Merge branch 'master' of git+ssh://scm.gforge.inria.fr//gitroot/vidjil/vidjil

Makefile

@@ -6,15 +6,25 @@ VIDJIL_SERVER_SRC = server/
 all:
 	make -C $(VIDJIL_ALGO_SRC)
 
-test: all
-	# make -C $(VIDJIL_SERVER_SRC) tests
-	make -C $(VIDJIL_ALGO_SRC)/tests 
+test:
+	make unit
+	make should
+	# make pytests
+
+test_with_fuse:
+	make unit
 	make should
 	make pytests
 
+unit: all
+	@echo "*** Launching unit tests..."
+	make -C $(VIDJIL_ALGO_SRC)/tests 
+	@echo "*** All .should_get tests passed"
+
 pytests:
 	@echo "*** Launching python tests..."
 	python server/fuse.py --test x
+	@echo "*** All python tests passed"
 
 should: all
 	@echo

algo/Makefile

@@ -8,7 +8,7 @@ LIBCORE=core/vidjil.a
 
 BINDIR=..
 
-CREATE_VERSION_GIT_H := $(shell ./create-git-version-h.sh)
+CREATE_VERSION_GIT_H := $(shell test -x ./create-git-version-h.sh && ./create-git-version-h.sh)
 
 .PHONY: all core clean forcedep
 

algo/core/affectanalyser.h

@@ -43,6 +43,8 @@ template<class T>
 class AffectAnalyser {
  public:
 
+  virtual ~AffectAnalyser() {}
+
   /* Queries */
 
   /**

algo/core/cluster-junctions.cpp

@@ -74,9 +74,9 @@ void comp_matrix::load(string file){
 
   char* tampon=(char*)malloc(windows.size()*sizeof(char));
   ifstream in_comp(file.c_str());
-  for(int i=0; i<windows.size();i++){
+  for(unsigned int i=0; i<windows.size();i++){
     in_comp.read(tampon, windows.size()*sizeof(char));
-    for(int j=0;j<windows.size(); j++){
+    for(unsigned int j=0;j<windows.size(); j++){
 	m[i][j]=tampon[j];
       }
   }
@@ -90,7 +90,7 @@ void comp_matrix::save(string file){
   
   ofstream out_comp(file.c_str());
   
-  for(int i=0; i<windows.size();i++){
+  for(unsigned int i=0; i<windows.size();i++){
     out_comp.write((char *)m[i],windows.size()*sizeof(char));
   }
   
@@ -99,7 +99,7 @@ void comp_matrix::save(string file){
  
 
 void comp_matrix::del(){
-  for (int i=0;i<windows.size();i++){
+  for (unsigned int i=0;i<windows.size();i++){
 	free(m[i]);
   }
   free(m);
@@ -112,7 +112,6 @@ list<list<junction> >  comp_matrix::cluster(string forced_edges, int w, ostream
     
     
   typedef map<junction,list<Sequence> > mjs ;
-  typedef list<string> li ;
 
   map <string, map <string, bool> > graph ;
   

algo/core/dynprog.cpp

@@ -343,11 +343,11 @@ void DynProg::backtrack()
   linkgap = new int[x.size()+1];
   gap2 = new int[y.size()+1];
       
-  for (int i = 0; i <=x.size(); i++) {
+  for (unsigned int i = 0; i <=x.size(); i++) {
     gap1[i] = 0;
     linkgap[i] = 0;
   }
-  for (int i = 0; i <= y.size(); i++) {
+  for (unsigned int i = 0; i <= y.size(); i++) {
     gap2[i] = 0;
   }
   

algo/core/fasta.cpp

@@ -197,7 +197,7 @@ void OnlineFasta::next() {
 
     // Compute seq
     current.seq = new int[current.sequence.length()];
-    for (int i=0; i< current.sequence.length(); i++)
+    for (unsigned int i=0; i< current.sequence.length(); i++)
       {
 	current.seq[i] = nuc_to_int(current.sequence[i]) ;
       }

algo/core/lazy_msa.cpp

@@ -52,7 +52,7 @@ void LazyMsa::alignOne(string *align, int one){
   
   ostringstream stream;
     
