From 8daeb715c3e8ec8486f26708361698095084232f Mon Sep 17 00:00:00 2001 From: janengelhardt Date: Mon, 23 May 2011 19:09:37 +0200 Subject: [PATCH] 'Add Rfam database sequence retrieval' merged; JAL-580 Change-Id: Ic7de2f4904af47bb04c91ffef4be6c66ff134607 --- src/jalview/ws/dbsources/Pfam.java | 2 +- src/jalview/ws/dbsources/Rfam.java | 111 ++++++++++++++++++++++++++++++++ src/jalview/ws/dbsources/RfamFull.java | 74 +++++++++++++++++++++ src/jalview/ws/dbsources/RfamSeed.java | 72 +++++++++++++++++++++ src/jalview/ws/dbsources/Xfam.java | 69 ++++++++++++++++++++ 5 files changed, 327 insertions(+), 1 deletion(-) create mode 100644 src/jalview/ws/dbsources/Rfam.java create mode 100644 src/jalview/ws/dbsources/RfamFull.java create mode 100644 src/jalview/ws/dbsources/RfamSeed.java create mode 100644 src/jalview/ws/dbsources/Xfam.java diff --git a/src/jalview/ws/dbsources/Pfam.java b/src/jalview/ws/dbsources/Pfam.java index 1ae72fb..1afccd6 100644 --- a/src/jalview/ws/dbsources/Pfam.java +++ b/src/jalview/ws/dbsources/Pfam.java @@ -120,7 +120,7 @@ protected abstract String getXFAMURL(); // individual references to each sequence in each family alignment that's // retrieved. startQuery(); - AlignmentI rcds = new jalview.io.FormatAdapter().readFile(getPFAMURL() + AlignmentI rcds = new jalview.io.FormatAdapter().readFile(getXFAMURL() + queries.trim().toUpperCase(), jalview.io.FormatAdapter.URL, "STH"); for (int s = 0, sNum = rcds.getHeight(); s < sNum; s++) diff --git a/src/jalview/ws/dbsources/Rfam.java b/src/jalview/ws/dbsources/Rfam.java new file mode 100644 index 0000000..d720f4b --- /dev/null +++ b/src/jalview/ws/dbsources/Rfam.java @@ -0,0 +1,111 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5) + * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * + * 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 . + */ +package jalview.ws.dbsources; + +import com.stevesoft.pat.Regex; + +import jalview.ws.seqfetcher.DbSourceProxy; + +/** + * Contains methods for fetching sequences from Rfam database + * + * @author Lauren Michelle Lui + */ +abstract public class Rfam extends Xfam implements DbSourceProxy +{ + + public Rfam() + { + super(); + // all extensions of this RFAM source base class are DOMAINDB sources + addDbSourceProperty(jalview.datamodel.DBRefSource.DOMAINDB); + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.DbSourceProxy#getAccessionSeparator() Left here for + * consistency with Pfam class + */ + public String getAccessionSeparator() + { + // TODO Auto-generated method stub + return null; + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.DbSourceProxy#getAccessionValidator() * Left here for + */ + public Regex getAccessionValidator() + { + // TODO Auto-generated method stub + return null; + } + + /* + * (non-Javadoc) + * + * Left here for consistency with Pfam class + * + * @see jalview.ws.DbSourceProxy#getDbSource() public String getDbSource() { * + * this doesn't work - DbSource is key for the hash of DbSourceProxy instances + * - 1:many mapping for DbSource to proxy will be lost. * suggest : RFAM is an + * 'alignment' source - means proxy is higher level than a sequence source. + * return jalview.datamodel.DBRefSource.RFAM; } + */ + + /* + * (non-Javadoc) + * + * @see jalview.ws.DbSourceProxy#getDbVersion() + */ + @Override + public String getDbVersion() + { + // TODO Auto-generated method stub + return null; + } + + /**Returns base URL for selected Rfam alignment type + * + * @return RFAM URL stub for this DbSource + */ + @Override + protected abstract String getXFAMURL(); + + /* + * (non-Javadoc) + * + * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String) + */ + public boolean isValidReference(String accession) + { + return accession.indexOf("RF") == 0; + } + + /* (non-Javadoc) + * @see jalview.ws.dbsources.Xfam#getXfamSource() + */ + public String getXfamSource() + { + return jalview.datamodel.DBRefSource.RFAM; + } + +} diff --git a/src/jalview/ws/dbsources/RfamFull.java b/src/jalview/ws/dbsources/RfamFull.java new file mode 100644 index 0000000..f8b1952 --- /dev/null +++ b/src/jalview/ws/dbsources/RfamFull.java @@ -0,0 +1,74 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5) + * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * + * 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 . + */ + +package jalview.ws.dbsources; + +import