int count_sequences_stockholm(char* string)
{
char* p1 = string;
int i = 0;
int j = 0;
int n = 0;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
if (!(byg_start("//",p1))){
break;
}
j = byg_end("#",p1);
if(j != 1){
n++;
}
}
if(!n){
return 0;
}
return n;
}
int count_sequences_clustalw(char* string)
{
char* p1 = string;
int i = 0;
int j = 0;
int c = 0;
int n = 0;
int f = 0;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
j = byg_end(" ",p1);
f = byg_end("\n",p1);
if(f > 2 && f>j && j!= 1){
if(c ==0){
i = j;
while(p1[i] != '\n'){
//if (!isspace((int)p1[i])){
// len++;
//}
i++;
}
}
c++;
}else{
if (c){
if(c > n){
n = c;
}
c =0;
}
}
}
if(!n){
return 0;
}
return n;
}
struct alignment* read_sequences_uniprot_xml(struct alignment* aln,char* string)
{
int c = 0;
int n = 0;
int i = 0;
int j = 0;
char *p1 = 0;
int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,23,13,14,15,16,17,17,18,19,20,21,22};
//int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,-1,13,14,15,16,17,-1,18,19,20,21,22};
/*aln = (struct alignment *) malloc(sizeof(struct alignment));
numseq = byg_count("<entry",string);
if(!numseq){
k_printf("No sequences found!\n");
exit(1);
}
numprofiles = (numseq << 1) - 1;
aln->s = malloc(sizeof(int*) * (numseq ));
aln->seq = malloc(sizeof(char*) * (numseq ));
aln->si = 0;
aln->ft = 0;
aln->sl = malloc(sizeof(int) * (numprofiles));
aln->sip = malloc(sizeof(int*)* numprofiles);
aln->nsip = malloc(sizeof(int)* numprofiles);
aln->sn = malloc(sizeof(char*) * numseq);
aln->lsn = malloc(sizeof(int) * numseq);
for (i =0;i < numprofiles;i++){
aln->sip[i] = 0;
aln->nsip[i] = 0;
}
for(i =0;i < numseq;i++){
aln->sip[i] = malloc(sizeof(int)*1);
aln->nsip[i] = 1;
aln->sip[i][0] = i;
}*/
p1 = string;
c = 0;
while(aln->sl[c]){
c++;
}
while((i = byg_end("<entry",p1))!=-1){
p1+=i;// p1 is at start of entry;
i = byg_end("<name>",p1);
p1 +=i; //p1 is at the end of the sequence name tag
j = byg_start("</name>",p1);
aln->lsn[c] = j;
aln->sn[c] = malloc(sizeof(char)*(j+1));
for (i = 0;i < j;i++){
aln->sn[c][i] = p1[i];
}
aln->sn[c][j] = 0;
while((i = byg_end("<sequence",p1))!= -1 ){
i = byg_end("<sequence",p1);
p1+= i;
i = byg_end(">",p1);
p1 +=i;
}
j = byg_start("</sequence>",p1);
aln->s[c] = malloc(sizeof(int)*(j+1));
aln->seq[c] = malloc(sizeof(char)*(j+1));
n = 0;
for (i = 0;i < j;i++){
if(isalpha((int)p1[i])){
aln->s[c][n] = aacode[toupper(p1[i])-65];
aln->seq[c][n] = p1[i];
n++;
}
}
aln->s[c][n] = 0;
aln->seq[c][n] = 0;
aln->sl[c] = n;
c++;
}
free(string);
return aln;
}
struct feature* read_ft(struct feature* ft,char* p)
{
int i,j;
struct feature *n = 0;
struct feature *old_n = 0;
char tmp[10];
char* p1 = 0;
p1 = p;
while((j = byg_end("<fitem>",p1))!= -1){
i = byg_end("</seq-info>",p1);
if(j >i){
break;
}
n = malloc(sizeof(struct feature));
n->next = 0;
n->color = -1;
p1+=j;// p1 is at start of entry;
i = byg_end("<ftype>",p1);
p1 +=i; //p1 is at the end of the sequence name tag
j = byg_start("</ftype>",p1);
n->type = malloc(sizeof(char*)*(j+1));
for (i = 0; i < j;i++){
n->type[i] = p1[i];
}
n->type[j] = 0;
i = byg_end("<fstart>",p1);
p1+= i;
j = byg_start("</fstart>",p1);
