--- /dev/null
+/*\r
+ * Jalview - A Sequence Alignment Editor and Viewer\r
+ * Copyright (C) 2005 AM Waterhouse, J Procter, G Barton, M Clamp, S Searle\r
+ *\r
+ * This program is free software; you can redistribute it and/or\r
+ * modify it under the terms of the GNU General Public License\r
+ * as published by the Free Software Foundation; either version 2\r
+ * of the License, or (at your option) any later version.\r
+ *\r
+ * This program is distributed in the hope that it will be useful,\r
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of\r
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the\r
+ * GNU General Public License for more details.\r
+ *\r
+ * You should have received a copy of the GNU General Public License\r
+ * along with this program; if not, write to the Free Software\r
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA\r
+ */\r
+/*\r
+ * This extension was written by bsb at sanger.ac.uk\r
+ */\r
+package jalview.io;\r
+import java.io.*;\r
+import java.util.*;\r
+import jalview.datamodel.*;\r
+import com.stevesoft.pat.*;\r
+//import org.apache.log4j.*;\r
+\r
+/**\r
+ * This class is supposed to parse a Stockholm format file into Jalview\r
+ * @author bsb at sanger.ac.uk\r
+ * @version 0.3\r
+ */\r
+public class StockholmFile extends AlignFile\r
+{\r
+ //static Logger logger = Logger.getLogger("jalview.io.StockholmFile");\r
+\r
+ public StockholmFile()\r
+ {\r
+ }\r
+\r
+\r
+ public StockholmFile(String inFile, String type) throws IOException\r
+ {\r
+ super(inFile, type);\r
+ }\r
+\r
+ public void initData()\r
+ {\r
+ super.initData();\r
+ }\r
+\r
+ /**\r
+ * Parse a file in Stockholm format into Jalview's data model. The file has\r
+ * to be passed at construction time\r
+ * @throws IOException If there is an error with the input file\r
+ */\r
+ public void parse() throws IOException\r
+ {\r
+ // --------------- Variable Definitions -------------------\r
+ String line;\r
+ String version;\r
+ // String id;\r
+ Hashtable alAnn = new Hashtable(); // Alignment wide annotations\r
+ Hashtable seqAnn = new Hashtable(); // Sequence related annotations\r
+ Hashtable seqs = new Hashtable();\r
+ Regex p, r, rend, s, x;\r
+\r
+ // ------------------ Parsing File ----------------------\r
+ // First, we have to check that this file has STOCKHOLM format, i.e. the first line must match\r
+ r = new Regex("# STOCKHOLM ([\\d\\.]+)");\r
+ if(!r.search(nextLine()))\r
+ {\r
+ throw new IOException("This file is not in valid STOCKHOLM format: First line does not contain '# STOCKHOLM'");\r
+ }\r
+ else\r
+ {\r
+ version = r.stringMatched(1);\r
+ //logger.debug("Stockholm version: " + version);\r
+ }\r
+\r
+// We define some Regexes here that will be used regularily later\r
+ rend = new Regex("\\/\\/"); // Find the end of an alignment\r
+ p = new Regex("(\\S+)\\/(\\d+)\\-(\\d+)"); // split sequence id in id/from/to\r
+ s = new Regex("(\\S+)\\s+(\\w{2})\\s+(.*)"); // Parses annotation subtype\r
+ r = new Regex("#=(G[FSRC]?)\\s+(.*)"); // Finds any annotation line\r
+ x = new Regex("(\\S+)\\s+(\\S+)"); //split id from sequence\r
+\r
+ rend.optimize();\r
+ p.optimize();\r
+ s.optimize();\r
