Source code for k1lib.bioinfo.cli.bio

# AUTOGENERATED FILE! PLEASE DON'T EDIT
"""
This is for functions that are actually biology-related
"""
from k1lib.bioinfo.cli.init import settings, BaseCli
import k1lib.bioinfo.cli as cli
import os
from typing import Iterator, Union
__all__ = ["go",
           "transcribe", "complement", "translate", "medAa", "longAa"]
[docs]def go(term:int): """Looks up a GO term""" if settings["oboFile"] is None and not os.path.exists("go.obo"): answer = input("""No gene ontology obo file specified! You can: - Specify the file using `settings['oboFile']='/some/folder/go.obo'` - Download this automatically to file `go.obo` You want to download this automatically? (y/n) """) if answer.lower().startswith("y"): url = "http://current.geneontology.org/ontology/go.obo" print(f"Downloading from {url}... ", end="") cli.wget(url); print("Finished!") else: return print("Aborted") file = settings["oboFile"] or "go.obo"; term = f"{term}".rjust(7, "0") cli.cat(file) | cli.grep(f"id: GO:{term}", 0, 10) > cli.stdout print(f"https://www.ebi.ac.uk/QuickGO/GTerm?id=GO:{term}") if settings["lookupImgs"]: class Repr: def _repr_html_(self): return f"""<img src="http://amigo.geneontology.org/visualize?mode=amigo&term_data_type=string&format=png&inline=false&term_data=GO%3A{term}" />""" return Repr()
[docs]class transcribe(BaseCli): """Transcribes (DNA -> RNA) incoming rows"""
[docs] def __ror__(self, it:Union[Iterator[str], str]): if isinstance(it, str): it = [it] for line in it: yield line.lower().replace("t", "u")
[docs]class complement(BaseCli):
[docs] def __ror__(self, it:Union[Iterator[str], str]): if isinstance(it, str): it = [it] for line in it: line = line.lower().replace("a", "0").replace("t", "1")\ .replace("u", "1").replace("c", "2").replace("g", "3") yield line.replace("0", "t").replace("1", "a").replace("2", "g").replace("3", "c")
ntAa = {"UUU": "F", "UUC": "F", "UUA": "L", "UUG": "L", "UCU": "S", "UCC": "S", "UCA": "S", "UCG": "S", "UAU": "Y", "UAC": "Y", "UAA": "*", "UAG": "*", "UGU": "C", "UGC": "C", "UGA": "*", "UGG": "W", "CUU": "L", "CUC": "L", "CUA": "L", "CUG": "L", "CCU": "P", "CCC": "P", "CCA": "P", "CCG": "P", "CAU": "H", "CAC": "H", "CAA": "Q", "CAG": "Q", "CGU": "R", "CGC": "R", "CGA": "R", "CGG": "R", "AUU": "I", "AUC": "I", "AUA": "I", "AUG": "M", "ACU": "T", "ACC": "T", "ACA": "T", "ACG": "T", "AAU": "N", "AAC": "N", "AAA": "K", "AAG": "K", "AGU": "S", "AGC": "S", "AGA": "R", "AGG": "R", "GUU": "V", "GUC": "V", "GUA": "V", "GUG": "V", "GCU": "A", "GCC": "A", "GCA": "A", "GCG": "A", "GAU": "D", "GAC": "D", "GAA": "E", "GAG": "E", "GGU": "G", "GGC": "G", "GGA": "G", "GGG": "G"} _shortAa = {v:v for v in ntAa.values()} _medAa = { "F": "Phe", "L": "Leu", "I": "Ile", "M": "Met", "V": "Val", "S": "Ser", "P": "Pro", "T": "Thr", "A": "Ala", "Y": "Tyr", "*": "Stop", "H": "His", "Q": "Gln", "N": "Asn", "K": "Lys", "D": "Asp", "E": "Glu", "C": "Cys", "W": "Trp", "R": "Arg", "G": "Gly", "U": "Sec", "?": "?" } _longAa = { "F": "Phenylalanine", "L": "Leucine", "I": "Isoleucine", "M": "Methionine", "V": "Valine", "S": "Serine", "P": "Proline", "T": "Threonine", "A": "Alanine", "Y": "Tyrosine", "*": "Stop", "H": "Histidine", "Q": "Glutamine", "N": "Asparagine", "K": "Lysine", "D": "AsparticAcid", "E": "GlutamicAcid", "C": "Cysteine", "W": "Tryptophan", "R": "Arginine", "G": "Glycine", "U": "Selenocysteine", "?": "?" }
[docs]class translate(BaseCli):
[docs] def __init__(self, length:int=0): """Translates incoming rows. :param length: 0 for short (L), 1 for med (Leu), 2 for long (Leucine)""" self.delim = "" if length == 0 else " " self.dict = [_shortAa, _medAa, _longAa][length]
[docs] def __ror__(self, it:Iterator[str]): if isinstance(it, str): it = [it] it = it | transcribe() for line in it: line = line.replace(" ", "") answer = ""; n = len(line) for i in range(0, n - n % 3, 3): codon = line[i:i+3].upper() answer += (self.dict[ntAa[codon]] if codon in ntAa else "?") + self.delim yield answer
[docs]class medAa(BaseCli): """Converts short aa sequence to medium one"""
[docs] def __ror__(self, it:Iterator[str]): if isinstance(it, str): it = [it] for line in it: yield " ".join(_medAa[c] for c in line)
[docs]class longAa(BaseCli): """Converts short aa sequence to long one"""
[docs] def __ror__(self, it:Iterator[str]): if isinstance(it, str): it = [it] for line in it: yield " ".join(_longAa[c] for c in line)