update README and change KMER to k-mer

README.md

@@ -1,14 +1,14 @@
 # UniqueKMER
-Generate unique KMERs for every contig in a FASTA file.  
+Generate unique k-mers for every contig in a FASTA file.  
 
-Unique KMER is consisted of KMER keys (i.e. ATCGATCCTTAAGG) that are only presented in one contig, but not presented in any other contigs (for both forward and reverse strands).  
+Unique k-mer is consisted of k-mer keys (i.e. ATCGATCCTTAAGG) that are only presented in one contig, but not presented in any other contigs (for both forward and reverse strands).  
 
-This tool accepts the input of a FASTA file consisting of many contigs, and extract unique KMERs for each contig.
+This tool accepts the input of a FASTA file consisting of many contigs, and extract unique k-mers for each contig.
 
-The output unique KMER file and Genome file can be used for fastv: https://github.com/OpenGene/fastv, which is an ultra-fast tool to identify and visualize microbial sequences from sequencing data.
+The output unique k-mer file and Genome file can be used for fastv: https://github.com/OpenGene/fastv, which is an ultra-fast tool to identify and visualize microbial sequences from sequencing data.
 
 # what does UniqueKMER output?
-This tool outputs a folder (folder name can be specified by `-o/--outdir`), which contains a `index.html` and a subfolder `genomes_kmers`. The subfolder `genomes_kmers` contains a KMER file and a Genome file for each contig, both in FASTA format. You can open the `index.html` with any browser, then click on the contig names to find its KMER file and Genome file.
+This tool outputs a folder (folder name can be specified by `-o/--outdir`), which contains a `index.html` and a subfolder `genomes_kmers`. The subfolder `genomes_kmers` contains a k-mer file and a Genome file for each contig, both in FASTA format. You can open the `index.html` with any browser, then click on the contig names to find its k-mer file and Genome file.
 * a small example: http://opengene.org/uniquekmer/test/index.html. This is generated by a small FASTA (http://opengene.org/test.fasta)
 * a big example: http://opengene.org/uniquekmer/virus/index.html. This is generated by a big FASTA (http://opengene.org/viral.genomic.fasta) containing all NCBI complete RefSeq release of viral sequences, which can be found from https://ftp.ncbi.nlm.nih.gov/refseq/release/viral/
 
@@ -27,17 +27,17 @@ uniquekmer -f test.fasta
 You can get the test.fasta from: http://opengene.org/test.fasta
 
