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

Added the kmer filter to LCS alignments, and now obiblobs containing

Browse Source 
encoded sequences are directly put in int16_t arrays for the alignment
This commit is contained in:
Celine Mercier
2016-11-18 16:29:28 +01:00
parent 08e67a090f
commit 70c49e214a
17 changed files with 653 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

214
src/sse_banded_LCS_alignment.c
View File

@ -17,6 +17,8 @@
#include "utils.h"
#include "_sse.h"
#include "sse_banded_LCS_alignment.h"
#include "obiblob.h"
#include "encode.h" // TODO move putBlobInSeq function to encode.c ?
#define DEBUG_LEVEL 0 // TODO has to be defined somewhere else (cython compil flag?)
@ -107,7 +109,7 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
max = INT16_MAX - l1;
numberOfRegistersPerLine = bandLengthTotal / 8;
numberOfRegistersFor3Lines = 3 * numberOfRegistersPerLine;
numberOfRegistersFor3Lines = 3 * numberOfRegistersPerLine;
SSEregisters = (um128*) calloc(numberOfRegistersFor3Lines * 2, sizeof(um128));
l_ali_SSEregisters = SSEregisters + numberOfRegistersFor3Lines;
@ -115,7 +117,7 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
// preparer registres SSE
for (j=0; j<numberOfRegistersFor3Lines; j++)
l_ali_SSEregisters[j].i = _MM_LOAD_SI128(address+j*8);
l_ali_SSEregisters[j].i = _MM_LOAD_SI128((const __m128i*)(address+j*8));
p_diag = SSEregisters;
p_gap1 = SSEregisters+numberOfRegistersPerLine;
@ -151,13 +153,15 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
k2 = line - k1 - 1;
nucs1.i = _MM_LOADU_SI128(seq1+l1-k1);
nucs2.i = _MM_LOADU_SI128(seq2+k2);
nucs1.i = _MM_LOADU_SI128((const __m128i*)(seq1+l1-k1));
nucs2.i = _MM_LOADU_SI128((const __m128i*)(seq2+k2));
/* fprintf(stderr, "\nnucs, r %d, k1 = %d, k2 = %d\n", j, k1, k2);
printreg(nucs1.i);
printreg(nucs2.i);
*/
// if (print)
// {
// fprintf(stderr, "\nnucs, r %d, k1 = %d, k2 = %d\n", j, k1, k2);
// printreg(nucs1.i);
// printreg(nucs2.i);
// }
// computing diagonal score :
scores.i = _MM_AND_SI128(_MM_CMPEQ_EPI16(nucs1.i, nucs2.i), _MM_SET1_EPI16(1));
@ -199,25 +203,26 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
_MM_AND_SI128(p_gap2_j->i, boolean_reg.i),
_MM_ANDNOT_SI128(boolean_reg.i, current.i));
/*
fprintf(stderr, "\nline = %d", line);
fprintf(stderr, "\nDiag, r %d : ", j);
printreg((*(p_diag_j)).i);
fprintf(stderr, "Gap1 : ");
printreg((*(p_gap1_j)).i);
fprintf(stderr, "Gap2 : ");
printreg((*(p_gap2_j)).i);
fprintf(stderr, "current : ");
printreg(current.i);
fprintf(stderr, "L ALI\nDiag r %d : ", j);
printreg((*(p_l_ali_diag_j)).i);
fprintf(stderr, "Gap1 : ");
printreg((*(p_l_ali_gap1_j)).i);
fprintf(stderr, "Gap2 : ");
printreg((*(p_l_ali_gap2_j)).i);
fprintf(stderr, "current : ");
printreg(l_ali_current.i);
*/
// if (print)
// {
// fprintf(stderr, "\nline = %d", line);
// fprintf(stderr, "\nDiag, r %d : ", j);
// printreg((*(p_diag_j)).i);
// fprintf(stderr, "Gap1 : ");
// printreg((*(p_gap1_j)).i);
// fprintf(stderr, "Gap2 : ");
// printreg((*(p_gap2_j)).i);
// fprintf(stderr, "current : ");
// printreg(current.i);
// fprintf(stderr, "L ALI\nDiag r %d : ", j);
// printreg((*(p_l_ali_diag_j)).i);
// fprintf(stderr, "Gap1 : ");
// printreg((*(p_l_ali_gap1_j)).i);
// fprintf(stderr, "Gap2 : ");
// printreg((*(p_l_ali_gap2_j)).i);
// fprintf(stderr, "current : ");
// printreg(l_ali_current.i);
// }
// diag = gap1 and gap1 = current
