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 foundational 2013 paper introducing Variational Autoencoders and the reparameterization trick, enabling end-to-end gradient-based training of generative models with continuous latent variables by making the sampling operation differentiable through a clever mathematical transformation.
Discover how Importance Weighted Autoencoders (IWAEs) use the same architecture as VAEs with a fundamentally more powerful objective to leverage multiple samples effectively.
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.
A 2023 software update paper documenting major improvements to the SELFIES Python library, including architectural redesign using directed molecular graphs for faster performance, expanded chemical feature support, semantic constraints for validity, and user-friendly customization APIs that transform SELFIES from proof-of-concept into production-ready tool.
The 2020 paper that introduced SELFIES: how Mario Krenn and colleagues created a molecular representation that guarantees every generated string corresponds to a valid chemical structure.
Build a robust Python CLI tool that converts both SMILES and SELFIES notation into publication-quality 2D molecular images, complete with formulas and legends.
An in-depth overview of SELFIES, the 100% robust molecular string representation designed to overcome SMILES limitations in machine learning, where every possible string (even random ones) decodes to a valid molecule through local operations, customizable valence rules, and graph-based internal representations.
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 provocative 2024 Nature Machine Intelligence paper challenging the assumption that invalid SMILES are failures, showing empirically that the ability to generate invalid outputs actually improves chemical language model performance by enabling quality filtering and providing richer training signals.
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.