 # more examples
-### set the KMER key length
+### set the k-mer key length
 ```shell
 # 16-mer (i.e. ATCGATCGATCGATCG...)
 uniquekmer -f test.fasta -k 16
 ```
-### filter the KMER keys that can be mapped to a reference genome (i.e. human genome)
+### filter the k-mer keys that can be mapped to a reference genome (i.e. human genome)
 ```shell
-# KMER sequences that can be mapped to hg38 with `edit distance <=2`  will be removed
+# k-mer sequences that can be mapped to hg38 with `edit distance <=2`  will be removed
 uniquekmer -f test.fasta -r hg38.fasta -e 2
 ```
-### set the spacing to avoid many continuous KMER keys
+### set the spacing to avoid many continuous k-mer keys
 ```shell
 # the spacing will be 2, which means if `key(pos)` is stored, then `key(pos+1)`  and `key(pos+2)` will be skipped
 uniquekmer -f test.fasta -s 2
@@ -47,10 +47,18 @@ options:
 ```shel
   -f, --fasta            FASTA input file name (string)
   -o, --outdir           Directory for output. Default is unique_kmers in the current directory. (string [=unique_kmers])
-  -k, --kmer             The length k of KMER (10~32), default 25 (int [=25])
+  -k, --kmer             The length k of k-mer (10~32), default 25 (int [=25])
   -s, --spacing          If a key with POS is recorded, then skip [POS+1...POS+spacing] to avoid too compact result (0~100). default 0 means no skipping. (int [=0])
   -g, --genome_limit     Process up to genome_limit genomes in the FASTA input file. Default 0 means no limit. This option is for DEBUG. (int [=0])
-  -r, --ref              Reference genome FASTA file name. Specify this only when you want to filter out the unique KMER that can be mapped to reference genome. (string [=])
-  -e, --edit_distance    KMER mapped to reference genome with edit distance <= edit_distance will be removed (0~16). 3 for default. (int [=3])
+  -r, --ref              Reference genome FASTA file name. Specify this only when you want to filter out the unique k-mer that can be mapped to reference genome. (string [=])
+  -e, --edit_distance    k-mer mapped to reference genome with edit distance <= edit_distance will be removed (0~16). 3 for default. (int [=3])
   -?, --help             print this message
 ```
+
+## get the pre-built k-mer file, genomes file or k-mer collection file for viruses
+* You can download `k-mer` files and `genomes` files of viruses from http://opengene.org/uniquekmer/viral/index.html. This is generated by extracting unique k-mers for all genomes in a big FASTA (http://opengene.org/viral.genomic.fasta), which contains all NCBI complete RefSeq release of viral sequences that can be found from https://ftp.ncbi.nlm.nih.gov/refseq/release/viral/. The k-mers that can be mapped to human reference genome (GRCh38) with `edit_distance <= 3` have already been filtered out.
+* You can download the `k-mer collection` file for viral genomes from: http://opengene.org/viral.kc.fasta.gz
+
+## get the pre-built k-mer file, genomes file or k-mer collection file for viruses and human microorganisms
+* You can download `k-mer` files and `genomes` files of viruses from http://opengene.org/uniquekmer/microbial/index.html. This is generated by extracting unique k-mers for all genomes in a big FASTA (http://opengene.org/microbial.genomic.fasta), which contains genomes for the viruses above and common human microorganisms. The k-mers that can be mapped to human reference genome (GRCh38) with `edit_distance <= 3` have already been filtered out.
+* You can download the `k-mer collection` file for viral genomes from: http://opengene.org/microbial.kc.fasta.gz

src/main.cpp

@@ -15,7 +15,7 @@ mutex logmtx;
 int main(int argc, char* argv[]){
     // display version info if no argument is given
     if(argc == 1) {
-        cerr << "UniqueKMER: Generate unique KMERs for every contig in a FASTA file." << endl << "version " << UNIQUEKMER_VER << endl;
+        cerr << "UniqueKMER: Generate unique k-mers for every contig in a FASTA file." << endl << "version " << UNIQUEKMER_VER << endl;
     }
     if (argc == 2 && strcmp(argv[1], "test")==0){
         UnitTest tester;
@@ -30,11 +30,11 @@ int main(int argc, char* argv[]){
     cmdline::parser cmd;
     cmd.add<string>("fasta", 'f', "FASTA input file name", true, "");
     cmd.add<string>("outdir", 'o', "Directory for output. Default is unique_kmers in the current directory.", false, "unique_kmers");
-    cmd.add<int>("kmer", 'k', "The length k of KMER (10~32), default 25", false, 25); 
+    cmd.add<int>("kmer", 'k', "The length k of k-mer (10~32), default 25", false, 25); 
     cmd.add<int>("spacing", 's', "If a key with POS is recorded, then skip [POS+1...POS+spacing] to avoid too compact result (0~100). default 0 means no skipping.", false, 0); 
     cmd.add<int>("genome_limit", 'g', "Process up to genome_limit genomes in the FASTA input file. Default 0 means no limit. This option is for DEBUG.", false, 0); 
-    cmd.add<string>("ref", 'r', "Reference genome FASTA file name. Specify this only when you want to filter out the unique KMER that can be mapped to reference genome.", false, "");
-    cmd.add<int>("edit_distance", 'e', "KMER mapped to reference genome with edit distance <= edit_distance will be removed (0~16). 3 for default.", false, 3);
+    cmd.add<string>("ref", 'r', "Reference genome FASTA file name. Specify this only when you want to filter out the unique k-mer that can be mapped to reference genome.", false, "");
+    cmd.add<int>("edit_distance", 'e', "k-mer mapped to reference genome with edit distance <= edit_distance will be removed (0~16). 3 for default.", false, 3);
 
     cmd.parse_check(argc, argv);
 
@@ -69,7 +69,7 @@ int main(int argc, char* argv[]){
 
     time_t t2 = time(NULL);
 
-    cerr << endl << "Please find results (index.html, KMER/Genome files) in folder: " << opt.outdir << endl;
+    cerr << endl << "Please find results (index.html, k-mer/Genome files) in folder: " << opt.outdir << endl;
     cerr << endl << command << endl;
     cerr << "uniquekmer v" << UNIQUEKMER_VER << ", time used: " << (t2)-t1 << " seconds" << endl;