for (i = 0; i < j;i++){
tmp[i] = p1[i];
}
tmp[j] = 0;
n->start = atoi(tmp);
i = byg_end("<fstop>",p1);
p1+= i;
j = byg_start("</fstop>",p1);
for (i = 0; i < j;i++){
tmp[i] = p1[i];
}
tmp[j] = 0;
n->end = atoi(tmp);
i = byg_end("<fnote>",p1);
p1+= i;
j = byg_start("</fnote>",p1);
n->note = malloc(sizeof(char*)*(j+1));
for (i = 0; i < j;i++){
n->note[i] = p1[i];
}
n->note[j] = 0;
if((old_n = ft)!= 0){
while(old_n->next!=0){
old_n = old_n->next;
}
old_n->next = n;
}else{
ft = n;
}
n = 0;
}
return ft;
}
struct alignment* read_alignment_macsim_xml(struct alignment* aln,char* string)
{
int c = 0;
int n = 0;
int i = 0;
int j = 0;
char *p = 0;
int max = 0;
int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,23,13,14,15,16,17,17,18,19,20,21,22};
//int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,-1,13,14,15,16,17,-1,18,19,20,21,22};
/*aln = (struct alignment*) malloc(sizeof(struct alignment));
numseq = byg_count("<seq-name>",string);
if(!numseq){
k_printf("No sequences found!\n");
exit(1);
}
numprofiles = (numseq << 1) - 1;
aln->s = malloc(sizeof(int*) * (numseq ));
aln->seq = malloc(sizeof(char*) * (numseq ));
aln->ft = malloc(sizeof(struct feature* ) * (numseq));
aln->si = malloc(sizeof(struct sequence_information* ) * (numseq));
aln->sl = malloc(sizeof(int) * (numprofiles));
aln->sip = malloc(sizeof(int*)* numprofiles);
aln->nsip = malloc(sizeof(int)* numprofiles);
aln->sn = malloc(sizeof(char*) * numseq);
aln->lsn = malloc(sizeof(int) * numseq);
for (i =0;i < numprofiles;i++){
aln->sip[i] = 0;
aln->nsip[i] = 0;
}
for(i =0;i < numseq;i++){
aln->ft[i] = 0;
aln->si[i] = 0;
aln->sip[i] = malloc(sizeof(int)*1);
aln->nsip[i] = 1;
aln->sip[i][0] = i;
}*/
p = string;
if(byg_count("<g>",p)){
while((i = byg_start("<g>",p))!=-1){
p+=i;
j = byg_end("<r>",p);
for(i = 0; i< j;i++){
p[i] = ' ';
}
i = byg_start("</r>",p);
p+=i;
j = byg_end("</g>",p);
for(i = 0; i< j;i++){
p[i] = ' ';
}
}
}
p = string;
c = 0;
while(aln->sl[c]){
c++;
}
while((i = byg_end("<sequence",p))!=-1){
p+=i;// p1 is at start of entry;
max = byg_end("</sequence>",p);
i = byg_end("<seq-name>",p);
if(i < max){
p +=i; //p1 is at the end of the sequence name tag
j = byg_start("</seq-name>",p);
aln->lsn[c] = j;
aln->sn[c] = malloc(sizeof(char)*(j+1));
for (i = 0;i < j;i++){
aln->sn[c][i] = p[i];
}
aln->sn[c][j] = 0;
}
i = byg_end("<ftable>",p);
if(i < max){
aln->ft[c] = read_ft(aln->ft[c],p);
}
i = byg_end("<seq-data>",p);
if(i < max){
p+= i;
j = byg_start("</seq-data>",p);
aln->s[c] = malloc(sizeof(int)*(j+1));
aln->seq[c] = malloc(sizeof(char)*(j+1));
n = 0;
for (i = 0;i < j;i++){
if((int)p[i]>32){
if(isalpha((int)p[i])){
aln->s[c][n] = aacode[toupper(p[i])-65];
}else{
aln->s[c][n] = -1;
}
aln->seq[c][n] = p[i];
n++;
}
}
aln->s[c][n] = 0;
aln->seq[c][n] = 0;
aln->sl[c] = n;
}
c++;
}
free(string);
return aln;
}
struct alignment* read_alignment_from_swissprot(struct alignment* aln,char* string)
{
//int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,-1,13,14,15,16,17,-1,18,19,20,21,22};
int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,23,13,14,15,16,17,17,18,19,20,21,22};
int i,j,c,n;
char* p = 0;
p = string;
