dnaBitEncoding.c

#define C_SHIFT 1                    //01
#define G_SHIFT 2                    //10
#define T_SHIFT 3                    //11
/**
 * 
 * @param readString: The DNA sequence to be encoded 
 * @param stringLength : The number of characters in the DNA sequence
 * @return uint8_t type array of bits
 */
uint8_t *bitEncode(char *readString, int stringLength) {
    
    uint8_t *binaryFormat;
    int requiredLength;   //length of the array to be created

    if (stringLength % 4 == 0) {
        requiredLength = stringLength / 4;  // stringLength * 2 / 8 to be precise
    } else {
        requiredLength = stringLength / 4 + 1;
    }
    
    binaryFormat = calloc(sizeof(char), requiredLength);      //calloc ensures bits are set to 0

    for (int i = 0; i < stringLength; i++) {
        switch (readString[i]) {
            case 'A':
                //since A is encoded to 00 and we have used calloc, nothign to be done
                break;
            case 'C':
                binaryFormat[i / 4] |= C_SHIFT << (6 - (i % 4) * 2);
                break;
            case 'G':
                binaryFormat[i / 4] |= G_SHIFT << (6 - (i % 4) * 2);
                break;
            case 'T':
                binaryFormat[i / 4] |= T_SHIFT << (6 - (i % 4) * 2);
                break;
            default:
                printf("Invalid Alphabet \n");
                return binaryFormat;
        }
    }
    return binaryFormat;
}