readme updated

Author: jaebeom-kim

README.md

@@ -143,7 +143,8 @@ Downloaded files are stored in `OUTDIR/DB_NAME` directory, which can be provided
 ---
 
 ## Classification
-> [!NOTE] We commend running software like `fastp` or `fastplong` to remove adapters and low-quality reads before classification. 
+> [!NOTE] 
+> We commend running software like `fastp` or `fastplong` to remove adapters and low-quality reads before classification. 
 ```
 metabuli classify <i:FASTA/Q> <i:DBDIR> <o:OUTDIR> <Job ID> [options]
 - INPUT : FASTA/Q file of reads you want to classify. (gzip supported)
@@ -243,13 +244,15 @@ metabuli classifiedRefiner <i:read-by-read classification> <i:DBDIR> [options]
 
 * Options
    --threads : The number of threads to utilize (all by default)
+   --min-score : Remove classifications with score below this value
    --remove-unclassified : Remove unclassified reads
-   --exclude-taxid : Remove list of taxids as well as its children (e.g., 1758,9685,1234)
-   --select-taxid : Select list of taxids as well as its children (e.g., 1758,9685,1234)
+   --exclude-taxid : Remove list of taxids as well as its children (e.g., 1758,9685)
+   --select-taxid : Select list of taxids as well as its children (e.g., 1758,9685)
    --select-columns : Select list of columns with number and handle full lineage as 7 (generated if absent) (e.g., 2,5,7,3)
-   --report : Write report of refined classification file
+   --report : Write report of refined classification results
    --rank : Adjust classification to the specified rank
-   --rank-file-type : Choose how to handle reads assigned to higher taxonomic ranks when using the --rank option. [0: exclude higher rank, 1: include higher rank, 2: make separate file for higher rank classification]
+   --rank-file-type : Choose how to handle classifications at higher ranks when using --rank option. 
+        [0: exclude them, 1: include them, 2: make separate file for them]
 
 ```
 #### Output

src/commons/LocalParameters.cpp

@@ -633,6 +633,7 @@ LocalParameters::LocalParameters() :
     classifiedRefiner.push_back(&RANK);
     classifiedRefiner.push_back(&HIGHER_RANK_FILE);
     classifiedRefiner.push_back(&PARAM_THREADS);
+    classifiedRefiner.push_back(&MIN_SCORE);
 
 
 }

src/util/classifiedRefiner.cpp

@@ -48,8 +48,20 @@ ClassificationResult parseFields(const std::vector<std::string>& fields) {
     return result;
 }
 
+void classifiedRefinerDefault(LocalParameters & par){
+    par.removeUnclassified = false;
+    par.excludeTaxid = "";
+    par.selectTaxid = "";
+    par.selectColumns = "";
+    par.report = false;
+    par.rank = "";
+    par.higherRankFile = 0;
+    par.minScore = 0.0;
+}
+
 int classifiedRefiner(int argc, const char **argv, const Command &command) {
     LocalParameters &par = LocalParameters::getLocalInstance();
+    classifiedRefinerDefault(par);
     par.parseParameters(argc, argv, command, true, Parameters::PARSE_ALLOW_EMPTY, 0);
     const string &classifiedFile = par.filenames[0];
     const string &taxonomyDir = par.filenames[1];
@@ -72,7 +84,7 @@ int classifiedRefiner(int argc, const char **argv, const Command &command) {
 
 int classifiedRefiner(const string &classifiedFile, const string&taxonomyDir, const LocalParameters &par) {
     #ifdef OPENMP
-    omp_set_num_threads(par.threads);
+        omp_set_num_threads(par.threads);
     #endif
 
     const string & nodesFile = taxonomyDir + "/nodes.dmp";
@@ -303,7 +315,8 @@ int classifiedRefiner(const string &classifiedFile, const string&taxonomyDir, co
                     // remove unclassified
                     if (!(par.removeUnclassified == true && data.isClassified == false) &&
                         !(contamsTaxIds.size() > 0 && checktaxId(taxonomy, contamsTaxIds, data.taxonomyId)) &&
-                        !(targetsTaxIds.size() > 0 && !checktaxId(taxonomy, targetsTaxIds, data.taxonomyId))) {
+                        !(targetsTaxIds.size() > 0 && !checktaxId(taxonomy, targetsTaxIds, data.taxonomyId)) && 
+                        !(data.isClassified == true && par.minScore > data.dnaIdentityScore)) { 
 
                         stringstream ss;
                         stringstream tt;