Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Use ksw2 to align soft-clipped ends from ungapped alignment #382

Open
wants to merge 13 commits into
base: main
Choose a base branch
from
Open

Use ksw2 to align soft-clipped ends from ungapped alignment #382

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
02ea196
Update ksw2 to the most recent upstream version
marcelm Feb 15, 2023
4f6d50a
Move ksw2 files to a subdirectory and add license
marcelm Feb 15, 2023
237cb91
Implement Aligner::ksw_extend()
marcelm Feb 17, 2023
a90d697
Add operator<< for ksw_extz_t
marcelm Mar 13, 2023
b89e3d7
Turn the ref parameter of some functions into string_view
marcelm Dec 14, 2023
36513bc
Add operator<< for AlignmentInfo
marcelm Dec 15, 2023
92d221b
Explicitly set a wildcard score in the ksw score matrix
marcelm Dec 15, 2023
13938c5
Pass ref as a string_view
marcelm Dec 15, 2023
9d72201
Make ksw actually use the score matrix
marcelm Dec 15, 2023
c36cc0a
Return empty alignment if query is empty
marcelm Dec 15, 2023
7d23a81
Add soft clipping to CIGAR if necessary
marcelm Dec 15, 2023
26b472e
If ungapped alignment is softclipped, ksw_extend soft-clipped ends
marcelm Dec 15, 2023
83edcf2
Update baseline commit
marcelm Dec 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Turn the ref parameter of some functions into string_view
  • Loading branch information
@marcelm
marcelm committed Feb 22, 2024
commit b89e3d78b43c86a107299c3f4faec54ee17d1cf1
10 changes: 5 additions & 5 deletions src/aligner.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
#include "ksw2/ksw2.h"
#include "aligner.hpp"

AlignmentInfo Aligner::align(const std::string &query, const std::string &ref) const {
AlignmentInfo Aligner::align(const std::string& query, const std::string_view ref) const {
m_align_calls++;
AlignmentInfo aln;
int32_t maskLen = query.length() / 2;
Expand All @@ -30,8 +30,8 @@ AlignmentInfo Aligner::align(const std::string &query, const std::string &ref) c

StripedSmithWaterman::Alignment alignment_ssw;

// query must be NULL-terminated
auto flag = ssw_aligner.Align(query.c_str(), ref.c_str(), ref.size(), filter, &alignment_ssw, maskLen);
// only query must be NULL-terminated
auto flag = ssw_aligner.Align(query.c_str(), ref.begin(), ref.size(), filter, &alignment_ssw, maskLen);
if (flag != 0) {
aln.edit_distance = 100000;
aln.ref_start = 0;
Expand Down Expand Up @@ -121,7 +121,7 @@ AlignmentInfo Aligner::align(const std::string &query, const std::string &ref) c
* of the query, once for each end.
*/
std::tuple<size_t, size_t, int> highest_scoring_segment(
const std::string& query, const std::string& ref, int match, int mismatch, int end_bonus
const std::string& query, const std::string_view ref, int match, int mismatch, int end_bonus
) {
size_t n = query.length();

Expand Down Expand Up @@ -156,7 +156,7 @@ std::tuple<size_t, size_t, int> highest_scoring_segment(
}

AlignmentInfo hamming_align(
const std::string &query, const std::string &ref, int match, int mismatch, int end_bonus
const std::string &query, const std::string_view ref, int match, int mismatch, int end_bonus
) {
AlignmentInfo aln;
if (query.length() != ref.length()) {
Expand Down
9 changes: 5 additions & 4 deletions src/aligner.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,9 @@ struct Aligner {
ksw_gen_simple_mat(ksw_matrix_m, ksw_matrix, parameters.match, -parameters.mismatch);
}

AlignmentInfo align(const std::string &query, const std::string &ref) const;
AlignmentInfo align(const std::string& query, const std::string_view ref) const;
AlignmentInfo ksw_extend(const std::string& query, const std::string& ref, bool right_align) const;

AlignmentParameters parameters;

unsigned calls_count() {
Expand All @@ -55,7 +56,7 @@ struct Aligner {
int8_t ksw_matrix[25];
};

inline int hamming_distance(const std::string &s, const std::string &t) {
inline int hamming_distance(const std::string& s, const std::string_view t) {
if (s.length() != t.length()){
return -1;
}
Expand All @@ -71,11 +72,11 @@ inline int hamming_distance(const std::string &s, const std::string &t) {
}

std::tuple<size_t, size_t, int> highest_scoring_segment(
const std::string& query, const std::string& ref, int match, int mismatch, int end_bonus
const std::string& query, const std::string_view ref, int match, int mismatch, int end_bonus
);

AlignmentInfo hamming_align(
const std::string &query, const std::string &ref, int match, int mismatch, int end_bonus
const std::string& query, const std::string_view ref, int match, int mismatch, int end_bonus
);

#endif
4 changes: 2 additions & 2 deletions src/aln.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,7 +213,7 @@ inline Alignment extend_seed(
bool consistent_nam
) {
const std::string query = nam.is_rc ? read.rc : read.seq;
const std::string& ref = references.sequences[nam.ref_id];
const std::string_view ref = references.sequences[nam.ref_id];

const auto projected_ref_start = nam.projected_ref_start();
const auto projected_ref_end = std::min(nam.ref_end + query.size() - nam.query_end, ref.size());
Expand All @@ -222,7 +222,7 @@ inline Alignment extend_seed(
int result_ref_start;
bool gapped = true;
if (projected_ref_end - projected_ref_start == query.size() && consistent_nam) {
std::string ref_segm_ham = ref.substr(projected_ref_start, query.size());
std::string_view ref_segm_ham = ref.substr(projected_ref_start, query.size());
auto hamming_dist = hamming_distance(query, ref_segm_ham);

if (hamming_dist >= 0 && (((float) hamming_dist / query.size()) < 0.05) ) { //Hamming distance worked fine, no need to ksw align
Expand Down