Skip to content

Commit d87a48b

Browse files
committed
[BFX-533] Sync HiFi settings with mm2 recomendations
Deactivate rmt.t and best_n.t until we find better test data
1 parent 9a20679 commit d87a48b

20 files changed

+82
-87
lines changed

src/AlignSettings.cpp

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -738,10 +738,10 @@ PacBio::CLI_v2::Interface AlignSettings::CreateCLI()
738738
});
739739

740740
i.HelpFooter(R"(Alignment modes of --preset:
741-
SUBREAD : -k 19 -w 10 -o 5 -O 56 -e 4 -E 1 -A 2 -B 5 -z 400 -Z 50 -r 2000 -L 0.5 -g 5000
742-
CCS or HiFi : -k 19 -w 10 -u -o 5 -O 56 -e 4 -E 1 -A 2 -B 5 -z 400 -Z 50 -r 2000 -L 0.5 -g 5000
743-
ISOSEQ : -k 15 -w 5 -u -o 2 -O 32 -e 1 -E 0 -A 1 -B 2 -z 200 -Z 100 -r 200000 -L 0.5 -g 2000 -C 5 -G 200000
744-
UNROLLED : -k 15 -w 15 -o 2 -O 32 -e 1 -E 0 -A 1 -B 2 -z 200 -Z 100 -r 2000 -L 0.5 -g 10000)");
741+
SUBREAD : -k 19 -w 19 -o 5 -O 56 -e 4 -E 1 -A 2 -B 5 -z 400 -Z 50 -r 2000 -g 5000
742+
CCS or HiFi : -k 19 -w 19 -u -o 6 -O 26 -e 2 -E 1 -A 1 -B 4 -z 400 -Z 50 -r 2000 -g 5000
743+
ISOSEQ : -k 15 -w 5 -u -o 2 -O 32 -e 1 -E 0 -A 1 -B 2 -z 200 -Z 100 -r 200000 -g 2000 -C 5 -G 200000
744+
UNROLLED : -k 15 -w 15 -o 2 -O 32 -e 1 -E 0 -A 1 -B 2 -z 200 -Z 100 -r 2000 -g 10000)");
745745

746746
i.RegisterVersionPrinter(Pbmm2::PrintPbmm2VersionSingle);
747747

src/MM2Helper.cpp

Lines changed: 11 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -233,7 +233,7 @@ void MM2Helper::PreInit(const MM2Settings& settings, std::string* preset)
233233
break;
234234
case AlignmentMode::CCS:
235235
IdxOpts.k = 19;
236-
IdxOpts.w = 10;
236+
IdxOpts.w = 19;
237237
break;
238238
case AlignmentMode::ISOSEQ:
239239
IdxOpts.k = 15;
@@ -280,16 +280,20 @@ void MM2Helper::PreInit(const MM2Settings& settings, std::string* preset)
280280
break;
281281
case AlignmentMode::CCS:
282282
*preset = "CCS / HiFi";
283-
MapOpts.a = 2;
284-
MapOpts.q = 5;
285-
MapOpts.q2 = 56;
286-
MapOpts.e = 4;
283+
MapOpts.a = 1;
284+
MapOpts.q = 6;
285+
MapOpts.q2 = 26;
286+
MapOpts.e = 2;
287287
MapOpts.e2 = 1;
288-
MapOpts.b = 5;
288+
MapOpts.b = 4;
289289
MapOpts.zdrop = 400;
290290
MapOpts.zdrop_inv = 50;
291291
MapOpts.bw = 2000;
292-
MapOpts.max_gap = 5000;
292+
MapOpts.max_gap = 10000;
293+
MapOpts.occ_dist = 500;
294+
MapOpts.min_mid_occ = 50;
295+
MapOpts.max_mid_occ = 500;
296+
MapOpts.min_dp_max = 500;
293297
break;
294298
case AlignmentMode::ISOSEQ:
295299
*preset = "ISOSEQ";

