# get a local copy of source code
git clone --recursive https://github.com/GATB/rconnector.git

# compile the code an run a simple test on your computer
cd rconnector
sh INSTALL

Usage: sh short_read_connector_counter.sh index -b read_file -i dumped_index_name [OPTIONS]
   -b read_files for bank
     Example: -b data/c1.fasta.gz
   -i <string>. File of the index file to be created. Example "my_index.dumped"
   -k <int> value (<32). Set the length of used kmers. Must fit the compiled value. Default=31
   -f <int> value. Fingerprint size. Size of the key associated to each indexed value, limiting false positives. Default=12
   -G <int> value. gamma value. MPHF expert users parameter - Default=2
   -a <int> kmer_abundance_min (kmer from bank seen less than this value both in the bank are not indexed). Default=2
   -l Keep low complexity regions (default false)
   -t <int> number of thread used. Default=0 (all)

Usage: sh short_read_connector_counter.sh query -i indexed_file -q read_file_of_files [OPTIONS]
MANDATORY:
 -i index created by short_read_connector_counter.sh index (read only)
   Example: -i my_index.dumped
 -q read_file_of_files for query
   Example: -q data/fof.txt (with fof being a file of file descriptor)
OPTIONS:
   -w <int> window_size. See option -s. If the windows size is zero (default value), then the full read is considered. Default=0
   -s <int> kmer_threshold: Minimal percentage of shared kmer span for considering a query read as similar to a data set.  
            The kmer span is the number of bases from the read query covered by a kmer shared with the bank.
   -l Keep low complexity regions (default false)
            If a read of length 80 has a kmer-span of 60, then the percentage of shared kmer span is 75%. If a least a windows (of size "windows_size") contains at least kmer_threshold percent of positions covered by shared kmers, the read is output.
   -p <string> prefix. All out files will start with this prefix. Default="short_read_connector_res"
   -t <int> number of thread used. Default=0 (all)

 #query_read_id (from bank data/c2.fasta.gz) mean median min max percentage_shared_positions -- number of shared 31mers with banq my_counter_index.dumped
0 3.614286 4 2 5 100.000000

# First index the kmers from data/c1.fasta.gz:
sh ./short_read_connector_linker.sh index -b data/c1.fasta.gz -i my_linker_index.dumped

# Once indexation is made once, multiple queries may be performed as: 
ls data/c2.fasta.gz > fof.txt # creates a file of files, check the section "Input read sets" for details
sh ./short_read_connector_linker.sh query -i my_linker_index.dumped -q fof.txt  

cat short_read_connector_res.txt #to check the results

Usage: sh short_read_connector_linker.sh index -b read_file  -i dumped_index_name [OPTIONS]
   -b read_files for bank
     Example: -b data/c1.fasta.gz
   -i <string>. File of the index file to be created. Example "my_index.dumped"
   -k <int> value (<32). Set the length of used kmers. Must fit the compiled value. Default=31
   -f <int> value. Fingerprint size. Size of the key associated to each indexed value, limiting false positives. Default=12
   -G <int> value. gamma value. MPHF expert users parameter - Default=2
   -a <int> kmer_abundance_min (kmer from bank seen less than this value both in the bank are not indexed). Default=2
   -l Keep low complexity regions (default false)
   -t <int> number of thread used. Default=0 (all)

Usage: sh short_read_connector_linker.sh query -i indexed_file -q read_file_of_files [OPTIONS]
MANDATORY:
 -i index created by short_read_connector_linker.sh index (read only)
   Example: -i my_index.dumped
 -q read_file_of_files for query
   Example: -q data/fof.txt (with fof being a file of file descriptor)
OPTIONS:
   -w <int> window_size. See option -s. If the windows size is zero (default value), then the full read is considered. Default=0
   -s <int> kmer_threshold: Minimal percentage of shared kmer span for considering 2 reads as similar.  
            The kmer span is the number of bases from the read query covered by a kmer shared with the target read.
            If a read of length 80 has a kmer-span of 60 with another read (of unkonwn size) from the bank, then the percentage of shared kmer span is 75%. If a least a windows (of size "windows_size") contains at least kmer_threshold percent of position covered by shared kmers, the read couple is output.
                 TRICK: with kmer_threshold<=0 a single kmer is sufficient in the linker mode to link two reads. 
   -l Keep low complexity regions (default false)
   -p <string> prefix. All out files will start with this prefix. Default="short_read_connector_res"
   -t <int> number of thread used. Default=0 (all)
   -r do not output precision about pair of similar reads. Only ids of reads from queries similar to at least one read from bank are output.

#query_read_id [target_read_id-kmer_span (k=31)-kmer_span query_percentage]* or U (unvalid read, containing not only ACGT characters or low complexity read)
#Target read set: my_linker_index.dumped
#Query read set number data/c2.fasta.gz
0:675-93-93.000000 808-89-89.000000

 with fof_reads.txt:

 * reads_R1.fq.gz
 * reads_R2.fq.gz

fof.txt:

reads1.fq.gz

reads2.fq.gz

fof.txt:

fof_reads1.txt

fof_reads2.txt

reads1_R1.fq.gz
reads1_R2.fq.gz

reads1_R1.fq.gz
reads1_R2.fq.gz