-package jalview.datamodel.xdb.embl;\r
-\r
-import jalview.datamodel.DBRefEntry;\r
-import jalview.datamodel.Sequence;\r
-import jalview.datamodel.SequenceFeature;\r
-import jalview.datamodel.SequenceI;\r
-\r
-import java.util.Enumeration;\r
-import java.util.Hashtable;\r
-import java.util.Iterator;\r
-import java.util.Vector;\r
-\r
-public class EmblEntry {\r
- String accession;\r
- String version;\r
- String taxDivision;\r
- String desc;\r
- String rCreated;\r
- String rLastUpdated;\r
- String lastUpdated;\r
- Vector keywords;\r
- Vector refs;\r
- Vector dbRefs;\r
- Vector features;\r
- EmblSequence sequence;\r
- /**\r
- * @return the accession\r
- */\r
- public String getAccession() {\r
- return accession;\r
- }\r
- /**\r
- * @param accession the accession to set\r
- */\r
- public void setAccession(String accession) {\r
- this.accession = accession;\r
- }\r
- /**\r
- * @return the dbRefs\r
- */\r
- public Vector getDbRefs() {\r
- return dbRefs;\r
- }\r
- /**\r
- * @param dbRefs the dbRefs to set\r
- */\r
- public void setDbRefs(Vector dbRefs) {\r
- this.dbRefs = dbRefs;\r
- }\r
- /**\r
- * @return the desc\r
- */\r
- public String getDesc() {\r
- return desc;\r
- }\r
- /**\r
- * @param desc the desc to set\r
- */\r
- public void setDesc(String desc) {\r
- this.desc = desc;\r
- }\r
- /**\r
- * @return the features\r
- */\r
- public Vector getFeatures() {\r
- return features;\r
- }\r
- /**\r
- * @param features the features to set\r
- */\r
- public void setFeatures(Vector features) {\r
- this.features = features;\r
- }\r
- /**\r
- * @return the keywords\r
- */\r
- public Vector getKeywords() {\r
- return keywords;\r
- }\r
- /**\r
- * @param keywords the keywords to set\r
- */\r
- public void setKeywords(Vector keywords) {\r
- this.keywords = keywords;\r
- }\r
- /**\r
- * @return the lastUpdated\r
- */\r
- public String getLastUpdated() {\r
- return lastUpdated;\r
- }\r
- /**\r
- * @param lastUpdated the lastUpdated to set\r
- */\r
- public void setLastUpdated(String lastUpdated) {\r
- this.lastUpdated = lastUpdated;\r
- }\r
- /**\r
- * @return the refs\r
- */\r
- public Vector getRefs() {\r
- return refs;\r
- }\r
- /**\r
- * @param refs the refs to set\r
- */\r
- public void setRefs(Vector refs) {\r
- this.refs = refs;\r
- }\r
- /**\r
- * @return the releaseCreated\r
- */\r
- public String getRCreated() {\r
- return rCreated;\r
- }\r
- /**\r
- * @param releaseCreated the releaseCreated to set\r
- */\r
- public void setRcreated(String releaseCreated) {\r
- this.rCreated = releaseCreated;\r
- }\r
- /**\r
- * @return the releaseLastUpdated\r
- */\r
- public String getRLastUpdated() {\r
- return rLastUpdated;\r
- }\r
- /**\r
- * @param releaseLastUpdated the releaseLastUpdated to set\r
- */\r
- public void setRLastUpdated(String releaseLastUpdated) {\r
- this.rLastUpdated = releaseLastUpdated;\r
- }\r
- /**\r
- * @return the sequence\r
- */\r
- public EmblSequence getSequence() {\r
- return sequence;\r
- }\r
- /**\r
- * @param sequence the sequence to set\r
- */\r
- public void setSequence(EmblSequence sequence) {\r
- this.sequence = sequence;\r
- }\r
- /**\r
- * @return the taxDivision\r
- */\r
- public String getTaxDivision() {\r
- return taxDivision;\r
- }\r
- /**\r
- * @param taxDivision the taxDivision to set\r
- */\r
- public void setTaxDivision(String taxDivision) {\r
- this.taxDivision = taxDivision;\r
- }\r
- /**\r
- * @return the version\r
- */\r
- public String getVersion() {\r
- return version;\r
- }\r
- /**\r
- * @param version the version to set\r
- */\r
- public void setVersion(String version) {\r
- this.version = version;\r
- }\r
-/*\r
- * EMBL Feature support is limited. The text below is included for the benefit of\r
- * any developer working on improving EMBL feature import in Jalview.\r
- * Extract from EMBL feature specification\r
- * see http://www.embl-ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html\r
-3.5 Location\r
-3.5.1 Purpose\r
-\r
-The location indicates the region of the presented sequence which corresponds \r
-to a feature. \r
-\r
-3.5.2 Format and conventions\r
-The location contains at least one sequence location descriptor and may \r
-contain one or more operators with one or more sequence location descriptors. \r
-Base numbers refer to the numbering in the entry. This numbering designates \r
-the first base (5' end) of the presented sequence as base 1. \r
-Base locations beyond the range of the presented sequence may not be used in \r
-location descriptors, the only exception being location in a remote entry (see \r
-3.5.2.1, e). \r
-\r
-Location operators and descriptors are discussed in more detail below. \r
-\r
-3.5.2.1 Location descriptors\r
-\r
-The location descriptor can be one of the following: \r
-(a) a single base number\r
-(b) a site between two indicated adjoining bases\r
-(c) a single base chosen from within a specified range of bases (not allowed for new\r
- entries)\r
-(d) the base numbers delimiting a sequence span\r
