motifDataset.h

/**************************************************************************
 * Copyright (c) 2005-2011 T. M. Murali                                   *
 * Copyright (c) 2008-2011 Naveed Massjouni                               *
 * Copyright (c) 2004 Greg Grothaus                                       *
 *                                                                        *
 * This file is part of Biorithm.                                         *
 *                                                                        *
 * Biorithm is free software: you can redistribute it and/or modify       *
 * it under the terms of the GNU General Public License as published by   *
 * the Free Software Foundation, either version 3 of the License, or      *
 * (at your option) any later version.                                    *
 *                                                                        *
 * Biorithm is distributed in the hope that it will be useful,            *
 * but WITHOUT ANY WARRANTY; without even the implied warranty of         *
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the          *
 * GNU General Public License for more details.                           *
 *                                                                        *
 * You should have received a copy of the GNU General Public License      *
 * along with Biorithm.  If not, see <http://www.gnu.org/licenses/>.      *
 *                                                                        *
 **************************************************************************/

#ifndef MOTIFDATASETGREG
#define MOTIFDATASETGREG

#include<iostream>
#include<map>
#include<set>
#include<string>
#include<vector>

#include "setTemplates.C"
using namespace std;

class ProbeInfo
{
private:
  string _probeId;
  string _symbol;
  string _description;
public:
  ProbeInfo()
    {}
  
  ProbeInfo(string i, string s, string d)
      : _probeId(i), _symbol(s), _description(d)
    {
      if ("" == _probeId)
        {
          cerr << "Probe info cannot have an empty string as the probe ID." << endl;
          exit(-1);
        }
    }
  virtual ~ProbeInfo()
    {}

  string getDescription() const
    {
      return(_description);
    }

  string getSymbol() const
    {
      return(_symbol);
    }

  string getURL(string stub) const
    {
      if ("" != _symbol)
        return(stub + _symbol);
      return(stub + _probeId);
    }
};
  


class motifDataset
{
public:
  virtual vector<vector<int> >* classToExperiments() = 0;
  virtual vector<vector<int> >* experimentsToClass() = 0;
//              virtual vector<string>* classes() const = 0;

  virtual string computeClassNameForSamples(const set< int > &columnSet, double frac = 1) const = 0;
  
  virtual int computeClassIndexForSamples(const set< int > &columnSet, double frac = 1) const = 0;
  
  virtual string getClassNameForSample(unsigned int index) const = 0;

  virtual unsigned int getClassIndexForSample(unsigned int index) const = 0;
  
  virtual string getClassName(unsigned int index) const = 0;

  virtual unsigned int getClassSize(unsigned int index) const = 0;

  virtual unsigned int getNumClasses() const = 0;  
  
  virtual vector<string>* probes() = 0;
  virtual vector<string>* samples() = 0;
  virtual double operator()(int,int) = 0;
  virtual double operator()(string,string) = 0;

  virtual bool exists(int,int) = 0;
  virtual bool exists(string,string) = 0;

  virtual int getColumnIndex(string name) const = 0;

  virtual void getRowAliases(string name, set< string >& aliases) const;

  virtual void getRowAliases(const set< string > & names, set< string >& aliases)
    const;

  virtual void getRowsForAlias(string otherName, set< string > &rows) const;
  
  virtual int getRowIndex(string name) const = 0;

  virtual string getRowName(unsigned int index) const = 0;

  virtual bool isAlias(string probe, string alias) const;

  virtual bool isProbe(string id) const = 0;

  virtual void readProbeAliases(string aliasFile) = 0;

  bool getProbeInfo(string probeId, ProbeInfo &info) const;
  
  
  virtual void readProbeInfo(string infoFile) = 0;

  virtual string getProbeURL() const
    {
      return(_probeURL);
    }
  
  virtual void setProbeURL(string url)
    {
      _probeURL = url;
    }


protected:

  // probe aliases.
  map< string, set < string > > _probesToAliases;
  map< string, set < string > > _aliasesToProbes;

  // probe info
  map< string, ProbeInfo > _probesToInfo;

  string _probeURL;
  
  void _addAlias(string probe, string alias)
    {
      _probesToAliases[probe].insert(alias);
      _aliasesToProbes[alias].insert(probe);
    }

  void _addInfo(string probe, string symbol, string name)
    {
      _probesToInfo[probe] = ProbeInfo(probe, symbol, name);
    }

  
};




#endif