+ r.optimize();\r
+ x.optimize();\r
+\r
+ while ( (line = nextLine()) != null)\r
+ {\r
+ if (line.length() == 0) continue;\r
+ if(rend.search(line))\r
+ {\r
+// End of the alignment, pass stuff back\r
+\r
+ this.noSeqs = seqs.size();\r
+ //logger.debug("Number of sequences: " + this.noSeqs);\r
+ Enumeration accs = seqs.keys();\r
+ while (accs.hasMoreElements())\r
+ {\r
+ String acc = (String) accs.nextElement();\r
+ //logger.debug("Processing sequence " + acc);\r
+ String seq = (String) seqs.get(acc);\r
+ if (maxLength < seq.length())\r
+ {\r
+ maxLength = seq.length();\r
+ }\r
+ int start = 1;\r
+ int end = -1;\r
+ String sid = acc;\r
+ // Split accession in id and from/to\r
+ if (p.search(acc))\r
+ {\r
+ sid = p.stringMatched(1);\r
+ start = Integer.parseInt(p.stringMatched(2));\r
+ end = Integer.parseInt(p.stringMatched(3));\r
+ }\r
+ //logger.debug(sid + ", " + start + ", " + end);\r
+\r
+ Sequence seqO = new Sequence(sid, seq, start, end);\r
+ Hashtable features = null;\r
+ // We need to adjust the positions of all features to account for gaps\r
+ try\r
+ {\r
+ features = (Hashtable) ((Hashtable) seqAnn.get(acc)).get("features");\r
+ }\r
+ catch (java.lang.NullPointerException e)\r
+ {\r
+ //loggerwarn("Getting Features for " + acc + ": " + e.getMessage());\r
+ //continue;\r
+ }\r
+ // if we have features\r
+ if (features != null)\r
+ {\r
+ Enumeration i = features.keys();\r
+ while(i.hasMoreElements())\r
+ {\r
+ String type = i.nextElement().toString();\r
+ Hashtable content = (Hashtable) features.get(type);\r
+\r
+ Enumeration j = content.keys();\r
+ while(j.hasMoreElements())\r
+ {\r
+ String desc = j.nextElement().toString();\r
+ String ns = content.get(desc).toString();\r
+ char[] byChar = ns.toCharArray();\r
+ for (int k = 0; k < byChar.length; k++)\r
+ {\r
+ char c = byChar[k];\r
+ if (! (c == ' ' || c == '_' ||\r
+ c == '-'))\r
+ {\r
+ int new_pos = seqO.findPosition(k);\r
+ SequenceFeature feat =\r
+ new SequenceFeature(type,\r
+ desc, new_pos, new_pos, 0f, null);\r
+\r
+ seqO.addSequenceFeature(feat);\r
+ }\r
+ }\r
+ }\r
+\r
+ }\r
+\r
+ }\r
+ //logger.debug("Adding seq " + acc + " from " + start + " to " + end + ": " + seq);\r
+ this.seqs.addElement(seqO);\r
+ }\r
+ }\r
+ else if (!r.search(line))\r
+ {\r
+ //System.err.println("Found sequence line: " + line);\r
+\r
+ // Split sequence in sequence and accession parts\r
+ if(!x.search(line))\r
+ {\r
+ //logger.error("Could not parse sequence line: " + line);\r
+ throw new IOException("Could not parse sequence line: " + line);\r
+ }\r
+ String ns = (String) seqs.get(x.stringMatched(1));\r
+ if (ns == null) ns = "";\r
+ ns += x.stringMatched(2);\r
+\r
+ seqs.put(x.stringMatched(1), ns);\r
+ }\r
+ else\r
+ {\r
+ String annType = r.stringMatched(1);\r
+ String annContent = r.stringMatched(2);\r
+\r
+ //System.err.println("type:" + annType + " content: " + annContent);\r
+\r
+ if (annType.equals("GF"))\r
+ {\r
+ /* Generic per-File annotation, free text\r
+ * Magic features:\r
+ * #=GF NH <tree in New Hampshire eXtended format>\r
+ * #=GF TN <Unique identifier for the next tree>\r
+ * Pfam descriptions:\r
+ 7. DESCRIPTION OF FIELDS\r
+\r
+ Compulsory fields:\r
