Adding example for parsing large FASTA files

andreasprlic · andreasprlic · commit 5ed645d17870 · 2015-06-17T14:42:05.000-07:00
diff --git a/core/readwrite.md b/core/readwrite.md
@@ -0,0 +1,64 @@
+Reading and Writing of Basic sequence file formats
+==================================================
+
+
+TODO: needs more examples
+
+
+## FASTA
+
+BioJava can be used to parse large FASTA files. The example below can parse a 1GB (compressed) version of TREMBL with standard memory settings.
+
+
+```java
+    
+    
+    
+     /** Download a large file, e.g. ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz
+     * and pass in path to local location of file
+     *
+     * @param args
+     */
+        public static void main(String[] args) {
+
+            if ( args.length < 1) {
+                System.err.println("First argument needs to be path to fasta file");
+                return;
+            }
+
+            File f = new File(args[0]);
+
+            if ( ! f.exists()) {
+                System.err.println("File does not exist " + args[0]);
+                return;
+            }
+
+            try {
+
+                // automatically uncompresses files using InputStreamProvider
+                InputStreamProvider isp = new InputStreamProvider();
+                
+                InputStream inStream = isp.getInputStream(f);
+                
+                FastaReader<ProteinSequence, AminoAcidCompound> fastaReader = new FastaReader<ProteinSequence, AminoAcidCompound>(
+                        inStream,
+                        new GenericFastaHeaderParser<ProteinSequence, AminoAcidCompound>(),
+                        new ProteinSequenceCreator(AminoAcidCompoundSet.getAminoAcidCompoundSet()));
+                
+                LinkedHashMap<String, ProteinSequence> b;
+
+
+                int nrSeq = 0;
+                
+                while ((b = fastaReader.process(10)) != null) {
+                    for (String key : b.keySet()) {
+                        nrSeq++;
+                        System.out.println(nrSeq + " : " + key + " " + b.get(key));
+                    }
+
+                }
+            } catch (Exception ex) {
+                Logger.getLogger(ParseFastaFileDemo.class.getName()).log(Level.SEVERE, null, ex);
+            }
+        }
+```
