Main namespace of vdj_pipe library. More...

Namespaces
	test
	Namespace for unit-tests.

Classes
class	Ambiguous_window_filter

class	Apply_many
	Apply enclosed processing step multiple times to sequence reads of specified kind: forward, reverse, or merged. More...

class	Apply_one
	Apply enclosed processing step once to a sequence read of specified kind: forward, reverse, or merged. More...

class	Average_quality_filter

class	Average_quality_window_filter

struct	base_exception

class	Best_match_pair

struct	Blank

class	Blank_step

class	Character_filter

class	Command_line_options

class	Composition_stats

struct	Config_paired_emid_reads

struct	Config_paired_reads

struct	Config_single_reads

class	External_mid_infile
	Look for external MIDs in separate files. More...

class	External_mid_inline
	Look for external MIDs in FASTA/Q description lines. More...

class	File

class	File_input
	File target is supposed to exist at construction time. More...

class	File_istream

class	File_ostream

class	File_ostream_queue
	stack of recently used output file streams More...

class	File_ostream_variant
	Select output file based on variables in value map. More...

class	File_output
	File target is created if needed at construction time. More...

class	Find_shared

struct	Finish_visitor

class	Get_match_length
	Set a fraction of sequence length to match. More...

class	Histogram_1d
	simple unsigned integer-based histogram More...

class	Histogram_step

class	Homopolymer_filter

class	Id_iterator

struct	Identity
	why is it not in STL? More...

class	Input_manager

struct	Is_ambiguous

class	Length_filter

struct	Lib_info
	library info More...

class	Match_fraction_length
	Set a fraction of sequence length to match. More...

struct	Match_full_length
	Require full sequence to match. More...

class	Match_ignore_ends
	Set a minimal sequence length to match allowing for some mismatch at ends. More...

class	Match_min_length
	Set a minimal sequence length to match. More...

class	Match_step

class	Merge_paired

struct	Merge_result

class	Min_quality_filter

class	Min_quality_window_filter

class	Output_manager

class	Parser_fasta

class	Parser_fastq
	Parser for FASTQ files. More...

class	Parser_qual

class	Pipe_environment

class	Pipe_paired_emid_read
	process paired reads with external MIDs More...

class	Pipe_paired_read
	process paired reads with external MIDs More...

class	Pipe_single_read

class	Pipeline

class	Pipeline_input

struct	Qual_record

class	Qual_stats

class	Quality

struct	Queable_ofstream

class	Read_info

class	Read_info_store
	Store sequence-related information. More...

struct	Run_visitor

class	Seq_entry

class	Seq_file

class	Seq_file_entry

class	Seq_file_map

class	Seq_fls
	store short sequence in an integer More...

struct	Seq_match

struct	Seq_meta

struct	Seq_pos

struct	Seq_qual_record

struct	Seq_record

class	Seq_store
	Store sequence and related information. More...

class	Step_variant_store

class	Summary_visitor

class	Summary_visitor2

struct	Type_index

class	Unambiguous_interval_iter

class	Value_ids_emid
	Provides access to standard eMID values. More...

class	Value_ids_paired
	Provides access to standard values for paired read pipeline. More...

class	Value_ids_single
	Provides access to standard values for single read pipeline. More...

class	Value_map
	Store values mapped against name strings and value IDs. More...

struct	Value_names

class	Variable_path

class	Vm_access_paired
	Access to value map for paired read pipeline and processing steps. More...

class	Vm_access_paired_emid
	Access to value map for paired eMID read pipeline and processing steps. More...

class	Vm_access_single

class	Write_seq

class	Write_value

Typedefs
typedef boost::variant< Blank, bool, long, double, std::string, sequence_interval, Qual_record::quality >	value_variant

typedef boost::numeric::interval< int, boost::numeric::interval_lib::policies< boost::numeric::interval_lib::rounded_math< int >, detail::Interval_checking_policy< int > > >	sequence_interval

typedef Seq_pos< Read_id >	sub_seq

typedef Seq_pos< Seq_id >	super_seq

typedef boost::multi_array< int, 2 >	scoring_matrix_t

typedef boost::make_recursive_variant_over< step::paired_read_vector >::type	step_variant_paired

typedef boost::make_recursive_variant_over< step::paired_emid_read_vector >::type	step_variant_paired_emid

typedef boost::make_recursive_variant_over< step::single_read_vector >::type	step_variant_single

typedef boost::make_recursive_variant_over< step::all_steps_vector >::type	step_variant_all