-(e) a remote entry identifier followed by a local location descriptor\r
- (i.e., a-d)\r
-\r
-A site between two adjoining nucleotides, such as endonucleolytic cleavage \r
-site, is indicated by listing the two points separated by a carat (^). The \r
-permitted formats for this descriptor are n^n+1 (for example 55^56), or, for \r
-circular molecules, n^1, where "n" is the full length of the molecule, ie \r
-1000^1 for circular molecule with length 1000.\r
-\r
-A single base chosen from a range of bases is indicated by the first base\r
-number and the last base number of the range separated by a single period\r
-(e.g., '12.21' indicates a single base taken from between the indicated\r
-points). From October 2006 the usage of this descriptor is restricted :\r
-it is illegal to use "a single base from a range" (c) either on its own or\r
-in combination with the "sequence span" (d) descriptor for newly created entries.\r
-The existing entries where such descriptors exist are going to be retrofitted.\r
-\r
-Sequence spans are indicated by the starting base number and the ending base \r
-number separated by two periods (e.g., '34..456'). The '<' and '>' symbols may \r
-be used with the starting and ending base numbers to indicate that an end \r
-point is beyond the specified base number. The starting and ending base \r
-positions can be represented as distinct base numbers ('34..456') or a site \r
-between two indicated adjoining bases. \r
-\r
-A location in a remote entry (not the entry to which the feature table \r
-belongs) can be specified by giving the accession-number and sequence version \r
-of the remote entry, followed by a colon ":", followed by a location \r
-descriptor which applies to that entry's sequence (i.e. J12345.1:1..15, see \r
-also examples below) \r
-\r
-3.5.2.2 Operators\r
-\r
-The location operator is a prefix that specifies what must be done to the \r
-indicated sequence to find or construct the location corresponding to the \r
-feature. A list of operators is given below with their definitions and most \r
-common format. \r
-\r
-complement(location) \r
-Find the complement of the presented sequence in the span specified by "\r
-location" (i.e., read the complement of the presented strand in its 5'-to-3' \r
-direction) \r
-\r
-join(location,location, ... location) \r
-The indicated elements should be joined (placed end-to-end) to form one \r
-contiguous sequence \r
-\r
-order(location,location, ... location) \r
-The elements can be found in the \r
-specified order (5' to 3' direction), but nothing is implied about the \r
-reasonableness about joining them \r
-\r
-Note : location operator "complement" can be used in combination with either "\r
-join" or "order" within the same location; combinations of "join" and "order" \r
-within the same location (nested operators) are illegal.\r
-\r
-\r
-\r
-3.5.3 Location examples \r
-\r
-The following is a list of common location descriptors with their meanings: \r
-\r
-Location Description \r
-\r
-467 Points to a single base in the presented sequence \r
-\r
-340..565 Points to a continuous range of bases bounded by and\r
- including the starting and ending bases\r
-\r
-<345..500 Indicates that the exact lower boundary point of a feature\r
- is unknown. The location begins at some base previous to\r
- the first base specified (which need not be contained in \r
- the presented sequence) and continues to and includes the \r
- ending base \r
-\r
-<1..888 The feature starts before the first sequenced base and \r
- continues to and includes base 888\r
-\r
-1..>888 The feature starts at the first sequenced base and \r
- continues beyond base 888\r
-\r
-102.110 Indicates that the exact location is unknown but that it is \r
- one of the bases between bases 102 and 110, inclusive\r
-\r
-123^124 Points to a site between bases 123 and 124\r
-\r
-join(12..78,134..202) Regions 12 to 78 and 134 to 202 should be joined to form \r
- one contiguous sequence\r
-\r
-\r
-complement(34..126) Start at the base complementary to 126 and finish at the \r
- base complementary to base 34 (the feature is on the strand \r
- complementary to the presented strand)\r
-\r
-\r
-complement(join(2691..4571,4918..5163))\r
- Joins regions 2691 to 4571 and 4918 to 5163, then \r
- complements the joined segments (the feature is on the \r
- strand complementary to the presented strand) \r
-\r
-join(complement(4918..5163),complement(2691..4571))\r
- Complements regions 4918 to 5163 and 2691 to 4571, then \r
- joins the complemented segments (the feature is on the \r
- strand complementary to the presented strand)\r
- \r
-J00194.1:100..202 Points to bases 100 to 202, inclusive, in the entry (in \r
- this database) with primary accession number 'J00194'\r
- \r
-join(1..100,J00194.1:100..202)\r
- Joins region 1..100 of the existing entry with the region\r
- 100..202 of remote entry J00194\r
-\r
- */\r
- /**\r
- * Recover annotated sequences from EMBL file\r
- * @param noNa don't return nucleic acid sequences \r
