B:BD[
2.377394] → [
2.377394:384270]
26×10 DataFrame
Row │ chrom pos variant variantType zygosity ref alt refCount altCount readsCount
│ SubStrin…? Int64 SubStrin…? String? String15 SubStrin… SubStrin… Int64 Int64 Int64
─────┼────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
1 │ NC_000015.10 74343027 g.74343027C>T snv heterozygous C T 61 58 120
2 │ NC_000015.10 75400778 g.75400778C>G snv heterozygous C G 108 79 187
3 │ NC_000015.10 89327201 g.89327201C>T snv heterozygous C T 243 241 486
4 │ NC_000015.10 48767448 g.48767448A>C snv heterozygous A C 72 70 142
5 │ NC_000015.10 75411685 g.75411685T>C snv heterozygous T C 79 81 160
6 │ NC_000015.10 66703292 g.66703292C>T snv heterozygous C T 70 60 130
7 │ NC_000015.10 89325639 g.89325639G>A snv heterozygous G A 257 267 524
8 │ NC_000015.10 89330184 g.89330184G>A snv heterozygous G A 258 287 548
9 │ NC_000015.10 89330184 g.89330184G>A snv heterozygous G A 258 287 548
10 │ NC_000015.10 89325639 g.89325639G>A snv heterozygous G A 257 267 524
11 │ NC_000015.10 42401752 g.42401752G>A snv homozygous G A 61 212 273
12 │ NC_000015.10 89327201 g.89327201C>T snv heterozygous C T 243 241 486
13 │ NC_000015.10 38339896 g.38339896G>A snv heterozygous G A 56 86 144
14 │ NC_000015.10 26869324 g.26869324A>T snv heterozygous A T 62 49 113
15 │ NC_000015.10 66435145 g.66435145G>A snv heterozygous G A 98 95 193
16 │ NC_000015.10 60514655 g.60514655G>A snv heterozygous G A 94 99 194
17 │ NC_000015.10 42410947 g.42410947A>G snv heterozygous A G 153 123 276
18 │ NC_000015.10 75430368 g.75430368C>T snv heterozygous C T 80 62 142
19 │ NC_000015.10 25375494 g.25375494T>C snv heterozygous T C 103 104 207
20 │ NC_000015.10 60497497 g.60497497C>A snv heterozygous C A 61 65 126
21 │ NC_000015.10 74891539 g.74891539C>T snv heterozygous C T 118 124 242
22 │ NC_000015.10 48488433 g.48488433A>G snv heterozygous A G 367 122 492
23 │ NC_000015.10 89318565 g.89318565A>G snv heterozygous A G 303 98 404
24 │ NC_000015.10 89323426 g.89323426C>G snv heterozygous C G 93 109 202
25 │ NC_000015.10 89318595 g.89318595T>C snv heterozygous T C 321 128 453
26 │ NC_000015.10 48488437 g.48488437T>C snv heterozygous T C 356 132 488
CLOSED: [2023-05-01 Mon 17:18]
***** TODO Chromosome1 15 :Test haplotype caller : échec
SCHEDULED: <2023-05-01 Mon>
#+begin_src
julia -Jbisonex.so --project=. insertVariants.jl `63003856_S135_chr15.bam` 63003856_S135_chr15_inserted.bam
scp 63003856_S135_chr15_inserted.bam* meso:/Work/Users/apraga/bisonex/tests/synthetic/
#+end_src
#+begin_src sh :dir /ssh:meso:/Work/Users/apraga/bisonex/tests/synthetic :results silent
ln -s /Work/Projects/bisonex/data/dbSNP/GRCh38.p13/dbSNP.gz .
ln -s /Work/Projects/bisonex/data/dbSNP/GRCh38.p13/dbSNP.gz.tbi .
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.dict .
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.fna .
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.fna.fai .
