Sequence * translate_swapped(Sequence * swapped)
{
CodonTable * ct;
int i,j;
Sequence * out;
out = Sequence_alloc();
out->name = stringalloc(swapped->name);
out->seq = calloc(1+swapped->len/3,sizeof(char));
ct = read_CodonTable_file("codon.table");
for(i=0,j=0;i<swapped->len;i+=3,j++) {
out->seq[j] = aminoacid_from_seq(ct,swapped->seq+i);
if( isupper(swapped->seq[i]) && isupper(swapped->seq[i+1]) &&
isupper(swapped->seq[i+2]) ) {
out->seq[j] = toupper(out->seq[j]);
} else{
out->seq[j] = tolower(out->seq[j]);
}
}
out->seq[j] = '\0';
return out;
}
cDNA * get_cDNA_from_Transcript(Transcript * trs)
{
Genomic * gn;
Sequence * base;
int i;
char buffer[64];
if( trs->cDNA != NULL)
return trs->cDNA;
if( trs->parent == NULL ) {
warn("Cannot get cDNA, as no parent Gene!");
return NULL;
}
if ( (gn = get_Genomic_from_Gene(trs->parent)) == NULL ) {
warn("Cannot get cDNA, as cannot get Genomic sequence from Gene");
return NULL;
}
base = Sequence_alloc();
sprintf(buffer,"%s.sp",Genomic_name(gn));
base->name = stringalloc(buffer);
base->seq = ckcalloc(length_Transcript(trs)+1,sizeof(char));
base->seq[0]='\0';
for(i=0;i<trs->ex_len;i++) {
strncat(base->seq,gn->baseseq->seq+trs->exon[i]->start,trs->exon[i]->end-trs->exon[i]->start);
}
make_len_type_Sequence(base);
base->type = SEQUENCE_CDNA;
trs->cDNA = cDNA_from_Sequence(base);
return trs->cDNA;
}
Protein * get_Protein_from_Translation(Translation * ts,CodonTable * ct)
{
cDNA * cd;
int i,j;
Sequence * seq;
char buffer[64];
assert(ts);
assert(ct);
/* fprintf(stderr,"Codon table is %d\n",ct);*/
if( ts->protein != NULL)
return ts->protein;
if( ts->parent == NULL ) {
warn("Cannot get Protein from translation as no parent!");
return NULL;
}
cd = get_cDNA_from_Transcript(ts->parent);
if( cd == NULL ) {
warn("Cannot make translation as can't get transcript!");
return NULL;
}
if( cd->baseseq == NULL ) {
warn("A bad error - a non NULL cDNA with a null sequence object. No translation here!");
return NULL;
}
if( cd->baseseq->len == 0 ) {
warn("Attempting to translate a zero length cDNA. Yikes!");
return NULL;
}
seq = Sequence_alloc();
sprintf(buffer,"%s.tr",cDNA_name(cd));
seq->name = stringalloc(buffer);
seq->seq = ckcalloc((cd->baseseq->len/3) + 2,sizeof(char));
seq->type = SEQUENCE_PROTEIN;
if( cd->baseseq->len%3 != 0 ) {
warn("Problem in making translation, cDNA is not mod3! - length is %d - transcript id %s",cd->baseseq->len,seq->name);
}
for(i=0,j=0;i<cd->baseseq->len;i+=3,j++) {
if( is_stop_codon(codon_from_seq(cd->baseseq->seq+i),ct) == TRUE ) {
if( i+3 >= cd->baseseq->len )
break;
else {
warn("Got a stop codon in the middle of a translation at postion [%d]. Yuk!",i);
seq->seq[j] = '*';
}
} else {
seq->seq[j] = aminoacid_from_seq(ct,cd->baseseq->seq+i);
}
}
seq->seq[j]='\0';
make_len_type_Sequence(seq);
/*write_fasta_Sequence(seq,stdout);*/
seq->type = SEQUENCE_PROTEIN;
ts->protein = Protein_from_Sequence(seq);
return ts->protein;
}
Sequence * extract_dna_LinkStream(LinkStream * ln,LinkNumberArrayDebug * lnad,int nmer_size)
{
LinkStream * runner;
LinkStream * prev;
LinkStream * next;
int i = 0;
Sequence * out;
int flipped = 0;
assert(ln);
i++;
if( lnad->extraction != 0 ) {
fprintf(lnad->ofp,"Extracting DNA from linkstream %d\n",ln);
}
ln->have_seen = 1;
if( ln->a == NULL ) {
if( ln->b->x == ln ) {
runner = ln->b->y;
} else {
runner = ln->b->x;
}
} else {
if( ln->a->x == ln ) {
runner = ln->a->y;
} else {
runner = ln->a->x;
}
}
prev = ln;
while( runner != NULL ) {
/* to find the outgoing link from here, test neither a nor b
is not NULL and figure out the right way to go from the
fact that the link is back to ourselves */
if( runner->a == NULL || runner->b == NULL ) {
/* other end of stream */
break;
}
runner->have_seen = 1;
i++;
if( lnad->extraction > 2 ) {
fprintf(lnad->ofp,"Extracting DNA from linkstream %d, runner %d, position count %d\n",ln,runner,i);
}
if( runner->a->x == runner && runner->a->y != prev) {
next = runner->a->y;
} else if ( runner->a->y == runner && runner->a->x != prev ) {
next = runner->a->x;
} else if( runner->b->x == runner && runner->b->y != prev) {
next = runner->b->y;
} else if ( runner->b->y == runner && runner->b->x != prev ) {
next = runner->b->x;
} else {
fatal("Unable to move off edge!");
}
prev = runner;
runner = next;
}
out = Sequence_alloc();
out->seq = calloc(i+1,sizeof(char));
i = 0;
flipped = ln->starting_flip;
if( ln->a == NULL ) {
out->seq[0] = first_char_from_dnanumber(ln->number,nmer_size,flipped);
} else {
/* b is NULL, indicating a 3' end of a sequence, so flip the flip*/
out->seq[0] = first_char_from_dnanumber(ln->number,nmer_size,!flipped);
}
if( ln->a == NULL ) {
if( ln->b->x == ln ) {
runner = ln->b->y;
} else {
runner = ln->b->x;
}
if( ln->b->twist == 1 ) {
flipped = !flipped;
}
} else {
if( ln->a->x == ln ) {
runner = ln->a->y;
} else {
runner = ln->a->x;
}
/* as b is always on the reverse strand, invert the flipped sense as we read down it*/
if( ln->a->twist == 0 ) {
flipped = !flipped;
}
}
prev = ln;
i++;
while( runner != NULL ) {
/* to find the outgoing link from here, test neither a nor b
is not NULL and figure out the right way to go from the
fact that the link is back to ourselves */
if( runner->a == NULL || runner->b == NULL ) {
/* other end of stream */
break;
}
out->seq[i] = first_char_from_dnanumber(runner->number,nmer_size,flipped);
i++;
if( runner->a->x == runner && runner->a->y != prev) {
next = runner->a->y;
if( runner->a->twist == 1 ) {
flipped = !flipped;
}
} else if ( runner->a->y == runner && runner->a->x != prev ) {
next = runner->a->x;
if( runner->a->twist == 1 ) {
flipped = !flipped;
}
} else if( runner->b->x == runner && runner->b->y != prev) {
next = runner->b->y;
if( runner->b->twist == 1 ) {
flipped = !flipped;
}
} else if ( runner->b->y == runner && runner->b->x != prev ) {
next = runner->b->x;
if( runner->b->twist == 1 ) {
flipped = !flipped;
}
} else {
fatal("Unable to move off edge!");
}
prev = runner;
runner = next;
}
runner->have_seen = 1;
return out;
}