/*numseq = byg_count("ID ",p);
if(!numseq){
k_printf("No sequences found!\n");
exit(1);
}
aln = (struct alignment *) malloc(sizeof(struct alignment));
numprofiles = (numseq << 1) - 1;
aln->ft = 0;
aln->si = 0;
aln->s = malloc(sizeof(int*) * (numseq ));
aln->seq = malloc(sizeof(char*) * (numseq ));
aln->sl = malloc(sizeof(int) * (numprofiles));
aln->sip = malloc(sizeof(int*)* numprofiles);
aln->nsip = malloc(sizeof(int)* numprofiles);
aln->sn = malloc(sizeof(char*) * numseq);
aln->lsn = malloc(sizeof(int) * numseq);
for (i =0;i < numprofiles;i++){
aln->sip[i] = 0;
aln->nsip[i] = 0;
}
for (i = numseq;i--;){
aln->sip[i] = malloc(sizeof(int)*1);
aln->nsip[i] = 1;
aln->sip[i][0] = i;
}*/
c = 0;
while(aln->sl[c]){
c++;
}
k_printf("found sequence:\n");
while ((i = byg_end("ID ",p)) != -1){
p+=i;
j = byg_start(" ",p);
aln->lsn[c] = j;
aln->sn[c] = malloc(sizeof(char)*(j+1));
for (i = 0;i < j;i++){
aln->sn[c][i] = p[i];
}
aln->sn[c][j] = 0;
p+= j;
j = byg_end("SQ ",p);
p+= j;
j = byg_end("\n",p);
p+= j;
j = byg_start("//",p);
k_printf("found sequence:\n");
aln->s[c] = malloc(sizeof(int)*(j+1));
aln->seq[c] = malloc(sizeof(char)*(j+1));
n = 0;
for (i = 0;i < j;i++){
if((int)p[i] > 32){
if(isalpha((int)p[i])){
aln->s[c][n] = aacode[toupper(p[i])-65];
}else{
aln->s[c][n] = -1;
}
k_printf("%c",p[i]);
aln->seq[c][n] = p[i];
n++;
}
}
k_printf("\n\n");
aln->s[c][n] = 0;
aln->seq[c][n] = 0;
aln->sl[c] = n;
c++;
}
free(string);
return aln;
}
struct alignment* read_alignment_clustal(struct alignment* aln,char* string)
{
int c = 0;
int n = 0;
int len = 0;
int i = 0;
int j = 0;
int start = 0;
char *p1 = 0;
int local_numseq = 0;
int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,23,13,14,15,16,17,17,18,19,20,21,22};
//int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,-1,13,14,15,16,17,-1,18,19,20,21,22};
//aln = (struct alignment*) malloc(sizeof(struct alignment));
p1 = string;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
j = byg_end(" ",p1);
n = byg_end("\n",p1);
if(n > 2 && n>j && j!= 1){
if(c ==0){
i = j;
while(p1[i] != '\n'){
if ((int)p1[i] > 32){
len++;
}
i++;
}
}
c++;
}else{
if (c){
if(c > local_numseq){
local_numseq = c;
}
c =0;
}
}
}
/*numprofiles = (numseq << 1) - 1;
aln->s = malloc(sizeof(int*) * (numseq ));
aln->seq = malloc(sizeof(char*) * (numseq ));
aln->ft = 0;
aln->si = 0;
aln->sl = malloc(sizeof(int) * (numprofiles));
aln->sip = malloc(sizeof(int*)* numprofiles);
aln->nsip = malloc(sizeof(int)* numprofiles);
aln->sn = malloc(sizeof(char*) * numseq);
aln->lsn = malloc(sizeof(int) * numseq);
for (i =0;i < numprofiles;i++){
aln->sip[i] = 0;
aln->nsip[i] = 0;
}
for(i =0;i < numseq;i++){
aln->lsn[i] = 0;
aln->sip[i] = malloc(sizeof(int)*1);
aln->nsip[i] = 1;
aln->sip[i][0] = i;
aln->sl[i] = 0;*/
start = 0;
while(aln->sl[start]){
start++;
}
for(i =start;i < local_numseq+start;i++){
aln->s[i] = malloc(sizeof(int)*(len+1));
aln->seq[i] = malloc(sizeof(char)*(len+1));
}
p1 = string;
c = start;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
j = byg_end(" ",p1);
n = byg_end("\n",p1);
if(n > 2 && n>j && j!= 1){
if(aln->lsn[c] == 0){
aln->lsn[c] = j;
aln->sn[c] = malloc(sizeof(char)*(j+1));
