ravila4

# Functions for parallelizing things

def init_spark(nproc=-1, appname="sparksession"):
    """Function to start a Spark executor."""
    from pyspark.sql import SparkSession
    if nproc == -1:
        # Use all CUPs
        spark = SparkSession.builder.master(
                "local[*]").appName(appname).getOrCreate()
    else:

ravila4

def flatten_json(y):
    out = {}

    def flatten(x, name=''):
        if type(x) is dict:
            for a in x:
                flatten(x[a], name + a + '_')
        elif type(x) is list:
            i = 0
            for a in x:

ravila4

ravila4

#!/usr/bin/env python

# Sequence alignment using PyMOL
# The purpose of this script is to generate a sequence alignment between
# the original crystal structure of the apo and holo models, and the sequence
# of the finalised, ungapped Rosetta models. This allows us to get a 1 to 1
# corresponcence between the residue numberings in both structures.

# USAGE: Run once from the project root.
# "pockets.csv" contains the information about apo holo pairs.

ravila4

import xmltodict
import pandas as pd

with open("full_database.xml") as db:
    doc = xmltodict.parse(db.read())

values = []
for item in doc['drugbank']['drug']:
    logp = None
    try:

ravila4

ravila4

ravila4

#!/usr/bin/env bash

set -Eeuo pipefail

cd "$(dirname "${BASH_SOURCE[0]}")" >/dev/null 2>&1

trap cleanup SIGINT SIGTERM ERR EXIT

usage() {
  cat <<EOF

ravila4

#!/bin/bash

# Genesets aggregated by taxid
aggs=`curl -s "https://mygeneset.info/v1/query?q=*&facets=taxid&facet_size=100"`
taxids=`echo $aggs | jq -r '.facets.taxid.terms | map(.term) | @csv'`
counts=`echo $aggs | jq -r '.facets.taxid.terms | map(.count) | @csv'`

# Query scientific name for each taxid
resp=`curl -s -X POST -d "q=${taxids}" "http://t.biothings.io/v1/query"`
species=`echo $resp | jq -r 'map(.scientific_name) | @csv'`

ravila4