), "/GSE70970/GSE70970_RAW.tar"),
exdir = paste0(tempdir(), "/GSE70970/Data")
)
# Add IDs
targets$IDFILE <- list.files(paste0(tempdir(), "/GSE70970/Data"))
library(NACHO)
#>
#> Attaching package: 'NACHO'
#> The following object is masked from 'package:BiocGenerics':
#>
#> normalize
GSE70970_sum <- summarise(
data_directory = paste0(tempdir(), "/GSE70970/Data"), # Where the data is
ssheet_csv = targets, # The samplesheet
id_colname = "IDFILE", # Name of the column that contains the identfiers
housekeeping_genes = NULL, # Custom list of housekeeping genes
housekeeping_predict = TRUE, # Predict the housekeeping genes based on the data?
normalisation_method = "GEO", # Geometric mean or GLM
n_comp = 5 # Number indicating the number of principal components to compute.
)
#> [NACHO] Importing RCC files.
#> [NACHO] Performing QC and formatting data.
#> [NACHO] Searching for the best housekeeping genes.
#> [NACHO] Computing normalisation factors using "GEO" method for housekeeping genes prediction.
#> [NACHO] The following predicted housekeeping genes will be used for normalisation:
#> - hsa-miR-103
#> - hsa-let-7e
#> - hsa-miR-1260
#> - hsa-miR-500+hsa-miR-501-5p
#> - hsa-miR-1274b
#> [NACHO] Computing normalisation factors using "GEO" method.
#> [NACHO] Missing values have been replaced with zeros for PCA.
#> [NACHO] Normalising data using "GEO" method with housekeeping genes.
#> [NACHO] Returning a list.
#> $ access : character
#> $ housekeeping_genes : character
#> $ housekeeping_predict: logical
#> $ housekeeping_norm : logical
#> $ normalisation_method: character
#> $ remove_outliers : logical
#> $ n_comp : numeric
#> $ data_directory : character
#> $ pc_sum : data.frame
#> $ nacho : data.frame
#> $ outliers_thresholds : list
#> $ raw_counts : data.frame
#> $ normalised_counts : data.frame
sessioninfo::session_info()
#> ─ Session info ──────────────────────────────────────────────────────────
#> setting value
#> version R version 3.6.1 (2019-07-05)
#> os Debian GNU/Linux 9 (stretch)
#> system x86_64, linux-gnu
#> ui X11
#> language en_GB.UTF-8
#> collate en_US.UTF-8
#> ctype en_US.UTF-8
#> tz Etc/UTC
#> date 2019-11-15
#>
#> ─ Packages ──────────────────────────────────────────────────────────────
#> package * version date lib source
#> assertthat 0.2.1 2019-03-21 [1] CRAN (R 3.6.1)
#> backports 1.1.5 2019-10-02 [1] CRAN (R 3.6.1)
#> Biobase * 2.44.0 2019-05-02 [1] Bioconductor
#> BiocGenerics * 0.30.0 2019-05-02 [1] Bioconductor
#> cli 1.1.0 2019-03-19 [1] CRAN (R 3.6.1)
#> colorspace 1.4-1 2019-03-18 [1] CRAN (R 3.6.1)
#> crayon 1.3.4 2017-09-16 [1] CRAN (R 3.6.1)
#> curl 4.2 2019-09-24 [1] CRAN (R 3.6.1)
#> digest 0.6.21 2019-09-20 [1] CRAN (R 3.6.1)
#> dplyr 0.8.3 2019-07-04 [1] CRAN (R 3.6.1)
#> ellipsis 0.3.0 2019-09-20 [1] CRAN (R 3.6.1)
#> evaluate 0.14 2019-05-28 [1] CRAN (R 3.6.1)
#> GEOquery * 2.52.0 2019-05-02 [1] Bioconductor
#> ggplot2 3.2.1 2019-08-10 [1] CRAN (R 3.6.1)
#> glue 1.3.1 2019-03-12 [1] CRAN (R 3.6.1)
#> gtable 0.3.0 2019-03-25 [1] CRAN (R 3.6.1)
#> highr 0.8 2019-03-20 [1] CRAN (R 3.6.1)
#> hms 0.5.1 2019-08-23 [1] CRAN (R 3.6.1)
#> htmltools 0.4.0 2019-10-04 [1] CRAN (R 3.6.1)