for (i = 0;i < j;i++){
aln->sn[c][i] = p1[i];
}
aln->sn[c][j] = 0;
}
for (i = j;i < n;i++){
if((int)p1[i] > 32){
if(isalpha((int)p1[i])){
aln->s[c][aln->sl[c]] = aacode[toupper(p1[i])-65];
}else{
aln->s[c][aln->sl[c]] = -1;
}
aln->seq[c][aln->sl[c]] = p1[i];
aln->sl[c]++;
}
}
c++;
}else{
if (c != start){
//c =0;
c = start;
}
}
}
for (i = start; i < local_numseq+start;i++){
aln->s[i][aln->sl[i]] = 0;
aln->seq[i][aln->sl[i]] = 0;
}
free(string);
return aln;
}
struct alignment* read_alignment_stockholm(struct alignment* aln,char* string)
{
int c = 0;
int n = 0;
int i = 0;
int j = 0;
char *p1 = 0;
int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,23,13,14,15,16,17,17,18,19,20,21,22};
//int aacode[26] = {0,1,2,3,4,5,6,7,8,-1,9,10,11,12,-1,13,14,15,16,17,-1,18,19,20,21,22};
/*aln = (struct alignment*) malloc(sizeof(struct alignment));
p1 = string;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
if (!(byg_start("//",p1))){
break;
}
j = byg_end("#",p1);
if(j != 1){
numseq++;
}
}
numprofiles = (numseq << 1) - 1;
aln->s = malloc(sizeof(int*) * (numseq ));
aln->seq = malloc(sizeof(char*) * (numseq ));
aln->ft = 0;
aln->si = 0;
aln->sl = malloc(sizeof(int) * (numprofiles));
aln->sip = malloc(sizeof(int*)* numprofiles);
aln->nsip = malloc(sizeof(int)* numprofiles);
aln->sn = malloc(sizeof(char*) * numseq);
aln->lsn = malloc(sizeof(int) * numseq);
for (i =0;i < numprofiles;i++){
aln->sip[i] = 0;
aln->nsip[i] = 0;
}
for(i =0;i < numseq;i++){
aln->sip[i] = malloc(sizeof(int)*1);
aln->nsip[i] = 1;
aln->sip[i][0] = i;
}*/
c = 0;
while(aln->sl[c]){
c++;
}
p1 = string;
while((i = byg_end("\n",p1))!=-1){
p1+=i;
if (!(byg_start("//",p1))){
break;
}
j = byg_end("#",p1);
if(j != 1){
j = byg_start(" ",p1);
aln->lsn[c] = j;
aln->sn[c] = malloc(sizeof(char)*(j+1));
for (i = 0;i < j;i++){
aln->sn[c][i] = p1[i];
}
aln->sn[c][j] = 0;
p1+=j;
j = byg_start("\n",p1);
aln->s[c] = malloc(sizeof(int)*(j+1));
aln->seq[c] = malloc(sizeof(char)*(j+1));
n = 0;
for (i = 0;i < j;i++){
if((int)p1[i] > 32){
if(isalpha((int)p1[i])){
aln->s[c][n] = aacode[toupper(p1[i])-65];
}else{
aln->s[c][n] = -1;
}
aln->seq[c][n] = p1[i];
n++;
}
}
aln->s[c][n] = 0;
aln->seq[c][n] = 0;
aln->sl[c] = n;
c++;
}
}
free(string);
return aln;
}
int read_sam_chunk(struct read_info** ri,struct parameters* param,FILE* file)
{
//char line[MAX_LINE];
int column = 0;
int i,j,g,tmp;
int c = 0;
ri = clear_read_info(ri, param->num_query);
char *line = NULL;
size_t len = 0;
ssize_t read;
while ((read = getline(&line, &len, file)) != -1) {
//while(fgets(line, MAX_LINE, file)){
if(line[0] != '@'){
column = 1; //<QNAME>
tmp = 0;
for(j = 0;j < read;j++){
tmp++;
if(isspace((int)line[j])){
break;
}
}
MMALLOC(ri[c]->name,sizeof(unsigned char)* tmp);
for(j = 0;j < read;j++){
if(isspace((int)line[j])){
ri[c]->name[j] = 0;
break;
}
ri[c]->name[j] = line[j];
}
for(i = 0; i < read;i++){
if(line[i] == '\n'){
break;
}
if(isspace((int)line[i])){
column++;
switch(column){
case 2: // <FLAG>
tmp = atoi(line+i+1);
ri[i]->strand = (tmp & 0x10);
//WARNING - read should be reverse complemented if mapped to negative strand before tagdusting...