- * @param sourceDb TODO\r
- * @param noProtein don't return any translated protein sequences marked in features\r
- * @return dataset sequences with DBRefs and features - DNA always comes first\r
- */\r
- public jalview.datamodel.SequenceI[] getSequences(boolean noNa, boolean noPeptide, String sourceDb) {\r
- Vector seqs=new Vector();\r
- Sequence dna=null;\r
- if (!noNa) {\r
- dna = new Sequence(sourceDb+"|"+accession, sequence.getSequence());\r
- dna.setDescription(desc);\r
- dna.addDBRef(new DBRefEntry(sourceDb, version, accession));\r
- // TODO: add mapping for parentAccession attribute\r
- // TODO: transform EMBL Database refs to canonical form\r
- if (dbRefs!=null)\r
- for (Iterator i=dbRefs.iterator(); i.hasNext(); dna.addDBRef((DBRefEntry)i.next()));\r
- }\r
- for (Iterator i=features.iterator(); i.hasNext(); ) {\r
- EmblFeature feature = (EmblFeature) i.next();\r
- if (!noNa) {\r
- if (feature.dbRefs!=null && feature.dbRefs.size()>0) {\r
- for (Iterator dbr=feature.dbRefs.iterator(); dbr.hasNext(); dna.addDBRef((DBRefEntry)dbr.next()) )\r
- ;\r
- }\r
- }\r
- if (feature.getName().equalsIgnoreCase("CDS")) {\r
- // extract coding region(s)\r
- jalview.datamodel.Mapping map = null;\r
- int[] exon=null;\r
- if (feature.locations!=null && feature.locations.size()>0) {\r
- for (Iterator locs=feature.locations.iterator();\r
- locs.hasNext(); ) {\r
- EmblFeatureLocations loc = (EmblFeatureLocations) locs.next();\r
- int[] se = loc.getElementRanges();\r
- if (exon==null) {\r
- exon=se;\r
- } else {\r
- int[] t=new int[exon.length+se.length];\r
- System.arraycopy(exon, 0, t, 0, exon.length);\r
- System.arraycopy(se, 0, t, exon.length,se.length);\r
- exon=t;\r
- }\r
- }\r
- }\r
- String prseq=null;\r
- String prname=new String();\r
- String prid=null;\r
- Hashtable vals=new Hashtable();\r
- int prstart=1;\r
- // get qualifiers\r
- if (feature.getQualifiers()!=null && feature.getQualifiers().size()>0) {\r
- for (Iterator quals=feature.getQualifiers().iterator(); quals.hasNext(); ) {\r
- Qualifier q = (Qualifier) quals.next();\r
- if (q.getName().equals("translation")) \r
- {\r
- prseq=q.getValue();\r
- } \r
- else\r
- if (q.getName().equals("protein_id")) \r
- {\r
- prid=q.getValue();\r
- }\r
- else\r
- if (q.getName().equals("codon_start"))\r
- {\r
- prstart = Integer.parseInt(q.getValue());\r
- }\r
- else \r
- if (q.getName().equals("product")){\r
- prname = q.getValue();\r
- } else {\r
- // throw anything else into the additional properties hash\r
- vals.put(q.getName(), q.getValue());\r
- }\r
- }\r
- }\r
- Sequence product=null;\r
- if (prseq!=null && prname!=null && prid!=null) {\r
- // extract proteins.\r
- if (!noPeptide) {\r
- product = new Sequence(sourceDb+"|"+"EMBLCDS|"+prid+"|"+prname, prseq, prstart, prstart+prseq.length()-1);\r
- product.setDescription("Protein Product from "+sourceDb);\r
- seqs.add(product);\r
- }\r
- // we have everything - create the mapping and perhaps the protein sequence\r
- map = new jalview.datamodel.Mapping(product, exon, new int[] { prstart, prstart+prseq.length()-1}, 3, 1);\r
- // add cds feature to dna seq - this may include the stop codon\r
- for (int xint=0;xint<exon.length; xint+=2) {\r
- SequenceFeature sf = new SequenceFeature();\r
- sf.setBegin(exon[xint]);\r
- sf.setEnd(exon[xint+1]);\r
- sf.setType(feature.getName());\r
- sf.setFeatureGroup(jalview.datamodel.DBRefSource.EMBL);\r
- sf.setDescription("Exon "+(1+xint)+" for protein '"+prname+"' EMBLCDS:"+prid);\r
- if (vals!=null && vals.size()>0) {\r
- Enumeration kv = vals.elements();\r
- while (kv.hasMoreElements()) {\r
- Object key=kv.nextElement();\r
- if (key!=null)\r
- sf.setValue(key.toString(), vals.get(key));\r
- }\r
- }\r
- dna.addSequenceFeature(sf);\r
- }\r
- }\r
- // add dbRefs to sequence\r
- if (feature.dbRefs!=null && feature.dbRefs.size()>0) \r
- {\r
- for (Iterator dbr=feature.dbRefs.iterator(); dbr.hasNext(); ) \r
- {\r
- DBRefEntry ref = (DBRefEntry)dbr.next();\r
- ref.setSource(jalview.util.DBRefUtils.getCanonicalName(ref.getSource()));\r
- if (ref.getSource().equals(jalview.datamodel.DBRefSource.UNIPROT)) \r
- {\r
- ref.setMap(map);\r
- }\r
- if (product!=null) {\r
- DBRefEntry pref = new DBRefEntry(ref.getSource(), ref.getVersion(), ref.getAccessionId());\r
- pref.setMap(null); // reference is direct\r
- }\r
- dna.addDBRef(ref);\r
- }\r
- }\r
- \r
- } else {\r
- // General feature type.\r
- if (!noNa) {\r
- if (feature.dbRefs!=null && feature.dbRefs.size()>0) {\r
- for (Iterator dbr=feature.dbRefs.iterator(); dbr.hasNext(); dna.addDBRef((DBRefEntry)dbr.next()) )\r
- ;\r
- }\r
- }\r
- }\r
-\r
- }\r
- if (!noNa) {\r
- seqs.add(dna);\r
- }\r
- SequenceI[] sqs = new SequenceI[seqs.size()];\r
- for (int i=0,j=seqs.size();i<j; i++) {\r
- sqs[i] = (SequenceI) seqs.elementAt(i);\r
- seqs.set(i, null);\r
- }\r
- return sqs;\r
- }\r
-}\r
+/*
+ * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+ * Copyright (C) $$Year-Rel$$ The Jalview Authors
+ *
+ * This file is part of Jalview.
