... | @@ -840,6 +840,40 @@ conda activate AGB |
... | @@ -840,6 +840,40 @@ conda activate AGB |
|
agb.py -i methylation_aware_results/assembly/flye/lr/merged/no_barcode/ -a Flye -o flye_methylation_agb_output
|
|
agb.py -i methylation_aware_results/assembly/flye/lr/merged/no_barcode/ -a Flye -o flye_methylation_agb_output
|
|
```
|
|
```
|
|
|
|
|
|
|
|
##### MAPPABILITY #####
|
|
|
|
- Assessing how "mappable" the assemblies are with the short, long and merged bam files
|
|
|
|
- i.e. the number of reads mapping back to the assemblies
|
|
|
|
```
|
|
|
|
cd /scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/results/mapping
|
|
|
|
conda activate anvio6
|
|
|
|
srun -p interactive -t 4:00:00 --pty bash -i # interactive session
|
|
|
|
|
|
|
|
# getting the "mappability" using a launcher script for the following:
|
|
|
|
sbatch -t 1:00:00 -N 1 -n 4 get_mappability.sh
|
|
|
|
>>>
|
|
|
|
# metaG
|
|
|
|
samtools flagstat sr/bwa_mem/ONT3_MG_xx_Rashi_S11_reads-x-ONT3_MG_xx_Rashi_S11-megahit_contigs.bam > sr_mappability.txt
|
|
|
|
samtools flagstat lr/merged/no_barcode/no_barcode_reads-x-no_barcode-flye_contigs.bam > lr_mappability.txt
|
|
|
|
|
|
|
|
samtools flagstat bwa_merged_metaspades_hybrid/bwa_merged_metaspades_hybrid.bam > hybrid_bwa_merged.txt
|
|
|
|
samtools flagstat bwa_sr_metaspades_hybrid/bwa_sr_metaspades_hybrid.bam > hybrid_bwa_sr.txt
|
|
|
|
samtools flagstat bwa_lr_metaspades_hybrid/bwa_lr_metaspades_hybrid.bam > hybrid_bwa_lr.txt
|
|
|
|
|
|
|
|
samtools flagstat mmi_merged_metaspades_hybrid/mmi_merged_metaspades_hybrid.bam > hybrid_mmi_merged.txt
|
|
|
|
samtools flagstat mmi_sr_metaspades_hybrid/mmi_sr_metaspades_hybrid.bam > hybrid_mmi_sr.txt
|
|
|
|
samtools flagstat mmi_lr_metaspades_hybrid/mmi_lr_metaspades_hybrid.bam > hybrid_mmi_lr.txt
|
|
|
|
|
|
|
|
# metaT
|
|
|
|
samtools flagstat ./metaT/sr/FastSelectHalf1_MT_Rashi_S12_reads-x-lr_no_barcode_sr_ONT3_MG_xx_Rashi_S11-metaspades_hybrid_contigs.bam > hybrid_metaT_sr.txt
|
|
|
|
samtools flagstat ./metaT/sr/FastSelectHalf1_MT_Rashi_S12_reads-x-ONT3_MG_xx_Rashi_S11-megahit_contigs.bam > megahit_metaT_sr.txt
|
|
|
|
>>>
|
|
|
|
|
|
|
|
# collating all the results in one place
|
|
|
|
for file in *.txt; do echo $file; egrep 'total | mapped' $file | head -n 2; done | paste - - - | \
|
|
|
|
sed $'1 i\\\nsample\ttotal\tmapped\tpercent_mapped' | sed 's/ + 0 in total (QC-passed reads + QC-failed reads)//g' | \
|
|
|
|
sed s'/ + 0 mapped//g' | sed 's/ : N\/A)//g' | sed s'/(//g' | sed s'/.txt//g' | \
|
|
|
|
awk '{print$0=$1"\t"$2"\t"$3"\t"$4}' > mappability_index.tsv
|
|
|
|
```
|
|
##### Notes - for 2018_GDB data #####
|
|
##### Notes - for 2018_GDB data #####
|
|
1. Flye does not produce metabat bins. Reason == only 2 contigs (less than 1500 bp) have coverages over 1.
|
|
1. Flye does not produce metabat bins. Reason == only 2 contigs (less than 1500 bp) have coverages over 1.
|
|
2. Should we adjust the "minCV" parameter for metabat?
|
|
2. Should we adjust the "minCV" parameter for metabat?
|
... | | ... | |