Last active
October 19, 2020 19:56
-
-
Save lcolladotor/242dcc56515b77fdc4cf7341f824fcf9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library("BiocFileCache") | |
library("SummarizedExperiment") | |
library("googlesheets4") | |
## Location for temporarely downloading the files | |
bfc_temp <- BiocFileCache(tempdir()) | |
## Download the BSP1 and BSP2 data | |
bsp1_data <- bfcrpath(bfc_temp, "https://s3.us-east-2.amazonaws.com/jaffe-nat-neuro-2018/rse_gene_BrainSeq_Phase1_hg19_TopHat2_EnsemblV75.rda") | |
bsp2_data <- bfcrpath(bfc_temp, "https://s3.us-east-2.amazonaws.com/libd-brainseq2/rse_gene_unfiltered.Rdata") | |
## For BSP1, use the data at JHPCE with the MDD and BPD samples | |
bsp1_data <- "/dcl01/ajaffe/data/lab/brainseq_phase1/count_data/dlpfc_polyA_brainseq_phase1_hg38_rseGene_merged_n732.rda" | |
## Same file as the one available on the web for BSP2 | |
bsp2_data <- "/dcl01/lieber/ajaffe/lab/brainseq_phase2/expr_cutoff/unfiltered/rse_gene_unfiltered.Rdata" | |
## Load into R | |
load(bsp1_data, verbose = TRUE) | |
rse_bsp1 <- rse_gene | |
load(bsp2_data, verbose = TRUE) | |
rse_bsp2 <- rse_gene | |
## Explore how the data is labeled | |
colnames(colData(rse_bsp1)) | |
colnames(colData(rse_bsp2)) | |
## Extract a few variables of interest | |
meta_bsp1 <- with(colData(rse_bsp1), data.frame( | |
"BrainID" = BrNum, | |
"SampleID" = RNum, | |
"Diagnosis" = Dx, | |
"Age" = Age, | |
"Sex" = Sex, | |
"Region" = "DLPFC", | |
"RNAseqDataAvailable" = TRUE, | |
"GenotypingPlatform" = NA, | |
"Phase" = "BSP1", | |
"GenotypeRegion" = NA, | |
"IDAT_prefix" = NA | |
)) | |
meta_bsp2 <- with(colData(rse_bsp2), data.frame( | |
"BrainID" = BrNum, | |
"SampleID" = RNum, | |
"Diagnosis" = Dx, | |
"Age" = Age, | |
"Sex" = Sex, | |
"Region" = Region, | |
"RNAseqDataAvailable" = TRUE, | |
"GenotypingPlatform" = NA, | |
"Phase" = "BSP2", | |
"GenotypeRegion" = NA, | |
"IDAT_prefix" = NA | |
)) | |
## Combine | |
meta_both <- rbind(meta_bsp1, meta_bsp2) | |
## Share | |
ss <- gs4_create( | |
"BSP1_BSP2_samples" | |
) | |
sheet_write(meta_both, ss = "1BAEJcjUM5qfFdFSAoo7bToFgaWHdNd6YjLd0NYkWjHw") | |
with(meta_both, table(Diagnosis, Phase)) | |
# Phase | |
# Diagnosis BSP1 BSP2 | |
# Bipolar 67 0 | |
# Control 336 614 | |
# MDD 150 0 | |
# Schizo 179 286 | |
## View data at https://docs.google.com/spreadsheets/d/1BAEJcjUM5qfFdFSAoo7bToFgaWHdNd6YjLd0NYkWjHw/edit?usp=sharing | |
## Reproducibility information | |
options(width = 120) | |
sessioninfo::session_info() | |
# - Session info ------------------------------------------------------------------------------------------------------- | |
# setting value | |
# version R version 4.0.2 (2020-06-22) | |
# os Windows 10 x64 | |
# system x86_64, mingw32 | |
# ui RStudio | |
# language (EN) | |
# collate English_United States.1252 | |
# ctype English_United States.1252 | |
# tz America/New_York | |
# date 2020-10-19 | |
# | |
# - Packages ----------------------------------------------------------------------------------------------------------- | |
# package * version date lib source | |
# askpass 1.1 2019-01-13 [1] CRAN (R 4.0.2) | |
# assertthat 0.2.1 2019-03-21 [1] CRAN (R 4.0.2) | |
# backports 1.1.10 2020-09-15 [1] CRAN (R 4.0.2) | |
# Biobase * 2.48.0 2020-04-27 [1] Bioconductor | |
# BiocFileCache * 1.12.1 2020-08-04 [1] Bioconductor | |
# BiocGenerics * 0.34.0 2020-04-27 [1] Bioconductor | |
# bit 4.0.4 