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 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.
The 2020 paper that introduced SELFIES: Mario Krenn and colleagues created a molecular representation that solves SMILES validity problems. It guarantees every generated string corresponds to a valid chemical structure.
SELFIES is a molecular string representation where every possible string decodes to a valid molecule, solving the invalid-output problem that limits SMILES in generative machine learning.
ICLR 2025 paper introducing DenoiseVAE, which learns adaptive, atom-specific noise distributions through a VAE framework to improve denoising-based pre-training for molecular force field prediction, outperforming fixed Gaussian noise approaches on quantum chemistry benchmarks.
A NeurIPS 2021 method paper introducing Noise Contrastive Priors to address the VAE ‘prior hole’ problem, where standard Gaussian priors assign high density to regions of latent space that don’t correspond to realistic data, using energy-based models trained with contrastive learning to match the aggregate posterior.
A complete guide to implementing modern Variational Autoencoders in PyTorch. Includes a copy-pasteable implementation, explanation of KL annealing to fix posterior collapse, and a deep dive into stable standard deviation parameterizations.
An in-depth guide to GANs: how two neural networks compete to generate realistic data, the math behind it, and the evolution of objective functions that stabilize training.