pappso::AaStringCodec Class Reference

code and decode amino acid string sequence to unique integer More...

#include <aastringcodec.h>

Public Member Functions
	AaStringCodec (const AaCode &aaCode)
	AaStringCodec (const AaStringCodec &other)
	~AaStringCodec ()
std::size_t	getLimitMax (std::size_t size) const
	get the maximum code number for a given peptide size
uint32_t	code (const QString &aa_str) const
	get integer from amino acide suite string
uint32_t	codeLlc (const QString &aa_str) const
	get the lowest common denominator integer from amino acide suite string
uint32_t	codeLlc (std::vector< uint8_t >::const_iterator it_begin, std::size_t size) const
	get the lowest common denominator integer from amino acide code vector
QString	decode (uint32_t code) const
QStringList	decode (const std::vector< uint32_t > &code_list) const
double	getMass (uint32_t code) const
std::vector< CodeToMass >	generateLlcCodeListUpToMaxPeptideSize (std::size_t size) const
	generates all possible combination of llc code mass llc : the lowest common code denominator for a given aa formula
std::vector< CodeToMass >	generateLlcCodeListByMaxPeptideSize (std::size_t size) const
	generates all possible combination of llc code mass llc : the lowest common code denominator for a given aa formula
bool	codeOnlyContains (uint32_t code, const std::vector< uint8_t > &aa_ok) const
	tell if a code only contains a list of amino acid
bool	uniqueCodeContainsAminoAcid (uint32_t code, uint8_t aa_ok, int times) const
	tell if a unique code only contains one amino acid 1 or n times
const AaCode &	getAaCode () const

Private Member Functions
void	recGenerateModel (std::vector< CodeToMass > &glist, std::vector< uint8_t > &model, std::size_t position) const
	recursive method to generate models
CodeToMass	generateCodeMassFromModel (const std::vector< uint8_t > &model) const

Private Attributes
uint32_t	m_base = 0
const AaCode &	m_aaCode
std::vector< uint32_t >	m_units

Detailed Description

code and decode amino acid string sequence to unique integer

Definition at line 51 of file aastringcodec.h.

Constructor & Destructor Documentation

AaStringCodec() [1/2]

AaStringCodec::AaStringCodec

(

const AaCode &

aaCode

)

Default constructor

Definition at line 33 of file aastringcodec.cpp.

                                                 : m_aaCode(aaCode)
{
 
  m_base = m_aaCode.getSize() + 1;
  m_units.resize(10);
  uint32_t unit = 1;
  for(auto &this_unit : m_units)
    {
      this_unit = unit;
      unit *= m_base;
    }
}

References m_aaCode, m_base, and m_units.

Referenced by AaStringCodec().

AaStringCodec() [2/2]

AaStringCodec::AaStringCodec

(

const AaStringCodec &

other

)

Copy constructor

Parameters

other

TODO

Definition at line 46 of file aastringcodec.cpp.

  : m_aaCode(other.m_aaCode)
{
  m_base  = other.m_base;
  m_units = other.m_units;
}

References AaStringCodec(), m_aaCode, m_base, and m_units.

~AaStringCodec()

AaStringCodec::~AaStringCodec

(

)

Destructor

Definition at line 53 of file aastringcodec.cpp.

{
}

Member Function Documentation

code()

uint32_t pappso::AaStringCodec::code

(

const QString &

aa_str

)

const

get integer from amino acide suite string

Definition at line 59 of file aastringcodec.cpp.

{
 
  std::size_t pos = 0;
  uint32_t code   = 0;
  for(auto &aa_char : aa_str)
    {
      code += m_aaCode.getAaCode(aa_char.toLatin1()) * m_units[pos];
      pos++;
    }
  return code;
}

References code(), m_aaCode, and m_units.

Referenced by code(), codeLlc(), codeLlc(), codeOnlyContains(), decode(), decode(), getLimitMax(), getMass(), and uniqueCodeContainsAminoAcid().

codeLlc() [1/2]

uint32_t pappso::AaStringCodec::codeLlc

(

const QString &

aa_str

)

const

get the lowest common denominator integer from amino acide suite string

Definition at line 73 of file aastringcodec.cpp.

{
  std::vector<uint8_t> llc_vec;
 
  for(auto &aa_char : aa_str)
    {
      llc_vec.push_back(m_aaCode.getAaCode(aa_char.toLatin1()));
    }
  std::sort(llc_vec.begin(), llc_vec.end(), std::greater<uint8_t>());
 
 
  std::size_t pos = 0;
  uint32_t code   = 0;
  for(auto &aa_code : llc_vec)
    {
      code += (uint32_t)aa_code * m_units[pos];
      pos++;
    }
  return code;
}

References code(), m_aaCode, and m_units.

