NCBI C Toolkit Cross Reference

C/tools/dust.h

  1 /* dust.h
  2 * ===========================================================================
  3 *
  4 *                            PUBLIC DOMAIN NOTICE                          
  5 *               National Center for Biotechnology Information
  6 *                                                                          
  7 *  This software/database is a "United States Government Work" under the   
  8 *  terms of the United States Copyright Act.  It was written as part of    
  9 *  the author's official duties as a United States Government employee and 
 10 *  thus cannot be copyrighted.  This software/database is freely available 
 11 *  to the public for use. The National Library of Medicine and the U.S.    
 12 *  Government have not placed any restriction on its use or reproduction.  
 13 *                                                                          
 14 *  Although all reasonable efforts have been taken to ensure the accuracy  
 15 *  and reliability of the software and data, the NLM and the U.S.          
 16 *  Government do not and cannot warrant the performance or results that    
 17 *  may be obtained by using this software or data. The NLM and the U.S.    
 18 *  Government disclaim all warranties, express or implied, including       
 19 *  warranties of performance, merchantability or fitness for any particular
 20 *  purpose.                                                                
 21 *                                                                          
 22 *  Please cite the author in any work or product based on this material.   
 23 *
 24 * ===========================================================================
 25 *
 26 * File Name:  dust.h
 27 *
 28 * Author(s):    Roma Tatusov, John Kuzio
 29 *   
 30 * Version Creation Date: 5/26/95
 31 *
 32 * $Revision: 6.1 $
 33 *
 34 * File Description:  a utility to find low complexity NA regions
 35 *
 36 * Modifications:  
 37 * --------------------------------------------------------------------------
 38 * Date       Name        Description of modification
 39 * -------  ----------  -----------------------------------------------------
 40 *
 41 * $Log: dust.h,v $
 42 * Revision 6.1  1999/08/18 17:57:56  sicotte
 43 * added includes for prototypes
 44 *
 45 * Revision 6.0  1997/08/25 18:53:06  madden
 46 * Revision changed to 6.0
 47 *
 48 * Revision 5.2  1997/02/14 22:29:48  kuzio
 49 * filter function updates
 50 *
 51  * Revision 5.1  1997/02/11  00:20:45  kuzio
 52  * support for graphs added
 53  *
 54  * Revision 5.0  1996/05/28  13:43:15  ostell
 55  * Set to revision 5.0
 56  *
 57  * Revision 4.0  1995/07/26  13:50:15  ostell
 58  * force revision to 4.0
 59  *
 60  * Revision 1.1  1995/05/26  18:47:47  kuzio
 61  * Initial revision
 62  *
 63 *
 64 * ==========================================================================
 65 */
 66 #include <objseq.h>
 67 #include <seqport.h>
 68 #include <objloc.h>
 69 
 70 extern SeqLocPtr BioseqDust PROTO ((BioseqPtr bsp, Int4 start, Int4 end,
 71                       Int2 level, Int2 window, Int2 minwin, Int2 linker));
 72 extern SeqLocPtr SeqLocDust PROTO ((SeqLocPtr slp,
 73                       Int2 level, Int2 window, Int2 minwin, Int2 linker));
 74 extern FloatHiPtr DustGraph PROTO ((SeqPortPtr spp, Int4 length,
 75                       Int2 level, Int2 window, Int2 minwin, Int2 linker));
 76 
 77 /****************************************************************************
 78 
 79 Added notes:
 80 
 81         the values of the BioseqDust parameters:
 82                         start, end
 83         are passed to a SeqPortNew function, and these should be set
 84         appropriately.
 85 
 86         calling the functions BioseqDust or SeqLocDust with any or all of
 87         the parameters:
 88                         window, level, minwin, linker
 89         set to -1, sets the values for those variables to standard
 90         dust defaults.
 91 
 92         parameter       what it is              default         range
 93 
 94         level           cut off score           20              2 - 64
 95 
 96         window          size of dusting window  64              8 - 256
 97 
 98         minwin          minimum length of       4               4 - 128
 99                         dusted region
100 
101         linker          minimum allowable       1               1 - 32
102                         distance between
103                         dusted regions
104 
105         dust turns all totally ambiguous (N) or invalid nucleotides into
106         adenosines (A).  the former is because dust retrieves sequence using
107         2-bit encoding; other ambiguities are resolved accordingly.  the
108         latter is stubbornness on dust's part; in such cases, an
109         informational notice is sent out.
110 
111         normalization by length isn't good.  increasing the size of the
112         scanning window, thereby increasing the number of triplets looked
113         at in a pass (increasing the length), will produce different "dusts".
114 
115 ****************************************************************************/
116
[ source navigation ] [ diff markup ] [ identifier search ] [ freetext search ] [ file search ]
This page was automatically generated by the LXR engine.
Visit the LXR main site for more information.