Mercurial > repos > prog > lcmsmatching

annotate UniprotEntry.R @ 3:f61ce21ed17c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 UniprotEntry <- methods::setRefClass("UniprotEntry", 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 createUniprotEntryFromXml <- 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 # Set XML namespace
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
14 ns <- c(uniprot = "http://uniprot.org/uniprot")
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
15
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
16 entries <- list()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
17
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
18 # Define xpath expressions
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
19 xpath.values <- character()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
20 xpath.values[[BIODB.NAME]] <- "/uniprot:uniprot/uniprot:entry/uniprot:name"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
21 xpath.values[[BIODB.GENE.SYMBOLS]] <- "//uniprot:gene/uniprot:name"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
22 xpath.values[[BIODB.FULLNAMES]] <- "//uniprot:protein//uniprot:fullName"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
23 xpath.values[[BIODB.SEQUENCE]] <- "//uniprot:entry/uniprot:sequence"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
24 xpath.values[[BIODB.ACCESSION]] <- "//uniprot:accession[1]"
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
25 xpath.attr <- list()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
26 xpath.attr[[BIODB.KEGG.ID]] <- list(path = "//uniprot:dbReference[@type='KEGG']", attr = 'id')
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
27 xpath.attr[[BIODB.NCBI.GENE.ID]] <- list(path = "//uniprot:dbReference[@type='GeneID']", attr = 'id')
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
28 xpath.attr[[BIODB.ENZYME.ID]] <- list(path = "//uniprot:dbReference[@type='EC']", attr = 'id')
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
29 xpath.attr[[BIODB.MASS]] <- list(path = "//uniprot:entry/uniprot:sequence", attr = 'mass')
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
30 xpath.attr[[BIODB.LENGTH]] <- list(path = "//uniprot:entry/uniprot:sequence", attr = 'length')
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 for (content in contents) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
33
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
34 # Create instance
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
35 entry <- UniprotEntry$new()
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
36
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
37 # If the entity doesn't exist (i.e.: no <id>.xml page), then it returns an HTML page
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
38 if ( ! grepl("^<!DOCTYPE html ", content, perl = TRUE)) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
39
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
40 # Parse XML
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
41 xml <- XML::xmlInternalTreeParse(content, asText = TRUE)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
42
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
43 # Test value xpath
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
44 for (field in names(xpath.values)) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
45 v <- XML::xpathSApply(xml, xpath.values[[field]], XML::xmlValue, namespaces = ns)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
46 if (length(v) > 0)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
47 entry$setField(field, v)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
48 }
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 # Test attribute xpath
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
51 for (field in names(xpath.attr)) {
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
52 v <- XML::xpathSApply(xml, xpath.attr[[field]]$path, XML::xmlGetAttr, xpath.attr[[field]]$attr, namespaces = ns)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
53 if (length(v) > 0)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
54 entry$setField(field, v)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
55 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
56
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
57 # Remove new lines from sequence string
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
58 seq <- entry$getField(BIODB.SEQUENCE)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
59 if ( ! is.na(seq))
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
60 entry$setField(BIODB.SEQUENCE, gsub("\\n", "", seq))
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
61 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
62
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
63 entries <- c(entries, entry)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
64 }
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
65
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
66 # Replace elements with no accession id by NULL
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
67 entries <- lapply(entries, function(x) if (is.na(x$getField(BIODB.ACCESSION))) NULL else x)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
68
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
69 # 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
70 if (drop && length(contents) == 1)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
71 entries <- entries[[1]]
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
72
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
73 return(entries)
20d69a062da3 planemo upload for repository https://github.com/workflow4metabolomics/lcmsmatching.git commit d4048accde6bdfd5b3e14f5394902d38991854f8
prog
parents:
diff changeset
74 }