Commit 5ed645d
committed
Adding example for parsing large FASTA files
1 parent ad1dfab commit 5ed645d
1 file changed
Lines changed: 64 additions & 0 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
@@ -0,0 +1,64 @@ | |||
| 1 | + Reading and Writing of Basic sequence file formats | ||
| 2 | + ================================================== | ||
| 3 | + | ||
| 4 | + | ||
| 5 | + TODO: needs more examples | ||
| 6 | + | ||
| 7 | + | ||
| 8 | + ## FASTA | ||
| 9 | + | ||
| 10 | + BioJava can be used to parse large FASTA files. The example below can parse a 1GB (compressed) version of TREMBL with standard memory settings. | ||
| 11 | + | ||
| 12 | + | ||
| 13 | + ```java | ||
| 14 | + | ||
| 15 | + | ||
| 16 | + | ||
| 17 | + /** Download a large file, e.g. ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_trembl.fasta.gz | ||
| 18 | + * and pass in path to local location of file | ||
| 19 | + * | ||
| 20 | + * @param args | ||
| 21 | + */ | ||
| 22 | + public static void main(String[] args) { | ||
| 23 | + | ||
| 24 | + if ( args.length < 1) { | ||
| 25 | + System.err.println("First argument needs to be path to fasta file"); | ||
| 26 | + return; | ||
| 27 | + } | ||
| 28 | + | ||
| 29 | + File f = new File(args[0]); | ||
| 30 | + | ||
| 31 | + if ( ! f.exists()) { | ||
| 32 | + System.err.println("File does not exist " + args[0]); | ||
| 33 | + return; | ||
| 34 | + } | ||
| 35 | + | ||
| 36 | + try { | ||
| 37 | + | ||
| 38 | + // automatically uncompresses files using InputStreamProvider | ||
| 39 | + InputStreamProvider isp = new InputStreamProvider(); | ||
| 40 | + | ||
| 41 | + InputStream inStream = isp.getInputStream(f); | ||
| 42 | + | ||
| 43 | + FastaReader<ProteinSequence, AminoAcidCompound> fastaReader = new FastaReader<ProteinSequence, AminoAcidCompound>( | ||
| 44 | + inStream, | ||
| 45 | + new GenericFastaHeaderParser<ProteinSequence, AminoAcidCompound>(), | ||
| 46 | + new ProteinSequenceCreator(AminoAcidCompoundSet.getAminoAcidCompoundSet())); | ||
| 47 | + | ||
| 48 | + LinkedHashMap<String, ProteinSequence> b; | ||
| 49 | + | ||
| 50 | + | ||
| 51 | + int nrSeq = 0; | ||
| 52 | + | ||
| 53 | + while ((b = fastaReader.process(10)) != null) { | ||
| 54 | + for (String key : b.keySet()) { | ||
| 55 | + nrSeq++; | ||
| 56 | + System.out.println(nrSeq + " : " + key + " " + b.get(key)); | ||
| 57 | + } | ||
| 58 | + | ||
| 59 | + } | ||
| 60 | + } catch (Exception ex) { | ||
| 61 | + Logger.getLogger(ParseFastaFileDemo.class.getName()).log(Level.SEVERE, null, ex); | ||
| 62 | + } | ||
| 63 | + } | ||
| 64 | + ``` | ||
0 commit comments