dae.genomic_resources.genomic_position_table package

Subpackages

dae.genomic_resources.genomic_position_table.tests package

Submodules

dae.genomic_resources.genomic_position_table.line module

class dae.genomic_resources.genomic_position_table.line.BigWigLine(raw_line: tuple)[source]

Bases: object

Represents a line read from a bigWig file.

get(key: str | int) → str | int | float[source]

row() → tuple[source]

class dae.genomic_resources.genomic_position_table.line.Line(raw_line: tuple, chrom_key: int = 0, pos_begin_key: int = 1, pos_end_key: int = 2, ref_key: int | None = None, alt_key: int | None = None)[source]

Bases: object

Represents a line read from a genomic position table.

Provides attribute access to a number of important columns - chromosome, start position, end position, reference allele and alternative allele.

alt: str | None

chrom: str

fchrom: str

get(key: str | int) → str[source]

pos_begin: int

pos_end: int

ref: str | None

row() → tuple[source]

class dae.genomic_resources.genomic_position_table.line.LineBase(*args, **kwargs)[source]

Bases: Protocol

Protocol for genomic position table lines.

alt: str | None

chrom: str

fchrom: str

get(key: str | int) → Any[source]

pos_begin: int

pos_end: int

ref: str | None

row() → tuple[source]

class dae.genomic_resources.genomic_position_table.line.LineBuffer[source]

Bases: object

Represent a line buffer for Tabix genome position table.

append(line: LineBase) → None[source]

clear() → None[source]

contains(chrom: str, pos: int) → bool[source]

fetch(chrom: str, pos_begin: int, pos_end: int) → Generator[LineBase, None, None][source]: Return a generator of rows matching the region.

find_index(chrom: str, pos: int) → int[source]: Find index in line buffer that contains the passed position.

peek_first() → LineBase[source]

peek_last() → LineBase[source]

pop_first() → LineBase[source]

prune(chrom: str, pos: int) → None[source]: Prune the buffer if needed.

region() → tuple[str | None, int | None, int | None][source]: Return region stored in the buffer.

class dae.genomic_resources.genomic_position_table.line.VCFLine(raw_line: VariantRecord, allele_index: int | None)[source]

Bases: object

Line adapter for lines derived from a VCF file.

Implements functionality for handling multi-allelic variants and INFO fields.

get(key: str | int) → Any[source]: Get a value from the INFO field of the VCF line.

row() → tuple[source]

dae.genomic_resources.genomic_position_table.table module

class dae.genomic_resources.genomic_position_table.table.GenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: ABC

Abstraction over genomic scores table.

ALT = 'alternative'

CHROM = 'chrom'

POS_BEGIN = 'pos_begin'

POS_END = 'pos_end'

REF = 'reference'

abstract close() → None[source]: Close the resource.

abstract get_all_records() → Generator[LineBase, None, None][source]: Return generator of all records in the table.

abstract get_chromosome_length(chrom: str, step: int = 100000000) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_chromosomes() → list[str][source]: Return list of contigs in the genomic position table.

get_column_key(col: str) → int | None[source]: Find the index of a column in the table.

abstract get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

abstract get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[LineBase, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

map_chromosome(chromosome: str) → str | None[source]: Map a chromosome from reference genome to file chromosome.

abstract open() → GenomicPositionTable[source]

unmap_chromosome(chromosome: str) → str | None[source]: Map a chromosome file contigs to reference genome chromosome.

dae.genomic_resources.genomic_position_table.table.adjust_zero_based_line(line: Line) → Line[source]: Adjust a zero-based line.

dae.genomic_resources.genomic_position_table.table.get_idx(key: str | int, header: tuple | None) → int[source]

dae.genomic_resources.genomic_position_table.table.zero_based_adjust(raw: tuple, pos_begin_key: str | int, pos_end_key: str | int, header: tuple | None) → tuple[source]: Adjust a zero-based record.

