Updated readme for Krona (#28)

README.md

@@ -83,11 +83,11 @@ metabuli classify --seq-mode 1 read.fna dbdir outdir jobid
    --spacing-mask : Binary patterend mask for spaced k-mer. The same mask must be used for DB creation and classification. A mask should contain at least eight '1's, and '0' means skip.
    
   * --min-score and --min-sp-score for precision mode are optimized only for short reads.
-  * We don't recommend use them for long reads.
+  * We don't recommend using them for long reads.
 ```
 
-This will generate two result files: `Job ID_classifications.tsv` and `Job ID_report.tsv`
-#### Job ID_classifications.tsv
+This will generate two result files: `JobID_classifications.tsv`, `JobID_report.tsv`, and `JobID_krona.html`.
+#### JobID_classifications.tsv
 1. Classified or not
 2. Read ID
 3. Taxonomy identifier
@@ -105,8 +105,8 @@ This will generate two result files: `Job ID_classifications.tsv` and `Job ID_re
 0       read_3     0       294     0       0       0       no rank
 ```
 
-#### Job ID_report.tsv
-Proportion of reads that are assigned to each taxon.
+#### JobID_report.tsv
+The proportion of reads that are assigned to each taxon.
 ```
 #Example
 33.73   77571   77571   0       no rank unclassified
@@ -125,6 +125,10 @@ Proportion of reads that are assigned to each taxon.
 0.01    24      24      170539  subspecies                      RS_GCF_000204275.1
 ```
 
+#### JobID_krona.html
+It is for an interactive taxonomy report (Krona). You can use any modern web browser to open `JobID_krona.html`.
+<p align="left"><img src="https://raw.githubusercontent.com/steineggerlab/Metabuli/master/.github/image.png" height="350" /></p>
+
 #### Resource requirements
 Metabuli can classify reads against a database of any size as long as the database is fits in the hard disk, regardless of the machine's RAM size.
 We tested it with a MacBook Air (2020, M1, 8 GiB), where we classified about 1.5 M paired-end 150 bp reads (~5 GiB in size) against a database built with ~23K prokaryotic genomes (~69 GiB in size)

src/commons/Classifier.cpp

@@ -1,5 +1,7 @@
 #include "Classifier.h"
 #include "LocalParameters.h"
+#include "krona_prelude.html.h"
+#include "taxonomyreport.cpp"
 #include <ctime>
 
 Classifier::Classifier(LocalParameters & par) : maskMode(par.maskMode), maskProb(par.maskProb) {
@@ -341,8 +343,9 @@ void Classifier::startClassify(const LocalParameters &par) {
     cout << "The number of matches: " << totalMatchCnt << endl;
     readClassificationFile.close();
 
+
     // Write report files
-    writeReportFile(outDir + "/" + jobId + "_report.tsv", numOfSeq, taxCounts);
+    writeReportFile(outDir, numOfSeq, taxCounts);
 
     // Memory deallocation
     free(matchBuffer.buffer);
@@ -2074,12 +2077,20 @@ void Classifier::writeReadClassification(const vector<Query> & queryList, int qu
     }
 }
 
-void Classifier::writeReportFile(const string &reportFileName, int numOfQuery, unordered_map<TaxID, unsigned int> &taxCnt) {
+void Classifier::writeReportFile(const string &outdir, int numOfQuery, unordered_map<TaxID, unsigned int> &taxCnt) {
     unordered_map<TaxID, TaxonCounts> cladeCounts = taxonomy->getCladeCounts(taxCnt);
     FILE *fp;
-    fp = fopen(reportFileName.c_str(), "w");
+    fp = fopen((outdir + + "/" + jobId + "_report.tsv").c_str(), "w");
     writeReport(fp, cladeCounts, numOfQuery);
     fclose(fp);
+
+    // Write Krona chart
+    FILE *kronaFile = fopen((outDir + "/" + jobId + "_krona.html").c_str(), "w");
+    fwrite(krona_prelude_html, krona_prelude_html_len, sizeof(char), kronaFile);
+    fprintf(kronaFile, "<node name=\"all\"><magnitude><val>%zu</val></magnitude>", numOfQuery);
+    kronaReport(kronaFile, *taxonomy, cladeCounts, numOfQuery);
+    fprintf(kronaFile, "</node></krona></div></body></html>");
+
 }
 
 void Classifier::writeReport(FILE *FP, const std::unordered_map<TaxID, TaxonCounts> &cladeCounts,