#> knitr 1.25 2019-09-18 [1] CRAN (R 3.6.1)
#> lazyeval 0.2.2 2019-03-15 [1] CRAN (R 3.6.1)
#> lifecycle 0.1.0 2019-08-01 [1] CRAN (R 3.6.1)
#> limma 3.40.6 2019-07-26 [1] Bioconductor
#> magrittr 1.5 2014-11-22 [1] CRAN (R 3.6.1)
#> munsell 0.5.0 2018-06-12 [1] CRAN (R 3.6.1)
#> NACHO * 0.6.1 2019-10-12 [1] CRAN (R 3.6.1)
#> pillar 1.4.2 2019-06-29 [1] CRAN (R 3.6.1)
#> pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 3.6.1)
#> purrr 0.3.3 2019-10-18 [1] CRAN (R 3.6.1)
#> R6 2.4.0 2019-02-14 [1] CRAN (R 3.6.1)
#> Rcpp 1.0.2 2019-07-25 [1] CRAN (R 3.6.1)
#> readr 1.3.1 2018-12-21 [1] CRAN (R 3.6.1)
#> rlang 0.4.0 2019-06-25 [1] CRAN (R 3.6.1)
#> rmarkdown 1.16 2019-10-01 [1] CRAN (R 3.6.1)
#> scales 1.0.0 2018-08-09 [1] CRAN (R 3.6.1)
#> sessioninfo 1.1.1 2018-11-05 [1] CRAN (R 3.6.1)
#> stringi 1.4.3 2019-03-12 [1] CRAN (R 3.6.1)
#> stringr 1.4.0 2019-02-10 [1] CRAN (R 3.6.1)
#> tibble 2.1.3 2019-06-06 [1] CRAN (R 3.6.1)
#> tidyr 1.0.0 2019-09-11 [1] CRAN (R 3.6.1)
#> tidyselect 0.2.5 2018-10-11 [1] CRAN (R 3.6.1)
#> vctrs 0.2.0 2019-07-05 [1] CRAN (R 3.6.1)
#> withr 2.1.2 2018-03-15 [1] CRAN (R 3.6.1)
#> xfun 0.10 2019-10-01 [1] CRAN (R 3.6.1)
#> xml2 1.2.2 2019-08-09 [1] CRAN (R 3.6.1)
#> yaml 2.2.0 2018-07-25 [1] CRAN (R 3.6.1)
#> zeallot 0.1.0 2018-01-28 [1] CRAN (R 3.6.1)
#>
#> [1] /usr/local/lib/R/site-library
#> [2] /usr/local/lib/R/libraryI restarted R and tried again now it worked, sry dont know what went wrong the first time.
best regards
Sebastian
library(GEOquery)
Loading required package: Biobase
Loading required package: BiocGenerics
Loading required package: parallel
Attaching package: ‘BiocGenerics’
The following objects are masked from ‘package:parallel’:
clusterApply, clusterApplyLB, clusterCall, clusterEvalQ, clusterExport, clusterMap, parApply, parCapply,
parLapply, parLapplyLB, parRapply, parSapply, parSapplyLB
The following objects are masked from ‘package:stats’:
IQR, mad, sd, var, xtabs
The following objects are masked from ‘package:base’:
anyDuplicated, append, as.data.frame, basename, cbind, colnames, dirname, do.call, duplicated, eval, evalq,
Filter, Find, get, grep, grepl, intersect, is.unsorted, lapply, Map, mapply, match, mget, order, paste, pmax,
pmax.int, pmin, pmin.int, Position, rank, rbind, Reduce, rownames, sapply, setdiff, sort, table, tapply, union,
unique, unsplit, which, which.max, which.min
Welcome to Bioconductor
Vignettes contain introductory material; view with 'browseVignettes()'. To cite Bioconductor, see
'citation("Biobase")', and for packages 'citation("pkgname")'.
Setting options('download.file.method.GEOquery'='auto')
Setting options('GEOquery.inmemory.gpl'=FALSE)
gse <- getGEO("GSE70970")
Found 1 file(s)
GSE70970_series_matrix.txt.gz
trying URL 'https://ftp.ncbi.nlm.nih.gov/geo/series/GSE70nnn/GSE70970/matrix/GSE70970_series_matrix.txt.gz'
Content type 'application/x-gzip' length 351607 bytes (343 KB)
==================================================
downloaded 343 KB
Parsed with column specification:
cols(
.default = col_double(),
ID_REF = col_character()
)
See spec(...) for full column specifications.
