@@ -6,67 +6,71 @@ There are multiple ways how to read a Genbank file. |
6 | 6 | ## Method 1: Read a Genbank file using the GenbankProxySequenceReader |
7 | 7 |
|
8 | 8 | ```java |
9 | | - |
10 | | - GenbankProxySequenceReader<AminoAcidCompound> genbankProteinReader |
11 | | - = new GenbankProxySequenceReader<AminoAcidCompound>("/tmp", "NP_000257", AminoAcidCompoundSet.getAminoAcidCompoundSet()); |
12 | | - ProteinSequence proteinSequence = new ProteinSequence(genbankProteinReader); |
13 | | - genbankProteinReader.getHeaderParser().parseHeader(genbankProteinReader.getHeader(), proteinSequence); |
14 | | - System.out.println("Sequence" + "(" + proteinSequence.getAccession() + "," + proteinSequence.getLength() + ")=" + |
15 | | -proteinSequence.getSequenceAsString().substring(0, 10) + "..."); |
16 | | - |
17 | | - GenbankProxySequenceReader<NucleotideCompound> genbankDNAReader |
18 | | - = new GenbankProxySequenceReader<NucleotideCompound>("/tmp", "NM_001126", DNACompoundSet.getDNACompoundSet()); |
19 | | - DNASequence dnaSequence = new DNASequence(genbankDNAReader); |
20 | | - genbankDNAReader.getHeaderParser().parseHeader(genbankDNAReader.getHeader(), dnaSequence); |
21 | | - System.out.println("Sequence" + "(" + dnaSequence.getAccession() + "," + dnaSequence.getLength() + ")=" + |
22 | | -dnaSequence.getSequenceAsString().substring(0, 10) + "..."); |
23 | | - |
| 9 | +GenbankProxySequenceReader<AminoAcidCompound> genbankProteinReader = |
| 10 | + new GenbankProxySequenceReader<AminoAcidCompound>("/tmp", "NP_000257", |
| 11 | + AminoAcidCompoundSet.getAminoAcidCompoundSet()); |
| 12 | +ProteinSequence proteinSequence = new ProteinSequence(genbankProteinReader); |
| 13 | +genbankProteinReader.getHeaderParser().parseHeader( |
| 14 | + genbankProteinReader.getHeader(), proteinSequence); |
| 15 | +System.out.format("Sequence(%s,%d)=%s...", |
| 16 | + proteinSequence.getAccession(), |
| 17 | + proteinSequence.getLength(), |
| 18 | + proteinSequence.getSequenceAsString().substring(0, 10)); |
| 19 | + |
| 20 | +GenbankProxySequenceReader<NucleotideCompound> genbankDNAReader = |
| 21 | + new GenbankProxySequenceReader<NucleotideCompound>("/tmp", "NM_001126", |
| 22 | + DNACompoundSet.getDNACompoundSet()); |
| 23 | +DNASequence dnaSequence = new DNASequence(genbankDNAReader); |
| 24 | +genbankDNAReader.getHeaderParser().parseHeader(genbankDNAReader.getHeader(), dnaSequence); |
| 25 | +System.out.format("Sequence(%s,%d)=%s...", dnaSequence.getAccession(), |
| 26 | + dnaSequence.getLength(), |
| 27 | + dnaSequence.getSequenceAsString().substring(0, 10)); |
24 | 28 | ``` |
25 | 29 |
|
26 | 30 |
|
27 | 31 | ## Method 2: Read a Genbank file using GenbankReaderHelper |
28 | 32 |
|
29 | 33 | ```java |
30 | | - File dnaFile = new File("src/test/resources/NM_000266.gb"); |
31 | | - File protFile = new File("src/test/resources/BondFeature.gb"); |
32 | | - |
33 | | - LinkedHashMap<String, DNASequence> dnaSequences = GenbankReaderHelper.readGenbankDNASequence( dnaFile ); |
34 | | - for (DNASequence sequence : dnaSequences.values()) { |
35 | | - System.out.println( sequence.getSequenceAsString() ); |
36 | | - } |
37 | | - |
38 | | - LinkedHashMap<String, ProteinSequence> protSequences = GenbankReaderHelper.readGenbankProteinSequence(protFile); |
39 | | - for (ProteinSequence sequence : protSequences.values()) { |
40 | | - System.out.println( sequence.getSequenceAsString() ); |
41 | | - } |
42 | | - |
| 34 | +File dnaFile = new File("src/test/resources/NM_000266.gb"); |
| 35 | +File protFile = new File("src/test/resources/BondFeature.gb"); |
| 36 | + |
| 37 | +LinkedHashMap<String, DNASequence> dnaSequences = |
| 38 | + GenbankReaderHelper.readGenbankDNASequence( dnaFile ); |
| 39 | +for (DNASequence sequence : dnaSequences.values()) { |
| 40 | + System.out.println( sequence.getSequenceAsString() ); |
| 41 | +} |
| 42 | + |
| 43 | +LinkedHashMap<String, ProteinSequence> protSequences = |
| 44 | + GenbankReaderHelper.readGenbankProteinSequence(protFile); |
| 45 | +for (ProteinSequence sequence : protSequences.values()) { |
| 46 | + System.out.println( sequence.getSequenceAsString() ); |
43 | 47 | ``` |
44 | 48 |
|
45 | 49 | ## Method 3: Read a Genbank file using the GenbankReader Object |
46 | 50 |
|
47 | 51 | ```java |
48 | | - |
49 | | - FileInputStream is = new FileInputStream(dnaFile); |
