git clone https://github.com/zxgsy520/biodb.git
cd  biodb/bin    
chmod 755 *    #Linux system can be used directly
cd ../scripts
chmod 755 *   #Supports all systems but requires python and related packages

wget -c https://github.com/zxgsy520/biodb/archive/refs/heads/main.zip
unzip main.zip

parse-table -conf parse-table.conf -file txt.tsv -segment_order=ascii,size_desc -placement_order=row,col -interpolate_type count -color_source row -transparency 1 -fade_transparency 0 -ribbon_layer_order=size_asc >parsed.txt
cat  parsed.txt |make-conf -dir data
circos -conf chord_circos.conf 

wget -c https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/new_taxdump/new_taxdump.tar.gz
tar -zxvf new_taxdump.tar.gz
lineage2tax.py fullnamelineage.dmp >species.taxonomy
get_taxid.py rankedlineage.dmp --kingdom Bacteria >Bacteria.taxid
awk '{print $1}' species.taxonomy |sort -u >all.tax.id
#wget -c https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdump.tar.gz
#taxonkit list -j 4 --ids 10239 --data-dir ./taxonomy >Viruses.taxid
#blastdbcmd -db ../nr -dbtype "prot" -taxidlist Viruses.taxid -out Viruses.fa
#blastdbcmd -db ../nr -dbtype "prot" -taxidlist Viruses.taxid -out  viruses.fasta2_newtaxid -outfmt "%a %T"

taxonkit lineage all.tax.id --data-dir ./new_taxdump --threads 8 | awk '$2!=""' > lineage.txt
taxonkit reformat lineage.txt --format "k__{k}|p__{p}|c__{c}|o__{o}|f__{f}|g__{g}|s__{s}" --data-dir ./new_taxdump --threads 8 >kraken.temp_taxonomy 
 print_tax.py kraken.temp_taxonomy >kraken.taxonomy #提取第1和第3列，将真菌的Eukaryota替换为Fungi

wget -c https://ftp.ebi.ac.uk/pub/databases/Rfam/14.6/Rfam.cm.gz
wget -c https://ftp.ebi.ac.uk/pub/databases/Rfam/14.6/rfam2go/rfam2go
wget -c https://ftp.ebi.ac.uk/pub/databases/Rfam/14.6/database_files/family.txt.gz
zcat family.txt.gz |awk -F '\t' '{print $1"\t"$2"\t"$4"\t"$19"\t"$30}' >family.txt
gunzip Rfam.cm.gz
cmpress Rfam.cm

wget -c ftp://ftp.neb.com/pub/rebase/protein_seqs.txt

https://ftp.ncbi.nlm.nih.gov/hmm/TIGRFAMs/

wget -c https://ftp.ncbi.nlm.nih.gov/blast/db/FASTA/nr.gz
mv nr.gz nr.fa.gz
gunzip nr.fa.gz
diamond makedb --in nr.fa --db nr --taxonmap prot.accession2taxid.gz --taxonnodes nodes.dmp --taxonnames names.dmp

wget -c https://genome-idx.s3.amazonaws.com/kraken/k2_viral_20210517.tar.gz

https://www.kegg.jp/entry/ko:K23120

rename_cogid.py cog-20.fa -c cog-20.cog.csv >cog.fasta
diamond makedb --in cog.fasta -d cog

deal_with_cazy.py IPR002102.fasta -d IPR001119.tsv >CAZy.add.fasta

#----------------------
#individuation
grep_id.py all.CAZy.out -i ${sample}.id >${sample}.CAZy.out
cazyproc.py ${sample}.CAZy.out --activ CAZy.activities.txt \
  --subfam CAZy.subfam.txt -o ${sample}.cazy_classify.tsv >${sample}.cazy.tsv
plot_cazy.py ${sample}.cazy_classify.tsv -p ${sample}
get_cazy_tax.py ${sample}.cazy.tsv --tax NR_anno_tax.txt >${sample}.CAZy_tax.tsv
stat_function_class.py ${sample}.CAZy_tax.tsv  --kingdom Bacteria --level p > ${sample}.phylum_stat_cazy_tax.tsv
tax2chord.py ${sample}.phylum_stat_cazy_tax.tsv --display 5 >${sample}.phylum_chord.tsv

wget -c http://ftp.ebi.ac.uk/pub/databases/swissprot/release/uniprot_sprot.fasta.gz

./cat_vog_protein.py vog_protein/*.faa --annotations vog.annotations.tsv.gz >vogdb.fasta
or
./build_vogdb.py vog.proteins.all.fa >vogdb.fasta