jalview.ws.seqfetcher.DbSourceProxy; + +/** + * Flyweight class specifying retrieval of Full family alignments from RFAM + * + * @author Lauren Michelle Lui + * + */ +public class RfamFull extends Rfam implements DbSourceProxy +{ + public RfamFull() + { + super(); + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.dbsources.Rfam#getXFAMURL() + */ + protected String getXFAMURL() + { + return "http://rfam.sanger.ac.uk/family/alignment/download/format?alnType=full&nseLabels=0&format=stockholm&acc="; + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.seqfetcher.DbSourceProxy#getDbName() + */ + public String getDbName() + { + return "RFAM (Full)"; + } + + public String getDbSource() + { + return getDbName(); // so we have unique DbSource string. + } + + public String getTestQuery() + { + // Can be retrieved from http://rfam.janelia.org/cgi-bin/getdesc?acc=RF00014 + // or + // http://rfam.sanger.ac.uk/family/alignment/download/format?alnType=full&nseLabels=0&format=stockholm&acc=RF00014 + return "RF00014"; + } + + public String getDbVersion() + { + return null; + } + +} diff --git a/src/jalview/ws/dbsources/RfamSeed.java b/src/jalview/ws/dbsources/RfamSeed.java new file mode 100644 index 0000000..7c6a82d --- /dev/null +++ b/src/jalview/ws/dbsources/RfamSeed.java @@ -0,0 +1,72 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5) + * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * + * 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 . + */ +package jalview.ws.dbsources; + +import jalview.ws.seqfetcher.DbSourceProxy; + +/** + * Flyweight class specifying retrieval of Seed family alignments from RFAM + * + * @author Lauren Michelle Lui + * + */ +public class RfamSeed extends Rfam implements DbSourceProxy +{ + public RfamSeed() + { + super(); + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.dbsources.Rfam#getRFAMURL() + */ + protected String getXFAMURL() + { + return "http://rfam.sanger.ac.uk/family/alignment/download/format?alnType=seed&nseLabels=0&format=stockholm&acc="; + // Janelia Farms url + // "http://rfam.janelia.org/cgi-bin/getalignment?type=seed&fmt=stockholm&acc="; + } + + /* + * (non-Javadoc) + * + * @see jalview.ws.seqfetcher.DbSourceProxy#getDbName() + */ + public String getDbName() + { + return "RFAM (Seed)"; + } + + public String getDbSource() + { + return getDbName(); // so we have unique DbSource string. + } + + public String getTestQuery() + { + return "RF00014"; + } // http://rfam.janelia.org/cgi-bin/getdesc?acc=RF00014 + + public String getDbVersion() + { + return null; + } + +} diff --git a/src/jalview/ws/dbsources/Xfam.java b/src/jalview/ws/dbsources/Xfam.java new file mode 100644 index 0000000..b092a25 --- /dev/null +++ b/src/jalview/ws/dbsources/Xfam.java @@ -0,0 +1,69 @@ +/* + * Jalview - A Sequence Alignment Editor and Viewer (Version 2.5) + * Copyright (C) 2010 J Procter, AM Waterhouse, G Barton, M Clamp, S Searle + * + * 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 . + */ +package jalview.ws.dbsources; + +import jalview.datamodel.AlignmentI; +import jalview.datamodel.DBRefEntry; +import jalview.ws.seqfetcher.DbSourceProxyImpl; + +/** + * Acts as a superclass for the Rfam and Pfam classes + * + * @author Lauren Michelle Lui + * + */ +public abstract class Xfam extends DbSourceProxyImpl +{ + + public Xfam() + { + super(); + } + + protected abstract String getXFAMURL(); + + public abstract String getDbVersion(); + + abstract String getXfamSource(); + + public AlignmentI getSequenceRecords(String queries) throws Exception + { + // TODO: this is not a perfect implementation. We need to be able to add + // individual references to each sequence in each family alignment that's + // retrieved. + startQuery(); + AlignmentI rcds = new jalview.io.FormatAdapter().readFile(getXFAMURL() + + queries.trim().toUpperCase(), jalview.io.FormatAdapter.URL, + "STH"); + for (int s = 0, sNum = rcds.getHeight(); s < sNum; s++) + { + rcds.getSequenceAt(s).addDBRef(new DBRefEntry(getXfamSource(), + // getDbSource(), + getDbVersion(), queries.trim().toUpperCase())); + if (!getDbSource().equals(getXfamSource())) + { // add the specific ref too + rcds.getSequenceAt(s).addDBRef( + new DBRefEntry(getDbSource(), getDbVersion(), queries + .trim().toUpperCase())); + } + } + stopQuery(); + return rcds; + } + +} \ No newline at end of file -- 1.7.10.2