obitools3/src/obi_align.h

/****************************************************************************
 * Sequence alignment functions header file	                                *
 ****************************************************************************/

/**
 * @file obi_align.h
 * @author Celine Mercier
 * @date May 11th 2016
 * @brief Header file for the functions handling the alignment of DNA sequences.
 */


#ifndef OBI_ALIGN_H_
#define OBI_ALIGN_H_


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

#include "obidms.h"
#include "obidmscolumn.h"
#include "obitypes.h"


/**
 * @brief Aligns a NUC_SEQ column with itself.
 *
 * @param seq_view A pointer on the view where the column to align is.
 * @param seq_column A pointer on the OBI_SEQ column to align.
 * @param score_view A pointer on the view to write the outputs to.
 * @param id1_column A pointer on the OBI_STR column in score_view where the id of the first sequence should be written.
 * @param id2_column A pointer on the OBI_STR column in score_view where the id of the second sequence should be written.
 * @param score_column A pointer on the OBI_FLOAT column in score_view where the alignment score should be written.
 * @param threshold Score threshold. If the score is normalized and expressed in similarity, it is an identity, e.g. 0.95
 * 					for an identity of 95%. If the score is normalized and expressed in distance, it is (1.0 - identity),
 * 					e.g. 0.05 for an identity of 95%. If the score is not normalized and expressed in similarity, it is
 * 					the length of the Longest Common Subsequence. If the score is not normalized and expressed in distance,
 *                  it is (reference length - LCS length). Only sequence pairs with a similarity above the threshold are printed.
 * @param normalize Whether the score should be normalized with the reference sequence length.
 * @param reference The reference length. 0: The alignement length; 1: The longest sequence's length; 2: The shortest sequence's length.
 * @param similarity_mode Whether the score should be expressed in similarity (true) or distance (false).
 *
 * @returns A value indicating the success of the operation.
 * @retval 0 if the operation was successfully completed.
 * @retval -1 if an error occurred.
 *
 * @since May 2016
 * @author Celine Mercier (celine.mercier@metabarcoding.org)
 */
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);


/**
 * @brief
 *
 * TODO
 *
 */
//int obi_align_two_columns(Obiview_p seq_view, OBIDMS_column_p seq_column_1, OBIDMS_column_p seq_column_2,
//						  Obiview_p score_view, OBIDMS_column_p score_column,
//						  double threshold, bool normalize, int reference, bool similarity_mode);


#endif /* OBI_ALIGN_H_ */