drive.models package

Submodules

drive.models.data_container module

class drive.models.data_container.Data(networks: List[Network_Interface], output_path: Path, carriers: Dict[str, Dict[str, Set[str]]], phenotype_descriptions: Dict[str, Dict[str, str]])

Bases: object

main class to hold the data from the network analysis and the different pvalues

carriers: Dict[str, Dict[str, Set[str]]]

networks: List[Network_Interface]

output_path: Path

phenotype_descriptions: Dict[str, Dict[str, str]]

class drive.models.data_container.Data_Interface(*args, **kwargs)

Bases: Protocol

Protocol defining what attributes the DataHolder Interface needs to have

carriers: Dict[str, Dict[str, Set[str]]]

networks: List[Network_Interface]

output_path: Path

phenotype_descriptions: Dict[str, Dict[str, str]]

drive.models.generate_indices module

class drive.models.generate_indices.FileIndices(*args, **kwargs)

Bases: Protocol

get_haplotype_id(data: DataFrame, ind_id_indx: int, phase_col_indx: int, col_name: str) → None

class drive.models.generate_indices.Germline(id1_indx: int = 0, hap1_indx: int = 1, id2_indx: int = 2, hap2_indx: int = 3, chr_indx: int = 4, str_indx: int = 5, end_indx: int = 6, cM_indx: int = 10, unit: int = 11)

Bases: FileIndices

cM_indx: int = 10

chr_indx: int = 4

end_indx: int = 6

get_haplotype_id(data: DataFrame, ind_id_indx: int, phase_col_indx: int, col_name: str) → None

hap1_indx: int = 1

hap2_indx: int = 3

id1_indx: int = 0

id2_indx: int = 2

str_indx: int = 5

unit: int = 11

class drive.models.generate_indices.HapIBD(id1_indx: int = 0, hap1_indx: int = 1, id2_indx: int = 2, hap2_indx: int = 3, chr_indx: int = 4, str_indx: int = 5, end_indx: int = 6, cM_indx: int = 7)

Bases: FileIndices

cM_indx: int = 7

chr_indx: int = 4

end_indx: int = 6

get_haplotype_id(data: DataFrame, ind_id_indx: int, phase_col_indx: int, col_name: str) → None

hap1_indx: int = 1

hap2_indx: int = 3

id1_indx: int = 0

id2_indx: int = 2

str_indx: int = 5

class drive.models.generate_indices.Rapid(id1_indx: int = 1, hap1_indx: int = 3, id2_indx: int = 2, hap2_indx: int = 4, chr_indx: int = 0, cM_indx: int = 7, str_indx: int = 5, end_indx: int = 6)

Bases: FileIndices

cM_indx: int = 7

chr_indx: int = 0

end_indx: int = 6

get_haplotype_id(data: DataFrame, ind_id_indx: int, phase_col_indx: int, col_name: str) → None

hap1_indx: int = 3

hap2_indx: int = 4

id1_indx: int = 1

id2_indx: int = 2

str_indx: int = 5

drive.models.generate_indices.create_indices(ibd_file_format: str) → FileIndices

Factory method to generate the proper file indice object based on the ibd program

Parameters:

ibd_file_format (str) – string indicating what ibd program was used identify IBD segments. EX: hapibd, ilash, rapid, and germline. expects this value to be lower case

Returns:

returns an object that conforms to the FileIndices protocol. It will have the method getHAPID. It will also have the correct indices for the ibd program

Return type:

FileIndices

Raises:

ValueError – Raises a value error if the user passes an ibd_file_format that is not hapibd, hap-ibd, germline, ilash, rapid

class drive.models.generate_indices.iLASH(id1_indx: int = 0, hap1_indx: int = 1, id2_indx: int = 2, hap2_indx: int = 3, chr_indx: int = 4, str_indx: int = 5, end_indx: int = 6, cM_indx: int = 9)

Bases: FileIndices

cM_indx: int = 9

chr_indx: int = 4

end_indx: int = 6

get_haplotype_id(data: DataFrame, ind_id_indx: int, phase_col_indx: int, col_name: str) → None

hap1_indx: int = 1

hap2_indx: int = 3

id1_indx: int = 0

id2_indx: int = 2

str_indx: int = 5

drive.models.networks module

class drive.models.networks.Network(clst_id: float, true_positive_count: int, true_positive_percent: float, false_negative_edges: List[int], false_negative_count: int, members: Union[Set[int], Set[str]], haplotypes: Union[List[int], List[str]], min_pvalue_str: str = '', pvalues: Dict[str, Dict[str, Any]] = <factory>)

Bases: object

clst_id: float

false_negative_count: int

false_negative_edges: List[int]

haplotypes: List[int] | List[str]

members: Set[int] | Set[str]

min_pvalue_str: str = ''

print_members_list() → str

Returns a string that has all of the members ids separated by space

Returns:

returns a string where the members list attribute is formatted as a string for the output file. Individuals strings are joined by comma.

Return type:

str

pvalues: Dict[str, Dict[str, Any]]

true_positive_count: int

true_positive_percent: float

class drive.models.networks.Network_Interface(*args, **kwargs)

Bases: Protocol

clst_id: float

false_negative_count: int

false_negative_edges: List[int]

haplotypes: List[int]

members: Set[int]

min_pvalue_str: str = ''

print_members_list() → str

Returns a string that has all of the members ids separated by space

Returns:

returns a string where the members list attribute is formatted as a string for the output file. Individuals strings are joined by comma.

Return type:

str

pvalues: Dict[str, str] = Field(name=None,type=None,default=<dataclasses._MISSING_TYPE object>,default_factory=<class 'dict'>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=None)

true_positive_count: int

true_positive_percent: float

drive.models.types module

class drive.models.types.Filter(*args, **kwargs)

Bases: Protocol

ibd_pd: DataFrame

ibd_vs: DataFrame

class drive.models.types.Genes(chr, start, end)

Bases: tuple

chr

Alias for field number 0

end

Alias for field number 2

start

Alias for field number 1

Module contents