/* Performs some basic tests. Feel free to define additional tests. */
void test_basic() {
Row *sparse_matrix;
unsigned char small[] = {
0x01, 0x02, 0x03,
0x04, 0x05, 0x06,
0x07, 0x08, 0x09
};
unsigned char empty[] = {
0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF
};
unsigned char tiny[] = { 56 };
unsigned char sample[] = {
0xFF, 0x01, 0x02,
0xFF, 0XFF, 0XFF,
0x03, 0x04, 0x05,
0x06, 0xFF, 0x07
};
sparse_matrix = dense_to_sparse(small, 3, 3);
test_sparse("small", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(empty, 3, 3);
test_sparse("empty", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(tiny, 1, 1);
test_sparse("tiny", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(sample, 3, 4);
test_sparse("sample", sparse_matrix);
free_sparse(sparse_matrix);
}
int main(int argc, char **argv) {
Image img;
Row *sparse_matrix;
if ( argc != 2 ) {
test_basic();
} else {
img = load_bmp(argv[1]);
sparse_matrix = dense_to_sparse(img.data, img.width, img.height);
test_sparse(argv[1], sparse_matrix);
free_sparse(sparse_matrix);
}
return 0;
}
void
iterate(Fastal_param *param, void *method_arguments_p, char *aln_file_name, char *out_file_name_end, int iteration_number)
{
// calculate alignment length
//count gap
int it_coutner_2 = 0;
const int LINE_LENGTH = 200;
char line[LINE_LENGTH];
char *seq1 = (char*)vcalloc(1,sizeof(char));
char *seq2 = (char*)vcalloc(1,sizeof(char));
Fastal_profile **profiles =(Fastal_profile**) vcalloc(3,sizeof(Fastal_profile*));
initiate_profiles(profiles, param);
Fastal_profile *gap_prf = profiles[0];
Fastal_profile *no_gap_prf = profiles[1];
int alphabet_size = param->alphabet_size;
int *gap_list_1 = (int*)vcalloc(1, sizeof(int));
int *gap_list_1_length = (int*)vcalloc(1, sizeof(int));
*gap_list_1_length = 1;
int num_gaps_1 = 0;
int *gap_list_2 = (int*)vcalloc(1, sizeof(int));
int *gap_list_2_length = (int*)vcalloc(1, sizeof(int));
*gap_list_2_length = 1;
int num_gaps_2 = 0;
int alignment_length = 1;
//from here repeat!
int it_counter = 0;
char *out_file_name = aln_file_name;
int *gap_profile = (int*)vcalloc(alignment_length, sizeof(int));
// while (it_counter < alignment_length)
// {
FILE *alignment_file = fopen(aln_file_name,"r");
if (alignment_file == NULL)
{
printf("Could not open alignment file %s\n", aln_file_name);
exit(1);
}
alignment_length = 0;
int tmp_len = -1;
fgets(line, LINE_LENGTH , alignment_file);
while(fgets(line, LINE_LENGTH , alignment_file)!=NULL)
{
tmp_len = -1;
if (line[0] == '>')
{
break;
}
while ((line[++tmp_len] != '\n') && (line[tmp_len] != '\0'));
alignment_length += tmp_len;
}
// printf("ALN_LENGTH %i\n", alignment_length);
seq1 =(char*)vrealloc(seq1, (1+alignment_length)*sizeof(char));
gap_profile = (int*)vrealloc(gap_profile, alignment_length * sizeof(int));
int i;
for (i = 0; i < alignment_length; ++i)
{
gap_profile[i] = 0;
}
int number_of_sequences = 0;
int pos = -1;
fseek (alignment_file , 0 , SEEK_SET);
while(fgets(line, LINE_LENGTH , alignment_file)!=NULL)
{
if (line[0] == '>')
{
++number_of_sequences;
pos = -1;
}
else
{
i = -1;
while ((line[++i] != '\n') && (line[i] != '\0'))
{
++pos;
if (line[i] == '-')
{
++gap_profile[pos];
}
}
}
}
double max_entrop = 0;
int column_index = 0;
double entrop = 0;
double last = 0;
double p;
// for (i = it_counter; i<=it_counter; ++i)
// {
// p = gap_profile[i]/(double)number_of_sequences;
// if (!p)
// {
// entrop = 0;
// }
// else
// {
// entrop = (-1)*(p*log(p) + (1-p)*log(1-p) ) ;
// }
// if (entrop > max_entrop)
// {
// column_index = i;
// max_entrop = entrop;
// }
// last = entrop;
// }
// ++it_counter;
// if (max_entrop < 0.6)
// {
// printf("CONTINUE %f\n",entrop);
// continue;
// }
// column_index = 18;//it_counter-1;
// if (column_index == 19)