tests/cram/baminput_21.t

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@
1818
*Generating BAI (glob)
1919
*Mapped Reads: 52 (glob)
2020
*Alignments: 96 (glob)
21-
*Mapped Bases: 242437 (glob)
21+
*Mapped Bases: 243366 (glob)
2222
*Mean Gap-Compressed Sequence Identity* (glob)
2323
*Max Mapped Read Length* (glob)
2424
*Mean Mapped Read Length* (glob)

tests/cram/baminput_23.t

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,4 +16,3 @@
1616
*Z-drop inv : 50 (glob)
1717
*Bandwidth : 2000 (glob)
1818
*Max gap : 5000 (glob)
19-
*Long join flank ratio : 0.5 (glob)

tests/cram/baminput_24.t

Lines changed: 14 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -16,7 +16,6 @@
1616
*Z-drop inv : 50 (glob)
1717
*Bandwidth : 2000 (glob)
1818
*Max gap : 5000 (glob)
19-
*Long join flank ratio : 0.5 (glob)
2019

2120
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/default_overrides.bam --log-level DEBUG --preset SUBREAD -o 5 -O 56 -e 4 -E 1 -k 19 -w 10 -A 2 -B 5 -z 400 -Z 50 -r 1000 -L 0.4 -g 10000 2>&1| grep DEBUG
2221
*Minimap2 parameters* (glob)
@@ -33,41 +32,38 @@
3332
*Z-drop inv : 50 (glob)
3433
*Bandwidth : 1000 (glob)
3534
*Max gap : 10000 (glob)
36-
*Long join flank ratio : 0.4 (glob)
3735

3836
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --log-level DEBUG --preset CCS 2>&1| grep DEBUG
3937
*Minimap2 parameters* (glob)
4038
*Kmer size : 19 (glob)
41-
*Minimizer window size : 10 (glob)
39+
*Minimizer window size : 19 (glob)
4240
*Homopolymer compressed : false (glob)
43-
*Gap open 1 : 5 (glob)
44-
*Gap open 2 : 56 (glob)
45-
*Gap extension 1 : 4 (glob)
41+
*Gap open 1 : 6 (glob)
42+
*Gap open 2 : 26 (glob)
43+
*Gap extension 1 : 2 (glob)
4644
*Gap extension 2 : 1 (glob)
47-
*Match score : 2 (glob)
48-
*Mismatch penalty : 5 (glob)
45+
*Match score : 1 (glob)
46+
*Mismatch penalty : 4 (glob)
4947
*Z-drop : 400 (glob)
5048
*Z-drop inv : 50 (glob)
5149
*Bandwidth : 2000 (glob)
52-
*Max gap : 5000 (glob)
53-
*Long join flank ratio : 0.5 (glob)
50+
*Max gap : 10000 (glob)
5451

5552
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --log-level DEBUG --preset HiFi 2>&1| grep DEBUG
5653
*Minimap2 parameters* (glob)
5754
*Kmer size : 19 (glob)
58-
*Minimizer window size : 10 (glob)
55+
*Minimizer window size : 19 (glob)
5956
*Homopolymer compressed : false (glob)
60-
*Gap open 1 : 5 (glob)
61-
*Gap open 2 : 56 (glob)
62-
*Gap extension 1 : 4 (glob)
57+
*Gap open 1 : 6 (glob)
58+
*Gap open 2 : 26 (glob)
59+
*Gap extension 1 : 2 (glob)
6360
*Gap extension 2 : 1 (glob)
64-
*Match score : 2 (glob)
65-
*Mismatch penalty : 5 (glob)
61+
*Match score : 1 (glob)
62+
*Mismatch penalty : 4 (glob)
6663
*Z-drop : 400 (glob)
6764
*Z-drop inv : 50 (glob)
6865
*Bandwidth : 2000 (glob)
69-
*Max gap : 5000 (glob)
70-
*Long join flank ratio : 0.5 (glob)
66+
*Max gap : 10000 (glob)
7167

