d33bs

curl https://pyenv.run | bash
pyenv install 3.11
pip install poetry
git clone -b jump-umap-example https://github.com/d33bs/coSMicQC
cd coSMicQC
poetry install
poetry run jupyter lab

d33bs

"""
Seeks to query and extract biological process data from OLS4
using web API, Pandas, and Parquet.

API reference:
https://www.ebi.ac.uk/ols4/swagger-ui/index.html

Lab or group: Greene Lab
"""

d33bs

"""
Seek name and mechanism of action for drugs from Drugbank dataset.

Data reference:
https://go.drugbank.com/releases/latest#full

Lab or group: JRaviLab
"""

from typing import Dict, Any

d33bs

import pandas as pd
import numpy as np
import pyarrow as pa
import pyarrow.parquet as pq
import os

# Constants for the table dimensions and chunk size
n_rows = 10000
n_cols = 5000
chunk_size = 1000