50 | | - GenbankReader<DNASequence, NucleotideCompound> dnaReader = new GenbankReader<DNASequence, NucleotideCompound>( |
51 | | - is, |
52 | | - new GenericGenbankHeaderParser<DNASequence,NucleotideCompound>(), |
53 | | - new DNASequenceCreator(DNACompoundSet.getDNACompoundSet()) |
54 | | - ); |
55 | | - dnaSequences = dnaReader.process(); |
56 | | - is.close(); |
57 | | - System.out.println(dnaSequences); |
58 | | - |
59 | | - is = new FileInputStream(protFile); |
60 | | - GenbankReader<ProteinSequence, AminoAcidCompound> protReader = new GenbankReader<ProteinSequence, AminoAcidCompound>( |
61 | | - is, |
62 | | - new GenericGenbankHeaderParser<ProteinSequence,AminoAcidCompound>(), |
63 | | - new ProteinSequenceCreator(AminoAcidCompoundSet.getAminoAcidCompoundSet()) |
64 | | - ); |
65 | | - protSequences = protReader.process(); |
66 | | - is.close(); |
67 | | - System.out.println(protSequences); |
68 | | - |
69 | | - ``` |
| 52 | +FileInputStream is = new FileInputStream(dnaFile); |
| 53 | +GenbankReader<DNASequence, NucleotideCompound> dnaReader = |
| 54 | + new GenbankReader<DNASequence, NucleotideCompound>( |
| 55 | + is, |
| 56 | + new GenericGenbankHeaderParser<DNASequence,NucleotideCompound>(), |
| 57 | + new DNASequenceCreator(DNACompoundSet.getDNACompoundSet()) |
| 58 | + ); |
| 59 | +dnaSequences = dnaReader.process(); |
| 60 | +is.close(); |
| 61 | +System.out.println(dnaSequences); |
| 62 | + |
| 63 | +is = new FileInputStream(protFile); |
| 64 | +GenbankReader<ProteinSequence, AminoAcidCompound> protReader = |
| 65 | + new GenbankReader<ProteinSequence, AminoAcidCompound>( |
| 66 | + is, |
| 67 | + new GenericGenbankHeaderParser<ProteinSequence,AminoAcidCompound>(), |
| 68 | + new ProteinSequenceCreator(AminoAcidCompoundSet.getAminoAcidCompoundSet()) |
| 69 | + ); |
| 70 | +protSequences = protReader.process(); |
| 71 | +is.close(); |
| 72 | +System.out.println(protSequences); |
| 73 | +``` |
70 | 74 |
|
71 | 75 |
|
72 | 76 | # Write a Genbank file |
@@ -75,28 +79,28 @@ dnaSequence.getSequenceAsString().substring(0, 10) + "..."); |
75 | 79 | Use the GenbankWriterHelper to write DNA sequences into a Genbank file. |
76 | 80 |
|
77 | 81 | ```java |
78 | | - |
79 | | - // First let's read dome DNA sequences from a genbank file |
80 | | - |
81 | | - File dnaFile = new File("src/test/resources/NM_000266.gb"); |
82 | | - LinkedHashMap<String, DNASequence> dnaSequences = GenbankReaderHelper.readGenbankDNASequence( dnaFile ); |
83 | | - ByteArrayOutputStream fragwriter = new ByteArrayOutputStream(); |
84 | | - ArrayList<DNASequence> seqs = new ArrayList<DNASequence>(); |
85 | | - for(DNASequence seq : dnaSequences.values()) { |
86 | | - seqs.add(seq); |
87 | | - } |
88 | | - |
89 | | - // ok now we got some DNA sequence data. Next step is to write it |
90 | | - |
91 | | - GenbankWriterHelper.writeNucleotideSequence(fragwriter, seqs, |
92 | | - GenbankWriterHelper.LINEAR_DNA); |
93 | | - |
94 | | - // the fragwriter object now contains a string representation in the Genbank format |
95 | | - // and you could write this into a file |
96 | | - // or print it out on the console |
97 | | - System.out.println(fragwriter.toString()); |
98 | | - |
| 82 | +// First let's read dome DNA sequences from a genbank file |
| 83 | + |
| 84 | +File dnaFile = new File("src/test/resources/NM_000266.gb"); |
| 85 | +LinkedHashMap<String, DNASequence> dnaSequences = |
| 86 | + GenbankReaderHelper.readGenbankDNASequence( dnaFile ); |
| 87 | +ByteArrayOutputStream fragwriter = new ByteArrayOutputStream(); |
| 88 | +ArrayList<DNASequence> seqs = new ArrayList<DNASequence>(); |
| 89 | +for(DNASequence seq : dnaSequences.values()) { |
| 90 | + seqs.add(seq); |
| 91 | +} |
| 92 | + |
| 93 | +// ok now we got some DNA sequence data. Next step is to write it |
| 94 | + |
| 95 | +GenbankWriterHelper.writeNucleotideSequence(fragwriter, seqs, |
| 96 | + GenbankWriterHelper.LINEAR_DNA); |
| 97 | + |
| 98 | +// the fragwriter object now contains a string representation in the Genbank format |
| 99 | +// and you could write this into a file |
| 100 | +// or print it out on the console |
| 101 | +System.out.println(fragwriter.toString()); |
99 | 102 | ``` |
| 103 | + |
100 | 104 | <!--automatically generated footer--> |
101 | 105 |
|
102 | 106 | --- |
|