whitead

from rdkit.Chem import MolFromSmiles, MolToSmiles
    
smi = "..."
MolToSmiles(MolFromSmiles(smi), canonical=False, doRandom=True, isomericSmiles=True, kekuleSmiles=True)

whitead

import click
import time
import requests
import xml.etree.ElementTree as ET
from vesta import vesta_layout, send_to_vesta


def get_departures(station_name):
    api_key = "MW9S-E7SL-26DU-VV8V"
    base_url = "https://api.bart.gov/api/etd.aspx"

whitead

The paper by Caldas (2023) explored an approach to avoid the need for web server maintenance and cost by hosting a static file on sites like Github. The application developed was a JavaScript implementation of TensorFlow framework to predict the solubility of small molecules. The model implements a deep ensemble approach to report model uncertainty when reporting the prediction. The model was evaluated using RMSE, MAE, and correlation coefficient and outperformed the baseline models (Caldas2023 pages 6-7). The paper also provides a review of methods for calculating solution free energies and modelling systems in solution (Caldas2023 pages 11-12). The authors' model, kde10LSTM Aug, achieved a RMSE of 0.983 and a %±0.5log of 40.0% in the solubility challenge 1 dataset, outperforming 62% of the published RMSE values and 50% of the %±0.5log (Caldas2023 pages 9-10). This paper is significant as it provides an efficient and cost-effective approach to predict the solubility of small molecules with improved accuracy.

whitead

import rdkit
from rdkit import Chem
from rdkit.Chem import AllChem
import exmol
import skunk
import math
import matplotlib.pyplot as plt
import textwrap
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager

whitead

import requests
import tempfile
def get_pdb(query_string):
    url = "https://search.rcsb.org/rcsbsearch/v1/query"
    query = {
        "query": {
            "type": "terminal",
            "service": "full_text",
            "parameters": {"value": query_string},
        },

whitead

tranches = pd.read_csv('https://gist.githubusercontent.com/whitead/f47887e45bbd2f38332182d2d422da6b/raw/a3948beac9b9034dab432b697c5ec238503ac5d0/tranches.txt')
def get_mol_batch(batch_size = 32):
  for t in tranches.values:
    d = pd.read_csv(t[0], sep=' ')    
    for i in range(len(d) // batch_size):
      yield d.iloc[i * batch_size:(i + 1) * batch_size, 0].values

whitead

http://files.docking.org/2D/AA/AAAA.smi
http://files.docking.org/2D/AA/AAAB.smi
http://files.docking.org/2D/AA/AAAC.smi
http://files.docking.org/2D/AA/AAAD.smi
http://files.docking.org/2D/AA/AABA.smi
http://files.docking.org/2D/AA/AABB.smi
http://files.docking.org/2D/AA/AABD.smi
http://files.docking.org/2D/AA/AACA.smi
http://files.docking.org/2D/AA/AACB.smi
http://files.docking.org/2D/AA/AACD.smi

whitead

from matplotlib.collections import LineCollection


fps = 60.
stride = 1
duration = (T - 5) / fps / stride
print(duration, fps)
all_segments = [make_segments(paths, i) for i in range(N)]

fig = plt.figure(figsize=(1080 //180, 1080 // 180), dpi=180)

whitead

	ALA	ARG	ASN	ASP	CYS	GLN	GLU	HIS	ILE	LEU	LYS	MET	PHE	PRO	SER	THR	TRP	TYR	VAL
ALA	-0.34	0.08	0.04	0.15	-0.13	0.01	0.03	0.12	-0.2	-0.2	0.02	-0.18	-0.16	-0.01	0.03	-0.02	0.03	-0.02	-0.2
ARG	0.08	0.08	-0.08	-0.74	0.26	-0.2	-0.78	0.08	0.23	0.14	0.3	0.17	0.15	-0.1	-0.08	-0.03	-0.11	0.01	0.26
ASN	0.04	-0.08	-0.54	-0.47	0.12	-0.32	-0.26	-0.08	0.42	0.34	-0.25	0.23	0.14	-0.1	-0.32	-0.24	-0.01	0	0.25

whitead

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import seaborn as sns

sns.set_context('talk')
sns.set_style('darkgrid')
ps = [0.001, 0.005, 0.01, 0.02, 0.035]
cities = ['Rural Montana', 'Seattle', 'Minneapolis', 'Chicago', 'Miami']
cp = sns.cubehelix_palette(len(ps), start=0.5, rot=-0.75)