-    for (int i=0; i<ref.size(); i++){
+    for (unsigned int i=0; i<ref.size(); i++){
       for (int j=0; j<gapRef[one][i] ; j++){
 	stream <<"-";
       }
@@ -66,7 +66,7 @@ void LazyMsa::alignOne(string *align, int one){
 
   ostringstream stream2;
     
-    for (int i=0; i<sequences[one].size(); i++){
+    for (unsigned int i=0; i<sequences[one].size(); i++){
       for (int j=0; j<gapSeq[one][i] ; j++){
 	stream2 <<"-";
       }
@@ -84,19 +84,19 @@ void LazyMsa::align(string *align){
   
   int *maxGap= new int [ref.size()+1];
   
-  for (int i = 0; i< ref.size()+1; i++){
+  for (unsigned int i = 0; i< ref.size()+1; i++){
     maxGap[i]=0;
   }
   
   for (int i=0; i<sizeUsed+1; i++){
-   for (int j=0; j<ref.size()+1; j++){
+   for (unsigned int j=0; j<ref.size()+1; j++){
      if ( gapRef[i][j] > maxGap[j] ) maxGap[j]=gapRef[i][j];
    }
   }
   
   ostringstream stream;
     
-    for (int i=0; i<ref.size(); i++){
+    for (unsigned int i=0; i<ref.size(); i++){
       for (int j=0; j<maxGap[i] ; j++){
 	stream <<"-";
       }
@@ -111,11 +111,11 @@ void LazyMsa::align(string *align){
   for (int i=0; i<sizeUsed+1; i++){
     ostringstream stream2;
   
-    for (int j = 0; j< ref.size()+1; j++){
+    for (unsigned int j = 0; j< ref.size()+1; j++){
       gapSeq[i][link[i][j]]+=maxGap[j]-gapRef[i][j];
     }
     
-    for (int j=0; j<sequences[i].size(); j++){
+    for (unsigned int j=0; j<sequences[i].size(); j++){
       for (int k=0; k<gapSeq[i][j] ; k++){
 	stream2 <<"-";
       }

algo/core/read_score.cpp

@@ -60,6 +60,7 @@ void KmerAffectReadScore::setUnknownScore(float score) {
 ////////////////////////////////////////////////////////////////////////////////
 
 ReadLengthScore::ReadLengthScore(){}
+ReadLengthScore::~ReadLengthScore(){}
 
 float ReadLengthScore::getScore(const string &sequence) const {
   return sequence.size();

algo/core/read_score.h

@@ -11,6 +11,8 @@
  */
 class VirtualReadScore {
  public:
+  virtual ~VirtualReadScore() {}
+
   /**
    * @param sequence: some text
    * @return the score associated to the sequence.
@@ -62,6 +64,7 @@ public:
 class ReadLengthScore: public VirtualReadScore {
  public:
   ReadLengthScore();
+  ~ReadLengthScore();
 
   /**
    * @return the sequence length

algo/core/segment.cpp

@@ -175,7 +175,7 @@ KmerSegmenter::KmerSegmenter(Sequence seq, IKmerStore<KmerAffect> *index,
   int s = (size_t)index->getS() ;
   int length = sequence.length() ;
 
-  if (length < (size_t) s) 
+  if (length < s) 
     {
       because = UNSEG_TOO_SHORT;
       kaa = NULL;
@@ -568,7 +568,7 @@ FineSegmenter::FineSegmenter(Sequence seq, Fasta &rep_V, Fasta &rep_J,
       // Trim J
       Jstart += b_r;
       del_J += b_r;
-        if (Jstart>=sequence.length())
+      if (Jstart>=(int) sequence.length())
 	  Jstart=sequence.length()-1;
     }
 
@@ -611,7 +611,6 @@ void FineSegmenter::FineSegmentD(Fasta &rep_V, Fasta &rep_D, Fasta &rep_J){
     int tag_D;
     int length = 0 ;
     int begin = 0;
-    int score;
     