+ ------------------\r
+\r
+ AC Accession number: Accession number in form PFxxxxx.version or PBxxxxxx.\r
+ ID Identification: One word name for family.\r
+ DE Definition: Short description of family.\r
+ AU Author: Authors of the entry.\r
+ SE Source of seed: The source suggesting the seed members belong to one family.\r
+ GA Gathering method: Search threshold to build the full alignment.\r
+ TC Trusted Cutoff: Lowest sequence score and domain score of match in the full alignment.\r
+ NC Noise Cutoff: Highest sequence score and domain score of match not in full alignment.\r
+ TP Type: Type of family -- presently Family, Domain, Motif or Repeat.\r
+ SQ Sequence: Number of sequences in alignment.\r
+ AM Alignment Method The order ls and fs hits are aligned to the model to build the full align.\r
+ // End of alignment.\r
+\r
+ Optional fields:\r
+ ----------------\r
+\r
+ DC Database Comment: Comment about database reference.\r
+ DR Database Reference: Reference to external database.\r
+ RC Reference Comment: Comment about literature reference.\r
+ RN Reference Number: Reference Number.\r
+ RM Reference Medline: Eight digit medline UI number.\r
+ RT Reference Title: Reference Title.\r
+ RA Reference Author: Reference Author\r
+ RL Reference Location: Journal location.\r
+ PI Previous identifier: Record of all previous ID lines.\r
+ KW Keywords: Keywords.\r
+ CC Comment: Comments.\r
+ NE Pfam accession: Indicates a nested domain.\r
+ NL Location: Location of nested domains - sequence ID, start and end of insert.\r
+\r
+ Obsolete fields:\r
+ -----------\r
+ AL Alignment method of seed: The method used to align the seed members.\r
+ */\r
+ // Let's save the annotations, maybe we'll be able to do something with them later...\r
+ Regex an = new Regex("(\\w+)\\s*(.*)");\r
+ if (an.search(annContent)) alAnn.put(an.stringMatched(1), an.stringMatched(2));\r
+ }\r
+ else if(annType.equals("GS"))\r
+ {\r
+ // Generic per-Sequence annotation, free text\r
+ /* Pfam uses these features:\r
+ Feature Description\r
+ --------------------- -----------\r
+ AC <accession> ACcession number\r
+ DE <freetext> DEscription\r
+ DR <db>; <accession>; Database Reference\r
+ OS <organism> OrganiSm (species)\r
+ OC <clade> Organism Classification (clade, etc.)\r
+ LO <look> Look (Color, etc.)\r
+ */\r
+ if (s.search(annContent))\r
+ {\r
+ String acc = s.stringMatched(1);\r
+ String type = s.stringMatched(2);\r
+ String content = s.stringMatched(3);\r
+\r
+ Hashtable ann;\r
+ if (seqAnn.containsKey(acc))\r
+ {\r
+ ann = (Hashtable) seqAnn.get(acc);\r
+ }\r
+ else\r
+ {\r
+ ann = new Hashtable();\r
+ }\r
+ ann.put(type, content);\r
+ seqAnn.put(acc, ann);\r
+ }\r
+ else\r
+ {\r
+ throw new IOException("Error parsing " + line);\r
+ }\r
+ }\r
+ else if(annType.equals("GC"))\r
+ {\r
+ // Generic per-Column annotation, exactly 1 char per column\r
+ }\r
+ else if(annType.equals("GR"))\r
+ {\r
+ // Generic per-Sequence AND per-Column markup, exactly 1 char per column\r
+ /*\r
+ Feature Description Markup letters\r
+ ------- ----------- --------------\r
+ SS Secondary Structure [HGIEBTSCX]\r
+ SA Surface Accessibility [0-9X]\r
+ (0=0%-10%; ...; 9=90%-100%)\r