2020-08-04 [1] CRAN (R 4.0.2) | |
# bit64 4.0.5 2020-08-30 [1] CRAN (R 4.0.2) | |
# bitops 1.0-6 2013-08-17 [1] CRAN (R 4.0.0) | |
# blob 1.2.1 2020-01-20 [1] CRAN (R 4.0.2) | |
# callr 3.5.1 2020-10-13 [1] CRAN (R 4.0.2) | |
# cellranger 1.1.0 2016-07-27 [1] CRAN (R 4.0.2) | |
# cli 2.1.0 2020-10-12 [1] CRAN (R 4.0.2) | |
# crayon 1.3.4 2017-09-16 [1] CRAN (R 4.0.2) | |
# curl 4.3 2019-12-02 [1] CRAN (R 4.0.2) | |
# DBI 1.1.0 2019-12-15 [1] CRAN (R 4.0.2) | |
# dbplyr * 1.4.4 2020-05-27 [1] CRAN (R 4.0.2) | |
# DelayedArray * 0.14.1 2020-07-15 [1] Bioconductor | |
# desc 1.2.0 2018-05-01 [1] CRAN (R 4.0.2) | |
# devtools * 2.3.2 2020-09-18 [1] CRAN (R 4.0.2) | |
# digest 0.6.25 2020-02-23 [1] CRAN (R 4.0.2) | |
# dplyr 1.0.2 2020-08-18 [1] CRAN (R 4.0.2) | |
# ellipsis 0.3.1 2020-05-15 [1] CRAN (R 4.0.2) | |
# fansi 0.4.1 2020-01-08 [1] CRAN (R 4.0.2) | |
# fs 1.5.0 2020-07-31 [1] CRAN (R 4.0.2) | |
# gargle 0.5.0 2020-05-06 [1] CRAN (R 4.0.2) | |
# generics 0.0.2 2018-11-29 [1] CRAN (R 4.0.2) | |
# GenomeInfoDb * 1.24.2 2020-06-15 [1] Bioconductor | |
# GenomeInfoDbData 1.2.3 2020-06-30 [1] Bioconductor | |
# GenomicRanges * 1.40.0 2020-04-27 [1] Bioconductor | |
# glue 1.4.2 2020-08-27 [1] CRAN (R 4.0.2) | |
# googledrive 1.0.1 2020-05-05 [1] CRAN (R 4.0.2) | |
# googlesheets4 * 0.2.0 2020-05-08 [1] CRAN (R 4.0.2) | |
# here 0.1 2017-05-28 [1] CRAN (R 4.0.2) | |
# httr 1.4.2 2020-07-20 [1] CRAN (R 4.0.2) | |
# IRanges * 2.22.2 2020-05-21 [1] Bioconductor | |
# jsonlite 1.7.1 2020-09-07 [1] CRAN (R 4.0.2) | |
# lattice 0.20-41 2020-04-02 [1] CRAN (R 4.0.2) | |
# lifecycle 0.2.0 2020-03-06 [1] CRAN (R 4.0.2) | |
# magrittr 1.5 2014-11-22 [1] CRAN (R 4.0.2) | |
# Matrix 1.2-18 2019-11-27 [1] CRAN (R 4.0.2) | |
# matrixStats * 0.57.0 2020-09-25 [1] CRAN (R 4.0.2) | |
# memoise 1.1.0 2017-04-21 [1] CRAN (R 4.0.2) | |
# openssl 1.4.3 2020-09-18 [1] CRAN (R 4.0.2) | |
# pillar 1.4.6 2020-07-10 [1] CRAN (R 4.0.2) | |
# pkgbuild 1.1.0 2020-07-13 [1] CRAN (R 4.0.2) | |
# pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.0.2) | |
# pkgload 1.1.0 2020-05-29 [1] CRAN (R 4.0.2) | |
# prettyunits 1.1.1 2020-01-24 [1] CRAN (R 4.0.2) | |
# processx 3.4.4 2020-09-03 [1] CRAN (R 4.0.2) | |
# ps 1.3.4 2020-08-11 [1] CRAN (R 4.0.2) | |
# purrr 0.3.4 2020-04-17 [1] CRAN (R 4.0.2) | |
# R6 2.4.1 2019-11-12 [1] CRAN (R 4.0.2) | |
# rappdirs 0.3.1 2016-03-28 [1] CRAN (R 4.0.2) | |
# Rcpp 1.0.5 2020-07-06 [1] CRAN (R 4.0.2) | |
# RCurl 1.98-1.2 2020-04-18 [1] CRAN (R 4.0.0) | |
# remotes 2.2.0 2020-07-21 [1] CRAN (R 4.0.2) | |
# rlang 0.4.7 2020-07-09 [1] CRAN (R 4.0.2) | |
# rprojroot 1.3-2 2018-01-03 [1] CRAN (R 4.0.2) | |
# RSQLite 2.2.1 2020-09-30 [1] CRAN (R 4.0.2) | |
# rstudioapi 0.11 2020-02-07 [1] CRAN (R 4.0.2) | |
# S4Vectors * 0.26.1 2020-05-16 [1] Bioconductor | |
# sessioninfo 1.1.1 2018-11-05 [1] CRAN (R 4.0.2) | |
# SummarizedExperiment * 1.18.2 2020-07-09 [1] Bioconductor | |
# testthat * 2.3.2 2020-03-02 [1] CRAN (R 4.0.2) | |
# tibble 3.0.3 2020-07-10 [1] CRAN (R 4.0.2) | |
# tidyselect 1.1.0 2020-05-11 [1] CRAN (R 4.0.2) | |
# usethis * 1.6.3 2020-09-17 [1] CRAN (R 4.0.2) | |
# vctrs 0.3.4 2020-08-29 [1] CRAN (R 4.0.2) | |
# withr 2.3.0 2020-09-22 [1] CRAN (R 4.0.2) | |
# XVector 0.28.0 2020-04-27 [1] Bioconductor | |
# zlibbioc 1.34.0 2020-04-27 [1] Bioconductor | |
# | |
# [1] D:/R/R-4.0.2/library |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment