obitools/obitools3
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 66 Wiki Activity

1st version of obi align command and reworked functions that handle

Browse Source 
column alignment
This commit is contained in:
Celine Mercier
2016-08-10 14:51:02 +02:00
parent 26b8e1f215
commit 2aaa87edcc
8 changed files with 373 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
src/obi_align.c
View File

@ -25,20 +25,25 @@
// TODO
// use openMP pragmas : garder scores en memoire et ecrire a la fin? (normalement c bon avec index)
// tout ecrire en stdint?
// check NUC_SEQS and score type (int or float if normalize)
// what's with multiple sequence/line columns?
// use openMP pragmas
// option pour ecrire en stdint?
// check NUC_SEQS view type? and score type (int or float if normalize)
// what's with multiple sequences/line columns?
// make function that put blobs in int16
int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview_p score_view, OBIDMS_column_p score_column, double threshold, bool normalize, int reference, bool similarity_mode)
int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column,
Obiview_p score_view, OBIDMS_column_p id1_column, OBIDMS_column_p id2_column, OBIDMS_column_p score_column,
double threshold, bool normalize, int reference, bool similarity_mode)
{
index_t i, j, k;
index_t seq_count;
char* seq1;
char* seq2;
const char* id1;
const char* id2;
double score;
OBIDMS_column_p id_column;
k = 0;
@ -57,6 +62,9 @@ int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview
return -1;
}
// Get the ID column pointer
id_column = obi_view_get_column(seq_view, ID_COLUMN);
seq_count = (seq_column->header)->lines_used;
for (i=0; i < (seq_count - 1); i++)
@ -65,8 +73,8 @@ int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview
{
//fprintf(stderr, "\ni=%lld, j=%lld, k=%lld", i, j, k);
seq1 = obi_column_get_obiseq_with_elt_idx_in_view(seq_view, seq_column, i, 0);
seq2 = obi_column_get_obiseq_with_elt_idx_in_view(seq_view, seq_column, j, 0);
seq1 = obi_get_seq_with_elt_idx_and_col_p_in_view(seq_view, seq_column, i, 0);
seq2 = obi_get_seq_with_elt_idx_and_col_p_in_view(seq_view, seq_column, j, 0);
if ((seq1 == NULL) || (seq2 == NULL))
{
@ -74,12 +82,32 @@ int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview
return -1;
}
// TODO filter
// TODO kmer filter
// Compute alignment score
score = generic_sse_banded_lcs_align(seq1, seq2, threshold, normalize, reference, similarity_mode);
// Get sequence ids
id1 = obi_get_str_with_elt_idx_and_col_p_in_view(seq_view, id_column, i, 0);
id2 = obi_get_str_with_elt_idx_and_col_p_in_view(seq_view, id_column, j, 0);
// Write sequence ids in output view
if (obi_set_str_with_elt_idx_and_col_p_in_view(score_view, id1_column, k, 0, id1) < 0)
{
obidebug(1, "\nError writing id1 in a column");
return -1;
}
if (obi_set_str_with_elt_idx_and_col_p_in_view(score_view, id2_column, k, 0, id2) < 0)
{
obidebug(1, "\nError writing id2 in a column");
return -1;
}
// Write score in output view
if (normalize)
{
if (obi_column_set_obifloat_with_elt_idx_in_view(score_view, score_column, k, 0, (obifloat_t) score) < 0)
if (obi_set_float_with_elt_idx_and_col_p_in_view(score_view, score_column, k, 0, (obifloat_t) score) < 0)
{
obidebug(1, "\nError writing alignment score in a column");
return -1;
@ -87,13 +115,16 @@ int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview
}
else
{
if (obi_column_set_obiint_with_elt_idx_in_view(score_view, score_column, k, 0, (obiint_t) score) < 0)
if (obi_set_int_with_elt_idx_and_col_p_in_view(score_view, score_column, k, 0, (obiint_t) score) < 0)
{
obidebug(1, "\nError writing alignment score in a column");
return -1;
}
}
free(seq1);
free(seq2);
k++;
}
}
@ -102,8 +133,82 @@ int obi_align_one_column(Obiview_p seq_view, OBIDMS_column_p seq_column, Obiview
}
int obi_align_two_columns(OBIDMS_column_p seq_column_1, OBIDMS_column_p seq_column_2, OBIDMS_column_p score_column, double threshold, bool normalize, int reference, bool similarity_mode)
{
// TODO
return 0;
}
// TODO discuss if 2 input views or 2 columns or both possible
//int obi_align_two_columns(Obiview_p seq_view, OBIDMS_column_p seq_column_1, OBIDMS_column_p seq_column_2, // TODO it's implied both seq columns are in the same view but maybe it shouldn't
// Obiview_p score_view, OBIDMS_column_p score_column,
// double threshold, bool normalize, int reference, bool similarity_mode)
//{
// index_t i, j, k;
// index_t seq_count_1;
// index_t seq_count_2;
// char* seq1;
// char* seq2;
// double score;
//
// k = 0;
//
// if (((seq_column_1->header)->returned_data_type != OBI_SEQ) || ((seq_column_2->header)->returned_data_type != OBI_SEQ))
// {
// obi_set_errno(OBI_ALIGN_ERROR);
// obidebug(1, "\nTrying to align a column of a different type than OBI_SEQ");
// return -1;
// }
//
// if ((normalize && ((score_column->header)->returned_data_type != OBI_FLOAT)) ||
// (!normalize && ((score_column->header)->returned_data_type != OBI_INT)))
// {
// obi_set_errno(OBI_ALIGN_ERROR);
// obidebug(1, "\nTrying to store alignment scores in a column of an inappropriate type");
// return -1;
// }
//
// seq_count_1 = (seq_column_1->header)->lines_used;
// seq_count_2 = (seq_column_2->header)->lines_used;
//
// for (i=0; i < (seq_count_1 - 1); i++)
// {
// for (j=0; j < seq_count_2; j++)
// {
// //fprintf(stderr, "\ni=%lld, j=%lld, k=%lld", i, j, k);
//
// seq1 = obi_get_seq_with_elt_idx_and_col_p_in_view(seq_view, seq_column_1, i, 0);
// seq2 = obi_get_seq_with_elt_idx_and_col_p_in_view(seq_view, seq_column_2, j, 0);
//
// if ((seq1 == NULL) || (seq2 == NULL))
// {
// obidebug(1, "\nError retrieving sequences to align");
// return -1;
// }
//
// // TODO kmer filter
//
// score = generic_sse_banded_lcs_align(seq1, seq2, threshold, normalize, reference, similarity_mode);
//
// if (normalize)
// {
// if (obi_set_float_with_elt_idx_and_col_p_in_view(score_view, score_column, k, 0, (obifloat_t) score) < 0)
// {
// obidebug(1, "\nError writing alignment score in a column");
// return -1;
// }
// }
// else
// {
// if (obi_set_int_with_elt_idx_and_col_p_in_view(score_view, score_column, k, 0, (obiint_t) score) < 0)
// {
// obidebug(1, "\nError writing alignment score in a column");
// return -1;
// }
// }
//
// free(seq1);
// free(seq2);
//
// k++;
// }
// }
//
// return 0;
//}