Home - Data in life

Categories

All (44)

Blog (6)

ChEMBL database (14)

Cheminformatics (12)

Data (1)

Data analytics projects (11)

Data preprocessing (2)

Datamol (4)

Deep learning (2)

Drug discovery & design (1)

Evcxr (1)

Ideas (1)

Jupyter (9)

Long COVID (4)

Machine learning projects (11)

Metabolism (2)

Molecular viz (1)

Notes (4)

Pandas (14)

Pills dataset series (3)

Plotly (5)

Polars (12)

PubChem (3)

Python (27)

Pytorch (1)

R (4)

RDKit (7)

Rare diseases (3)

Research (3)

Rust (1)

SQL (1)

Scikit-learn (7)

Shiny (5)

Structural alerts (1)

Tableau (1)

Toxicology (2)

Tree models (6)

Web-scraping (1)

itables (2)

🌟Blog status🌟

Welcome to my blog on selected cheminformatics, machine learning and data science projects in drug discovery.

Latest project - CYP-ADRs data (on adverse drug reactions for cytochrome P450 substrates) in this repository with ideas behind this work
Next project in the pipeline - there may be more to work on for the adverse drug reactions project…

Looking at minimising adverse drug reactions (ADRs)

Prevent model overfitting in deep neural networks

Building a simple deep learning model about adverse drug reactions

Notes on adverse drug reactions (ADRs) data

For strong and moderate strength cytochrome P450 (CYP) enzyme substrates

Cytochrome P450 and small drug molecules

CYP3A4 and 2D6 inhibitors

Boosted trees

Series 2.3.1 - AdaBoost, XGBoost and Scikit-mol

Using Molstar in Quarto

Random forest classifier

Series 2.2.1 - more on imbalanced dataset

Random forest

Series 2.2 - model building, imbalanced dataset, feature importances & hyperparameter tuning

Decision tree

Series 2.1.1 - data collection and preprocessing

Decision tree

Series 2.1.2 - data preprocessing and transformation

Decision tree

Series 2.1.3 - model building and estimating experimental errors

Molecular visualisation (Molviz) web application

Using Shiny for Python web application framework - part 2

Molecular visualisation (Molviz) web application

Interactive data table - part 1

Working with scaffolds in small molecules

Manipulating SMILES strings

Shinylive app in Python

Embedding app in Quarto document & using pyodide.http to import csv files

Shinylive app in Python

Embedding app in Quarto document for compounds in COVID-19 clinical trials

Shinylive app in Python

Data preparation for compounds in COVID-19 clinical trials

Shiny app in R

Small molecules in ChEMBL database

Pills dataset - Part 3

Using Rust for data visualisation

Pills dataset - Part 2

Text cleaning using Polars & visualising pills with Plotly

Pills dataset - Part 1

Web scraping, Polars & Pandas dataframe libraries

Small molecules in ChEMBL database

Series 1.1.1 - Parquet file in Polars dataframe library

Small molecules in ChEMBL database

Series 1.1.3 - Building logistic regression model using scikit-learn

Small molecules in ChEMBL database

Series 1.1.2 - Preprocessing data in Polars dataframe library

Small molecules in ChEMBL database

Series 1.1.4 - Evaluating logistic regression model in scikit-learn

Small molecules in ChEMBL database (old)

Series 1.1 - Polars dataframe library and machine learning in scikit-learn

Molecular similarities in selected COVID-19 antivirals

Using RDKit’s similarity map and fingerprint generator

PhD project

A research saga that went through COVID

Publications

Long COVID - an update

PDF table scraping, bar graph, interactive map & wordcloud

Table scraping from PDF

Using tabula-py in Python

Blog move

Phenotypes associated with rare diseases

Embracing social network

Natural history of rare diseases - malformation syndrome

Update on portfolio

Long COVID data in SQL

Portfolio projects

Long COVID dashboard

Drugs in rare diseases

Focussing on data analytics

The beginning of the data science journey

SERCA project