Referenced by pappso::ProteinIntegerCode::computePeptideCodeFragments().

codeLlc() [2/2]

uint32_t pappso::AaStringCodec::codeLlc	(	std::vector< uint8_t >::const_iterator	it_begin,
		std::size_t	size ) const

get the lowest common denominator integer from amino acide code vector

Definition at line 95 of file aastringcodec.cpp.

{
  std::vector<uint8_t> llc_vec;
 
  for(std::size_t i = 0; i < size; i++)
    {
      llc_vec.push_back(*it_begin);
      it_begin++;
    }
  std::sort(llc_vec.begin(), llc_vec.end(), std::greater<uint8_t>());
 
 
  std::size_t pos = 0;
  uint32_t code   = 0;
  for(auto &aa_code : llc_vec)
    {
      code += (uint32_t)aa_code * m_units[pos];
      pos++;
    }
  return code;
}

References code(), and m_units.

codeOnlyContains()

bool pappso::AaStringCodec::codeOnlyContains	(	uint32_t	code,
		const std::vector< uint8_t > &	aa_ok ) const

tell if a code only contains a list of amino acid

Parameters

code	the code to valid
aa_ok	list of required amino acids

Definition at line 269 of file aastringcodec.cpp.

{
 
  while(code > 0)
    {
      if(std::find(aa_ok.begin(), aa_ok.end(), (uint8_t)(code % m_base)) ==
         aa_ok.end())
        return false;
 
      code /= m_base;
    }
  return true;
}

References code(), and m_base.

decode() [1/2]

QStringList pappso::AaStringCodec::decode

(

const std::vector< uint32_t > &

code_list

)

const

Definition at line 136 of file aastringcodec.cpp.

{
  QStringList aa_string_list;
  for(auto code : code_list)
    {
      aa_string_list << decode(code);
    }
  return aa_string_list;
}

References code(), and decode().

decode() [2/2]

QString pappso::AaStringCodec::decode

(

uint32_t

code

)

const

Definition at line 120 of file aastringcodec.cpp.

{
  QString aa_suite;
 
  while(code > 0)
    {
      aa_suite.append(m_aaCode.getAa((uint8_t)(code % m_base)).getLetter());
      code /= m_base;
    }
 
  // qDebug() << aa_suite;
 
  return aa_suite;
}

References code(), m_aaCode, and m_base.

Referenced by decode().

generateCodeMassFromModel()

pappso::CodeToMass pappso::AaStringCodec::generateCodeMassFromModel ( const std::vector< uint8_t > & model ) const

private

Definition at line 238 of file aastringcodec.cpp.

{
  CodeToMass code_mass;
  std::size_t pos = 0;
  for(auto aacode : model)
    {
      code_mass.mass += m_aaCode.getMass(aacode);
 
      code_mass.code += (uint32_t)aacode * m_units[pos];
      pos++;
    }
 
  // qDebug() << code_mass.code << " " << code_mass.mass;
  return code_mass;
}

References pappso::CodeToMass::code, m_aaCode, m_units, and pappso::CodeToMass::mass.

Referenced by generateLlcCodeListUpToMaxPeptideSize(), and recGenerateModel().

generateLlcCodeListByMaxPeptideSize()

std::vector< CodeToMass > pappso::AaStringCodec::generateLlcCodeListByMaxPeptideSize

(

std::size_t

size

)

const

generates all possible combination of llc code mass llc : the lowest common code denominator for a given aa formula

generate only for this peptide size

Definition at line 192 of file aastringcodec.cpp.

{
  std::vector<CodeToMass> llc_list;
  if(size == 0)
    return llc_list;
  std::vector<uint8_t> model;
  model.resize(size, 0);
 
  for(uint8_t i = 1; i < m_base; i++)
    {
      model[0] = i;
      recGenerateModel(llc_list, model, 1);
    }
  return llc_list;
}

References m_base, and recGenerateModel().

generateLlcCodeListUpToMaxPeptideSize()

std::vector< CodeToMass > pappso::AaStringCodec::generateLlcCodeListUpToMaxPeptideSize

(

std::size_t

size

)

const

generates all possible combination of llc code mass llc : the lowest common code denominator for a given aa formula

generate from peptide size =1 to peptide size

Definition at line 163 of file aastringcodec.cpp.

