annotate HmdbEntry.R @ 3:f61ce21ed17c draft

planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit 476a081c0da66822f4e77070f5ce59d9f14511f4-dirty
author prog
date Thu, 02 Mar 2017 11:07:56 -0500
parents 20d69a062da3
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
1 #####################
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
2 # CLASS DECLARATION #
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
3 #####################
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
4
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
5 HmdbEntry <- methods::setRefClass("HmdbEntry", contains = "BiodbEntry")
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
6
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
7 ###########
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
8 # FACTORY #
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
9 ###########
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
10
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
11 createHmdbEntryFromXml <- function(contents, drop = FALSE) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
12
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
13 entries <- list()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
14
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
15 # Define xpath expressions
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
16 xpath.expr <- character()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
17 xpath.expr[[BIODB.ACCESSION]] <- "/metabolite/accession"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
18 xpath.expr[[BIODB.KEGG.ID]] <- "//kegg_id"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
19 xpath.expr[[BIODB.NAME]] <- "/metabolite/name"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
20 xpath.expr[[BIODB.FORMULA]] <- "/metabolite/chemical_formula"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
21 xpath.expr[[BIODB.SUPER.CLASS]] <- "//super_class"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
22 xpath.expr[[BIODB.AVERAGE.MASS]] <- "//average_molecular_weight"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
23 xpath.expr[[BIODB.MONOISOTOPIC.MASS]] <- "//monisotopic_moleculate_weight"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
24
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
25 for (content in contents) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
26
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
27 # Create instance
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
28 entry <- HmdbEntry$new()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
29
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
30 if ( ! is.null(content) && ! is.na(content)) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
31
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
32 # Parse XML
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
33 xml <- XML::xmlInternalTreeParse(content, asText = TRUE)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
34
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
35 # An error occured
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
36 if (length(XML::getNodeSet(xml, "//error")) == 0) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
37
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
38 # Test generic xpath expressions
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
39 for (field in names(xpath.expr)) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
40 v <- XML::xpathSApply(xml, xpath.expr[[field]], XML::xmlValue)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
41 if (length(v) > 0)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
42 entry$setField(field, v)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
43 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
44
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
45 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
46 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
47
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
48 entries <- c(entries, entry)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
49 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
50
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
51 # Replace elements with no accession id by NULL
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
52 entries <- lapply(entries, function(x) if (is.na(x$getField(BIODB.ACCESSION))) NULL else x)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
53
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
54 # If the input was a single element, then output a single object
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
55 if (drop && length(contents) == 1)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
56 entries <- entries[[1]]
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
57
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
58 return(entries)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
59 }