thanhleviet

name: 'Pathinder'
customWebsiteImage: "ghcr.io/loculus-project/website:microbioinfo-hackathon"
organisms:
  salmonella:
    schema:
      organismName: 'Salmonella'
      image: 'https://upload.wikimedia.org/wikipedia/commons/thumb/b/b4/SalmonellaNIAID.jpg/286px-SalmonellaNIAID.jpg'
      metadata:
        - name: location
          type: string

thanhleviet

#!/usr/bin/env python3
"""
Git Analysis Report Generator
This script generates an HTML report analysing commits in a Git repository.
Thanh Le Viet - TGHI
"""
import subprocess
from datetime import datetime
import os
from html import escape

thanhleviet

1. Nanopore basecalling with Dorado

https://github.com/nanoporetech/dorado

Setup

• dorado: https://cdn.oxfordnanoportal.com/software/analysis/dorado-0.4.3-linux-x64.tar.gz
• Dataset:

  https://dropoff.nbi.ac.uk/pickup?claimID=HejmBN7XJVbMRv74&claimPasscode=mxpYSGxyhKCmJG5z&emailAddr=1017
  

Claim ID: HejmBN7XJVbMRv74

thanhleviet

#!/usr/bin/env python
import argparse
import sys
import os
import pandas as pd
from biom import load_table, Table

def merge_biom_files_with_pandas(biom_files):
    dfs = []  # List to store DataFrames

thanhleviet

--[[

SLURM job submit filter for QOS

Some code and ideas pulled from https://github.com/edf-hpc/slurm-llnl-misc-plugins/blob/master/job_submit.lua

--]]

--########################################################################--
--

thanhleviet

import os
import csv
import argparse

def scan_paired_end_files(dir_path, pattern_list):
    # Initialize a list to store the sample IDs and file paths
    samples = []

    # Loop through all files in the directory
    for file_name in os.listdir(dir_path):

thanhleviet

library(patchwork)
library(ggplot2)
library(tidyverse)
data(mtcars)
data(iris)

mtcars.tf <- mtcars %>% 
  rownames_to_column("name") %>% 
  pivot_longer(names_to = "metrics", values_to = "values", mpg:carb)

thanhleviet

- hosts: all
  become: true
  become_user: root
  vars:
    singularity_version: 3.10.0
  pre_tasks:
    - name: Update apt packages
      apt:
        update_cache: true
        cache_valid_time: 86400 #One day

thanhleviet

#!/usr/bin/env python
import requests
import time
import pathlib
from joblib import Parallel, delayed
from pqdm.processes import pqdm

def url_template(id):
    url0 = "https://pubmlst.org/bigsdb?db=pubmlst_campylobacter_isolates&page=plugin&name=Contigs&format=text&isolate_id="
    url1 = "&match=1&pc_untagged=0&min_length=&header=1"

thanhleviet

library(dplyr)
library(ggtree)

tree <- read.tree("Benchmarking_tree_07Dec21.nwk")

tips <- tree$tip.label %>% 
  tibble(tip = .) %>% 
  mutate(sample = gsub("_[a-zA-Z\\_]+","",tip))