A 2024 Nature Machine Intelligence paper providing causal evidence that invalid SMILES generation improves chemical language model performance by filtering low-likelihood samples, while validity constraints (as in SELFIES) introduce structural biases that impair distribution learning.
This 2022 perspective paper reviews 250 years of chemical notation evolution and proposes 16 concrete research projects to extend SELFIES beyond traditional organic chemistry into polymers, crystals, and reactions.
A fault-tolerant RDKit wrapper treating molecular visualization as a software engineering problem, implementing strategy pattern for SVG generation with automatic raster fallback, native SELFIES support for generative AI workflows, and strict type safety for reliable batch processing of millions of molecules in training pipelines.
Kingma and Welling’s 2013 paper introducing Variational Autoencoders and the reparameterization trick, enabling end-to-end gradient-based training of generative models with continuous latent variables by moving the stochasticity outside the computational graph so that gradients can flow through a deterministic path.
Burda et al.’s ICLR 2016 paper introducing Importance Weighted Autoencoders, which use importance sampling to derive a strictly tighter log-likelihood lower bound than standard VAEs, addressing posterior collapse and improving generative quality. The model architecture remains the same.
Discover how Importance Weighted Autoencoders (IWAEs) use the same architecture as VAEs with a fundamentally more powerful objective to leverage multiple samples effectively.
A comprehensive 2020 analysis of the tautomerism problem in chemical databases, compiling 86 tautomeric transformation rules (20 existing, 66 new) and validating them across 400M+ structures to inform algorithmic improvements for InChI V2.
A comprehensive 2013 review explaining how InChI emerged as the global standard for chemical structure identifiers, covering its history as a response to the Internet’s need for non-proprietary molecular linking, its governance under IUPAC, and the technical layers that ensure uniqueness across diverse chemical databases.
A 2025 Faraday Discussions paper describing the major overhaul of InChI v1.07 that fixed more than 3000 bugs, added support for inorganic and organometallic compounds, and modernized the system to align with FAIR data principles for chemistry databases.
A 2019 format specification introducing two complementary standards for chemical mixtures. Mixfile provides comprehensive mixture descriptions and MInChI provides compact canonical identifiers. This addresses the long-standing lack of standardized machine-readable formats for multi-component chemical systems.
Can we create a SMILES-like notation for nanomaterials? A collaborative workshop tackles the challenge of representing complex, multi-component nanomaterials with a proposed extension to the established InChI system.
A 2023 software update paper documenting improvements to the SELFIES Python library (v2.1.1), including a streamlined context-free grammar, expanded support for aromatic systems and stereochemistry, customizable semantic constraints, ML utility functions, and performance benchmarks on 300K+ molecules.