p_diag_j->i = p_gap1_j->i;
@ -234,8 +239,8 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
{
if ((odd_line && even_BLL) || (even_line && odd_BLL))
{
p_gap2[j].i = _MM_LOADU_SI128((p_gap1[j].s16)-1);
p_l_ali_gap2[j].i = _MM_LOADU_SI128((p_l_ali_gap1[j].s16)-1);
p_gap2[j].i = _MM_LOADU_SI128((const __m128i*)((p_gap1[j].s16)-1));
p_l_ali_gap2[j].i = _MM_LOADU_SI128((const __m128i*)((p_l_ali_gap1[j].s16)-1));
if (j == 0)
{
p_gap2[j].i = _MM_INSERT_EPI16(p_gap2[j].i, 0, 0);
@ -244,8 +249,8 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
}
else
{
p_gap2[j].i = _MM_LOADU_SI128(p_gap1[j].s16+1);
p_l_ali_gap2[j].i = _MM_LOADU_SI128(p_l_ali_gap1[j].s16+1);
p_gap2[j].i = _MM_LOADU_SI128((const __m128i*)(p_gap1[j].s16+1));
p_l_ali_gap2[j].i = _MM_LOADU_SI128((const __m128i*)(p_l_ali_gap1[j].s16+1));
if (j == numberOfRegistersPerLine - 1)
{
p_gap2[j].i = _MM_INSERT_EPI16(p_gap2[j].i, 0, 7);
@ -267,7 +272,10 @@ void sse_banded_align_lcs_and_ali_len(int16_t* seq1, int16_t* seq2, int l1, int
l_loc = (int) floor((double)(bandLengthLeft) / (double)2) - ceil((double)(diff) / (double)2);
l_reg = (int)floor((double)l_loc/(double)8.0);
//fprintf(stderr, "\nl_reg = %d, l_loc = %d\n", l_reg, l_loc);
// if (print)
// fprintf(stderr, "\nl_reg = %d, l_loc = %d\n", l_reg, l_loc);
l_loc = l_loc - l_reg*8;
// extracting the results from the registers :
@ -357,8 +365,8 @@ double sse_banded_align_just_lcs(int16_t* seq1, int16_t* seq2, int l1, int l2, i
k2 = line - k1 - 1;
nucs1.i = _MM_LOADU_SI128(seq1+l1-k1);
nucs2.i = _MM_LOADU_SI128(seq2+k2);
nucs1.i = _MM_LOADU_SI128((const __m128i*)(seq1+l1-k1));
nucs2.i = _MM_LOADU_SI128((const __m128i*)(seq2+k2));
// computing diagonal score :
scores.i = _MM_AND_SI128(_MM_CMPEQ_EPI16(nucs1.i, nucs2.i), _MM_SET1_EPI16(1));
@ -381,7 +389,7 @@ double sse_banded_align_just_lcs(int16_t* seq1, int16_t* seq2, int l1, int l2, i
{
if ((odd_line && even_BLL) || (even_line && odd_BLL))
{
(*(p_gap2+j)).i = _MM_LOADU_SI128(((*(p_gap1+j)).s16)-1);
(*(p_gap2+j)).i = _MM_LOADU_SI128((const __m128i*)(((*(p_gap1+j)).s16)-1));
if (j == 0)
{
(*(p_gap2+j)).i = _MM_INSERT_EPI16((*(p_gap2+j)).i, 0, 0);
@ -389,7 +397,7 @@ double sse_banded_align_just_lcs(int16_t* seq1, int16_t* seq2, int l1, int l2, i
}
else
{
(*(p_gap2+j)).i = _MM_LOADU_SI128(((*(p_gap1+j)).s16)+1);
(*(p_gap2+j)).i = _MM_LOADU_SI128((const __m128i*)(((*(p_gap1+j)).s16)+1));
if (j == numberOfRegistersPerLine - 1)
{
(*(p_gap2+j)).i = _MM_INSERT_EPI16((*(p_gap2+j)).i, 0, 7);
@ -483,6 +491,41 @@ void putSeqInSeq(int16_t* seq, char* s, int l, bool reverse)
}
void putBlobInSeq(int16_t* seq, Obi_blob_p b, int l, bool reverse)
{
size_t i;
uint8_t shift;
uint8_t mask;
uint8_t nuc;
int16_t* target = seq;
int16_t* end = target + (size_t) l;
if (reverse)
{
for (i = l-1; target < end; target++, i--)
{
shift = 6 - 2*(i % 4);
mask = NUC_MASK_2B << shift;
nuc = (b->value[i/4] & mask) >> shift;
*target = (int16_t)nuc+1; // +1 because nucleotide can't be == 0 (0 is a default value used to initialize some registers)
}
}
else
{
for (i=0; target < end; target++, i++)
{
shift = 6 - 2*(i % 4);
mask = NUC_MASK_2B << shift;
nuc = (b->value[i/4] & mask) >> shift;
*target = (int16_t)nuc+1; // +1 because nucleotide can't be == 0 (0 is a default value used to initialize some registers)
}
}
}
void initializeAddressWithGaps(int16_t* address, int bandLengthTotal, int bandLengthLeft, int l1)