dae.genomic_resources.genomic_position_table.table_bigwig module

class dae.genomic_resources.genomic_position_table.table_bigwig.BigWigTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: GenomicPositionTable

bigWig format implementation of the genomic position table.

close() → None[source]: Close the resource.

get_all_records() → Generator[BigWigLine, None, None][source]: Return generator of all records in the table.

get_chromosome_length(chrom: str, step: int = 100000000) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[BigWigLine, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

open() → BigWigTable[source]

dae.genomic_resources.genomic_position_table.table_inmemory module

class dae.genomic_resources.genomic_position_table.table_inmemory.InmemoryGenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict, file_format: str)[source]

Bases: GenomicPositionTable

In-memory genomic position table.

FORMAT_DEF: ClassVar[dict] = {'csv': (',', '\n\r', False), 'mem': (None, ' \t\n\r', True), 'tsv': ('\t', '\n\r', False)}

close() → None[source]: Close the resource.

get_all_records() → Generator[LineBase, None, None][source]: Return generator of all records in the table.

get_chromosome_length(chrom: str, step: int = 0) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[LineBase, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

open() → InmemoryGenomicPositionTable[source]

dae.genomic_resources.genomic_position_table.table_tabix module

class dae.genomic_resources.genomic_position_table.table_tabix.TabixGenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: GenomicPositionTable

Represents Tabix file genome position table.

BUFFER_MAXSIZE = 20000

close() → None[source]: Close the resource.

get_all_records() → Generator[LineBase, None, None][source]: Return generator of all records in the table.

get_chromosome_length(chrom: str, step: int = 100000000) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_chromosomes() → list[str][source]: Return list of contigs in the genomic position table.

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_line_iterator(chrom: str | None = None, pos_begin: int | None = None) → Generator[LineBase | None, None, None][source]: Extract raw lines and wrap them in our Line adapter.

get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[LineBase, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

open() → TabixGenomicPositionTable[source]

dae.genomic_resources.genomic_position_table.table_vcf module

class dae.genomic_resources.genomic_position_table.table_vcf.VCFGenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: TabixGenomicPositionTable

Represents a VCF file genome position table.

CHROM = 'CHROM'

POS_BEGIN = 'POS'

POS_END = 'POS'

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_line_iterator(chrom: str | None = None, pos_begin: int | None = None) → Generator[VCFLine | None, None, None][source]: Extract raw lines and wrap them in our Line adapter.

open() → VCFGenomicPositionTable[source]

dae.genomic_resources.genomic_position_table.utils module

dae.genomic_resources.genomic_position_table.utils.build_genomic_position_table(resource: GenomicResource, table_definition: dict) → GenomicPositionTable[source]: Instantiate a genome position table from a genomic resource.

dae.genomic_resources.genomic_position_table.utils.save_as_tabix_table(table: GenomicPositionTable, full_file_path: str) → None[source]: Save a genome position table as Tabix table.

Module contents

class dae.genomic_resources.genomic_position_table.BigWigLine(raw_line: tuple)[source]

Bases: object

Represents a line read from a bigWig file.

get(key: str | int) → str | int | float[source]

row() → tuple[source]

class dae.genomic_resources.genomic_position_table.BigWigTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: GenomicPositionTable

bigWig format implementation of the genomic position table.

close() → None[source]: Close the resource.

get_all_records() → Generator[BigWigLine, None, None][source]: Return generator of all records in the table.

get_chromosome_length(chrom: str, step: int = 100000000) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[BigWigLine, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

open() → BigWigTable[source]

class dae.genomic_resources.genomic_position_table.Line(raw_line: tuple, chrom_key: int = 0, pos_begin_key: int = 1, pos_end_key: int = 2, ref_key: int | None = None, alt_key: int | None = None)[source]

Bases: object

Represents a line read from a genomic position table.

