# Tuco RNAseq work

#### begin by downloading the data

lftp -c 'set ssl:verify-certificate no set ftp:ssl-protect-data true set ftp:ssl-force true; open -u i20240711_150PE_NVX2+_25B_Lee_M004370,Aepujaji9oungah -e "mirror -c; quit" ftp://gslanalyzer.qb3.berkeley.edu:990'

#### genome vs transcriptome approach

Will need to determine if the genome (https://www.ncbi.nlm.nih.gov/datasets/genome/GCA_004027165.1/) or _de novo_ transcriptome approach will be better. The genome quality is probably really low

- [x] BUSCO %'s C:74.8%[S:69.5%,D:5.3%],F:9.4%,M:15.8%,n:9226
- [ ] Mapping rates

#### Run BUSCO

#!/bin/bash

#SBATCH --partition=macmanes,shared
#SBATCH -J tuco_busco
#SBATCH --cpus-per-task=24
#SBATCH --output busco_tuco.log
#SBATCH --exclude=node117

module purge
module load anaconda/colsa
conda activate busco-5.4.7

export AUGUSTUS_CONFIG_PATH=/mnt/lz01/hcgs/shared/databases/busco/augustus_config/

AUGUSTUS_CONFIG_PATH=/mnt/lz01/hcgs/shared/databases/busco/augustus_config/

busco -i $HOME/tuco/genome/GCA_004027165.1_CteSoc_v1_BIUU_genomic.fna \
        --cpu 24  \
        --out busco_tuco \
        --lineage $HOME/mammalia_odb10 \
        --download_path $HOME/databases/busco/ \
        --offline \
        --config /mnt/lz01/hcgs/shared/databases/busco/config.ini \
        --mode genome