src/seekdataset.h

/*****************************************************************************
* This file is provided under the Creative Commons Attribution 3.0 license.
*
* You are free to share, copy, distribute, transmit, or adapt this work
* PROVIDED THAT you attribute the work to the authors listed below.
* For more information, please see the following web page:
* http://creativecommons.org/licenses/by/3.0/
*
* This file is a component of the Sleipnir library for functional genomics,
* authored by:
* Curtis Huttenhower (chuttenh@princeton.edu)
* Mark Schroeder
* Maria D. Chikina
* Olga G. Troyanskaya (ogt@princeton.edu, primary contact)
*
* If you use this library, the included executable tools, or any related
* code in your work, please cite the following publication:
* Curtis Huttenhower, Mark Schroeder, Maria D. Chikina, and
* Olga G. Troyanskaya.
* "The Sleipnir library for computational functional genomics"
*****************************************************************************/
#ifndef SEEKDATASET_H
#define SEEKDATASET_H

#include "seekbasic.h"
#include "seekmap.h"
#include "datapair.h"
#include "seekplatform.h"

namespace Sleipnir {

class CSeekDBSetting{
public:
    CSeekDBSetting(const string &gvar,
        const string &sinfo, const string &plat,
        const string &prep, const string &db,
        const string &gene, const string &quant,
        const string &dset, const utype &numDB){
        m_gvarDirectory = gvar;
        m_sinfoDirectory = sinfo;
        m_platformDirectory = plat;
        m_prepDirectory = prep;
        m_dbDirectory = db;
        m_geneMapFile = gene;
        m_quantFile = quant;
        m_dsetFile = dset;
        m_numDB = numDB;
    }
    CSeekDBSetting(const char *gvar,
        const char* sinfo, const char* plat,
        const char* prep, const char* db,
        const char* gene, const char* quant,
        const char* dset, const utype &numDB){
        m_gvarDirectory = gvar;
        m_sinfoDirectory = sinfo;
        m_platformDirectory = plat;
        m_prepDirectory = prep;
        m_dbDirectory = db;
        m_geneMapFile = gene;
        m_quantFile = quant;
        m_dsetFile = dset;
        m_numDB = numDB;
    }

    ~CSeekDBSetting(){
    }

    string GetValue(const string &str){
        if(str=="gene")
            return m_geneMapFile;
        else if(str=="dset")
            return m_dsetFile;
        else if(str=="quant")
            return m_quantFile;
        else if(str=="gvar")
            return m_gvarDirectory;
        else if(str=="sinfo")
            return m_sinfoDirectory;
        else if(str=="db")
            return m_dbDirectory;
        else if(str=="prep")
            return m_prepDirectory;
        else if(str=="platform")
            return m_platformDirectory;
        else
            return "NULL";
    }

    utype GetNumDB(){
        return m_numDB;
    }

private:
    string m_gvarDirectory;
    string m_sinfoDirectory;
    string m_platformDirectory;
    string m_prepDirectory;
    string m_dbDirectory;
    string m_geneMapFile;
    string m_quantFile;
    string m_dsetFile;
    utype m_numDB;
};



class CSeekDataset{
public:

    enum DistanceMeasure{
        CORRELATION = 0, 
        Z_SCORE = CORRELATION + 1 
    };

    CSeekDataset();

    ~CSeekDataset();

    bool ReadDatasetAverageStdev(const string &);

    bool ReadGeneAverage(const string &);

    bool ReadGeneVariance(const string &);

    bool ReadGenePresence(const string &);

    bool InitializeGeneMap();

    bool InitializeQuery(const vector<utype> &);

    bool InitializeQueryBlock(const vector<utype> &);

    bool DeleteQuery();

    bool DeleteQueryBlock();

    bool InitializeDataMatrix(utype**, const vector<float> &,
        const utype&, const utype&, const bool=true, 
        const bool=false, const bool=false,
        const enum DistanceMeasure=Z_SCORE,
        const float cutoff=-1.0*CMeta::GetNaN(), 
        const bool=false, gsl_rng *rand=NULL);

    bool Copy(CSeekDataset *);

    utype** GetDataMatrix();

    unsigned char** GetMatrix();

    CSeekIntIntMap* GetGeneMap();

    CSeekIntIntMap* GetDBMap();

    CSeekIntIntMap* GetQueryMap();

    const vector<utype>& GetQuery() const;

    const vector<utype>& GetQueryIndex() const;

    float GetGeneVariance(const utype&) const;
    float GetGeneAverage(const utype&) const;
    float GetDatasetAverage() const;
    float GetDatasetStdev() const;
    utype GetNumGenes() const;

    bool InitializeCVWeight(const utype&);

    bool SetCVWeight(const utype&, const float&);

    float GetCVWeight(const utype&);

    const vector<float>& GetCVWeight() const;

    float GetDatasetSumWeight();

    void SetPlatform(CSeekPlatform &);
    CSeekPlatform& GetPlatform() const;

private:
    CSeekPlatform *platform;
    vector<float> geneAverage;
    vector<float> geneVariance;
    vector<char> genePresence;
    CSeekIntIntMap *geneMap;

    /* previously known as sinfo file */
    float m_fDsetAverage;
    float m_fDsetStdev;

    CSeekIntIntMap *dbMap;
    CSeekIntIntMap *queryMap;
    vector<utype> query;
    vector<utype> queryIndex;

    utype iQuerySize;
    utype iNumGenes;
    utype iDBSize;

    vector<float> weight;

    utype **rData;
    unsigned char **r;

    float sum_weight;
    bool m_bIsNibble;
};



}
#endif