What is Optical Chemical Structure Recognition (OCSR)?
A micro-review of Optical Chemical Structure Recognition (OCSR), covering rule-based systems to modern deep learning …
Datasets
MolParser-7M & WildMol: Large-Scale OCSR Datasets
MolParser-7M is the largest OCSR dataset with 7.7M image-text pairs of molecules and E-SMILES, including 400k real-world …
MolParser: End-to-End Molecular Structure Recognition
MolParser converts molecular images from scientific documents to machine-readable formats using end-to-end learning with …
ZINC-22: Multi-Billion Scale Database
ZINC-22 dataset provides 37+ billion make-on-demand molecules for virtual screening and modern drug discovery.
MARCEL: Molecular Representation & Conformers
MARCEL dataset provides 722K+ conformers across 76K+ molecules for drug discovery, catalysis, and molecular …
GEOM: Energy-Annotated Molecular Conformations
Dataset card for GEOM, providing energy-annotated molecular conformations generated via CREST/xTB and refined with DFT …
GDB-11: Chemical Universe Database (26.4M Molecules)
GDB-11 systematically enumerates 26.4M small organic molecules (up to 11 atoms of C, N, O, F) for virtual screening and …
GDB-13: Chemical Universe Database (970M Molecules)
A dataset card for the Generated Database 13 (GDB-13), a database of nearly 1 billion small organic molecules for …
GDB-17: Chemical Universe Database (166B Molecules)
Dataset card for GDB-17, containing 166 billion small organic molecules representing the largest enumerated chemical …
GEOM Dataset: 3D Molecular Conformer Generation
Learn how GEOM transforms 2D molecular graphs into dynamic 3D conformer ensembles for molecular machine learning …
Synthetic Isomer Data Generation Pipeline
An end-to-end cheminformatics pipeline transforming 1D chemical formulas into 3D conformer datasets using graph …
Sarcasm Detection with Transformers: A Cautionary Tale
Learn how dataset bias can lead to misleading results in NLP: a sarcasm detection model that actually learned to …