{
  std::vector<CodeToMass> llc_list;
  if(size == 0)
    return llc_list;
  std::vector<uint8_t> model;
  for(uint8_t p = 1; p <= size; p++)
    {
      model.resize(p, 0);
 
      for(uint8_t i = 1; i < m_base; i++)
        {
          model[0] = i;
          if(p == 1)
            {
              llc_list.push_back(generateCodeMassFromModel(model));
            }
          else
            {
              recGenerateModel(llc_list, model, 1);
            }
        }
    }
  return llc_list;
}

References generateCodeMassFromModel(), m_base, and recGenerateModel().

getAaCode()

const pappso::AaCode & pappso::AaStringCodec::getAaCode

(

)

const

Definition at line 307 of file aastringcodec.cpp.

{
  return m_aaCode;
}

References m_aaCode.

Referenced by pappso::ProteinIntegerCode::ProteinIntegerCode().

getLimitMax()

std::size_t pappso::AaStringCodec::getLimitMax

(

std::size_t

size

)

const

get the maximum code number for a given peptide size

Definition at line 257 of file aastringcodec.cpp.

{
 
  std::size_t code = 0;
  for(std::size_t pos = 0; pos < size; pos++)
    {
      code += (std::size_t)(m_base - 1) * (std::size_t)m_units[pos];
    }
  return code;
}

References code(), m_base, and m_units.

getMass()

double pappso::AaStringCodec::getMass

(

uint32_t

code

)

const

Definition at line 148 of file aastringcodec.cpp.

{
  double mass = 0;
 
  while(code > 0)
    {
      mass += m_aaCode.getMass((uint8_t)(code % m_base));
      code /= m_base;
    }
 
  return mass;
}

References code(), m_aaCode, and m_base.

recGenerateModel()

void pappso::AaStringCodec::recGenerateModel ( std::vector< CodeToMass > & glist, std::vector< uint8_t > & model, std::size_t position ) const

private

recursive method to generate models

Definition at line 210 of file aastringcodec.cpp.

{
  if(position == model.size())
    return;
 
  if(position == model.size() - 1)
    {
      uint8_t max = model[position - 1];
      for(uint8_t i = 1; i <= max; i++)
        {
          model[position] = i;
          glist.push_back(generateCodeMassFromModel(model));
        }
    }
  else
    {
      uint8_t max = model[position - 1];
      for(uint8_t i = 1; i <= max; i++)
        {
          model[position] = i;
          recGenerateModel(glist, model, position + 1);
        }
    }
}

References generateCodeMassFromModel(), and recGenerateModel().

Referenced by generateLlcCodeListByMaxPeptideSize(), generateLlcCodeListUpToMaxPeptideSize(), and recGenerateModel().

uniqueCodeContainsAminoAcid()

bool pappso::AaStringCodec::uniqueCodeContainsAminoAcid	(	uint32_t	code,
		uint8_t	aa_ok,
		int	times ) const

tell if a unique code only contains one amino acid 1 or n times

Parameters

code	the code to valid
aa_ok	the amino acid the code must contains
times	the number of aa_ok presence in code

Definition at line 285 of file aastringcodec.cpp.

{
 
  int number = 0;
  while(code > 0)
    {
      if(aa_ok == (uint8_t)(code % m_base))
        {
          number++;
          if(number == times)
            return true;
        }
 
      code /= m_base;
    }
  return false;
}

References code(), and m_base.

Member Data Documentation

m_aaCode

const AaCode& pappso::AaStringCodec::m_aaCode

private

Definition at line 147 of file aastringcodec.h.

Referenced by AaStringCodec(), AaStringCodec(), code(), codeLlc(), decode(), generateCodeMassFromModel(), getAaCode(), and getMass().

m_base

uint32_t pappso::AaStringCodec::m_base = 0

private

Definition at line 146 of file aastringcodec.h.

Referenced by AaStringCodec(), AaStringCodec(), codeOnlyContains(), decode(), generateLlcCodeListByMaxPeptideSize(), generateLlcCodeListUpToMaxPeptideSize(), getLimitMax(), getMass(), and uniqueCodeContainsAminoAcid().

m_units

std::vector<uint32_t> pappso::AaStringCodec::m_units

private

Definition at line 148 of file aastringcodec.h.

Referenced by AaStringCodec(), AaStringCodec(), code(), codeLlc(), codeLlc(), generateCodeMassFromModel(), and getLimitMax().

---

The documentation for this class was generated from the following files:

• pappsomspp/core/amino_acid/aastringcodec.h
• pappsomspp/core/amino_acid/aastringcodec.cpp