Enumerations
enum	Nucleotide { Adenine = 0, Cytosine = 1, Guanine = 2, Thymine = 3, Any = 4, Uracil = 5, Purine = 6, Pyrimidine = 7, Ketone = 8, Amine = 9, Strong = 10, Weak = 11, not_A = 12, not_C = 13, not_G = 14, not_T = 15 }

Functions
std::size_t	hash_value (Blank const &)

template<class ChT , class Tr >
std::basic_ostream< ChT, Tr > &	operator<< (std::basic_ostream< ChT, Tr > &os, Blank const &)

std::string const &	variable_type_str (const int which)

bool	is_blank (value_variant const &vv)

std::string const &	variable_type_str (value_variant const &vv)

VDJ_PIPE_DECL value_variant	parse_variant (std::string const &s)

VDJ_PIPE_DECL void	store_values (Seq_file_entry const &sfe, Value_map &vm)

VDJ_PIPE_DECL compression::Compression	extension_to_compression (std::string const &ext)
	guess file compression from low case extension string More...

VDJ_PIPE_DECL compression::Compression	compression_magic (std::istream &is)
	guess file compression from magic number More...

VDJ_PIPE_DECL format::Format	extension_to_format (std::string const &ext)
	guess file format from low case extension string More...

VDJ_PIPE_DECL void	path_decompose (std::string const &path, std::vector< std::string > &tv, std::vector< std::string > &nv)
	separate path into non-name and name areas More...

VDJ_PIPE_DECL std::string	path_assemble (std::vector< std::string > const &templ, detail::Queable_ofstream_types::val_ref_vector const &vals)
	assemble path from template and values More...

sequence_interval	sequence_interval_invalid ()

template<class MinLength >
void	remove_subsequences (Seq_store &ss, gdst::Gdst &st, MinLength const &min_len)
	identify unique sequences in sequence store, insert them into suffix tree, and remove non-unique ones

template<class Ch , class Tr >
std::basic_ostream< Ch, Tr > &	print_split (std::basic_ostream< Ch, Tr > &os, const boost::string_ref str, const Ch delim, const unsigned length)
	print string splitting it into parts of equal length More...

template<class Ch , class Tr >
std::basic_ostream< Ch, Tr > &	print_fasta (std::basic_ostream< Ch, Tr > &os, std::string const &name, Seq_record::sequence const &sequence, const unsigned length=80)
	print FASTA record More...

template<class Ch , class Tr >
std::basic_ostream< Ch, Tr > &	print_fasta (std::basic_ostream< Ch, Tr > &os, const std::string &name, const boost::string_ref sequence, const unsigned length=80)
	print FASTA record More...

template<class Ch , class Tr >
std::basic_ostream< Ch, Tr > &	print_qual (std::basic_ostream< Ch, Tr > &os, std::string const &name, Qual_record::quality const &qual, const unsigned length=80)
	print QUAL record More...

template<class Ch , class Tr >
std::basic_ostream< Ch, Tr > &	print_fastq (std::basic_ostream< Ch, Tr > &os, std::string const &name, Seq_record::sequence const &sequence, Qual_record::quality const &qual, const int offset=33)
	print FASTQ record More...

VDJ_PIPE_DECL std::string	sanitize (const char c)

VDJ_PIPE_DECL std::string	sanitize (std::string const &str)

VDJ_PIPE_DECL std::string	sanitize (const boost::string_ref str, const std::size_t max_len)

template<class Seq >
int	identity (Seq const &s1, const boost::string_ref s2, scoring_matrix_t const &sm, const std::size_t=0)

template<unsigned N, typename S >
int	identity (const Seq_fls< N, S > seq1, const Seq_fls< N, S > seq2, scoring_matrix_t const &sm, const unsigned len=N)

template<class ChT , class Tr >
std::basic_ostream< ChT, Tr > &	operator<< (std::basic_ostream< ChT, Tr > &os, Qual_record::quality const &qual)

bool	operator== (Seq_entry const &se1, Seq_entry const &se2)

bool	operator== (const boost::string_ref se1, Seq_entry const &se2)

bool	operator== (Seq_entry const &se1, const boost::string_ref se2)

std::size_t	hash_value (Seq_entry const &se)

