input_data.h

Go to the documentation of this file.

//
// common.h:
// Manage common types, parameters, and functions
 
#ifndef INPUT_DATA_H
#define INPUT_DATA_H
 
#include "fasta_query.h"
 
#include <string>
#include <vector>
// #include <map>
#include <map>
#include <unordered_map>
#include <mutex>
 
// Type definition for B-allele population frequency map (chr -> pos -> pfb)
// using PFBMap = std::unordered_map<std::string, std::map<int, double>>;
 
class InputData {
    public:
        InputData();
 
        void printParameters() const;
 
        std::string getLongReadBam() const;
 
        void setLongReadBam(std::string filepath);
 
        // Set the filepath to the HMM parameters.
        void setHMMFilepath(std::string filepath);
        std::string getHMMFilepath() const;
 
        // Set the filepath to the reference genome FASTA file.
        void setRefGenome(std::string filepath);
        std::string getRefGenome() const;
 
        // Set the filepath to the text file containing the locations of the
        // VCF files with population frequencies for each chromosome.
        void setAlleleFreqFilepaths(std::string filepath);
        std::string getAlleleFreqFilepath(std::string chr) const;
 
        // Set the filepath to the VCF file with SNP calls used for CNV
        // detection with the HMM.
        void setSNPFilepath(std::string filepath);
        std::string getSNPFilepath() const;
 
        // Set the ethnicity for SNP population frequencies.
        void setEthnicity(std::string ethnicity);
        std::string getEthnicity() const;
 
        // Set the assembly gaps file.
        void setAssemblyGaps(std::string filepath);
        std::string getAssemblyGaps() const;
 
        // Set/get a target chromosome for single-chromosome analysis.
        void setChromosome(std::string chr);
        std::string getChromosome() const;
 
        // Set the epsilon parameter for DBSCAN clustering.
        void setDBSCAN_Epsilon(double epsilon);
        double getDBSCAN_Epsilon() const;
 
        // Set the percentage of mean chromosome coverage to use for DBSCAN
        // minimum points.
        void setDBSCAN_MinPtsPct(double min_pts_pct);
        double getDBSCAN_MinPtsPct() const;
 
        // Set the output directory where the results will be written.
        void setOutputDir(std::string dirpath);
        std::string getOutputDir() const;
 
        // Set the number of threads to use when parallelization is possible.
        void setThreadCount(int thread_count);
        int getThreadCount() const;
 
        // Set the verbose flag to true if verbose output is desired.
        void setVerbose(bool verbose);
        bool getVerbose();
 
        // Set whether to extend the SNP CNV regions around the SV breakpoints
        // (+/- 1/2 SV length), save a TSV file, and generate HTML reports.
        void saveCNVData(bool save_cnv_data);
        bool getSaveCNVData() const;
 
        void setCNVOutputFile(std::string filepath);
        std::string getCNVOutputFile() const;
        
    private:
        std::string long_read_bam;
        std::string ref_filepath;
        std::string snp_vcf_filepath;
        std::string ethnicity;
        std::unordered_map<std::string, std::string> pfb_filepaths;  // Map of population frequency VCF filepaths by chromosome
        std::string output_dir;
        int min_reads;
        double dbscan_epsilon;
        double dbscan_min_pts_pct;
        std::string chr;  // Chromosome to analyze
        std::pair<int32_t, int32_t> start_end;  // Region to analyze
        int thread_count;
        std::string hmm_filepath;
        std::string cnv_filepath;
        std::string assembly_gaps;  // Assembly gaps file
        bool verbose;  // True if verbose output is enabled
        bool save_cnv_data;  // True if SNP CNV regions should be extended around SV breakpoints, and saved to a TSV file (Large performance hit)
        bool single_chr;
        std::string cnv_output_file;
};
 
#endif // INPUT_DATA_H