+ *
+ * Jalview is free software: you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation, either version 3
+ * of the License, or (at your option) any later version.
+ *
+ * Jalview is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
+ * PURPOSE. See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
+ * The Jalview Authors are detailed in the 'AUTHORS' file.
+ */
+package jalview.datamodel.xdb.embl;
+
+import jalview.analysis.SequenceIdMatcher;
+import jalview.bin.Cache;
+import jalview.datamodel.DBRefEntry;
+import jalview.datamodel.DBRefSource;
+import jalview.datamodel.FeatureProperties;
+import jalview.datamodel.Mapping;
+import jalview.datamodel.Sequence;
+import jalview.datamodel.SequenceFeature;
+import jalview.datamodel.SequenceI;
+import jalview.util.DBRefUtils;
+import jalview.util.DnaUtils;
+import jalview.util.MapList;
+import jalview.util.MappingUtils;
+import jalview.util.StringUtils;
+
+import java.text.ParseException;
+import java.util.Arrays;
+import java.util.Hashtable;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.Vector;
+import java.util.regex.Pattern;
+
+/**
+ * Data model for one entry returned from an EMBL query, as marshalled by a
+ * Castor binding file
+ *
+ * For example: http://www.ebi.ac.uk/ena/data/view/J03321&display=xml
+ *
+ * @see embl_mapping.xml
+ */
+public class EmblEntry
+{
+ private static final Pattern SPACE_PATTERN = Pattern.compile(" ");
+
+ String accession;
+
+ String entryVersion;
+
+ String sequenceVersion;
+
+ String dataClass;
+
+ String moleculeType;
+
+ String topology;
+
+ String sequenceLength;
+
+ String taxonomicDivision;
+
+ String description;
+
+ String firstPublicDate;
+
+ String firstPublicRelease;
+
+ String lastUpdatedDate;
+
+ String lastUpdatedRelease;
+
+ Vector<String> keywords;
+
+ Vector<DBRefEntry> dbRefs;
+
+ Vector<EmblFeature> features;
+
+ EmblSequence sequence;
+
+ /**
+ * @return the accession
+ */
+ public String getAccession()
+ {
+ return accession;
+ }
+
+ /**
+ * @param accession
+ * the accession to set
+ */
+ public void setAccession(String accession)
+ {
+ this.accession = accession;
+ }
+
+ /**
+ * @return the dbRefs
+ */
+ public Vector<DBRefEntry> getDbRefs()
+ {
+ return dbRefs;
+ }
+
+ /**
+ * @param dbRefs
+ * the dbRefs to set
+ */
+ public void setDbRefs(Vector<DBRefEntry> dbRefs)
+ {
+ this.dbRefs = dbRefs;
+ }
+
+ /**
+ * @return the features
+ */
+ public Vector<EmblFeature> getFeatures()
+ {
+ return features;
+ }
+
+ /**
+ * @param features
+ * the features to set
+ */
+ public void setFeatures(Vector<EmblFeature> features)
+ {
+ this.features = features;
+ }
+
+ /**
+ * @return the keywords
+ */
+ public Vector<String> getKeywords()
+ {
+ return keywords;
+ }
+
+ /**
+ * @param keywords
+ * the keywords to set
+ */
+ public void setKeywords(Vector<String> keywords)
+ {
+ this.keywords = keywords;
+ }
+
+ /**
+ * @return the sequence
+ */
+ public EmblSequence getSequence()
+ {
+ return sequence;
+ }
+
+ /**
+ * @param sequence
+ * the sequence to set
+ */
+ public void setSequence(EmblSequence sequence)
+ {
+ this.sequence = sequence;
+ }
+
+ /**
+ * Recover annotated sequences from EMBL file
+ *
+ * @param sourceDb
+ * @param peptides
+ * a list of protein products found so far (to add to)
+ * @return dna dataset sequence with DBRefs and features
+ */
+ public SequenceI getSequence(String sourceDb, List<SequenceI> peptides)
+ {
+ SequenceI dna = makeSequence(sourceDb);
+ if (dna == null)
+ {
+ return null;
+ }
+ dna.setDescription(description);
+ DBRefEntry retrievedref = new DBRefEntry(sourceDb, getSequenceVersion(),
+ accession);
+ dna.addDBRef(retrievedref);
+ // add map to indicate the sequence is a valid coordinate frame for the
+ // dbref
+ retrievedref
+ .setMap(new Mapping(null, new int[]
+ { 1, dna.getLength() }, new int[] { 1, dna.getLength() }, 1,
+ 1));
+
+ /*
+ * transform EMBL Database refs to canonical form
+ */
+ if (dbRefs != null)
+ {
+ for (DBRefEntry dbref : dbRefs)
+ {
+ dbref.setSource(DBRefUtils.getCanonicalName(dbref.getSource()));
+ dna.addDBRef(dbref);