+ TM TransMembrane [Mio]\r
+ PP Posterior Probability [0-9*]\r
+ (0=0.00-0.05; 1=0.05-0.15; *=0.95-1.00)\r
+ LI LIgand binding [*]\r
+ AS Active Site [*]\r
+ IN INtron (in or after) [0-2]\r
+ */\r
+ if (s.search(annContent))\r
+ {\r
+ String acc = s.stringMatched(1);\r
+ String type = s.stringMatched(2);\r
+ String seq = s.stringMatched(3);\r
+ String description = new String();\r
+\r
+ // Check for additional information about the current annotation\r
+ if (x.search(seq))\r
+ {\r
+ description = x.stringMatched(1);\r
+ seq = x.stringMatched(2);\r
+ }\r
+ // sequence id with from-to fields\r
+\r
+ Hashtable ann;\r
+ // Get an object with all the annotations for this sequence\r
+ if (seqAnn.containsKey(acc))\r
+ {\r
+ //logger.debug("Found annotations for " + acc);\r
+ ann = (Hashtable) seqAnn.get(acc);\r
+ }\r
+ else\r
+ {\r
+ //logger.debug("Creating new annotations holder for " + acc);\r
+ ann = new Hashtable();\r
+ seqAnn.put(acc, ann);\r
+ }\r
+\r
+ Hashtable features;\r
+ // Get an object with all the content for an annotation\r
+ if (ann.containsKey("features"))\r
+ {\r
+ //logger.debug("Found features for " + acc);\r
+ features = (Hashtable) ann.get("features");\r
+ }\r
+ else\r
+ {\r
+ //logger.debug("Creating new features holder for " + acc);\r
+ features = new Hashtable();\r
+ ann.put("features", features);\r
+ }\r
+\r
+ Hashtable content;\r
+ if (features.containsKey(this.id2type(type)))\r
+ {\r
+ //logger.debug("Found content for " + this.id2type(type));\r
+ content = (Hashtable) features.get(this.id2type(type));\r
+ }\r
+ else\r
+ {\r
+ //logger.debug("Creating new content holder for " + this.id2type(type));\r
+ content = new Hashtable();\r
+ features.put(this.id2type(type), content);\r
+ }\r
+ String ns = (String) content.get(description);\r
+ if (ns == null) ns = "";\r
+ ns += seq;\r
+ content.put(description, seq);\r
+ }\r
+ else\r
+ {\r
+ throw new IOException("Error parsing " + line);\r
+ }\r
+ }\r
+ else\r
+ {\r
+ throw new IOException("Unknown annotation detected: " + annType + " " + annContent);\r
+ }\r
+ }\r
+ }\r
+ }\r
+\r
+ public static String print(SequenceI[] s)\r
+ {\r
+ return "not yet implemented";\r
+ }\r
+\r
+ public String print()\r
+ {\r
+ return print(getSeqsAsArray());\r
+ }\r
+\r
+ private String id2type(String id)\r
+ {\r
+ // GR ids\r
+ if (id.equals("SS")) return "secondary structure";\r
+ else if (id.equals("SA")) return "surface accessibility";\r
+ else if (id.equals("TM")) return "transmembrane";\r
+ else if (id.equals("PP")) return "posterior probability";\r
+ else if (id.equals("LI")) return "ligand binding";\r
+ else if (id.equals("AS")) return "active site";\r
+ else if (id.equals("IN")) return "intron";\r
+ else if (id.equals("IR")) return "interacting residue";\r
+ // GS ids\r
+ else if (id.equals("AC")) return "accession";\r
+ else if (id.equals("OS")) return "organism";\r
+ else if (id.equals("CL")) return "class";\r
+ else if (id.equals("DE")) return "description";\r
+ else if (id.equals("DR")) return "reference";\r
+ else if (id.equals("LO")) return "look";\r
+ else return null;\r
+ }\r
+}\r
git://source.jalview.org / jalview.git / commitdiff