     // Create a zone where to look for D, adding at most EXTEND_D_ZONE nucleotides at each side
     int l = Vend - EXTEND_D_ZONE;
@@ -629,7 +628,6 @@ void FineSegmenter::FineSegmentD(Fasta &rep_V, Fasta &rep_D, Fasta &rep_J){
     end = align_against_collection(str, rep_D, false, true, &tag_D, &del_D_right, &del_D_left, &begin,
 				&length, &score_D, segment_cost);
     
-    score=score_D[0].first;
     best_D = tag_D;
     
     Dstart = l + begin;

algo/core/windows.cpp

@@ -29,7 +29,7 @@ vector<int> WindowsStorage::getStatus(junction window) {
 JsonList WindowsStorage::statusToJson(junction window) {
     JsonList result;
     
-    for (int i=0; i<status_by_window[window].size(); i++){
+    for (unsigned int i=0; i<status_by_window[window].size(); i++){
         if (status_by_window[window][i] !=0){
             ostringstream oss; 
             oss << i;

algo/tests/testCluster.cpp

@@ -26,7 +26,7 @@ void testCluster() {
    map<string, string> labels;
    WindowsStorage windows = WindowsStorage(labels);
 
-   Sequence seq = {"", "", "", ""};
+   Sequence seq = {"", "", "", "", NULL};
 
    windows.add("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAT", seq, 0);
    windows.add("AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA", seq, 0);

algo/vidjil.cpp

@@ -183,8 +183,11 @@ void usage(char *progname)
        << "Limits to report a clone" << endl
        << "  -R <nb>       minimal number of reads supporting a clone (default: " << MIN_READS_CLONE << ")" << endl
        << "  -% <ratio>    minimal percentage of reads supporting a clone (default: " << RATIO_READS_CLONE << ")" << endl
-       << "  -z <nb>       maximal number of clones reported (0: no limit) (default: " << MAX_CLONES << ")" << endl
-       << "  -A            reports all clones (-r 0 -R 1 -% 0 -z 0), to be used only on very small datasets" << endl
+       << endl
+
+       << "Limits to segment a clone" << endl
+       << "  -z <nb>       maximal number of clones to be segmented (0: no limit, do not use) (default: " << MAX_CLONES << ")" << endl
+       << "  -A            reports and segments all clones (-r 0 -R 1 -% 0 -z 0), to be used only on very small datasets" << endl
        << endl
 
        << "Fine segmentation options (second pass, see warning in doc/README)" << endl
@@ -207,6 +210,9 @@ void usage(char *progname)
        << "  -v            verbose mode" << endl
        << endl        
 
+       << "The full help is available in the doc/algo.org file."
+       << endl
+
        << endl 
        << "Examples (see doc/README)" << endl
        << "  " << progname << "             -G germline/IGH             -d data/Stanford_S22.fasta" << endl
@@ -219,7 +225,7 @@ void usage(char *progname)
 
 int main (int argc, char **argv)
 {
-  cout << "# Vidjil -- V(D)J recombinations analysis <http://bioinfo.lifl.fr/vidjil>" << endl
+  cout << "# Vidjil -- V(D)J recombinations analysis <http://www.vidjil.org/>" << endl
        << "# Copyright (C) 2011, 2012, 2013, 2014 by the Vidjil team" << endl
        << "# Bonsai bioinformatics at LIFL (UMR CNRS 8022, Université Lille) and Inria Lille" << endl 
        << endl ;
@@ -1495,6 +1501,7 @@ int main (int argc, char **argv)
     delete index ;
     delete json;
     delete windowsStorage;
+    delete json_samples;
 
     if (output_segmented)
       delete out_segmented;

browser/js/database.js

@@ -72,7 +72,7 @@ Database.prototype = {
             var msg = " Welcome to Vidjil! </br>"
                     + "Your browser currently does not recognize our SSL certificate. </br>"
                     + "To use the sample database, you need to accept this certificate and/or tag this website as a trusted one. </br>"
-                    + "<a href='"+DB_ADDRESS+"' target='_blank'>Follow this link<a/>"
+                    + "<a href='"+DB_ADDRESS+"'>Follow this link<a/>"
             popupMsg(msg)
         }
     },