column_index = 58;
out_file_name = vtmpnam(NULL);
char *edit_file_name = "EDIT";//vtmpnam(NULL);
FILE *edit_file = fopen(edit_file_name,"w");
char *profile_file_name = vtmpnam(NULL);
FILE *profile_file = fopen(profile_file_name,"w");
char *split_file_name = "AHA";//vtmpnam(NULL);
++it_coutner_2;
gap_prf = enlarge_prof(gap_prf, alignment_length, alphabet_size);
no_gap_prf = enlarge_prof(no_gap_prf, alignment_length, alphabet_size );
no_gap_prf->number_of_sequences = 0;
gap_prf->number_of_sequences = 0;
split_set(alignment_file, gap_prf, no_gap_prf, seq1, column_index, param->char2pos, split_file_name);
gap_prf -> length = alignment_length;
no_gap_prf -> length = alignment_length;
gap_list_1 = del_gap_from_profile(gap_prf, alphabet_size, gap_list_1, gap_list_1_length, &num_gaps_1 );
gap_list_2 = del_gap_from_profile(no_gap_prf, alphabet_size, gap_list_2, gap_list_2_length, &num_gaps_2 );
fclose(alignment_file);
profiles[0] = gap_prf;
profiles[1] = no_gap_prf;
alignment_length = gotoh_dyn(profiles, param, method_arguments_p, 0, edit_file, profile_file, 0);
seq1 =(char*)vrealloc(seq1, (1+alignment_length)*sizeof(char));
seq2 =(char*)vrealloc(seq2, (1+alignment_length)*sizeof(char));
fclose(edit_file);
edit_file = fopen(edit_file_name,"r");
edit2seq_pattern(edit_file, seq1, seq2);
fclose(edit_file);
fclose(profile_file);
write_iterated_aln(aln_file_name, out_file_name, split_file_name, seq1, gap_list_1, num_gaps_1, seq2, gap_list_2, num_gaps_2);
aln_file_name = out_file_name;
// if (it_coutner_2 == 2)
// break;
// }
char command[1000];
sprintf(command, "mv %s %s",out_file_name, out_file_name_end);
system(command);
vfree(seq1);
vfree(seq2);
vfree(gap_list_1);
vfree(gap_list_2);
if (!strcmp(param->method, "fast"))
{
free_sparse((Sparse_dynamic_param*)method_arguments_p);
}
else if (!strcmp(param->method, "nw"))
{
free_nw((Nw_param*)method_arguments_p, alphabet_size);
}
else if (!strcmp(param->method, "gotoh"))
{
free_gotoh((Gotoh_param*)method_arguments_p, alphabet_size);
}
}
/* Performs some basic tests. Feel free to define additional tests. */
void test_basic()
{
Row *sparse_matrix;
unsigned char small[] = {
0x01, 0x02, 0x03,
0x04, 0x05, 0x06,
0x07, 0x08, 0x09
};
unsigned char empty[] = {
0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF
};
unsigned char tiny[] = { 56 };
unsigned char empty_center[] = {
0x01, 0x02, 0x03,
0x04, 0xFF, 0x06,
0x07, 0x08, 0x09
};
unsigned char white_margins_empty_spots[] = {
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0x01, 0x01, 0x01, 0x01, 0xFF,
0xFF, 0x02, 0x02, 0x02, 0x02, 0xFF,
0xFF, 0x03, 0xFF, 0xFF, 0x03, 0xFF,
0xFF, 0xFF, 0x04, 0x04, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
};
unsigned char theres_a_seven_in_there[] = {
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0x07, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
};
unsigned char skips_middle_line[] = {
0x01, 0x02, 0x03,
0xFF, 0xFF, 0xFF,
0x07, 0x08, 0x09
};
sparse_matrix = dense_to_sparse(small, 3, 3);
test_sparse("small", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(empty, 3, 3);
test_sparse("empty", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(tiny, 1, 1);
test_sparse("tiny", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(empty_center, 3, 3);
test_sparse("empty_center", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(white_margins_empty_spots, 6, 6);
test_sparse("white_margins_empty_spots", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(theres_a_seven_in_there, 6, 6);
test_sparse("theres_a_seven_in_there", sparse_matrix);
free_sparse(sparse_matrix);
sparse_matrix = dense_to_sparse(skips_middle_line, 3, 3);
test_sparse("skips_middle_line", sparse_matrix);
free_sparse(sparse_matrix);
}