{
int i;
@ -491,7 +534,7 @@ void initializeAddressWithGaps(int16_t* address, int bandLengthTotal, int bandLe
int bm;
int value=INT16_MAX-l1;
numberOfRegistersPerLine = bandLengthTotal / 8;
numberOfRegistersPerLine = bandLengthTotal / 8;
bm = bandLengthLeft%2;
for (i=0; i < (3*numberOfRegistersPerLine*8); i++)
@ -543,7 +586,7 @@ double sse_banded_lcs_align(int16_t* seq1, int16_t* seq2, int l1, int l2, bool n
// fprintf(stderr, "\nid before normalizations = %f", id);
// fprintf(stderr, "\nlcs = %f, ali = %d\n", id, ali_length);
//fprintf(stderr, "\nlcs = %f, ali length = %d\n", id, ali_length);
if (!similarity_mode && !normalize)
switch(reference) {
@ -694,3 +737,98 @@ double generic_sse_banded_lcs_align(char* seq1, char* seq2, double threshold, bo
return(id);
}
double obiblob_sse_banded_lcs_align(Obi_blob_p seq1, Obi_blob_p seq2, double threshold, bool normalize, int reference, bool similarity_mode)
{
double id;
int l1, l2;
int lmax, lmin;
int sizeToAllocateForBand, sizeToAllocateForSeqs;
int maxBLL;
int LCSmin;
int shift;
int16_t* address;
int16_t* iseq1;
int16_t* iseq2;
address = NULL;
l1 = seq1->length_decoded_value;
l2 = seq2->length_decoded_value;
if (l1 > l2)
{
lmax = l1;
lmin = l2;
}
else
{
lmax = l2;
lmin = l1;
}
// If the score is expressed as a normalized distance, get the corresponding identity
if (!similarity_mode && normalize)
threshold = 1.0 - threshold;
// Calculate the minimum LCS length corresponding to the threshold
LCSmin = calculateLCSmin(lmax, lmin, threshold, normalize, reference, similarity_mode);
// Allocate space for matrix band if the alignment length must be computed
if ((reference == ALILEN) && (normalize || !similarity_mode)) // cases in which alignment length must be computed
{
sizeToAllocateForBand = calculateSizeToAllocate(lmax, lmin, LCSmin);
address = obi_get_memory_aligned_on_16(sizeToAllocateForBand, &shift);
if (address == NULL)
{
obi_set_errno(OBI_MALLOC_ERROR);
obidebug(1, "\nError getting a memory address aligned on 16 bytes boundary");
return 0; // TODO DOUBLE_MIN
}
}
// Allocate space for the int16_t arrays representing the sequences
maxBLL = calculateLeftBandLength(lmax, LCSmin);
sizeToAllocateForSeqs = 2*maxBLL+lmax;
iseq1 = (int16_t*) malloc(sizeToAllocateForSeqs*sizeof(int16_t));
iseq2 = (int16_t*) malloc(sizeToAllocateForSeqs*sizeof(int16_t));
if ((iseq1 == NULL) || (iseq2 == NULL))
{
obi_set_errno(OBI_MALLOC_ERROR);
obidebug(1, "\nError allocating memory for integer arrays to use in LCS alignment");
return 0; // TODO DOUBLE_MIN
}
// Initialize the int arrays
iniSeq(iseq1, (2*maxBLL)+lmax, 0);
iniSeq(iseq2, (2*maxBLL)+lmax, 255);
// Shift addresses to where the sequences have to be put
iseq1 = iseq1+maxBLL;
iseq2 = iseq2+maxBLL;
// Put the DNA sequences in the int arrays. Longest sequence must be first argument of sse_align function
if (l2 > l1)
{
putBlobInSeq(iseq1, seq2, l2, TRUE);
putBlobInSeq(iseq2, seq1, l1, FALSE);
// Compute alignment
id = sse_banded_lcs_align(iseq1, iseq2, l2, l1, normalize, reference, similarity_mode, address, LCSmin);
}
else
{
putBlobInSeq(iseq1, seq1, l1, TRUE);
putBlobInSeq(iseq2, seq2, l2, FALSE);
// Compute alignment
id = sse_banded_lcs_align(iseq1, iseq2, l1, l2, normalize, reference, similarity_mode, address, LCSmin);
}
// Free allocated elements
if (address != NULL)
free(address-shift);
free(iseq1-maxBLL);
free(iseq2-maxBLL);
return(id);
}