sudo apt-get install python3 python3-pip python3-matplotlib \
ipython3-notebook python3-mpltoolkits.basemap
sudo pip3 install -U pip
sudo -H pip3 install --upgrade pandas numpy scipy seaborn 
sudo -H pip3 install -U scikit-learn

usage: bubble_chart.py [-h] [-im_format {png,pdf,ps,eps,svg,tif,jpg}]
                       [--im_res dpi]
                       filename

positional arguments:
  filename              Input file dataframe i.e abundances profile

optional arguments:
  -h, --help            show this help message and exit
  -im_format {png,pdf,ps,eps,svg,tif,jpg}, -f {png,pdf,ps,eps,svg,tif,jpg}
                        Output format for images [png].
  --im_res dpi, -r dpi  Output resolution for images in dot per inch (dpi)
                        [dpi].

 python3 bubble_chart.py  data_bubbleplot.tab -f  png -r 300

python3 heatmap.py -h

usage: heatmap.py [-h] [-f {png,pdf,ps,eps,svg,tif,jpg}] [-r dpi] filename

 This script create a cluster map

positional arguments:
  filename              Input file derived mebs_output with classification

optional arguments:
  -h, --help            show this help message and exit
  -f {png,pdf,ps,eps,svg,tif,jpg}, --im_format {png,pdf,ps,eps,svg,tif,jpg}
                        Output format for images [png].
  -r dpi, --im_res dpi  Output resolution for images in dot per inch (dpi)
                        [dpi].

Example:
    $  python3 heatmap.py data.heatmap.tsv

usage: hist.py [-h] [-im_format {png,pdf,ps,eps,svg,tif,jpg}] [--im_res dpi]
               filename

positional arguments:
  filename              lenght file

optional arguments:
  -h, --help            show this help message and exit
  -im_format {png,pdf,ps,eps,svg,tif,jpg}, -f {png,pdf,ps,eps,svg,tif,jpg}
                        Output format for images [pdf].
  --im_res dpi, -r dpi  Output resolution for images in dot per inch (dpi)
                        [dpi].

Example:
$  python3 histplot.py  sample.lenght tab

perl Replace_tree_names.pl mapping_file tree > renamed_tree

pip3 install biopython

for i in *.fa; do seqkit stat $i  >> stats; done
for i in *.fa ; do perl gc.pl $i >$i.gc.tab ; done

#Sum the scaffold GC and get the average 

for i in *.tab; do awk '{sum+= $2; n++ } END { if (n > 0) print sum / n; }' $i > $i.GC.average ; done
 

cat file.fa | awk '$0 ~ ">" {if (NR > 1) {print c;} c=0;printf substr($0,2,100) "\t"; } $0 !~ ">" {c+=length($0);} END { print c; }' 

awk '$0 ~ ">" {if (NR > 1) {print c;} c=0;printf substr($0,2,100) "\t"; } $0 !~ ">" {c+=length($0);} END { print c; }' file.fa

seqkit fx2tab --length --name --header-line file.fa >> file.lenght 

samtools faidx file.fa  |  cut -f1-2 file.fa.fai > file.lenght.tab

grep -c ">" *.faa  | sed 's/:/\t/g' | cut -f 2 | Rscript -e 'data=abs(scan(file="stdin")); png("seq.png"); hist(data,xlab="secuences")'

scaffold_142207_c1_687
scaffold_98552_c1_471
scaffold_70258_c1_330
scaffold_155515_c1_771

python3 remove_sequences.py file.fa sequence_to_remove.txt > file_filtered.fa 

awk 'BEGIN{while((getline<"sequence_to_remove.txt")>0)l[">"$1]=1}/^>/{f=!l[$1]}f' file.fa > file_filtered.fa

grep -v -f sequence_to_remove.txt file.fa  > file_filtered.fa 

pullseq -i file.fa -n  sequences_to_extract.txt > extracted_sequences.fa

cat sequences_to_extract.txt  | xargs -n 1 samtools faidx file.fa >> extracted_sequences.fa 

sreformat fasta file.fa > file.reformat.fna
bedtools getfasta -fi file.reformat.fna -bed sequences_to_extract_coordinates.tab -fo file_out.fa

head identifiers.txt

PF13243
PF13249
PF02458

cat identifieres.txt | while read  pfam; do
desc=$(curl http://pfam.xfam.org/family/"$pfam"/desc | head -1);
printf "$pfam\t";
printf "$desc\n";
done 2> /dev/null \
> identifiers.desc.tab

paste <(awk '{print $1}' file1.txt ) <(awk '{print $2}' file2.txt ) > file3.txt

for next in $(cat ftp_GCA_download.txt); do wget  "$next"; done

or you can do wget -i ftp_GCA_download.txt

awk 'x[$1]++ == 1 { print $1 " is duplicated"}'

cut -f2,3 file1.txt > file2.txt

sed '/pattern/ s/^/replace_pattern/' file.txt

sed 's/pattern/replace_pattern/2' file.txt

sed 's/\s.*$//' file.fa > file2.fa

awk '{if (!$2) {print $1,"YourWords"} else {print $1, $2}}'  > file.tsv

wget http://ftp.ncbi.nlm.nih.gov/genomes/genbank/assembly_summary_genbank.txt

awk -F "\t" '$12=="Complete Genome" && $11=="latest"{print $20}' assembly_summary_genbank.txt

 alias server_jupyter='ssh -p XX  -L 8000:localhost:8888 user@XXX.X.XXX. XXX'

#Create an environment in which you can add Entrez Direct
conda create --name entrez

#Activate this new environment
conda activate entrez

#Install Entrez
conda install -c bioconda entrez-direct

#Compile a list of Accession numbers from NCBI (PROTEINS)

less list.txt

ABO08866.1
AFA39020.1
AFA39042.1
AFI78392.1
AOQ24367.1
APC08827.1
ATY72478.1

#Change file to comma separated instead of column
cat list.txt | tr "\n" "," | sed 's/,$//' > list.csv 

less list.csv 

ABO08866.1,AFA39020.1,AFA39042.1,AFI78392.1,AOQ24367.1,APC08827.1,ATY72478.1

#Make a usable script from the list

sed 's/^/efetch -db protein -format fasta -id /' list.csv > list.sh

less list.sh

efetch -db protein -format fasta -id ABO08866.1,AFA39020.1,AFA39042.1,AFI78392.1,AOQ24367.1,APC08827.1,ATY72478.1

#Run the new script
bash list.sh > list.fa

env_name=mapping_env; conda create -n $env_name && \
conda activate $env_name && \
conda install -c bioconda bwa=0.7.17 samtools=1.9 && \
echo "SUCCESS"

#index assembly we want to map to
#combined FASTA containing multiple MAGs in this case
bwa index genomes_combined.fna

#see the available parameters
bash bwa_bam_map.sh -h

#assembly we want to map to
#we can map to a combined FASTA containing multiple MAGs in this case
genomes_combined.fna

#reads we want to map
Meg22_1012.fastq.gz

#you can assign an identifier for the run with -s, the output bam and bam index filenames will contain this string

#ensure -b and -k (number of threads for bwa and samtools) do not exceed the number displayed with nproc

bash bwa_bam_map.sh -i genomes_combined.fna -r Meg22_1012.fastq.gz -o read_mapping_output_dir -s genomes_combined-Meg22_1012 -b 40 -k 40 -t /home/profile/tmp -e read_mapping_output_dir/error

bash bam_check.sh -b <directory with BAM files> -o <output directory> -j <number of parallel tests> -n <pattern of BAMs, e.g. Meg22*.bam . Omitting this will analyze all files ending with .bam in the directory>