FastBQSR/src/bqsr/bqsr_args.h

/*
Description: BQSR

Copyright : All right reserved by ICT

Author : Zhang Zhonghai
Date : 2025/10/10
*/
#pragma once

#include <string>
#include <vector>

using std::string;
using std::vector;

namespace nsbqsr {
enum IndexFormat { BAI, CSI };
}  // namespace nsbqsr

/* bqsr parameters */
struct BQSRArg {
    // common parameters
    
    string INPUT_FILE;  // input bam filename

    string OUTPUT_FILE;  // output bam filename

    int NUM_THREADS = 1;

    size_t MAX_MEM = ((size_t)1) << 30;  //  // 1G

    bool DUPLEX_IO = true;  //

    /* "Whether to create an index when writing VCF or coordinate sorted BAM output.", common = true */
    bool CREATE_INDEX = true;

    nsbqsr::IndexFormat INDEX_FORMAT = nsbqsr::IndexFormat::BAI;

    /* Add PG tag to each read in a SAM or BAM (PGTagArgumentCollection)*/
    bool ADD_PG_TAG_TO_READS = true;

    //
    string CLI_STR;

    //
    string START_TIME;

    string PROGRAM_RECORD_ID = "FastBQSR";

    // end of common parameters

    /**
     * The context covariate will use a context of this size to calculate its covariate value for base mismatches. Must be
     * between 1 and 13 (inclusive). Note that higher values will increase runtime and required java heap size.
     */
    int MISMATCHES_CONTEXT_SIZE = 2;

    /**
     * The context covariate will use a context of this size to calculate its covariate value for base insertions and deletions.
     * Must be between 1 and 13 (inclusive). Note that higher values will increase runtime and required java heap size.
     */
    int INDELS_CONTEXT_SIZE = 3;

    /**
     * The cycle covariate will generate an error if it encounters a cycle greater than this value.
     * This argument is ignored if the Cycle covariate is not used.
     */
    int MAXIMUM_CYCLE_VALUE = 500;

    /**
     * A default base qualities to use as a prior (reported quality) in the mismatch covariate model. This value will replace
     * all base qualities in the read for this default value. Negative value turns it off. [default is off]
     */
    int8_t MISMATCHES_DEFAULT_QUALITY = -1;

    /**
     * A default base qualities to use as a prior (reported quality) in the insertion covariate model. This parameter is used
     * for all reads without insertion quality scores for each base. [default is on]
     */
    int8_t INSERTIONS_DEFAULT_QUALITY = 45;

    /**
     * A default base qualities to use as a prior (reported quality) in the mismatch covariate model. This value will replace
     * all base qualities in the read for this default value. Negative value turns it off. [default is on]
     */
    int8_t DELETIONS_DEFAULT_QUALITY = 45;

    /**
     * Reads with low quality bases on either tail (beginning or end) will not be considered in the context. This parameter
     * defines the quality below which (inclusive) a tail is considered low quality
     */
    int8_t LOW_QUAL_TAIL = 2;

    /**
     * BQSR generates a quantization table for quick quantization later by subsequent tools. BQSR does not quantize the base
     * qualities, this is done by the engine with the -qq or -bqsr options. This parameter tells BQSR the number of levels of
     * quantization to use to build the quantization table.
     */
    int QUANTIZING_LEVELS = 16;

    /**
     * The tag name for the binary tag covariate (if using it)
     */
    string BINARY_TAG_NAME = "";

    /**
     * bqsr-baq-gap-open-penalty, BQSR BAQ gap open penalty (Phred Scaled).  Default value is 40.  30 is perhaps better
     * for whole genome call sets
     */
    double BAQGOP = 40;

    /**
     * This flag tells GATK not to modify quality scores less than this value. Instead they will be written out unmodified in
     * the recalibrated BAM file. In general it's unsafe to change qualities scores below < 6, since base callers use these
     * values to indicate random or bad bases. For example, Illumina writes Q2 bases when the machine has really gone wrong.
     * This would be fine in and of itself, but when you select a subset of these reads based on their ability to align to the
     * reference and their dinucleotide effect, your Q2 bin can be elevated to Q8 or Q10, leading to issues downstream.
     */
    int PRESERVE_QSCORES_LESS_THAN = 6;

    /**
     * enable-baq, do BAQ correction"
     */
    bool enableBAQ = false;

    /**
     * compute-indel-bqsr-tables, compute indel BQSR tables"
     */
    bool computeIndelBQSRTables = false;

    // --------------------------------------------------------------------------------------------------------------
    //
    // quality encoding checking arguments
    //
    // --------------------------------------------------------------------------------------------------------------

    /**
     * This flag tells GATK to use the original base qualities (that were in the data before BQSR/recalibration) which
     * are stored in the OQ tag, if they are present, rather than use the post-recalibration quality scores. If no OQ
     * tag is present for a read, the standard qual score will be used.
     */
    bool useOriginalBaseQualities = false;

    /**
     * If reads are missing some or all base quality scores, this value will be used for all base quality scores.
     * By default this is set to -1 to disable default base quality assignment.
     */
    int8_t defaultBaseQualities = -1;
};