|
| 1 | +--- |
| 2 | +title: Annotations:List |
| 3 | +permalink: wikis/Annotations%3AList |
| 4 | +--- |
| 5 | + |
| 6 | +How do I List the Annotations in a Sequence? |
| 7 | +-------------------------------------------- |
| 8 | + |
| 9 | +When you read in a annotates sequence file such as GenBank or EMBL there |
| 10 | +is a lot more detailed information in there than just the raw sequence. |
| 11 | +If the information has a sensible location then it ends up as a Feature. |
| 12 | +If it is more generic such as the species name then the information ends |
| 13 | +up as Annotations. |
| 14 | + |
| 15 | +BioJava Annotation objects are a bit like Map objects and they contian |
| 16 | +key value mappings. |
| 17 | + |
| 18 | +Below is the initial portion of an EMBL file |
| 19 | + |
| 20 | + ID AY130859 standard; DNA; HUM; 44226 BP. |
| 21 | + XX |
| 22 | + AC AY130859; |
| 23 | + XX |
| 24 | + SV AY130859.1 |
| 25 | + XX |
| 26 | + DT 25-JUL-2002 (Rel. 72, Created) |
| 27 | + DT 25-JUL-2002 (Rel. 72, Last updated, Version 1) |
| 28 | + XX |
| 29 | + DE Homo sapiens cyclin-dependent kinase 7 (CDK7) gene, complete cds. |
| 30 | + XX |
| 31 | + KW . |
| 32 | + XX |
| 33 | + OS Homo sapiens (human) |
| 34 | + OC Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia; |
| 35 | + OC Eutheria; Primates; Catarrhini; Hominidae; Homo. |
| 36 | + XX |
| 37 | + RN [1] |
| 38 | + RP 1-44226 |
| 39 | + RA Rieder M.J., Livingston R.J., Braun A.C., Montoya M.A., Chung M.-W., |
| 40 | + RA Miyamoto K.E., Nguyen C.P., Nguyen D.A., Poel C.L., Robertson P.D., |
| 41 | + RA Schackwitz W.S., Sherwood J.K., Witrak L.A., Nickerson D.A.; |
| 42 | + RT ; |
| 43 | + RL Submitted (11-JUL-2002) to the EMBL/GenBank/DDBJ databases. |
| 44 | + RL Genome Sciences, University of Washington, 1705 NE Pacific, Seattle, WA |
| 45 | + RL 98195, USA |
| 46 | + XX |
| 47 | + CC To cite this work please use: NIEHS-SNPs, Environmental Genome |
| 48 | + CC Project, NIEHS ES15478, Department of Genome Sciences, Seattle, WA |
| 49 | + CC (URL: http://egp.gs.washington.edu). |
| 50 | + |
| 51 | +The following program reads an EMBL file and lists its Annotation |
| 52 | +properties. The output of this program on the above file is listed below |
| 53 | +the program. |
| 54 | + |
| 55 | +```java import java.io.\*; import java.util.\*; |
| 56 | + |
| 57 | +import org.biojava.bio.\*; import org.biojava.bio.seq.\*; import |
| 58 | +org.biojava.bio.seq.io.\*; |
| 59 | + |
| 60 | +public class ListAnnotations { |
| 61 | + |
| 62 | +` public static void main(String[] args) {` |
| 63 | + |
| 64 | +` try {` |
| 65 | +` //read in an EMBL Record` |
| 66 | +` BufferedReader br = new BufferedReader(new FileReader(args[0]));` |
| 67 | +` ` |
| 68 | +` //for each sequence list the annotations` |
| 69 | +` for(SequenceIterator seqs = SeqIOTools.readEmbl(br); seqs.hasNext(); ){` |
| 70 | +` Annotation anno = seqs.nextSequence().getAnnotation();` |
| 71 | + |
| 72 | +` //print each key value pair` |
| 73 | +` for (Iterator i = anno.keys().iterator(); i.hasNext(); ) {` |
| 74 | +` Object key = i.next();` |
| 75 | +` System.out.println(key +" : "+ anno.getProperty(key));` |
| 76 | +` }` |
| 77 | +` }` |
| 78 | +` }` |
| 79 | +` catch (Exception ex) {` |
| 80 | +` ex.printStackTrace();` |
| 81 | +` }` |
| 82 | +` }` |
| 83 | + |
| 84 | +} ``` |
| 85 | + |
| 86 | +Program Output |
| 87 | + |
| 88 | + RN : [1] |
| 89 | + KW : . |
| 90 | + RL : [Submitted (11-JUL-2002) to the EMBL/GenBank/DDBJ databases., Genome Sciences, University of Washington, 1705 NE Pacific, Seattle, WA, 98195, USA] |
| 91 | + embl_accessions : [AY130859] |
| 92 | + DE : Homo sapiens cyclin-dependent kinase 7 (CDK7) gene, complete cds. |
| 93 | + SV : AY130859.1 |
| 94 | + AC : AY130859; |
| 95 | + FH : Key Location/Qualifiers |
| 96 | + XX : |
| 97 | + OC : [Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Euteleostomi; Mammalia;, Eutheria; Primates; Catarrhini; Hominidae; Homo.] |
| 98 | + RA : [Rieder M.J., Livingston R.J., Braun A.C., Montoya M.A., Chung M.-W.,, Miyamoto K.E., Nguyen C.P., Nguyen D.A., Poel C.L., Robertson P.D.,, Schackwitz W.S., Sherwood J.K., Witrak L.A., Nickerson D.A.;] |
| 99 | + ID : AY130859 standard; DNA; HUM; 44226 BP. |
| 100 | + DT : [25-JUL-2002 (Rel. 72, Created), 25-JUL-2002 (Rel. 72, Last updated, Version 1)] |
| 101 | + CC : [To cite this work please use: NIEHS-SNPs, Environmental Genome, Project, NIEHS ES15478, Department of Genome Sciences, Seattle, WA, (URL: http://egp.gs.washington.edu).] |
| 102 | + RT : ; |
| 103 | + OS : Homo sapiens (human) |
| 104 | + RP : 1-44226 |
0 commit comments