std::pair< std::size_t, std::size_t >	longest_average_interval (Qual_record::quality const &q, const std::size_t min_q, const std::size_t win)

std::pair< std::size_t, std::size_t >	longest_min_interval (Qual_record::quality const &q, const Qual_record::quality::value_type min_q)

std::pair< std::size_t, std::size_t >	longest_unambiguous_interval (Seq_record::sequence const &seq, const std::size_t max)

template<class Id >
bool	operator== (Seq_pos< Id > const &rp1, Seq_pos< Id > const &rp2)

template<class Id >
bool	operator< (Seq_pos< Id > const &rp1, Seq_pos< Id > const &rp2)

template<class Id >
bool	operator< (Seq_pos< Id > const &rp1, const Id rp2)

template<class Id >
bool	operator< (const Id rp1, Seq_pos< Id > const &rp2)

VDJ_PIPE_DECL compression::Compression	guess_compression_ext (std::string const &path)

VDJ_PIPE_DECL compression::Compression	guess_compression_magic (std::string const &path)

VDJ_PIPE_DECL std::pair< compression::Compression, format::Format >	guess_compression_format (std::string const &path)

VDJ_PIPE_DECL format::Format	guess_format (std::string const &path, const compression::Compression c)

VDJ_PIPE_DECL std::string	ensure_path_writable (std::string const &path)
	create file if does not exist along with parent directories if needed

VDJ_PIPE_DECL std::string	ensure_path_writable (std::string const &path, std::string const &header)
	if file does not exist, create and write header; create parent directories if needed

VDJ_PIPE_DECL bool	is_path_readable (std::string const &path)

VDJ_PIPE_DECL std::string	ensure_path_readable (std::string const &path)

VDJ_PIPE_DECL std::size_t	hash_value (File const &f)

Nucleotide	nucleotide_index (const char c)

bool	is_ambiguous (const char c)

Nucleotide	complement (const Nucleotide n)

char	complement (const char c)

char	to_capital (const Nucleotide n)

char	to_small (const Nucleotide n)

template<int Match, int Mismatch, int Approximate, int Uncertain>
scoring_matrix_t const &	scoring_matrix ()

int	identity (const Nucleotide n1, const Nucleotide n2, scoring_matrix_t const &sm=scoring_matrix< 2,-2, 1, 0 >())

template<class Range >
std::string	complement (Range const &r)

std::string	transform (const boost::string_ref seq, sequence_interval const &si, const bool reverse)
	Reverse-complement (optionally) a portion of a sequence.

template<class Ostr >
Ostr &	operator<< (Ostr &ostr, const Read_info si)

VDJ_PIPE_DECL std::ostream &	stamp (std::ostream &os, std::string const &pref="## ", std::string const &delim="; ", std::string const &suff="\n")

VDJ_PIPE_DECL std::string	stamp (std::string const &pref="## ", std::string const &delim="; ", std::string const &suff="\n")

VDJ_PIPE_DECL void	process_options (boost::property_tree::ptree const &pt)

VDJ_PIPE_DECL void	process_single_reads (boost::property_tree::ptree const &pt)

VDJ_PIPE_DECL void	process_paired_reads (boost::property_tree::ptree const &pt)

VDJ_PIPE_DECL void	process_paired_emid_reads (boost::property_tree::ptree const &pt)

VDJ_PIPE_DECL void	merge (std::string const &s1, Seq_qual_record::quality const &qv1, std::string const &s2, Seq_qual_record::quality const &qv2, const unsigned min_score, Merge_result &mr)

	VDJ_PIPE_OBJECT_ID (Val_id)

	VDJ_PIPE_OBJECT_ID (Mid_id)

	VDJ_PIPE_OBJECT_ID (Path_id)

	VDJ_PIPE_OBJECT_ID (Read_id)

	VDJ_PIPE_OBJECT_ID (Seq_id)

	VDJ_PIPE_OBJECT_ID (Mapped_id)

template<class Id >
boost::iterator_range< Id_iterator< Id > >	id_range (const Id id1, const Id id2)

template<typename T >
void	unused_variable (T const &)

VDJ_PIPE_DECL step_variant_paired	create_step_paired (Vm_access_paired const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

template<>
Config_paired_reads::processing_step	create_step< Config_paired_reads > (Config_paired_reads::value_map_access const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

VDJ_PIPE_DECL step_variant_single	create_step_single (Vm_access_single const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

template<>
Config_single_reads::processing_step	create_step< Config_single_reads > (Config_single_reads::value_map_access const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

VDJ_PIPE_DECL step_variant_paired_emid	create_step_paired_emid (Vm_access_paired_emid const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

template<>
Config_paired_emid_reads::processing_step	create_step< Config_paired_emid_reads > (Config_paired_emid_reads::value_map_access const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

template<class Config >
Config::processing_step	create_step (typename Config::value_map_access const &vma, boost::property_tree::ptree const &pt, Pipe_environment &pe)

Detailed Description

Main namespace of vdj_pipe library.

