Data and code required to reach the main conclusions of the benchmark paper (Small-Molecule Conformer Generators: Evaluation of Traditional Methods and AI Models on High-quality Datasets)

fastSMCG is a user-friendly webserver for small molecule conformer generation and analysis that integrates RDKit ETKDG algorithm and multiple AI models. It can be accessed free of charge at http://cadd.zju.edu.cn/fastsmcg/.

Contains the result raw data and demo scripts for plotting figures

Contains demo scripts for generating conformaers. For example, the ConfGenx method can be called to generate conformaers with a maximum ensemble size of 1 by running the command below

sbatch confgenx_001_submit.slurm

csv format: dataset-1.csv
pickle format: dataset-1.pkl
SD format: dataset.sdf
SMILES format: dataset.smi

csv format: dataset-1_with-index.csv
pickle format: dataset-1_with-index.pkl
SD format: dataset-1_with-index.sdf
SMILES format: dataset-1_with-index.smi
SD format: dataset-1_with-index_2d.sdf (contains 2D coordinates as input for ConfGenx method)

A demo script for calling AI models or RDKit ETKDG method to generate conformers
the RDKit ETKDG method can be called to generate conformaers with a maximum ensemble size of 1 by running the command below

bash run_fastsmcg.sh rdkit 1

Contains the result raw data and demo script for plotting figures

Contains demo scripts for generating conformaers. For example, the ConfGenx method can be called to generate conformaers by running the command below

sbatch confgenx_submit.slurm

csv format: dataset-2.csv
pickle format: dataset-2.pkl