File stored at:
/tmp/RtmpQb9ReH/GPL20699.soft
targets <- pData(phenoData(gse[[1]]))
getGEOSuppFiles(GEO = "GSE70970", baseDir = tempdir())
trying URL 'https://ftp.ncbi.nlm.nih.gov/geo/series/GSE70nnn/GSE70970/suppl//GSE70970_RAW.tar?tool=geoquery'
Content type 'application/x-tar' length 1986560 bytes (1.9 MB)
==================================================
downloaded 1.9 MB
trying URL 'https://ftp.ncbi.nlm.nih.gov/geo/series/GSE70nnn/GSE70970/suppl//GSE70970_characteristics_readme.txt.gz?tool=geoquery'
Content type 'application/x-gzip' length 672 bytes
downloaded 672 bytes
size isdir mode mtime ctime
/tmp/RtmpQb9ReH/GSE70970/GSE70970_RAW.tar 1986560 FALSE 664 2019-11-15 11:31:34 2019-11-15 11:31:34
/tmp/RtmpQb9ReH/GSE70970/GSE70970_characteristics_readme.txt.gz 672 FALSE 664 2019-11-15 11:31:35 2019-11-15 11:31:35
atime uid gid uname grname
/tmp/RtmpQb9ReH/GSE70970/GSE70970_RAW.tar 2019-11-15 11:31:32 1000 1000 sebastian sebastian
/tmp/RtmpQb9ReH/GSE70970/GSE70970_characteristics_readme.txt.gz 2019-11-15 11:31:34 1000 1000 sebastian sebastian
untar(
- tarfile = paste0(tempdir(), "/GSE70970/GSE70970_RAW.tar"),
- exdir = paste0(tempdir(), "/GSE70970/Data")
- )
targets$IDFILE <- list.files(paste0(tempdir(), "/GSE70970/Data"))
library(NACHO)
Attaching package: ‘NACHO’
The following object is masked from ‘package:BiocGenerics’:
normalize
library(NACHO)
GSE70970_sum <- summarise(
- data_directory = paste0(tempdir(), "/GSE70970/Data"), # Where the data is
- ssheet_csv = targets, # The samplesheet
- id_colname = "IDFILE", # Name of the column that contains the identfiers
- housekeeping_genes = NULL, # Custom list of housekeeping genes
- housekeeping_predict = TRUE, # Predict the housekeeping genes based on the data?
- normalisation_method = "GEO", # Geometric mean or GLM
- n_comp = 5 # Number indicating the number of principal components to compute.
- )
[NACHO] Importing RCC files.
|========================================================================================================|100% ~0 s remaining
[NACHO] Performing QC and formatting data.
[NACHO] Searching for the best housekeeping genes.
[NACHO] Computing normalisation factors using "GEO" method for housekeeping genes prediction.
[NACHO] The following predicted housekeeping genes will be used for normalisation:- hsa-miR-103
- hsa-let-7e
- hsa-miR-1260
- hsa-miR-500+hsa-miR-501-5p
- hsa-miR-1274b
[NACHO] Computing normalisation factors using "GEO" method.
[NACHO] Missing values have been replaced with zeros for PCA.
[NACHO] Normalising data using "GEO" method with housekeeping genes.
[NACHO] Returning a list.