browser/js/main.js

@@ -7,15 +7,15 @@ var CGI_ADDRESS = "http://127.0.1.1/cgi-bin/";
 if (typeof config != 'undefined') {
     if (config.cgi_address){
         if (config.cgi_address) CGI_ADDRESS = config.cgi_address
+        if (config.cgi_address == "default") CGI_ADDRESS = "http://"+window.location.hostname+"/cgi/"
+    }
+    if (config.use_database != undefined && config.use_database) {
         if (config.db_address) { DB_ADDRESS = config.db_address}
         if (config.db_address == "default") DB_ADDRESS = "https://"+window.location.hostname+"/vidjil/"
-        if (config.cgi_address == "default") CGI_ADDRESS = "http://"+window.location.hostname+"/cgi/"
-
         var fileref=document.createElement('script')
         fileref.setAttribute("type","text/javascript")
         fileref.setAttribute("src", DB_ADDRESS + "static/js/checkSSL.js")
         document.getElementsByTagName("head")[0].appendChild(fileref)
-
     }
 
     if (config.demo && config.demo.file.length != 0){

doc/CHANGELOG

 
 This changelog concerns the algorithmic part (C++) of Vidjil.
 
-2014-09-xx  The Vidjil Team
+2014-09-23  The Vidjil Team
 	* Export cause of non-segmentation in the .data
 	* New option to output segmented reads (-U), now by default segmented reads are not output one by one
 	* Updated .data .json output (the format will change again in a next release)

doc/algo.org

@@ -78,10 +78,86 @@ browser. They are intented for a command-line use only.
 Launching vidjil with =-h= option provides the list of parameters that can be
 used.
 
+** Main algorithm parameters
+
+#+BEGIN_EXAMPLE
+Window prediction
+  (use either -s or -k option, but not both)
+  -s <string>   spaced seed used for the V/J affectation
+                (default: #####-#####, ######-######, #######-#######, depends on germline)
+  -k <int>      k-mer size used for the V/J affectation (default: 10, 12, 13, depends on germline)
+                (using -k option is equivalent to set with -s a contiguous seed with only '#' characters)
+  -w <int>      w-mer size used for the length of the extracted window (default: 40)(default with -d: 60)
+#+END_EXAMPLE
+
+The =-s= and =-k= options are the options of the heuristic. A detailed
+explanation can be found in the paper. More help on that will be
+available in the following months. The defaults values should work.
+
+The =-w= option fixes the size of the "window" that is the main
+identifier to gather clones. The defaults values (40 for TRG, 60 for
+IGH) were selected to ensure a high-quality clone gathering. The
+high-throughput heuristic predicts the center of the "window" that may
+be shifted by a few bases from the actual "center" of the CDR3 (for TRG,
+less than 15 bases compared to the IMGT/V-QUEST or IgBlast prediction
+in >99% of cases). The extracted window should be large enough to
+fully contain the CDR3 as well as some part of the end of the V and
+the start of the J to uniquely identify a clone.
+
+Setting =-w= to 30 for TRG and 50 for IGH may "segment" (analyze) a
+few more reads, but may in some rare cases falsely cluster reads from
+different clones.  Setting =-w= to lower values is not recommended.
+
+** Threshold on clone output
+
+The following options control how many clones are output and analyzed.
+
+#+BEGIN_EXAMPLE
+Limit to keep a window
+  -r <nb>       minimal number of reads containing a window (default: 10)
+
+Limits to report a clone
+  -R <nb>       minimal number of reads supporting a clone (default: 10)
+  -% <ratio>    minimal percentage of reads supporting a clone (default: 0)
+
+Limits to segment a clone
+  -z <nb>       maximal number of clones to be segmented (0: no limit, do not use) (default: 20)
+  -A            reports and segments all clones (-r 0 -R 1 -% 0 -z 0), to be used only on very small datasets
+#+END_EXAMPLE
+
+The =-r/-R/-%= options are strong thresholds: if a clone does not have
+the requested number of reads, the clone is discarded (except when
+using =-l=, see below).
+The =-r= option is applied before the additional clusterization, the
+=-R/-%= options after it.
+The default =-r 10 -R 10= options are meant to only output clones that
+have a significant read support. You can safely put =-r 1 -R 1= if you
+want to detect all clones starting from the first read (especially for
+MRD detection).
+
+The =-z= option limits the number of clones that are fully analyzed,
+/with their V(D)J segmentation/, in particular to enable the browser
+to display the clones on the grid (otherwise they are displayed on the
+'?/?' axis).
+If you want to analyze more clones, you should use =-z 50= or
+=-z 100=.  It is not recommended to use larger values: outputting more
+than 100 clones is often not useful since they can't be visualized easily
+in the browser, and takes large computation time.
+Note that even if a clone is not in the top 20 (or 50, or 100) but
+still passes the =-R=, =-%= options, it is still reported in the .data
+file. If the clone is at some MRD point in the top 20 (or 50, or 100),
+it will be fully analyzed/segmented by this other point (and then
+collected by the =fuse.py= script, and then, on the browser, correctly
+displayed on the grid).
+
+The =-A= option disables all these thresholds. This option should be
+used only for test and debug purposes, on very small datasets, and
+produce large file and takes huge computation times.
+
 ** Force to follow some sequences
 
