Last active
February 6, 2018 14:34
-
-
Save agdiaz/3871397010caec0d4b2a89538b392186 to your computer and use it in GitHub Desktop.
Converts a DNA sequence in a binary file
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Compile: gcc -o dna2bit dna_bit.c | |
// Libraries | |
#include <stdio.h> | |
#include <string.h> | |
// Declare constants | |
#define A 0 // 00 | |
#define C 1 // 01 | |
#define G 2 // 10 | |
#define T 3 // 11 | |
#define BYTES_PER_BATCH 1 | |
// Declare headers and structs | |
struct Nucleotid translate(char c); | |
struct Nucleotid { unsigned int base: 2; }; | |
// Main function | |
// It receives as argument the path to save the dna and the sequence in the next format: | |
// ./dna_bit path/to/file.dna GATATATACAGGTACA | |
int main(int argc, char** params) { | |
FILE *write_ptr; | |
char* pathToFile = params[1]; | |
char* sequence = params[2]; | |
printf("Welcome to DNA2Bit version 0.0.1\n"); | |
printf("Input sequence: %s \n", sequence); | |
write_ptr = fopen(pathToFile, "wb"); | |
// Declare and first initialization of buffer variables: | |
unsigned int buffer = 0; | |
unsigned int basesInBufferCounter = 0; | |
unsigned int bytesWritten = 0; | |
// Iterate the sequence of chars | |
for (int baseCounter = 0; baseCounter < strlen(sequence); ++baseCounter) { | |
// Translate the char to the binary code | |
struct Nucleotid nucleotid = translate(sequence[baseCounter]); | |
// Puts the binary in the buffer and increments the counter | |
buffer = (buffer << 2) | nucleotid.base; | |
basesInBufferCounter++; | |
if (basesInBufferCounter == 4) { | |
// Write the 4 bases in the file (Write a byte) | |
fwrite(&buffer, BYTES_PER_BATCH, BYTES_PER_BATCH, write_ptr); | |
// Clean buffer variables | |
basesInBufferCounter = 0; | |
buffer = 0; | |
bytesWritten++; | |
} | |
} | |
// Closes the file and exit successfuly | |
fclose(write_ptr); | |
// Print statistics | |
printf("Total nucleotids written: %d\n", (int)strlen(sequence)); | |
printf("Total bytes written: %d\n", bytesWritten); | |
printf("File written in: %s\n", pathToFile); | |
return 0; | |
} | |
struct Nucleotid translate(char base) { | |
struct Nucleotid nucleotid; | |
if (base == 'A' || base == 'a') { | |
nucleotid.base = A; | |
} else if (base == 'C' || base == 'c') { | |
nucleotid.base = C; | |
} else if (base == 'G' || base == 'g') { | |
nucleotid.base = G; | |
} else { | |
nucleotid.base = T; | |
} | |
return nucleotid; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment