MICER treats optical chemical structure recognition as an image captioning task, using transfer learning with a fine-tuned ResNet encoder and attention-based LSTM decoder to convert molecular images into SMILES strings, reaching 97.54% sequence accuracy on synthetic data and 82.33% on real-world images.
This empirical study isolates the impact of chemical string representations on image-to-text translation models. It finds that while SMILES offers the highest overall accuracy, SELFIES provides a guarantee of structural validity, offering a trade-off for OCSR tasks.
ChemGrapher replaces rule-based chemical OCR with a deep learning pipeline using semantic segmentation to identify atom and bond candidates, followed by specialized classification networks to resolve stereochemistry and bond multiplicity, reducing error rates compared to OSRA across all tested styles.
DECIMER adapts the “Show, Attend and Tell” image captioning architecture to translate chemical structure images into SMILES strings. By leveraging massive synthetic datasets generated from PubChem, it demonstrates that deep learning can perform optical chemical recognition without complex, hand-engineered rule systems.
A 2021 deep learning system using a two-stage approach for OCSR, encoding images into continuous CDDD embeddings before decoding to SMILES. It leverages extensive data augmentation to handle rotations, distortions, and rendering variations for fast and robust molecular structure recognition.
Proposes a new OCSR workflow that improves recognition rates by separating adhesive chemical symbols and specifically handling virtual/real wedge bonds using vectorization, achieving 90% exact match vs 82.2% for OSRA baseline.
A 2021 image-to-text approach treating OCSR as an image captioning task. It uses Transformers with SELFIES representation to convert molecular structure diagrams into SMILES strings, enabling extraction of visual chemical knowledge from scientific literature.
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.
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.