biofkit 0.1.5

With biofkit you can deal with pdb file (extract sequence, atom information and so on) very easily.

biofkit

Biofkit is now containing only one module with one package which can deal with pdb file (extract sequence, atom information and so on) very easily.

How to Install

Conda

conda install -c chou_uken biofkit

Mamba

mamba install -c chou_uken biofkit

Pip

pip install biofkit

How to Use

ProteinKit

from biofkit.proteinKit import pdbKit

# if argument fasta is True, a fasta file will be created in the same path as the pdb file.
def pdb2Seq(pdbFilePath: str, fastaFilePath: str = None, fastaLineLen: int = 80) -> dict[str, str]:
    # pdfFilePath: the file path of the pdb you want to transfer.
    # fastaFilePath: The path to save the fasta files, do not contain your fasta file name.
    # fastaLineLen: How many residues are contained in a single line of the fasta, only work when `fasta` is true.

# load the information of all amino-acid-residue atoms into a list. output[idx] shows the information of an atom.
pdb2List(pdbFilePath: str, csvPath: str = None, colName: bool = False) -> list[list[int, str, str, int, str, float, float, float]]:
    # pdbFilePath: the file path of the pdb you want to load.
    # csvPath: if given, then write a csv file for your atom information.
    # colName: a prepared colname list for the output. If colName is true, the output[0] will be such a list shown below. May help when column names are needed.
    pdbInfoColumns: [str] = ['Serial', 'Atom', 'ResName', 'ResSeq', 'ChainId', 'X', 'Y', 'Z']

# load the information of all amimo-acid-residue atoms into a dictionary, which can be converted into a dataframe with famous `pandas`.
pdb2Dict(pdbFilePath: str) -> dict[str, list]:
    # pdbFilePath: the file path of the pdb you want to load.

SeqKit

from biofkit.seqKit import convKit

# Read fasta files and generate a dictionary whose keys are taxonomy and values are sequences
def readFasta(fastaFilePath: str) -> dict[str, str]:
    # fastaFilePath: the path of your fasta file.

# transcription
def dna2Rna(dnaSeq: str) -> str:
    # dnaSeq: the sequence of DNA, a string containing 'A', 'C', 'G', 'T' but without 'U'.

# reverse transcription
def rna2Dna(rnaSeq: str) -> str:
    # rnaSeq: the sequence of RNA, a string containing 'A', 'C', 'G', 'U' but without 'T'.
    
# DNA translation
def dna2Pro(dnaSeq: str, start: int = 0, end: int = -1) -> str:
    # dnaSeq: the sequence of DNA, a string containing 'A', 'C', 'G', 'T' but without 'U'.
    # start: From where to tranlate into protein.
    # end: To where to tranlate into protein.
    
# RNA tranlation
def rna2Pro(rnaSeq: str, start: int = 0, end: int = -1) -> str:
    # dnaSeq: the sequence of DNA, a string containing 'A', 'C', 'G', 'U' but without 'T'.
    # start: From where to tranlate into protein.
    # end: To where to tranlate into protein.

# DNA pairwise alignment
def pairwiseDnaAlign(fasta: str = '', seqA: str = 'ACGT', seqB: str = 'ACGTA', matrix: str = 'unitary', gapOpen: float = -10, gapExtend: float = -0.5, consoleWidth = 50) -> None:
    # fasta: the path of your fasta file.
    # seqA/B: If fasta file is not provided, seqA/B must be given.
    # matrix: Scoring matrix('unitary', 'blast', 'tt'(transition-transversion)).
    # gapOpen: punishment got when a gap opened.
    # gaoExtend: punishment got when a gap extended.
    # consoleWidth: How many bases printed in a line.

# Protein pairwise alignment
def pairwiseProtAlign(fasta: str = '', seqA: str = 'ACGT', seqB: str = 'ACGTT', matrix: str = 'unitary', gapOpen: float = -10, gapExtend: float = -0.5, consoleWidth = 50) -> None:
    # fasta: the path of your fasta file.
    # seqA/B: If fasta file is not provided, seqA/B must be given.
    # matrix: Scoring matrix('unitary', 'pam250', 'blosum62').
    # gapOpen: punishment got when a gap opened.
    # gaoExtend: punishment got when a gap extended.
    # consoleWidth: How many bases printed in a line.