+ }
+ }
+
+ SequenceIdMatcher matcher = new SequenceIdMatcher(peptides);
+ try
+ {
+ for (EmblFeature feature : features)
+ {
+ if (FeatureProperties.isCodingFeature(sourceDb, feature.getName()))
+ {
+ parseCodingFeature(feature, sourceDb, dna, peptides, matcher);
+ }
+ }
+ } catch (Exception e)
+ {
+ System.err.println("EMBL Record Features parsing error!");
+ System.err
+ .println("Please report the following to help@jalview.org :");
+ System.err.println("EMBL Record " + accession);
+ System.err.println("Resulted in exception: " + e.getMessage());
+ e.printStackTrace(System.err);
+ }
+
+ return dna;
+ }
+
+ /**
+ * @param sourceDb
+ * @return
+ */
+ SequenceI makeSequence(String sourceDb)
+ {
+ if (sequence == null)
+ {
+ System.err.println(
+ "No sequence was returned for ENA accession " + accession);
+ return null;
+ }
+ SequenceI dna = new Sequence(sourceDb + "|" + accession,
+ sequence.getSequence());
+ return dna;
+ }
+
+ /**
+ * Extracts coding region and product from a CDS feature and properly decorate
+ * it with annotations.
+ *
+ * @param feature
+ * coding feature
+ * @param sourceDb
+ * source database for the EMBLXML
+ * @param dna
+ * parent dna sequence for this record
+ * @param peptides
+ * list of protein product sequences for Embl entry
+ * @param matcher
+ * helper to match xrefs in already retrieved sequences
+ */
+ void parseCodingFeature(EmblFeature feature, String sourceDb,
+ SequenceI dna, List<SequenceI> peptides,
+ SequenceIdMatcher matcher)
+ {
+ boolean isEmblCdna = sourceDb.equals(DBRefSource.EMBLCDS);
+
+ int[] exons = getCdsRanges(feature);
+
+ String translation = null;
+ String proteinName = "";
+ String proteinId = null;
+ Map<String, String> vals = new Hashtable<>();
+
+ /*
+ * codon_start 1/2/3 in EMBL corresponds to phase 0/1/2 in CDS
+ * (phase is required for CDS features in GFF3 format)
+ */
+ int codonStart = 1;
+
+ /*
+ * parse qualifiers, saving protein translation, protein id,
+ * codon start position, product (name), and 'other values'
+ */
+ if (feature.getQualifiers() != null)
+ {
+ for (Qualifier q : feature.getQualifiers())
+ {
+ String qname = q.getName();
+ if (qname.equals("translation"))
+ {
+ // remove all spaces (precompiled String.replaceAll(" ", ""))
+ translation = SPACE_PATTERN.matcher(q.getValues()[0])
+ .replaceAll("");
+ }
+ else if (qname.equals("protein_id"))
+ {
+ proteinId = q.getValues()[0].trim();
+ }
+ else if (qname.equals("codon_start"))
+ {
+ try
+ {
+ codonStart = Integer.parseInt(q.getValues()[0].trim());
+ } catch (NumberFormatException e)
+ {
+ System.err.println("Invalid codon_start in XML for " + accession
+ + ": " + e.getMessage());
+ }
+ }
+ else if (qname.equals("product"))
+ {
+ // sometimes name is returned e.g. for V00488
+ proteinName = q.getValues()[0].trim();
+ }
+ else
+ {
+ // throw anything else into the additional properties hash
+ String[] qvals = q.getValues();
+ if (qvals != null)
+ {
+ String commaSeparated = StringUtils.arrayToSeparatorList(qvals,
+ ",");
+ vals.put(qname, commaSeparated);
+ }
+ }
+ }
+ }
+
+ DBRefEntry proteinToEmblProteinRef = null;
+ exons = MappingUtils.removeStartPositions(codonStart - 1, exons);
+
+ SequenceI product = null;
+ Mapping dnaToProteinMapping = null;
+ if (translation != null && proteinName != null && proteinId != null)
+ {
+ int translationLength = translation.length();
+
+ /*
+ * look for product in peptides list, if not found, add it
+ */
+ product = matcher.findIdMatch(proteinId);
+ if (product == null)
+ {
+ product = new Sequence(proteinId, translation, 1,
+ translationLength);
+ product.setDescription(((proteinName.length() == 0)
+ ? "Protein Product from " + sourceDb
+ : proteinName));
+ peptides.add(product);
+ matcher.add(product);
+ }
+
+ // we have everything - create the mapping and perhaps the protein
+ // sequence
+ if (exons == null || exons.length == 0)
+ {
+ /*
+ * workaround until we handle dna location for CDS sequence
+ * e.g. location="X53828.1:60..1058" correctly
+ */
+ System.err.println(
