View Javadoc

1   /*--------------------------------------------------------------------------
2    *  Copyright 2007 utgenome.org
3    *
4    *  Licensed under the Apache License, Version 2.0 (the "License");
5    *  you may not use this file except in compliance with the License.
6    *  You may obtain a copy of the License at
7    *
8    *     http://www.apache.org/licenses/LICENSE-2.0
9    *
10   *  Unless required by applicable law or agreed to in writing, software
11   *  distributed under the License is distributed on an "AS IS" BASIS,
12   *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   *  See the License for the specific language governing permissions and
14   *  limitations under the License.
15   *--------------------------------------------------------------------------*/
16  //--------------------------------------
17  // UTGB Common Project
18  //
19  // PSLPullParser.java
20  // Since: Jun 5, 2007
21  //
22  // $URL$ 
23  // $Author$
24  //--------------------------------------
25  package org.utgenome.format.psl;
26  
27  import java.io.BufferedReader;
28  
29  /**
30   * PSL lines represent alignments, and are typically taken from files generated by BLAT or psLayout. See the BLAT documentation for more details. All of the following fields are required on each data
31   * line within a PSL file:
32   * 
33   * <pre>
34   *  1. matches - Number of bases that match that aren't repeats
35   *  2. misMatches - Number of bases that don't match
36   *  3. repMatches - Number of bases that match but are part of repeats
37   *  4. nCount - Number of 'N' bases
38   *  5. qNumInsert - Number of inserts in query
39   *  6. qBaseInsert - Number of bases inserted in query
40   *  7. tNumInsert - Number of inserts in target
41   *  8. tBaseInsert - Number of bases inserted in target
42   *  9. strand - '+' or '-' for query strand. In mouse, second '+'or '-' is for genomic strand
43   *  10. qName - Query sequence name
44   *  11. qSize - Query sequence size
45   *  12. qStart - Alignment start position in query
46   *  13. qEnd - Alignment end position in query
47   *  14. tName - Target sequence name
48   *  15. tSize - Target sequence size
49   *  16. tStart - Alignment start position in target
50   *  17. tEnd - Alignment end position in target
51   *  18. blockCount - Number of blocks in the alignment
52   *  19. blockSizes - Comma-separated list of sizes of each block
53   *  20. qStarts - Comma-separated list of starting positions of each block in query
54   *  21. tStarts - Comma-separated list of starting positions of each block in target
55   * </pre>
56   * 
57   * @author leo
58   * 
59   */
60  public class PSLPullParser {
61  	
62  	BufferedReader _reader;
63  	
64  }