BIOS: seq.h Source File

00001 /*
00002  * Sequence module. 
00003  *
00004  * Assumes that DNA is stored as a character.
00005  * The DNA it generates will include the bases 
00006  * as lowercase tcag.  It will generally accept
00007  * uppercase as well, and also 'n' or 'N' or '-'
00008  * for unknown bases. 
00009  *
00010  * Amino acids are stored as single character upper case. 
00011  *
00012  * This file is copyright 2002 Jim Kent, but license is hereby
00013  * granted for all use - public, private or commercial. 
00014  */
00015 
00016 
00023 #ifndef DEF_SEQ_H
00024 #define DEF_SEQ_H
00025 
00026 #include "common.h"
00027 #include "bits.h"
00028 
00032 typedef struct {
00033   char *name;           /* Name of sequence. */
00034   char *sequence;       /* Sequence base by base. */
00035   int size;             /* Size of sequence. */
00036   Bits* mask;           /* Repeat mask (optional) */
00037 } Seq; 
00038 
00039 
00040 typedef Seq dnaSeq;     /* Preferred use if DNA */
00041 typedef Seq aaSeq;      /* Preferred use if protein. */
00042 
00043 
00044 /* Numerical values for bases. */
00045 #define T_BASE_VAL 0
00046 #define U_BASE_VAL 0
00047 #define C_BASE_VAL 1
00048 #define A_BASE_VAL 2
00049 #define G_BASE_VAL 3
00050 #define N_BASE_VAL 4   /* Used in 1/2 byte representation. */
00051 
00052 typedef char DNA;
00053 typedef char AA;
00054 typedef char Codon; 
00055 
00056 /* A little array to help us decide if a character is a 
00057  * nucleotide, and if so convert it to lower case. 
00058  * Contains zeroes for characters that aren't used
00059  * in DNA sequence. */
00060 extern DNA ntChars[256];
00061 extern AA aaChars[256];
00062 
00063 /* An array that converts alphabetical DNA representation
00064  * to numerical one: X_BASE_VAL as above.  For charaters
00065  * other than [atgcATGC], has -1. */
00066 extern int ntVal[256];
00067 extern int aaVal[256];
00068 extern int ntValLower[256];     /* NT values only for lower case. */
00069 extern int ntValUpper[256];     /* NT values only for upper case. */
00070 
00071 /* Like ntVal, but with T_BASE_VAL in place of -1 for nonexistent nucleotides. */
00072 extern int ntValNoN[256];     
00073 
00074 /* Like ntVal but with N_BASE_VAL in place of -1 for 'n', 'x', '-', etc. */
00075 extern int ntVal5[256];
00076 
00077 /* Inverse array - takes X_BASE_VAL int to a DNA char value. */
00078 extern DNA valToNt[];
00079 
00080 /* Similar array that doesn't convert to lower case. */
00081 extern DNA ntMixedCaseChars[256];
00082 
00083 /* Another array to help us do complement of DNA  */
00084 extern DNA ntCompTable[256];
00085 
00086 /* Arrays to convert between lower case indicating repeat masking, and
00087  * a 1/2 byte representation where the 4th bit indicates if the characeter
00088  * is masked. Uses N_BASE_VAL for `n', `x', etc.
00089  */
00090 extern int ntValMasked[256];
00091 extern DNA valToNtMasked[256];
00092  
00093 
00094 void seq_init (); 
00095 void seq_complement (DNA *dna, long length);
00096 void seq_reverseComplement (DNA *dna, long length);
00097 aaSeq* seq_translateSeqN (dnaSeq *inSeq, unsigned offset, unsigned size, int stop);
00098 aaSeq* seq_translateSeq (dnaSeq *inSeq, unsigned offset, int stop);
00099 int seq_seqIsLower (Seq *seq);
00100 Bits* seq_maskFromUpperCaseSeq (Seq *seq);
00101 void seq_toRna (DNA *dna);
00102 AA seq_lookupCodon (DNA *dna); 
00103 AA seq_lookupMitochondrialCodon (DNA *dna);
00104 Codon seq_codonVal (DNA *start);
00105 DNA* seq_valToCodon (int val);
00106 AA* seq_dnaTranslate (DNA *dna, int terminateAtStopCodon);
00107 void seq_dnaMixedCaseFilter (char *in, DNA *out);
00108 void seq_dnaFilter (char *in, DNA *out);
00109 void seq_aaFilter (char *in, DNA *out);
00110 void seq_dnaBaseHistogram (DNA *dna, int dnaSize, int histogram[4]);
00111 int seq_intronOrientation (DNA *iStart, DNA *iEnd);
00112 int seq_dnaOrAaScoreMatch (char *a, char *b, int size, int matchScore, int mismatchScore, char ignore);
00113 
00114 
00115 #endif