ydeng/bch441-work-abc-units
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updates to UniProtIDmap, and address httr/curl initialization bug

Browse Source
This commit is contained in:
hyginn 2020-09-25 02:27:42 +10:00
parent f3a436cb6e
commit 2775c7c9a8
2 changed files with 20 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
BIN-Data_integration.R
View File

@ -1,20 +1,15 @@
# tocID <- "BIN-Data_integration.R"
#
# ---------------------------------------------------------------------------- #
# PATIENCE ... #
# Do not yet work wih this code. Updates in progress. Thank you. #
# boris.steipe@utoronto.ca #
# ---------------------------------------------------------------------------- #
#
# Purpose: A Bioinformatics Course:
# R code accompanying the BIN-Data_integration unit.
#
# Version: 1.1
# Version: 1.2
#
# Date: 2018 10 - 2019 01
# Date: 2018-10 - 2020-09
# Author: Boris Steipe (boris.steipe@utoronto.ca)
#
# Versions:
# 1.2 2020 Maintenance and updates
# 1.1 Change from require() to requireNamespace(),
# use <package>::<function>() idiom throughout
# 1.0.1 Bugfix: UniProt ID Mapping service API change
@ -62,8 +57,8 @@
# To begin, we load httr, which supports sending and receiving data via the
# http protocol, just like a Web browser.
if (! requireNamespace("httpr", quietly=TRUE)) {
install.packages("httpr")
if (! requireNamespace("httr", quietly=TRUE)) {
install.packages("httr")
}
# Package information:
# library(help = httr) # basic information
@ -81,6 +76,12 @@ myQueryIDs <- "NP_010227 NP_00000 NP_011036"
# the URL of the server and send a list of items labelled as "query" in the body
# of the request. GET() and POST() are functions from httr.
# Note. A recent bug in the interaction between the server expectations and the
# curl client libraries requires the following initialization
httr::set_config(httr::config(http_version = 0))
# cf. https://stackoverflow.com/questions/44610845/stream-error-in-the-http-2-framing-layer-bigrquery-commands-error-in-r-studio-b
URL <- "https://www.uniprot.org/mapping/"
response <- httr::POST(URL,
body = list(from = "P_REFSEQ_AC", # Refseq Protein
@ -102,14 +103,6 @@ myMappedIDs <- read.delim(file = textConnection(httr::content(response)),
stringsAsFactors = FALSE)
myMappedIDs
# We actually only need columns 1 and 3, and we can also change the names
# to "From" and "To":
myMappedIDs <- myMappedIDs[ , c(1,3)]
colnames(myMappedIDs) <- c("From", "To")
myMappedIDs
# If this works as expected, you should see:
# From To
# 1 NP_010227 P39678
@ -138,6 +131,9 @@ myIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
# empty data frame if the mapping was unsuccessful. No rows are returned
# for IDs that are not mapped.
# Initialize curl
httr::set_config(httr::config(http_version = 0))
URL <- "https://www.uniprot.org/uploadlists/"
response <- httr::POST(URL,
body = list(from = mapFrom,
@ -149,7 +145,6 @@ myIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
myMap <- read.delim(file = textConnection(httr::content(response)),
sep = "\t",
stringsAsFactors = FALSE)
myMap <- myMap[ , c(1,3)]
colnames(myMap) <- c("From", "To")
} else {
myMap <- data.frame()
@ -187,8 +182,7 @@ myIDs <- data.frame(uID = c("P38903", "P31383", "P47177", "P47096", "Q07747",
"NP_012683", "NP_012559",
"NP_010038", "NP_014882",
"NP_012616", "NP_013254",
"NP_014555", "NP_013629"),
stringsAsFactors = FALSE)
"NP_014555", "NP_013629"))
myIDs
@ -212,7 +206,7 @@ myIDs$name[match(myQuery, myIDs$refID)]
#
# Note: if you want to do very many queries in large tables, use the
# Note: if you want to do very many queries in very large tables, use the
# fmatch() function in the "fastmatch" package for a considerable
# speedup.

6
scripts/ABC-dbUtilities.R
View File

@ -24,7 +24,7 @@
#TOC> 2.11 node2text() 311
#TOC> 2.12 dbFetchNCBItaxData() 323
#TOC> 2.13 UniProtIDmap() 362
#TOC> 3 TESTS 399
#TOC> 3 TESTS 401
#TOC>
#TOC> ==========================================================================
@ -373,6 +373,9 @@ UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
# empty data frame if the mapping was unsuccessful. No rows are returned
# for IDs that are not mapped.
# Initialize curl
httr::set_config(httr::config(http_version = 0))
URL <- "https://www.uniprot.org/uploadlists/"
response <- httr::POST(URL,
body = list(from = mapFrom,
@ -383,7 +386,6 @@ UniProtIDmap <- function (s, mapFrom = "P_REFSEQ_AC", mapTo = "ACC") {
if (httr::status_code(response) == 200) { # 200: oK
myMap <- read.delim(file = textConnection(httr::content(response)),
sep = "\t")
myMap <- myMap[ , c(1,3)]
colnames(myMap) <- c("From", "To")
} else {
myMap <- data.frame()