Load velocyto
ml velocyto
velocyto-team/velocyto.py#130
CB Z Cell identifier
UB appears to be UMI tag
# Try downloading an ENCODE RNAseq BAM file:
GM12878, RNASeq (GINGERAS), Total Long, Whole-cell
http://genome.crg.es/encode_RNA_dashboard/hg19/
Bio rep 1
wget --no-check-certificate http://hgdownload-test.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeCshlLongRnaSeq/releaseLatest/wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1.bam
Bio rep 2
wget --no-check-certificate http://hgdownload-test.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeCshlLongRnaSeq/releaseLatest/wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2.bam
# Add CB, UB tags
python3 add_cb_ub_tags.py wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1.bam
python3 add_cb_ub_tags.py wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2.bam
# Run velocyto
velocyto run -U wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1_withtags.bam ~/dat/ensembl/gtf/Homo_sapiens.GRCh37.87.chr.gtf.gz
samtools sort -l 7 -m 512M -t CB -O BAM -@ 8 -o /scratch/bclab/aramu/analysis/velocity/2019-01-02-test-velocyto/wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1_withtags_sorted.bam /scratch/bclab/aramu/analysis/velocity/2019-01-02-test-velocyto/wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1_withtags.bam
samtools view -bh wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2_withtags.sam | samtools sort -l 7 -m 512M -t CB -O BAM -@ 8 -o /scratch/bclab/aramu/analysis/velocity/2019-01-02-test-velocyto/wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2_withtags_sorted.bam
mv wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1_withtags_sorted.bam Rep1.bam
mv cellsorted_wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep1_withtags_sorted.bam cellsorted_Rep1.bam
mv wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2_withtags_sorted.bam Rep2.bam
mv cellsorted_wgEncodeCshlLongRnaSeqGm12878CellTotalAlnRep2_withtags_sorted.bam cellsorted_Rep2.bam
K562
wget --no-check-certificate http://hgdownload-test.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeCshlLongRnaSeq/releaseLatest/wgEncodeCshlLongRnaSeqK562CellTotalAlnRep1.bam
wget --no-check-certificate http://hgdownload-test.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeCshlLongRnaSeq/releaseLatest/wgEncodeCshlLongRnaSeqK562CellTotalAlnRep2.bam
mv wgEncodeCshlLongRnaSeqK562CellTotalAlnRep1.bam K562_Rep1.bam
mv wgEncodeCshlLongRnaSeqK562CellTotalAlnRep2.bam K562_Rep2.bam
python3 add_cb_ub_tags.py K562_Rep1.bam
python3 add_cb_ub_tags.py K562_Rep2.bam
# I might have overwritten the K562 Rep2 while combining the loom files :(
python3 combine_loom.py velocyto/Rep1_6T8PI.loom velocyto/Rep2_E9TS0.loom velocyto/K562_Rep1_withtags_TXR6K.loom velocyto/K562_Rep2_withtags_LCBND.loom combined_4samples_v2.loom
cp velocyto/K562_Rep2_withtags_LCBND.loom velocyto/combined_4samples.loom
python3 combine_loom.py velocyto/Rep1_6T8PI.loom velocyto/Rep2_E9TS0.loom velocyto/K562_Rep1_withtags_TXR6K.loom velocyto/K562_Rep2_withtags_OWVYP.loom combined_4samples_v2.loom