A PyTorch and TorchDrug based deep learning library for drug pair scoring. (KDD 2022)

A tensorflow.keras generative neural network for de novo drug design, first-authored in Nature Machine Intelligence while working at AstraZeneca.

A lightweight python-only library for reading and writing SMILES strings

Variational Autoencoder (VAE)-based molecular SMILES string generator

Encoder-decoders for translating different chemical formats.

The official codebase for the paper "A Hitchhiker's Guide to Deep Chemical Language Processing for Bioactivity Prediction"

Taffi component increment theory used to predict enthalpy of formation, standard entropy and heat capacity.

Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow

SMILES, SELFIES and Reaction SMILES augmentation using RDKit

Training pre-trained BERT language model on molecular SMILES from the Molecule Net benchmark by leveraging mixup and enumeration augmentations.

Script developed to transform the amino acid smiles to one letter code for later analysis

Binary string classification of SMILES with an LSTM

⬢⬢⬢ Organizing and processing tables of chemical structures.

Code to retrieve drugs against a desired target using the ChEMBL database API

This Streamlit app allows you to search for the most "druglike" molecules basing on the "Rule of five"

Bio-cheminformatics project in progress to predict small molecule inhibitory potential (IC50) against 11β-HSD1

SMILES converted into Graphs that contains atomic information, bonding informatics. Graphs considered as input for the NN to Predict Melting Pont of Liquid Crystals (LCs)

One-hot encoding for simple molecular-input line-entry system (SMILES) strings

All the codes used by team "SlytherinSeers" are available here.

Autoencoder for SMILES strings