 Vidjil allows to specify a list of windows that must be followed
-(even if those windows are 'rare', below the -r/-R/-% thresholds).
+(even if those windows are 'rare', below the =-r/-R/-%= thresholds).
 The parameter =-l= is made for providing such a list in a file following
 the following format: window label (separed by one space)
 

server/backup.sh

@@ -26,7 +26,7 @@ if [ $COMPLETE -eq 1 ]; then
         zip -r $filename web2py/applications/vidjil/uploads/ web2py/applications/vidjil/databases/
 else
         filename="${DIR}backup_essentials_"$now
-        zip -r $filename web2py/applications/vidjil/databases/ web2py/applications/vidjil/uploads/results_file* web2py/applications/vidjil/uploads/fused_file*
+        zip -r $filename web2py/applications/vidjil/databases/ web2py/applications/vidjil/uploads/results_file* web2py/applications/vidjil/uploads/fused_file* web2py/applications/vidjil/uploads/analysis_file*
 fi
 
 echo $filename

server/web2py/applications/vidjil/views/default/index.html

@@ -17,7 +17,7 @@
 <body onload="init()">
     <h4>Welcome to Vidjil !</h4>
 
-    The certificate is now validated. 
+    <!-- The certificate is now validated. -->
     <a id="browser" href="#">Go to Vidjil</a>
 
     <!--

server/web2py/applications/vidjil/views/patient/add.html

@@ -4,7 +4,12 @@
     <table>
         <tbody>
             <tr>
-                <td ><label for="patient_first_name" id="patient_first_name__label"> First Name: </label></td>
+                <td><label for="patient_id_label" id="patient_id_label__label">Patient ID: </label></td>
+                <td><input class="date" id="patient_id_label" name="id_label" type="text" value=""><span></span></td>
+                <td></td>
+            </tr>
+            <tr>
+                <td ><label for="patient_first_name" id="patient_first_name__label">First Name: </label></td>
                 <td ><input class="string" id="patient_first_name" name="first_name" type="text" value=""><span>*</span></td>
                 <td ></td>
             </tr>
@@ -18,11 +23,6 @@
                 <td><input class="date" id="patient_birth" name="birth" type="text" value=""><span>* (format: yyyy-mm-dd)</span></td>
                 <td></td>
             </tr>
-            <tr>
-                <td><label for="patient_id_label" id="patient_id_label__label">ID label </label></td>
-                <td><input class="date" id="patient_id_label" name="id_label" type="text" value=""><span>id used by hospital administration system</span></td>
-                <td></td>
-            </tr>
             <tr>
                 <td><label for="patient_info" id="patient_info__label">Info: </label></td>
                 <td><textarea class="text" cols="40" id="patient_info" name="info" rows="10"></textarea></td>