+ "Implementation Notice: EMBLCDS records not properly supported yet - Making up the CDNA region of this sequence... may be incorrect ("
+ + sourceDb + ":" + getAccession() + ")");
+ int dnaLength = dna.getLength();
+ if (translationLength * 3 == (1 - codonStart + dnaLength))
+ {
+ System.err.println(
+ "Not allowing for additional stop codon at end of cDNA fragment... !");
+ // this might occur for CDS sequences where no features are marked
+ exons = new int[] { dna.getStart() + (codonStart - 1),
+ dna.getEnd() };
+ dnaToProteinMapping = new Mapping(product, exons,
+ new int[]
+ { 1, translationLength }, 3, 1);
+ }
+ if ((translationLength + 1) * 3 == (1 - codonStart + dnaLength))
+ {
+ System.err.println(
+ "Allowing for additional stop codon at end of cDNA fragment... will probably cause an error in VAMSAs!");
+ exons = new int[] { dna.getStart() + (codonStart - 1),
+ dna.getEnd() - 3 };
+ dnaToProteinMapping = new Mapping(product, exons,
+ new int[]
+ { 1, translationLength }, 3, 1);
+ }
+ }
+ else
+ {
+ // Trim the exon mapping if necessary - the given product may only be a
+ // fragment of a larger protein. (EMBL:AY043181 is an example)
+
+ if (isEmblCdna)
+ {
+ // TODO: Add a DbRef back to the parent EMBL sequence with the exon
+ // map
+ // if given a dataset reference, search dataset for parent EMBL
+ // sequence if it exists and set its map
+ // make a new feature annotating the coding contig
+ }
+ else
+ {
+ // final product length truncation check
+ int[] cdsRanges = adjustForProteinLength(translationLength,
+ exons);
+ dnaToProteinMapping = new Mapping(product, cdsRanges,
+ new int[]
+ { 1, translationLength }, 3, 1);
+ if (product != null)
+ {
+ /*
+ * make xref with mapping from protein to EMBL dna
+ */
+ DBRefEntry proteinToEmblRef = new DBRefEntry(DBRefSource.EMBL,
+ getSequenceVersion(), proteinId,
+ new Mapping(dnaToProteinMapping.getMap().getInverse()));
+ product.addDBRef(proteinToEmblRef);
+
+ /*
+ * make xref from protein to EMBLCDS; we assume here that the
+ * CDS sequence version is same as dna sequence (?!)
+ */
+ MapList proteinToCdsMapList = new MapList(
+ new int[]
+ { 1, translationLength },
+ new int[]
+ { 1 + (codonStart - 1),
+ (codonStart - 1) + 3 * translationLength },
+ 1, 3);
+ DBRefEntry proteinToEmblCdsRef = new DBRefEntry(
+ DBRefSource.EMBLCDS, getSequenceVersion(), proteinId,
+ new Mapping(proteinToCdsMapList));
+ product.addDBRef(proteinToEmblCdsRef);
+
+ /*
+ * make 'direct' xref from protein to EMBLCDSPROTEIN
+ */
+ proteinToEmblProteinRef = new DBRefEntry(proteinToEmblCdsRef);
+ proteinToEmblProteinRef.setSource(DBRefSource.EMBLCDSProduct);
+ proteinToEmblProteinRef.setMap(null);
+ product.addDBRef(proteinToEmblProteinRef);
+ }
+ }
+ }
+
+ /*
+ * add cds features to dna sequence
+ */
+ String cds = feature.getName(); // "CDS"
+ for (int xint = 0; exons != null && xint < exons.length - 1; xint += 2)
+ {
+ int exonStart = exons[xint];
+ int exonEnd = exons[xint + 1];
+ int begin = Math.min(exonStart, exonEnd);
+ int end = Math.max(exonStart, exonEnd);
+ int exonNumber = xint / 2 + 1;
+ String desc = String.format("Exon %d for protein '%s' EMBLCDS:%s",
+ exonNumber, proteinName, proteinId);
+
+ SequenceFeature sf = makeCdsFeature(cds, desc, begin, end,
+ sourceDb, vals);
+
+ sf.setEnaLocation(feature.getLocation());
+ boolean forwardStrand = exonStart <= exonEnd;
+ sf.setStrand(forwardStrand ? "+" : "-");
+ sf.setPhase(String.valueOf(codonStart - 1));
+ sf.setValue(FeatureProperties.EXONPOS, exonNumber);
+ sf.setValue(FeatureProperties.EXONPRODUCT, proteinName);
+
+ dna.addSequenceFeature(sf);
+ }
+ }
+
+ /*
+ * add feature dbRefs to sequence, and mappings for Uniprot xrefs
+ */
+ boolean hasUniprotDbref = false;
+ if (feature.dbRefs != null)
+ {
+ boolean mappingUsed = false;
+ for (DBRefEntry ref : feature.dbRefs)
+ {
+ /*
+ * ensure UniProtKB/Swiss-Prot converted to UNIPROT
+ */
+ String source = DBRefUtils.getCanonicalName(ref.getSource());
+ ref.setSource(source);
+ DBRefEntry proteinDbRef = new DBRefEntry(ref.getSource(),
+ ref.getVersion(), ref.getAccessionId());
