conda install -c conda-forge -c bioconda plasmidid

plasmidID \
-1 SAMPLE_R1.fastq.gz  \
-2 SAMPLE_R2.fastq.gz \
-d YYYY-MM-DD_plasmids.fasta \
-c SAMPLE_assembled_contigs.fasta \
--no-trim \
-s SAMPLE

plasmidID \
-d YYYY-MM-DD_plasmids.fasta \
-c SAMPLE_contigs.fasta \
-s SAMPLE

plasmidID \
-d YYYY-MM-DD_plasmids.fasta \
-c SAMPLE_assembled_contigs.fasta \
-a annotation_file \
-s SAMPLE

summary_report_pid.py -i NO_GROUP/

usage : plasmidID <-1 R1> <-2 R2> <-d database(fasta)> <-s sample_name> [-g group_name] [options]

	Mandatory input data:
	-1 | --R1	<filename>	reads corresponding to paired-end R1 (mandatory)
	-2 | --R2	<filename>	reads corresponding to paired-end R2 (mandatory)
	-d | --database	<filename>	database to map and reconstruct (mandatory)
	-s | --sample	<string>	sample name (mandatory), less than 37 characters

	Optional input data:
	-g | --group	<string>	group name (optional). If unset, samples will be gathered in NO_GROUP group
	-c | --contigs	<filename>	file with contigs. If supplied, plasmidID will not assembly reads
	-a | --annotate <filename>	file with configuration file for specific annotation
	-o 		<output_dir>	output directory, by default is the current directory

	Pipeline options:
	--explore	Relaxes default parameters to find less reliable relationships within data supplied and database
	--only-reconstruct	Database supplied will not be filtered and all sequences will be used as scaffold
						This option does not require R1 and R2, instead a contig file can be supplied
	-w 			Undo winner takes it all algorithm when clustering by kmer - QUICKER MODE
	Trimming:
	--trimmomatic-directory Indicate directory holding trimmomatic .jar executable
	--no-trim	Reads supplied will not be quality trimmed

	Coverage and Clustering:
	-C | --coverage-cutoff	<int>	minimun coverage percentage to select a plasmid as scafold (0-100), default 80
	-S | --coverage-summary	<int>	minimun coverage percentage to include plasmids in summary image (0-100), default 90
	-f | --cluster	<int>	kmer identity to cluster plasmids into the same representative sequence (0 means identical) 		(0-1), default 0.5
	-k | --kmer	<int>	identity to filter plasmids from the database with kmer approach (0-1), default 0.95

	Contig local alignment
	-i | --alignment-identity <int>	minimun identity percentage aligned for a contig to annotate, default 90
	-l | --alignment-percentage <int>	minimun length percentage aligned for a contig to annotate, default 20
	-L | --length-total	<int>	minimun alignment length to filter blast analysis
	--extend-annotation <int>	look for annotation over regions with no homology found (base pairs), default 500bp

	Draw images:
	--config-directory <dir>	directory holding config files, default config_files/
	--config-file-individual <file-name> file name of the individual file used to reconstruct
	Additional options:

	-M | --memory	<int>	max memory allowed to use
	-T | --threads	<int>	number of threads
	-v | --version		version
	-h | --help		display usage message

example: ./plasmidID.sh -1 ecoli_R1.fastq.gz -2 ecoli_R2.fastq.gz -d database.fasta -s ECO_553 -G ENTERO
	./plasmidID.sh -1 ecoli_R1.fastq.gz -2 ecoli_R2.fastq.gz -d PacBio_sample.fasta -c scaffolds.fasta -C 60 -s ECO_60 -G ENTERO --no-trim

docker run -v $PWD:$PWD -w $PWD buisciii/plasmidid plasmidID.sh \
     -1 file_R1.fastq.gz  \
     -2 file_R2.fastq.gz \
     -d database.fasta \
     -c contigs.fasta \
     --trimmomatic-directory /scif/apps/trimmomatic/Trimmomatic-0.38 \
     -s KPN