ZZPVFXEHFL3QNDP4AMCX5OFVDJUO6NR5MNYH2EUW2DL2R3OG6SIQC
On récupére 2 échantillons pour ce patient sur HiSeq Exome
#+begin_src sh :dir /ssh:meso:/Work/Groups/bisonex/data/giab/GRCh38
wget https://raw.githubusercontent.com/genome-in-a-bottle/giab_data_indexes/master/NA12878/alignment.index.NA12878_HiSeq_Exome_Garvan_GRCh37_09252015 -O todl.txt
awk '{print $1}' todl.txt | wget -i -
#+end_src
On récupére le premier échantillons en prenant just le chromosome 1
wget
ftp://ftp-trace.ncbi.nlm.nih.gov/ReferenceSamples/giab/data/AshkenazimTrio/HG002_NA24385_son/OsloUniversityHospital_Exome/151002_7001448_0359_AC7F6GANXX_Sample_HG002-EEogPU_v02-KIT-Av5_AGATGTAC_L008.posiSrt.markDup.bam
wget ftp://ftp-trace.ncbi.nlm.nih.gov/ReferenceSamples/giab/data/AshkenazimTrio/HG002_NA24385_son/OsloUniversityHospital_Exome/151002_7001448_0359_AC7F6GANXX_Sample_HG002-EEogPU_v02-KIT-Av5_AGATGTAC_L008.posiSrt.markDup.bai
mv 151002_7001448_0359_AC7F6GANXX_Sample_HG002-EEogPU_v02-KIT-Av5_AGATGTAC_L008.posiSrt.markDup.bam NA12878_illumina_exome.bam
mv 151002_7001448_0359_AC7F6GANXX_Sample_HG002-EEogPU_v02-KIT-Av5_AGATGTAC_L008.posiSrt.markDup.bai NA12878_illumina_exome.bai
samtools view -b NA12878_illumina_exome.bam 1 > NA12878_illumina_exome_chr1.bam
samtools merge NA12878-NIST7035-HiSeq_Exome_Garan_GRCh37.bam project
.NIST_NIST7035_H7AP8ADXX_TAAGGCGA_1_NA12878.bwa.markDuplicates.bam project.NIST_NIST7035_H7AP8ADXX_TA
AGGCGA_2_NA12878.bwa.markDuplicates.bam
samtools index NA12878-NIST7035-HiSeq_Exome_Garan_GRCh37.bam
On va couper le chr1
***** TODO Filtrer variants introniques de référence avec vep
****** TODO variant calling seulf + seulement -f: nombreux FP
/Work/Users/apraga/bisonex/work/68/f1cf72a5a4078fdf743fb3844b369a
Type Filter TRUTH.TOTAL TRUTH.TP TRUTH.FN QUERY.TOTAL QUERY.FP QUERY.UNK FP.gt FP.al METRIC.Recall METRIC.Precision
INDEL ALL 519 284 235 52169 37789 14094 12 64 0.547206 0.007511
INDEL PASS 519 284 235 52169 37789 14094 12 64 0.547206 0.007511
SNP ALL 22131 17434 4697 357652 305313 34904 189 32 0.787764 0.054020
SNP PASS 22131 17434 4697 357652 305313 34904 189 32 0.787764 0.054020
METRIC.Frac_NA METRIC.F1_Score TRUTH.TOTAL.TiTv_ratio QUERY.TOTAL.TiTv_ratio TRUTH.TOTAL.het_hom_ratio QUERY.TOTAL.het_hom_ratio
0.270160 0.014820 NaN NaN 1.775956 0.509510
0.270160 0.014820 NaN NaN 1.775956 0.509510
0.097592 0.101108 2.971834 1.429533 1.579776 0.324923
0.097592 0.101108 2.971834 1.429533 1.579776 0.324923