+ if (source.equals(DBRefSource.UNIPROT))
+ {
+ String proteinSeqName = DBRefSource.UNIPROT + "|"
+ + ref.getAccessionId();
+ if (dnaToProteinMapping != null
+ && dnaToProteinMapping.getTo() != null)
+ {
+ if (mappingUsed)
+ {
+ /*
+ * two or more Uniprot xrefs for the same CDS -
+ * each needs a distinct Mapping (as to a different sequence)
+ */
+ dnaToProteinMapping = new Mapping(dnaToProteinMapping);
+ }
+ mappingUsed = true;
+
+ /*
+ * try to locate the protein mapped to (possibly by a
+ * previous CDS feature); if not found, construct it from
+ * the EMBL translation
+ */
+ SequenceI proteinSeq = matcher.findIdMatch(proteinSeqName);
+ if (proteinSeq == null)
+ {
+ proteinSeq = new Sequence(proteinSeqName,
+ product.getSequenceAsString());
+ matcher.add(proteinSeq);
+ peptides.add(proteinSeq);
+ }
+ dnaToProteinMapping.setTo(proteinSeq);
+ dnaToProteinMapping.setMappedFromId(proteinId);
+ proteinSeq.addDBRef(proteinDbRef);
+ ref.setMap(dnaToProteinMapping);
+ }
+ hasUniprotDbref = true;
+ }
+ if (product != null)
+ {
+ /*
+ * copy feature dbref to our protein product
+ */
+ DBRefEntry pref = proteinDbRef;
+ pref.setMap(null); // reference is direct
+ product.addDBRef(pref);
+ // Add converse mapping reference
+ if (dnaToProteinMapping != null)
+ {
+ Mapping pmap = new Mapping(dna,
+ dnaToProteinMapping.getMap().getInverse());
+ pref = new DBRefEntry(sourceDb, getSequenceVersion(),
+ this.getAccession());
+ pref.setMap(pmap);
+ if (dnaToProteinMapping.getTo() != null)
+ {
+ dnaToProteinMapping.getTo().addDBRef(pref);
+ }
+ }
+ }
+ dna.addDBRef(ref);
+ }
+ }
+
+ /*
+ * if we have a product (translation) but no explicit Uniprot dbref
+ * (example: EMBL AAFI02000057 protein_id EAL65544.1)
+ * then construct mappings to an assumed EMBLCDSPROTEIN accession
+ */
+ if (!hasUniprotDbref && product != null)
+ {
+ if (proteinToEmblProteinRef == null)
+ {
+ // assuming CDSPROTEIN sequence version = dna version (?!)
+ proteinToEmblProteinRef = new DBRefEntry(DBRefSource.EMBLCDSProduct,
+ getSequenceVersion(), proteinId);
+ }
+ product.addDBRef(proteinToEmblProteinRef);
+
+ if (dnaToProteinMapping != null
+ && dnaToProteinMapping.getTo() != null)
+ {
+ DBRefEntry dnaToEmblProteinRef = new DBRefEntry(
+ DBRefSource.EMBLCDSProduct, getSequenceVersion(),
+ proteinId);
+ dnaToEmblProteinRef.setMap(dnaToProteinMapping);
+ dnaToProteinMapping.setMappedFromId(proteinId);
+ dna.addDBRef(dnaToEmblProteinRef);
+ }
+ }
+ }
+
+ /**
+ * Helper method to construct a SequenceFeature for one cds range
+ *
+ * @param type
+ * feature type ("CDS")
+ * @param desc
+ * description
+ * @param begin
+ * start position
+ * @param end
+ * end position
+ * @param group
+ * feature group
+ * @param vals
+ * map of 'miscellaneous values' for feature
+ * @return
+ */
+ protected SequenceFeature makeCdsFeature(String type, String desc,
+ int begin, int end, String group, Map<String, String> vals)
+ {
+ SequenceFeature sf = new SequenceFeature(type, desc, begin, end, group);
+ if (!vals.isEmpty())
+ {
+ StringBuilder sb = new StringBuilder();
+ boolean first = true;
+ for (Entry<String, String> val : vals.entrySet())
+ {
+ if (!first)
+ {
+ sb.append(";");
+ }
+ sb.append(val.getKey()).append("=").append(val.getValue());
+ first = false;
+ sf.setValue(val.getKey(), val.getValue());
+ }
+ sf.setAttributes(sb.toString());
+ }
+ return sf;
+ }
+
+ /**
+ * Returns the CDS positions as a single array of [start, end, start, end...]
+ * positions. If on the reverse strand, these will be in descending order.
+ *
+ * @param feature
+ * @return
+ */
+ protected int[] getCdsRanges(EmblFeature feature)
+ {
+ if (feature.location == null)
+ {
+ return new int[] {};
+ }
+
+ try
+ {
+ List<int[]> ranges = DnaUtils.parseLocation(feature.location);
+ return listToArray(ranges);
+ } catch (ParseException e)
+ {
+ Cache.log.warn(
+ String.format("Not parsing inexact CDS location %s in ENA %s",
+ feature.location, this.accession));
+ return new int[] {};
+ }
+ }
+
+ /**
+ * Converts a list of [start, end] ranges to a single array of [start, end,
+ * start, end ...]