Provides attribute access to a number of important columns - chromosome, start position, end position, reference allele and alternative allele.

alt: str | None

chrom: str

fchrom: str

get(key: str | int) → str[source]

pos_begin: int

pos_end: int

ref: str | None

row() → tuple[source]

class dae.genomic_resources.genomic_position_table.LineBuffer[source]

Bases: object

Represent a line buffer for Tabix genome position table.

append(line: LineBase) → None[source]

clear() → None[source]

contains(chrom: str, pos: int) → bool[source]

fetch(chrom: str, pos_begin: int, pos_end: int) → Generator[LineBase, None, None][source]: Return a generator of rows matching the region.

find_index(chrom: str, pos: int) → int[source]: Find index in line buffer that contains the passed position.

peek_first() → LineBase[source]

peek_last() → LineBase[source]

pop_first() → LineBase[source]

prune(chrom: str, pos: int) → None[source]: Prune the buffer if needed.

region() → tuple[str | None, int | None, int | None][source]: Return region stored in the buffer.

class dae.genomic_resources.genomic_position_table.TabixGenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: GenomicPositionTable

Represents Tabix file genome position table.

BUFFER_MAXSIZE = 20000

alt_key: int | None

chrom_key: int

chrom_map: dict[str, str] | None

chrom_order: list[str] | None

close() → None[source]: Close the resource.

get_all_records() → Generator[LineBase, None, None][source]: Return generator of all records in the table.

get_chromosome_length(chrom: str, step: int = 100000000) → int[source]

Return the length of a chromosome (or contig).

Returned value is guarnteed to be larget than the actual contig length.

get_chromosomes() → list[str][source]: Return list of contigs in the genomic position table.

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_line_iterator(chrom: str | None = None, pos_begin: int | None = None) → Generator[LineBase | None, None, None][source]: Extract raw lines and wrap them in our Line adapter.

get_records_in_region(chrom: str | None = None, pos_begin: int | None = None, pos_end: int | None = None) → Generator[LineBase, None, None][source]

Return an iterable over the records in the specified range.

The interval is closed on both sides and 1-based.

header: Any

jump_threshold: int

line_iterator: Generator[LineBase | None, None, None] | None

open() → TabixGenomicPositionTable[source]

pos_begin_key: int

pos_end_key: int

pysam_file: TabixFile | VariantFile | None

ref_key: int | None

rev_chrom_map: dict[str, str] | None

stats: Counter

class dae.genomic_resources.genomic_position_table.VCFGenomicPositionTable(genomic_resource: GenomicResource, table_definition: dict)[source]

Bases: TabixGenomicPositionTable

Represents a VCF file genome position table.

CHROM = 'CHROM'

POS_BEGIN = 'POS'

POS_END = 'POS'

alt_key: int | None

chrom_key: int

chrom_map: dict[str, str] | None

chrom_order: list[str] | None

get_file_chromosomes() → list[str][source]

Return chromosomes in a genomic table file.

This is to be overwritten by the subclass. It should return a list of the chromosomes in the file in the order determinted by the file.

get_line_iterator(chrom: str | None = None, pos_begin: int | None = None) → Generator[VCFLine | None, None, None][source]: Extract raw lines and wrap them in our Line adapter.

header: Any

jump_threshold: int

line_iterator: Generator[LineBase | None, None, None] | None

open() → VCFGenomicPositionTable[source]

pos_begin_key: int

pos_end_key: int

pysam_file: PysamFile | None

ref_key: int | None

rev_chrom_map: dict[str, str] | None

stats: Counter

class dae.genomic_resources.genomic_position_table.VCFLine(raw_line: VariantRecord, allele_index: int | None)[source]

Bases: object

Line adapter for lines derived from a VCF file.

Implements functionality for handling multi-allelic variants and INFO fields.

get(key: str | int) → Any[source]: Get a value from the INFO field of the VCF line.

row() → tuple[source]

dae.genomic_resources.genomic_position_table.build_genomic_position_table(resource: GenomicResource, table_definition: dict) → GenomicPositionTable[source]: Instantiate a genome position table from a genomic resource.