Enumeration Type Documentation

enum vdj_pipe::Nucleotide

Enumerator
Uracil	U.
Purine	R : A, G.
Pyrimidine	Y : C, T, U.
Ketone	K : G, T, U.
Amine	M : A, C.
Strong	S : C, G.
Weak	W : A, T, U.
not_A	B : C G T.
not_C	D : A G T.
not_G	H : A C T.
not_T	V : A C G.

Function Documentation

VDJ_PIPE_DECL compression::Compression vdj_pipe::compression_magic ( std::istream & is )

guess file compression from magic number

Example ".gz" ".bz2"

VDJ_PIPE_DECL std::string vdj_pipe::ensure_path_readable ( std::string const & path )

Returns: canonical path name

Exceptions

if	path not readable

VDJ_PIPE_DECL compression::Compression vdj_pipe::extension_to_compression ( std::string const & ext )

guess file compression from low case extension string

Example ".gz" ".bz2"

VDJ_PIPE_DECL format::Format vdj_pipe::extension_to_format ( std::string const & ext )

guess file format from low case extension string

Example ".fq" ".fasta"

VDJ_PIPE_DECL compression::Compression vdj_pipe::guess_compression_ext ( std::string const & path )

Returns: compression based on file extension

VDJ_PIPE_DECL std::pair<compression::Compression, format::Format> vdj_pipe::guess_compression_format ( std::string const & path )

Returns: file compression and format based on file extension

VDJ_PIPE_DECL compression::Compression vdj_pipe::guess_compression_magic ( std::string const & path )

Returns: compression based on file magic number

VDJ_PIPE_DECL format::Format vdj_pipe::guess_format	(	std::string const &	path,
		const compression::Compression	c
	)

Returns: file compression and format based on file extension

template<class Seq >

int vdj_pipe::identity	(	Seq const &	s1,
		const boost::string_ref	s2,
		scoring_matrix_t const &	sm,
		const std::size_t	= `0`
	)

inline

compute identity score

template<unsigned N, typename S >

int vdj_pipe::identity	(	const Seq_fls< N, S >	seq1,
		const Seq_fls< N, S >	seq2,
		scoring_matrix_t const &	sm,
		const unsigned	len = `N`
	)

inline

compute identity score

VDJ_PIPE_DECL bool vdj_pipe::is_path_readable ( std::string const & path )

Returns: true if readable

std::pair<std::size_t,std::size_t> vdj_pipe::longest_average_interval	(	Qual_record::quality const &	q,
		const std::size_t	min_q,
		const std::size_t	win
	)

inline

Returns: starting position and length of the longest interval in which the sum of every sub-interval of length win is at least min_q

std::pair<std::size_t,std::size_t> vdj_pipe::longest_min_interval	(	Qual_record::quality const &	q,
		const Qual_record::quality::value_type	min_q
	)

inline

Returns: starting position and length of the longest interval in which every element is at least min_q

std::pair<std::size_t,std::size_t> vdj_pipe::longest_unambiguous_interval	(	Seq_record::sequence const &	seq,
		const std::size_t	max
	)

inline

Returns: starting position and length of the longest interval that contains fewer than max ambiguous nucleotides

VDJ_PIPE_DECL std::string vdj_pipe::path_assemble	(	std::vector< std::string > const &	templ,
		detail::Queable_ofstream_types::val_ref_vector const &	vals
	)

assemble path from template and values

Example: out_dir/{name1}-dir/{name2}file.fna

VDJ_PIPE_DECL void vdj_pipe::path_decompose	(	std::string const &	path,
		std::vector< std::string > &	tv,
		std::vector< std::string > &	nv
	)

separate path into non-name and name areas

Example: out_dir/{name1}-dir/{name2}file.fna