+ *
+ * @param ranges
+ * @return
+ */
+ int[] listToArray(List<int[]> ranges)
+ {
+ int[] result = new int[ranges.size() * 2];
+ int i = 0;
+ for (int[] range : ranges)
+ {
+ result[i++] = range[0];
+ result[i++] = range[1];
+ }
+ return result;
+ }
+
+ /**
+ * Truncates (if necessary) the exon intervals to match 3 times the length of
+ * the protein; also accepts 3 bases longer (for stop codon not included in
+ * protein)
+ *
+ * @param proteinLength
+ * @param exon
+ * an array of [start, end, start, end...] intervals
+ * @return the same array (if unchanged) or a truncated copy
+ */
+ static int[] adjustForProteinLength(int proteinLength, int[] exon)
+ {
+ if (proteinLength <= 0 || exon == null)
+ {
+ return exon;
+ }
+ int expectedCdsLength = proteinLength * 3;
+ int exonLength = MappingUtils.getLength(Arrays.asList(exon));
+
+ /*
+ * if exon length matches protein, or is shorter, or longer by the
+ * length of a stop codon (3 bases), then leave it unchanged
+ */
+ if (expectedCdsLength >= exonLength
+ || expectedCdsLength == exonLength - 3)
+ {
+ return exon;
+ }
+
+ int origxon[];
+ int sxpos = -1;
+ int endxon = 0;
+ origxon = new int[exon.length];
+ System.arraycopy(exon, 0, origxon, 0, exon.length);
+ int cdspos = 0;
+ for (int x = 0; x < exon.length; x += 2)
+ {
+ cdspos += Math.abs(exon[x + 1] - exon[x]) + 1;
+ if (expectedCdsLength <= cdspos)
+ {
+ // advanced beyond last codon.
+ sxpos = x;
+ if (expectedCdsLength != cdspos)
+ {
+ // System.err
+ // .println("Truncating final exon interval on region by "
+ // + (cdspos - cdslength));
+ }
+
+ /*
+ * shrink the final exon - reduce end position if forward
+ * strand, increase it if reverse
+ */
+ if (exon[x + 1] >= exon[x])
+ {
+ endxon = exon[x + 1] - cdspos + expectedCdsLength;
+ }
+ else
+ {
+ endxon = exon[x + 1] + cdspos - expectedCdsLength;
+ }
+ break;
+ }
+ }
+
+ if (sxpos != -1)
+ {
+ // and trim the exon interval set if necessary
+ int[] nxon = new int[sxpos + 2];
+ System.arraycopy(exon, 0, nxon, 0, sxpos + 2);
+ nxon[sxpos + 1] = endxon; // update the end boundary for the new exon
+ // set
+ exon = nxon;
+ }
+ return exon;
+ }
+
+ public String getSequenceVersion()
+ {
+ return sequenceVersion;
+ }
+
+ public void setSequenceVersion(String sequenceVersion)
+ {
+ this.sequenceVersion = sequenceVersion;
+ }
+
+ public String getSequenceLength()
+ {
+ return sequenceLength;
+ }
+
+ public void setSequenceLength(String sequenceLength)
+ {
+ this.sequenceLength = sequenceLength;
+ }
+
+ public String getEntryVersion()
+ {
+ return entryVersion;
+ }
+
+ public void setEntryVersion(String entryVersion)
+ {
+ this.entryVersion = entryVersion;
+ }
+
+ public String getMoleculeType()
+ {
+ return moleculeType;
+ }
+
+ public void setMoleculeType(String moleculeType)
+ {
+ this.moleculeType = moleculeType;
+ }
+
+ public String getTopology()
+ {
+ return topology;
+ }
+
+ public void setTopology(String topology)
+ {
+ this.topology = topology;
+ }
+
+ public String getTaxonomicDivision()
+ {
+ return taxonomicDivision;
+ }
+
+ public void setTaxonomicDivision(String taxonomicDivision)
+ {
+ this.taxonomicDivision = taxonomicDivision;
+ }
+
+ public String getDescription()
+ {
+ return description;
+ }
+
+ public void setDescription(String description)
+ {
+ this.description = description;
+ }
+
+ public String getFirstPublicDate()
+ {
+ return firstPublicDate;
+ }
+
+ public void setFirstPublicDate(String firstPublicDate)
+ {
+ this.firstPublicDate = firstPublicDate;
+ }
+
+ public String getFirstPublicRelease()
+ {
+ return firstPublicRelease;
+ }
+
+ public void setFirstPublicRelease(String firstPublicRelease)
+ {
+ this.firstPublicRelease = firstPublicRelease;
+ }
+
+ public String getLastUpdatedDate()
+ {
+ return lastUpdatedDate;
+ }
+
+ public void setLastUpdatedDate(String lastUpdatedDate)
+ {
+ this.lastUpdatedDate = lastUpdatedDate;
+ }
+
+ public String getLastUpdatedRelease()
+ {
+ return lastUpdatedRelease;
+ }
+
+ public void setLastUpdatedRelease(String lastUpdatedRelease)
+ {
+ this.lastUpdatedRelease = lastUpdatedRelease;
+ }
+
+ public String getDataClass()
+ {
+ return dataClass;
+ }
+
+ public void setDataClass(String dataClass)
+ {
+ this.dataClass = dataClass;
+ }
+}
git://source.jalview.org / jalview.git / blobdiff