obitools3/src/obi_align.c

/****************************************************************************
 * Sequence alignment functions				                                *
 ****************************************************************************/

/**
 * @file obi_align.c
 * @author Celine Mercier
 * @date May 4th 2016
 * @brief Functions handling sequence alignments.
 */


#include <stdlib.h>
#include <stdio.h>
#include <stdbool.h>

#include "obidebug.h"
#include "obierrno.h"
#include "obitypes.h"
#include "obiview.h"
#include "sse_banded_LCS_alignment.h"


#define DEBUG_LEVEL 0	// TODO has to be defined somewhere else (cython compil flag?)


// 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?
// 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)
{
	index_t i, j, k;
	index_t seq_count;
	char* seq1;
	char* seq2;
	double score;

	k = 0;

	if ((seq_column->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 = (seq_column->header)->lines_used;

	for (i=0; i < (seq_count - 1); i++)
	{
		for (j=i+1; j < seq_count; j++)
		{
			//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);

			if ((seq1 == NULL) || (seq2 == NULL))
			{
				obidebug(1, "\nError retrieving sequences to align");
				return -1;
			}

			// TODO filter
			score = generic_sse_banded_lcs_align(seq1, seq2, threshold, normalize, reference, similarity_mode);

			if (normalize)
			{
				if (obi_column_set_obifloat_with_elt_idx_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_column_set_obiint_with_elt_idx_in_view(score_view, score_column, k, 0, (obiint_t) score) < 0)
				{
					obidebug(1, "\nError writing alignment score in a column");
					return -1;
				}
			}

			k++;
		}
	}

	return 0;
}


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;
}