X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=src%2Fjalview%2Fdatamodel%2Fxdb%2Fembl%2FEmblEntry.java;h=a94988814fa114863eda6f37ef64661524324e94;hb=a45774ee31d9f35d4eff46d54d7deab719afb092;hp=0cee0b410a2bfc81cd4373ee406d05afc1085fee;hpb=506d60f0e188723ddc91c26824b41ac7034df3fe;p=jalview.git diff --git a/src/jalview/datamodel/xdb/embl/EmblEntry.java b/src/jalview/datamodel/xdb/embl/EmblEntry.java index 0cee0b4..a949888 100644 --- a/src/jalview/datamodel/xdb/embl/EmblEntry.java +++ b/src/jalview/datamodel/xdb/embl/EmblEntry.java @@ -1,20 +1,19 @@ /* - * Jalview - A Sequence Alignment Editor and Viewer (Version 2.4) - * Copyright (C) 2008 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.7) + * Copyright (C) 2011 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle * - * This program 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 2 - * of the License, or (at your option) any later version. + * This file is part of Jalview. * - * This program 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. + * 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. * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA + * 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 . */ package jalview.datamodel.xdb.embl; @@ -67,7 +66,7 @@ public class EmblEntry /** * @param accession - * the accession to set + * the accession to set */ public void setAccession(String accession) { @@ -84,7 +83,7 @@ public class EmblEntry /** * @param dbRefs - * the dbRefs to set + * the dbRefs to set */ public void setDbRefs(Vector dbRefs) { @@ -101,7 +100,7 @@ public class EmblEntry /** * @param desc - * the desc to set + * the desc to set */ public void setDesc(String desc) { @@ -118,7 +117,7 @@ public class EmblEntry /** * @param features - * the features to set + * the features to set */ public void setFeatures(Vector features) { @@ -135,7 +134,7 @@ public class EmblEntry /** * @param keywords - * the keywords to set + * the keywords to set */ public void setKeywords(Vector keywords) { @@ -152,7 +151,7 @@ public class EmblEntry /** * @param lastUpdated - * the lastUpdated to set + * the lastUpdated to set */ public void setLastUpdated(String lastUpdated) { @@ -169,7 +168,7 @@ public class EmblEntry /** * @param refs - * the refs to set + * the refs to set */ public void setRefs(Vector refs) { @@ -186,7 +185,7 @@ public class EmblEntry /** * @param releaseCreated - * the releaseCreated to set + * the releaseCreated to set */ public void setRcreated(String releaseCreated) { @@ -203,7 +202,7 @@ public class EmblEntry /** * @param releaseLastUpdated - * the releaseLastUpdated to set + * the releaseLastUpdated to set */ public void setRLastUpdated(String releaseLastUpdated) { @@ -220,7 +219,7 @@ public class EmblEntry /** * @param sequence - * the sequence to set + * the sequence to set */ public void setSequence(EmblSequence sequence) { @@ -237,7 +236,7 @@ public class EmblEntry /** * @param taxDivision - * the taxDivision to set + * the taxDivision to set */ public void setTaxDivision(String taxDivision) { @@ -254,7 +253,7 @@ public class EmblEntry /** * @param version - * the version to set + * the version to set */ public void setVersion(String version) { @@ -265,8 +264,8 @@ public class EmblEntry * EMBL Feature support is limited. The text below is included for the benefit * of any developer working on improving EMBL feature import in Jalview. * Extract from EMBL feature specification see - * http://www.embl-ebi.ac.uk/embl/Documentation/FT_definitions/feature_table.html - * 3.5 Location 3.5.1 Purpose + * http://www.embl-ebi.ac.uk/embl/Documentation + * /FT_definitions/feature_table.html 3.5 Location 3.5.1 Purpose * * The location indicates the region of the presented sequence