ChemGrapher
Deep learning OCSR method using semantic segmentation and classification CNNs to reconstruct chemical graphs with …
Molecular-Representation - Page 3
DECIMER: Deep Learning for Chemical Image Recognition
Deep learning method for optical chemical structure recognition using image captioning networks trained on millions of …
Img2Mol: Accurate SMILES from Molecular Depictions
Two-stage CNN approach for converting molecular images to SMILES using CDDD embeddings and extensive data augmentation.
Research on Chemical Expression Images Recognition
A 2015 methodology for Optical Chemical Structure Recognition (OCSR) focusing on improved handling of adhesive symbols …
IMG2SMI: Translating Molecular Structure Images to SMILES
Campos & Ji's method for converting 2D molecular images to SMILES strings using Transformers and SELFIES representation.
Molecular String Renderer: Robust Visualization Tool
A robust, type-safe Python library for converting chemical strings (SMILES, SELFIES, InChI) into publication-quality …
InChI and Tautomerism: Toward Comprehensive Treatment
Dhaked et al.'s comprehensive analysis of tautomerism in chemoinformatics, introducing 86 new tautomeric rules and their …
InChI: The Worldwide Chemical Structure Identifier Standard
Heller et al. (2013) explain how IUPAC's InChI became the global standard for representing chemical structures, its …
Making InChI FAIR and Sustainable for Inorganic Chemistry
InChI v1.07 modernizes chemical identifiers for FAIR principles and adds robust support for inorganic compounds.
Mixfile & MInChI: Machine-Readable Mixture Formats
Mixfile and MInChI provide the first standardized, machine-readable formats for representing chemical mixtures.
NInChI: Toward a Chemical Identifier for Nanomaterials
NInChI (Nanomaterials InChI) extends chemical identifiers to represent complex, multi-component nanomaterials.
Recent Advances in the SELFIES Library (2023)
Major updates to the SELFIES library, improved performance, expanded chemistry support, and new customization features.