#+end_src
puis
#+begin_src
gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output testchr15.vcf.gz --reference genomeRef.fna --tmp-dir . -L NC_000015.10
#+end_src
scp meso:/Work/Users/apraga/bisonex/tests/synthetic/testchr15.vcf.gz haplotypecaller-chr15.vcf.gz
Aucun variant inséré
- base quality ok
-
****** DONE bam out : non appelé
CLOSED: [2023-05-01 Mon 21:57]
gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output haplotypecaller-chr15.vcf.gz --reference genomeRef.f
na --tmp-dir . -L NC_000015.10 --bam-output debug.bam
****** DONE --linked-de-bruijn-graph : idem
CLOSED: [2023-05-01 Mon 21:57]
readlink testchr15.vcf.gz -f^C
[apraga@mesointeractive synthetic]$ gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output haplotypecaller-chr15.vcf.gz --reference genomeRef.fna --tmp-dir . -L NC_000015.10 --linked-de-bruijn-graph
****** TODO regénérer fastq
***** TODO Générer bam données pour tous les chromosomes
timeit julia -Jbisonex.so --project=. insertVariants.jl ~/code/bisonex/out/63003856/preprocessing/63003856_S135.bam 63003856_S135_inserted.bam
40min 516ms 835µs 405ns
Avertissement:
[W::bam_hdr_read] EOF marker is absent. The input is probably truncated
Inserted.bam et excluded.bam (fichier avant le merge) ont l'air ok...
On réessaie à la main : ça passe
#+begin_src
samtools merge test-all.bam inserted.bam excluded.bam
❯ mv test-all.bam `63003856_S135_inserted.bam` -f
❯ mv test-all.bam.bai `63003856_S135_chr15_inserted.bam.bai` -f
#+end_src
***** TODO BAm2fastq
SCHEDULED: <2023-05-01 Mon>
scp 63003856_S135_chr15_inserted.bam* meso:/Work/Groups/bisonex/data/synthetic/
***** TODO Lancer pipeline
SCHEDULED: <2023-05-01 Mon>
*** Divers
**** DONE Vérifier nombre de reads fastq - bam
CLOSED: [2022-10-09 Sun 22:31]
* DONE Plot : ashkenazim trio
CLOSED: [2023-04-18 Tue 21:28] SCHEDULED: <2023-04-16 Sun>
/Entered on/ [2023-04-16 Sun 17:29]
26×10 DataFrame
Row │ chrom pos variant variantType zygosity ref alt refCount altCount readsCount
│ SubStrin…? Int64 SubStrin…? String? String15 SubStrin… SubStrin… Int64 Int64 Int64
─────┼────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
1 │ NC_000015.10 74343027 g.74343027C>T snv heterozygous C T 61 58 120
2 │ NC_000015.10 75400778 g.75400778C>G snv heterozygous C G 108 79 187
3 │ NC_000015.10 89327201 g.89327201C>T snv heterozygous C T 243 241 486
4 │ NC_000015.10 48767448 g.48767448A>C snv heterozygous A C 72 70 142
5 │ NC_000015.10 75411685 g.75411685T>C snv heterozygous T C 79 81 160
6 │ NC_000015.10 66703292 g.66703292C>T snv heterozygous C T 70 60 130
7 │ NC_000015.10 89325639 g.89325639G>A snv heterozygous G A 257 267 524
8 │ NC_000015.10 89330184 g.89330184G>A snv heterozygous G A 258 287 548
9 │ NC_000015.10 89330184 g.89330184G>A snv heterozygous G A 258 287 548
10 │ NC_000015.10 89325639 g.89325639G>A snv heterozygous G A 257 267 524
11 │ NC_000015.10 42401752 g.42401752G>A snv homozygous G A 61 212 273
12 │ NC_000015.10 89327201 g.89327201C>T snv heterozygous C T 243 241 486
13 │ NC_000015.10 38339896 g.38339896G>A snv heterozygous G A 56 86 144
14 │ NC_000015.10 26869324 g.26869324A>T snv heterozygous A T 62 49 113
15 │ NC_000015.10 66435145 g.66435145G>A snv heterozygous G A 98 95 193
16 │ NC_000015.10 60514655 g.60514655G>A snv heterozygous G A 94 99 194
17 │ NC_000015.10 42410947 g.42410947A>G snv heterozygous A G 153 123 276
