A 2025 end-to-end OCSR system addressing both technical and data challenges, introducing MolParser-7M (7M+ image-text pairs) and MolDet (YOLO-based detector) for extracting and recognizing molecular structures from real-world documents with diverse quality and styles.
ZINC-22 is the world’s largest freely available database of commercially available compounds, containing over 37 billion make-on-demand molecules with sophisticated search capabilities and cloud-scale infrastructure designed for modern virtual screening campaigns.
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.
MARCEL provides a comprehensive benchmark for molecular representation learning with 722K+ conformers across four diverse subsets (Drugs-75K, Kraken, EE, BDE), enabling evaluation of conformer ensemble methods for property prediction in drug discovery and catalysis.
Comprehensive overview of SMILES notation for chemical structures, covering syntax for atoms, bonds, branches, rings, and stereochemistry, plus its key limitations for machine learning.
A foundational 1931 paper that derives exact mathematical laws for counting alkane structural isomers through recursive formulas, correcting historical errors and establishing validated benchmark counts up to C₄₀.
GEOM contains 450k+ molecules with 37M+ conformations, featuring energy annotations from semi-empirical (GFN2-xTB) and DFT methods for property prediction and molecular generation research.
GDB-11 contains 26.4 million systematically generated small organic molecules with up to 11 atoms, establishing the methodology for exploring drug-like chemical space computationally.
ICML 2025 methodological paper introducing SPHNet, which uses adaptive network sparsification to overcome the computational bottleneck of tensor products in SE(3)-equivariant networks, achieving 2-5x speedup while maintaining accuracy on DFT Hamiltonian prediction tasks.
Lennard-Jones’s landmark 1932 theoretical paper that applied quantum mechanical potential energy surfaces to gas-solid interactions, providing the first unified framework explaining both physisorption and chemisorption as different regions of the same energy landscape.
GDB-13 contains nearly 1 billion systematically generated small organic molecules with up to 13 atoms, achieving billion-scale chemical space exploration while maintaining drug-like properties.