$ access : character
$ housekeeping_genes : character
$ housekeeping_predict: logical
$ housekeeping_norm : logical
$ normalisation_method: character
$ remove_outliers : logical
$ n_comp : numeric
$ data_directory : character
$ pc_sum : data.frame
$ nacho : data.frame
$ outliers_thresholds : list
$ raw_counts : data.frame
$ normalised_counts : data.frame
sessioninfo::session_info()
─ Session info ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────
setting value
version R version 3.6.1 (2019-07-05)
os Ubuntu 18.04.3 LTS
system x86_64, linux-gnu
ui RStudio
language (EN)
collate en_US.UTF-8
ctype en_US.UTF-8
tz Europe/Berlin
date 2019-11-15
─ Packages ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
package * version date lib source
assertthat 0.2.1 2019-03-21 [1] CRAN (R 3.6.1)
backports 1.1.5 2019-10-02 [1] CRAN (R 3.6.1)
Biobase * 2.44.0 2019-05-02 [1] Bioconductor
BiocGenerics * 0.30.0 2019-05-02 [1] Bioconductor
cli 1.1.0 2019-03-19 [1] CRAN (R 3.6.1)
colorspace 1.4-1 2019-03-18 [1] CRAN (R 3.6.1)
crayon 1.3.4 2017-09-16 [1] CRAN (R 3.6.1)
curl 4.2 2019-09-24 [1] CRAN (R 3.6.1)
dplyr 0.8.3 2019-07-04 [1] CRAN (R 3.6.1)
ellipsis 0.3.0 2019-09-20 [1] CRAN (R 3.6.1)
GEOquery * 2.52.0 2019-05-02 [1] Bioconductor
ggplot2 3.2.1 2019-08-10 [1] CRAN (R 3.6.1)
glue 1.3.1 2019-03-12 [1] CRAN (R 3.6.1)
gtable 0.3.0 2019-03-25 [1] CRAN (R 3.6.1)
hms 0.5.2 2019-10-30 [1] CRAN (R 3.6.1)
knitr 1.26 2019-11-12 [1] CRAN (R 3.6.1)
lazyeval 0.2.2 2019-03-15 [1] CRAN (R 3.6.1)
lifecycle 0.1.0 2019-08-01 [1] CRAN (R 3.6.1)
limma 3.40.6 2019-07-26 [1] Bioconductor
magrittr 1.5 2014-11-22 [1] CRAN (R 3.6.1)
munsell 0.5.0 2018-06-12 [1] CRAN (R 3.6.1)
NACHO * 0.6.1 2019-10-12 [1] CRAN (R 3.6.1)
pillar 1.4.2 2019-06-29 [1] CRAN (R 3.6.1)
pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 3.6.1)
purrr 0.3.3 2019-10-18 [1] CRAN (R 3.6.1)
R6 2.4.1 2019-11-12 [1] CRAN (R 3.6.1)
Rcpp 1.0.3 2019-11-08 [1] CRAN (R 3.6.1)
readr 1.3.1 2018-12-21 [1] CRAN (R 3.6.1)
rlang 0.4.1 2019-10-24 [1] CRAN (R 3.6.1)
rstudioapi 0.10 2019-03-19 [1] CRAN (R 3.6.1)
scales 1.0.0 2018-08-09 [1] CRAN (R 3.6.1)
sessioninfo 1.1.1 2018-11-05 [1] CRAN (R 3.6.1)
stringi 1.4.3 2019-03-12 [1] CRAN (R 3.6.1)
tibble 2.1.3 2019-06-06 [1] CRAN (R 3.6.1)
tidyr 1.0.0 2019-09-11 [1] CRAN (R 3.6.1)
tidyselect 0.2.5 2018-10-11 [1] CRAN (R 3.6.1)
vctrs 0.2.0 2019-07-05 [1] CRAN (R 3.6.1)
withr 2.1.2 2018-03-15 [1] CRAN (R 3.6.1)
xfun 0.11 2019-11-12 [1] CRAN (R 3.6.1)
xml2 1.2.2 2019-08-09 [1] CRAN (R 3.6.1)
zeallot 0.1.0 2018-01-28 [1] CRAN (R 3.6.1)
[1] /home/sebastian/R/x86_64-pc-linux-gnu-library/3.6
[2] /usr/local/lib/R/site-library
[3] /usr/lib/R/site-library
[4] /usr/lib/R/library
Perfect!
Enjoy NACHO ;)
Hi Mcanouil,
Restarted R and tried to run the code fresh again. Still the same error!
`> GSE70970_sum <- summarize(
-
data_directory = paste0(tempdir(), "/GSE70970/Data"), # Where the data is -
ssheet_csv = targets, # The samplesheet -
id_colname = "IDFILE", # Name of the column that contains the identfiers -
housekeeping_genes = NULL, # Custom list of housekeeping genes -
housekeeping_predict = TRUE, # Predict the housekeeping genes based on the data? -
normalisation_method = "GEO", # Geometric mean or GLM -
n_comp = 5 # Number indicating the number of principal components to compute. - )`
Error goes like this : [NACHO] Importing RCC files. Error: Column cols must be length 1 (the number of rows), not 3
Any other solutions?
Thanks for quick response.
Athul