/*tmp = atoi(line+i+1);
ri[c]->strand[hit] = (tmp & 0x10);
if(tmp == 4){
ri[c]->hits[hit] = 0;
}else{
ri[c]->hits[hit] = 1;
}
hit++;*/
break;
case 3: // <RNAME>
break;
case 4: // <POS>
break;
case 5: // <MAPQ>
ri[c]->mapq = atof(line +i +1);
break;
case 6: // <CIGAR>
tmp = 0;
for(j = i+1;j < read;j++){
tmp++;
if(isspace((int)line[j])){
break;
}
}
ri[c]->cigar = malloc(sizeof(unsigned char)* tmp);
g = 0;
for(j = i+1;j < read;j++){
if(isspace((int)line[j])){
ri[c]->cigar[g] = 0;
break;
}
ri[c]->cigar[g] = line[j];
g++;
}
break;
case 7: // <MRNM>
break;
case 8: // <MPOS>
break;
case 9: // <ISIZE>
break;
case 10: // <SEQ>
tmp = 0;
for(j = i+1;j < read;j++){
tmp++;
if(isspace((int)line[j])){
break;
}
}
MMALLOC(ri[c]->seq,sizeof(unsigned char)* tmp);
MMALLOC(ri[c]->labels,sizeof(unsigned char)* tmp);
g = 0;
for(j = i+1;j < read;j++){
if(isspace((int)line[j])){
ri[c]->seq[g] = 0;
ri[c]->labels[g] = 0;
break;
}
ri[c]->seq[g] = nuc_code[(int)line[j]];
ri[c]->labels[g] = 0;
g++;
}
ri[c]->len = g;
break;
case 11: // <QUAL>
tmp = 0;
for(j = i+1;j < read;j++){
tmp++;
if(isspace((int)line[j])){
break;
}
}
g= 0;
MMALLOC(ri[c]->qual,sizeof(unsigned char)* tmp);
for(j = i+1;j < read;j++){
if(isspace((int)line[j])){
ri[c]->qual[g] = 0;
break;
}
ri[c]->qual[g] = line[j];
g++;
}
break;
default:
i = (int) read;
break;
} }
}
tmp = byg_end("NM:i:", line );
if(tmp){
ri[c]->errors = atoi(line+tmp);
//if(ri[c]->errors > 20){
///fprintf(stderr,"%s\n,%c,%c,%c,%d\n",line, *(line +tmp), *(line +tmp+1),*(line +tmp+2), ri[c]->errors);
//}
}else{
ri[c]->errors = -1;
}
tmp = byg_end("MD:Z:", line );
if(tmp){
g = 0;
for(j = tmp ;j < read;j++){
g++;
if(isspace((int)line[j])){
break;
}
}
ri[c]->md = malloc(sizeof(unsigned char)* g);
g = 0;
for(j = tmp ;j < read;j++){
if(isspace((int)line[j])){
ri[c]->md[g] = 0;
break;
}
ri[c]->md[g] = line[j];
g++;
}
}
//ri[c]->hits[hit] = 0xFFFFFFFFu;
c++;
if(c == param->num_query){
MFREE(line);
return c;
}
}
}
MFREE(line);
return c;
}