trvinh

#!/usr/bin/env python3
import argparse
import pandas as pd


def find_clusters(df: pd.DataFrame, protein_list: list) -> pd.DataFrame:
    """
    Given a dataframe and a list of protein IDs,
    return groups of proteins that belong to the same cluster (per chromosome).
    """

trvinh

import pandas as pd
import re
import argparse

def parse_gff(gff_file):
    """
    Parse GFF file and extract CDS with protein ID, gene locus, mRNA, chrom, strand, positions.
    """
    records = []

trvinh

#!/bin/env python

import os
import sys
import argparse
from pathlib import Path
import subprocess
import multiprocessing as mp
from tqdm import tqdm

trvinh

# create new conda env
mamba create -n phyloprofile_v1.20 r-base pkg-config pkgconfig fontconfig gsl lxml
# activate that env and start an R terminal
mamba activate phyloprofile_v1.20
R
# install phyloprofile from bioconductor
install.packages("BiocManager")
BiocManager::install("PhyloProfile")
# or install dev version from github
install.packages("devtools")

trvinh

library(data.table)
library(dplyr)

#' Split a multi ortholo group file into single files
splitDomainFile <- function(domainFile = NULL, outPath = NULL) {
    if (is.null(domainFile)) stop("Domain file cannot be NULL")
    if (is.null(outPath)) stop("Output path cannot be NULL")
    
    df <- fread(
        domainFile, header = TRUE, stringsAsFactors = FALSE, sep = "\t"

trvinh

from ete3 import NCBITaxa
ncbi = NCBITaxa()
ncbi.update_taxonomy_database()

trvinh

library(PhyloProfile)

processNcbiTaxonomy <- function(taxdmpfile = NULL) {
    if (is.null(taxdmpfile) || !file.exists(taxdmpfile)) {
        stop("taxdmp.zip file invalid!")
    } else temp <- taxdmpfile
    
    names <- utils::read.table(
        unz(temp, "names.dmp"), header = FALSE, fill = TRUE, sep = "\t",
        quote = "", comment.char = "", stringsAsFactors = FALSE

trvinh

# -*- coding: utf-8 -*-

from Bio import SeqIO
import argparse
import shutil

def combine_fa(fa_1, fa_2, out_file):
    """ Combine 2 fasta files """
    new_fa_dict = SeqIO.to_dict(SeqIO.parse(open(fa_2),'fasta'))
    existing_seq = SeqIO.to_dict(SeqIO.parse(open(fa_1),'fasta'))

trvinh

library(PhyloProfile)

setwd('PhyloProfile/data')

# load data 
data(taxonNamesReduced)
# modify the dataframe
# for example, rename Actinobacteria to Actinomycetota
taxonNamesReduced$fullName[
    taxonNamesReduced$rank == "phylum" & taxonNamesReduced$ncbiID == 201174

trvinh

import timeit

def test(st,en): 
    return random.randint(st, en)

t = timeit.Timer(lambda: test(10, 100))
print(t.timeit(10))