7268
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --preset foo 2>&1
7369
*Could not find --preset foo* (glob)

tests/cram/baminput_25.t

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -16,4 +16,3 @@
1616
*Z-drop inv : 50 (glob)
1717
*Bandwidth : 1000 (glob)
1818
*Max gap : 10000 (glob)
19-
*Long join flank ratio : 0.4 (glob)

tests/cram/baminput_26.t

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -4,16 +4,15 @@
44
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --log-level DEBUG --preset CCS 2>&1| grep DEBUG
55
*Minimap2 parameters* (glob)
66
*Kmer size : 19 (glob)
7-
*Minimizer window size : 10 (glob)
7+
*Minimizer window size : 19 (glob)
88
*Homopolymer compressed : false (glob)
9-
*Gap open 1 : 5 (glob)
10-
*Gap open 2 : 56 (glob)
11-
*Gap extension 1 : 4 (glob)
9+
*Gap open 1 : 6 (glob)
10+
*Gap open 2 : 26 (glob)
11+
*Gap extension 1 : 2 (glob)
1212
*Gap extension 2 : 1 (glob)
13-
*Match score : 2 (glob)
14-
*Mismatch penalty : 5 (glob)
13+
*Match score : 1 (glob)
14+
*Mismatch penalty : 4 (glob)
1515
*Z-drop : 400 (glob)
1616
*Z-drop inv : 50 (glob)
1717
*Bandwidth : 2000 (glob)
18-
*Max gap : 5000 (glob)
19-
*Long join flank ratio : 0.5 (glob)
18+
*Max gap : 10000 (glob)

tests/cram/baminput_27.t

Lines changed: 7 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -4,19 +4,18 @@
44
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --log-level DEBUG --preset HiFi 2>&1| grep DEBUG
55
*Minimap2 parameters* (glob)
66
*Kmer size : 19 (glob)
7-
*Minimizer window size : 10 (glob)
7+
*Minimizer window size : 19 (glob)
88
*Homopolymer compressed : false (glob)
9-
*Gap open 1 : 5 (glob)
10-
*Gap open 2 : 56 (glob)
11-
*Gap extension 1 : 4 (glob)
9+
*Gap open 1 : 6 (glob)
10+
*Gap open 2 : 26 (glob)
11+
*Gap extension 1 : 2 (glob)
1212
*Gap extension 2 : 1 (glob)
13-
*Match score : 2 (glob)
14-
*Mismatch penalty : 5 (glob)
13+
*Match score : 1 (glob)
14+
*Mismatch penalty : 4 (glob)
1515
*Z-drop : 400 (glob)
1616
*Z-drop inv : 50 (glob)
1717
*Bandwidth : 2000 (glob)
18-
*Max gap : 5000 (glob)
19-
*Long join flank ratio : 0.5 (glob)
18+
*Max gap : 10000 (glob)
2019

2120
$ "$PBMM2" align -j 1 "$IN" "$REF" "$CRAMTMP"/ccs_parameters.bam --preset foo 2>&1
2221
*Could not find --preset foo* (glob)

tests/cram/fastxinput_11.t

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
*Generating BAI (glob)
1616
*Mapped Reads: 52 (glob)
1717
*Alignments: 96 (glob)
18-
*Mapped Bases: 242437 (glob)
18+
*Mapped Bases: 243366 (glob)
1919
*Mean Gap-Compressed Sequence Identity* (glob)
2020
*Max Mapped Read Length* (glob)
2121
*Mean Mapped Read Length* (glob)

tests/cram/fastxinput_21.t

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@
1515
*Generating BAI (glob)
1616
*Mapped Reads: 52 (glob)
1717
*Alignments: 96 (glob)
18-
*Mapped Bases: 242437 (glob)
18+
*Mapped Bases: 243366 (glob)
1919
*Mean Gap-Compressed Sequence Identity* (glob)
2020
*Max Mapped Read Length* (glob)
2121
*Mean Mapped Read Length* (glob)

0 commit comments

Comments
 (0)