Computational Chemistry

Recent Advances in the SELFIES Library (2023)

An overview of the major updates to the SELFIES Python library, including improved performance, expanded chemical …...

Computational Chemistry

SELFIES: The Original Paper (Krenn et al. 2020)

A summary of the foundational 2020 paper that introduced SELFIES - the 100% robust molecular string representation …

Computational Chemistry
SELFIES strings guarantee 100% valid molecules - even when generated randomly

Converting SELFIES Strings to 2D Molecular Images

Learn how to visualize SELFIES molecular representations and explore their unique advantages through random sampling, …

Computational Chemistry
SELFIES representation of 2-Fluoroethenimine molecule

SELFIES (Self-Referencing Embedded Strings)

SELFIES is a 100% robust string-based representation for chemical molecules, designed for machine learning applications …...

Computational Chemistry

Invalid SMILES are Beneficial Rather than Detrimental to Chemical Language Models

Skinnider's 2024 Nature Machine Intelligence paper demonstrates that the ability to generate invalid SMILES is actually …...

Computational Chemistry

SELFIES and the Future of Molecular String Representations

A comprehensive perspective on molecular string representations, focusing on SELFIES as a 100% robust alternative to …...

Computational Chemistry

IMG2SMI: Translating Molecular Structure Images to SMILES

Campos & Ji's method for converting 2D molecular images to SMILES strings using Transformers and SELFIES representation....