18 │ NC_000015.10 75430368 g.75430368C>T snv heterozygous C T 80 62 142
19 │ NC_000015.10 25375494 g.25375494T>C snv heterozygous T C 103 104 207
20 │ NC_000015.10 60497497 g.60497497C>A snv heterozygous C A 61 65 126
21 │ NC_000015.10 74891539 g.74891539C>T snv heterozygous C T 118 124 242
22 │ NC_000015.10 48488433 g.48488433A>G snv heterozygous A G 367 122 492
23 │ NC_000015.10 89318565 g.89318565A>G snv heterozygous A G 303 98 404
24 │ NC_000015.10 89323426 g.89323426C>G snv heterozygous C G 93 109 202
25 │ NC_000015.10 89318595 g.89318595T>C snv heterozygous T C 321 128 453
26 │ NC_000015.10 48488437 g.48488437T>C snv heterozygous T C 356 132 488
CLOSED: [2023-05-01 Mon 17:18]
***** TODO Chromosome1 15 :Test haplotype caller : échec car CIGARE non mis à jour
SCHEDULED: <2023-05-01 Mon>
#+begin_src
julia -Jbisonex.so --project=. insertVariants.jl `63003856_S135_chr15.bam` 63003856_S135_chr15_inserted.bam
scp 63003856_S135_chr15_inserted.bam* meso:/Work/Users/apraga/bisonex/tests/synthetic/
#+end_src
#+begin_src sh :dir /ssh:meso:/Work/Users/apraga/bisonex/tests/synthetic :results silent
ln -s /Work/Projects/bisonex/data/dbSNP/GRCh38.p13/dbSNP.gz .
ln -s /Work/Projects/bisonex/data/dbSNP/GRCh38.p13/dbSNP.gz.tbi
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.dict .
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.fna .
ln -s /Work/Projects/bisonex/data/genome/GRCh38.p13/genomeRef.fna.fai .
#+end_src
puis
#+begin_src
gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output testchr15.vcf.gz --reference genomeRef.fna --tmp-dir . -L NC_000015.10
#+end_src
scp meso:/Work/Users/apraga/bisonex/tests/synthetic/testchr15.vcf.gz haplotypecaller-chr15.vcf.gz
Aucun variant inséré
- base quality ok
-
****** DONE bam out : non appelé
CLOSED: [2023-05-01 Mon 21:57]
gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output haplotypecaller-chr15.vcf.gz --reference genomeRef.f
na --tmp-dir . -L NC_000015.10 --bam-output debug.bam
****** DONE --linked-de-bruijn-graph : idem
CLOSED: [2023-05-01 Mon 21:57]
readlink testchr15.vcf.gz -f^C
[apraga@mesointeractive synthetic]$ gatk --java-options "-Xmx3072M" HaplotypeCaller --input 63003856_S135_chr15_inserted.bam --output haplotypecaller-chr15.vcf.gz --reference genomeRef.fna --tmp-dir . -L NC_000015.10 --linked-de-bruijn-graph
****** HOLD regénérer fastq
***** TODO Générer bam données pour tous les chromosomes
timeit julia -Jbisonex.so --project=. insertVariants.jl ~/code/bisonex/out/63003856/preprocessing/63003856_S135.bam 63003856_S135_inserted.bam
40min 516ms 835µs 405ns
Avertissement:
[W::bam_hdr_read] EOF marker is absent. The input is probably truncated
Inserted.bam et excluded.bam (fichier avant le merge) ont l'air ok...
On réessaie à la main : ça passe
#+begin_src
samtools merge test-all.bam inserted.bam excluded.bam
❯ mv test-all.bam `63003856_S135_inserted.bam` -f
❯ mv test-all.bam.bai `63003856_S135_chr15_inserted.bam.bai` -f
#+end_src
***** TODO BAm2fastq pour avoir CIGAR à jour
SCHEDULED: <2023-05-01 Mon>
rsync -avz 63003856_S135_inserted.bam* meso:/Work/Groups/bisonex/data/synthetic/
***** TODO Lancer pipeline
SCHEDULED: <2023-05-01 Mon>
*** Divers
**** DONE Vérifier nombre de reads fastq - bam
CLOSED: [2022-10-09 Sun 22:31]
* DONE Plot : ashkenazim trio
CLOSED: [2023-04-18 Tue 21:28] SCHEDULED: <2023-04-16 Sun>
/Entered on/ [2023-04-16 Sun 17:29]