which * corresponds to a feature. @@ -390,18 +389,16 @@ public class EmblEntry * * join(1..100,J00194.1:100..202) Joins region 1..100 of the existing entry * with the region 100..202 of remote entry J00194 - * */ /** * Recover annotated sequences from EMBL file * * @param noNa - * don't return nucleic acid sequences + * don't return nucleic acid sequences * @param sourceDb - * TODO + * TODO * @param noProtein - * don't return any translated protein sequences marked in - * features + * don't return any translated protein sequences marked in features * @return dataset sequences with DBRefs and features - DNA always comes first */ public jalview.datamodel.SequenceI[] getSequences(boolean noNa, @@ -416,8 +413,13 @@ public class EmblEntry // pointer exception dna = new Sequence(sourceDb + "|" + accession, sequence.getSequence()); dna.setDescription(desc); - dna.addDBRef(new DBRefEntry(sourceDb, version, accession)); - // TODO: add mapping for parentAccession attribute + DBRefEntry retrievedref = new DBRefEntry(sourceDb, version, 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)); // TODO: transform EMBL Database refs to canonical form if (dbRefs != null) for (Iterator i = dbRefs.iterator(); i.hasNext(); dna @@ -483,15 +485,15 @@ public class EmblEntry * decorate it with annotations. * * @param feature - * coding feature + * coding feature * @param sourceDb - * source database for the EMBLXML + * source database for the EMBLXML * @param seqs - * place where sequences go + * place where sequences go * @param dna - * parent dna sequence for this record + * parent dna sequence for this record * @param noPeptide - * flag for generation of Peptide sequence objects + * flag for generation of Peptide sequence objects */ private void parseCodingFeature(EmblFeature feature, String sourceDb, Vector seqs, Sequence dna, boolean noPeptide) @@ -577,16 +579,15 @@ public class EmblEntry } } Sequence product = null; + exon = adjustForPrStart(prstart, exon); + if (prseq != null && prname != null && prid != null) { // extract proteins. - product = new Sequence(prid, prseq, prstart, prstart + prseq.length() - - 1); - product - .setDescription(((prname.length() == 0) ? "Protein Product from " - + sourceDb - : prname)); - + product = new Sequence(prid, prseq, 1, prseq.length()); + product.setDescription(((prname.length() == 0) ? "Protein Product from " + + sourceDb + : prname)); if (!noPeptide) { // Protein is also added to vector of sequences returned @@ -599,25 +600,32 @@ public class EmblEntry System.err .println("Implementation Notice: EMBLCDS records not properly supported yet - Making up the CDNA region of this sequence... may be incorrect (" + sourceDb + ":" + getAccession() + ")"); - if (prseq.length() * 3 == dna.getSequence().length) + if (prseq.length() * 3 == (1 - prstart + dna.getSequence().length)) { + 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. exon = new int[] - { dna.getStart(), dna.getEnd() }; + { dna.getStart() + (prstart - 1), dna.getEnd() }; map = new jalview.datamodel.Mapping(product, exon, new int[] - { prstart, prstart + prseq.length() - 1 }, 3, 1); + { 1, prseq.length() }, 3, 1); } - if ((prseq.length() + 1) * 3 == dna.getSequence().length) + if ((prseq.length() + 1) * 3 == (1 - prstart + dna.getSequence().length)) { + System.err + .println("Allowing for additional stop codon at end of cDNA fragment... will probably cause an error in VAMSAs!"); exon = new int[] - { dna.getStart(), dna.getEnd() - 3 }; + { dna.getStart() + (prstart - 1), dna.getEnd() - 3 }; map = new jalview.datamodel.Mapping(product, exon, new int[] - { prstart, prstart + prseq.length() - 1 }, 3, 1); + { 1, prseq.length() }, 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 @@ -628,17 +636,24 @@ public class EmblEntry } else { - map = new jalview.datamodel.Mapping(product, exon, new int[] - { prstart, prstart + prseq.length() - 1 }, 3, 1); + // final product length trunctation check + + map = new jalview.datamodel.Mapping(product, + adjustForProteinLength(prseq.length(), exon), new int[] + { 1, prseq.length() }, 3, 1); // reconstruct the EMBLCDS entry + // TODO: this is only necessary when there codon annotation is + // complete (I think JBPNote) DBRefEntry pcdnaref = new DBRefEntry(); pcdnaref.setAccessionId(prid); pcdnaref.setSource(DBRefSource.EMBLCDS); pcdnaref.setVersion(getVersion()); // same as parent EMBL version. jalview.util.MapList mp = new jalview.util.MapList(new int[] - { 1 + (prstart - 1) * 3, - 1 + (prstart - 1) * 3 + (prseq.length() - 1) * 3 }, new int[] - { prstart, prstart + prseq.length() - 1 }, 3, 1); + { 1, prseq.length() }, new int[] + { 1 + (prstart - 1), (prstart - 1) + 3 * prseq.length() }, 1, 3); + // { 1 + (prstart - 1) * 3, + // 1 + (prstart - 1) * 3 + prseq.length() * 3 - 1 }, new int[] + // { 1prstart, prstart + prseq.length() - 1 }, 3, 1); pcdnaref.setMap(new Mapping(mp)); if (product != null) product.addDBRef(pcdnaref); @@ -697,16 +712,16 @@ public class EmblEntry } if (product != null) { - DBRefEntry pref = new DBRefEntry(ref.getSource(), ref - .getVersion(), ref.getAccessionId()); + DBRefEntry pref = new DBRefEntry(ref.getSource(), + ref.getVersion(), ref.getAccessionId()); pref.setMap(null); // reference is direct product.addDBRef(pref); // Add converse mapping reference if (map != null) { Mapping pmap = new Mapping(dna, map.getMap().getInverse()); - pref = new DBRefEntry(sourceDb, getVersion(), this - .getAccession()); + pref = new DBRefEntry(sourceDb, getVersion(), + this.getAccession()); pref.setMap(pmap); if (map.getTo() != null) { @@ -718,4 +733,91 @@ public class EmblEntry } } } + + private int[] adjustForPrStart(int prstart, int[] exon) + { + + int origxon[], sxpos = -1; + int sxstart, sxstop; // unnecessary variables used for debugging + // first adjust range for codon start attribute + if (prstart > 1) + { + origxon = new int[exon.length]; + System.arraycopy(exon, 0, origxon, 0, exon.length); + int cdspos = 0; + for (int x = 0; x < exon.length && sxpos == -1; x += 2) + { + cdspos += exon[x + 1] - exon[x] + 1; + if (prstart <= cdspos) + { + sxpos = x; + sxstart = exon[x]; + sxstop = exon[x + 1]; + // and adjust start boundary of first exon. + exon[x] = exon[x + 1] - cdspos + prstart; + break; + } + } + + if (sxpos > 0) + { + int[] nxon = new int[exon.length - sxpos]; + System.arraycopy(exon, sxpos, nxon, 0, exon.length - sxpos); + exon = nxon; + } + } + return exon; + } + + /** + * truncate the last exon interval to the prlength'th codon + * + * @param prlength + * @param exon + * @return new exon + */ + private int[] adjustForProteinLength(int prlength, int[] exon) + { + + int origxon[], sxpos = -1, endxon = 0, cdslength = prlength * 3; + int sxstart, sxstop; // unnecessary variables used for debugging + // first adjust range for codon start attribute + if (prlength >= 1 && exon != null) + { + origxon = new int[exon.length]; + System.arraycopy(exon, 0, origxon, 0, exon.length); + int cdspos = 0; + for (int x = 0; x < exon.length && sxpos == -1; x += 2) + { + cdspos += exon[x + 1] - exon[x] + 1; + if (cdslength <= cdspos) + { + // advanced beyond last codon. + sxpos = x; + sxstart = exon[x]; + sxstop = exon[x + 1]; + if (cdslength != cdspos) + { + System.err + .println("Truncating final exon interval on region by " + + (cdspos - cdslength)); + } + // locate the new end boundary of final exon as endxon + endxon = exon[x + 1] - cdspos + cdslength; + 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; + } }